Stwardnienie zanikowe boczne
Rokowania, prognozy i postęp choroby

Stwardnienie zanikowe boczne (ALS) to neurodegeneracyjna choroba o zmiennym przebiegu, z medianą przeżycia 3-5 lat od wystąpienia objawów, najczęściej kończącą się niewydolnością oddechową. Kluczowe czynniki prognostyczne obejmują miejsce początku choroby (opuszkowy vs rdzeniowy, HR=1,7), szybkość spadku funkcji w skali ALSFRS-R (HR=2,8), dysfunkcję wykonawczą (HR=2,11), podwyższony poziom neurofilamentu lekkiego w surowicy (HR=3,70) i płynie mózgowo-rdzeniowym (HR=6,80), obecność otępienia czołowo-skroniowego (HR=2,98), podtyp oddechowy ALS (HR=2,20), starszy wiek zachorowania (HR=1,03) oraz mutację C9orf72. Czynniki sprzyjające lepszemu rokowaniu to czysta postać pLMN lub pUMN (HR=0,32), wyższy wyjściowy wynik ALSFRS-R (HR=0,95), dłuższy czas od objawów do diagnozy (HR=0,97), młodszy wiek w momencie diagnozy, przewaga objawów górnego neuronu ruchowego oraz podwyższony poziom kinazy kreatynowej. Leczenie riluzolem daje medianę korzyści przeżycia około 3 miesięcy (HR 0,84), co jest mniejszym efektem niż wpływ innych predyktorów.

  1. Prognoza stwardnienia zanikowego bocznego – zagadnienia ogólne
  2. Kluczowe czynniki prognostyczne w stwardnieniu zanikowym bocznym
    1. Negatywne czynniki prognostyczne
    2. Pozytywne czynniki prognostyczne
    3. Czynniki o nieustalonym wpływie na rokowanie
  3. Modele prognostyczne w stwardnieniu zanikowym bocznym
    1. Wskaźnik Prognostyczny ALS (API)
    2. Model ENCALS
    3. Modele oparte na uczeniu maszynowym
  4. Praktyczne zastosowanie modelowania prognostycznego w ALS
    1. Znaczenie kliniczne
    2. Zastosowanie w badaniach klinicznych
    3. Indywidualizacja prognozy
  5. Ograniczenia obecnych modeli prognostycznych
  6. Perspektywy na przyszłość w prognozowaniu ALS
    1. Kolejne rozdziały

Prognoza stwardnienia zanikowego bocznego – zagadnienia ogólne

Stwardnienie zanikowe boczne (ALS) to postępująca choroba neurodegeneracyjna, charakteryzująca się wysoce zmiennym przebiegiem klinicznym i prognozą. Mediana przeżycia od wystąpienia objawów wynosi zazwyczaj 3-5 lat, przy czym zgon następuje najczęściej w wyniku niewydolności oddechowej.12 Jednakże czas przeżycia może znacząco się różnić – od kilku miesięcy do ponad 10 lat.34 Mediana przeżycia od początku objawów do zgonu/tracheostomii wynosi około 44 miesiące, natomiast mediana przeżycia od momentu diagnozy do punktu końcowego (zgon lub wdrożenie inwazyjnej wentylacji mechanicznej) to około 14 miesięcy.5

Identyfikacja kluczowych czynników wpływających na rokowanie ma fundamentalne znaczenie dla skutecznego planowania interwencji medycznych, podejmowania decyzji dotyczących końca życia oraz odpowiedniej stratyfikacji pacjentów w badaniach klinicznych.6 Dokładne narzędzia prognostyczne są niezbędne do optymalizacji opieki wielodyscyplinarnej, planowania interwencji, doradzania pacjentom w kwestiach decyzji dotyczących końca życia oraz odpowiedniej alokacji zasobów.7

Kluczowe czynniki prognostyczne w stwardnieniu zanikowym bocznym

W ocenie prognostycznej ALS zidentyfikowano szereg istotnych czynników predykcyjnych, które można wykorzystać do określenia przewidywanego czasu przeżycia pacjenta. Przeprowadzone badania wykazały następujące, najważniejsze czynniki prognostyczne:

Negatywne czynniki prognostyczne

  • Miejsce początku choroby – niespinalne początki choroby (w szczególności początek opuszkowy) wiążą się z gorszym rokowaniem (HR = 1,7)8
  • Szybkość spadku wyniku ALSFRS-R przed pierwszą oceną (HR = 2,8) – szybszy spadek funkcjonalny wiąże się z krótszym przeżyciem9
  • Dysfunkcja wykonawcza/zaburzenia poznawcze (HR = 2,11) – zaburzenia funkcji poznawczych znacząco pogarszają rokowanie1011
  • Podwyższony poziom neurofilamentu lekkiego (NFL) w surowicy (HR = 3,70) i płynie mózgowo-rdzeniowym (HR = 6,80)12
  • Współwystępowanie otępienia czołowo-skroniowego (FTD) (HR = 2,98)13
  • Podtyp oddechowy ALS (HR = 2,20)14
  • Starszy wiek w momencie zachorowania (HR = 1,03) – im starszy wiek w momencie wystąpienia objawów, tym gorsze rokowanie1516
  • Obecność mutacji C9orf7217

Pozytywne czynniki prognostyczne

  • Czysta postać dolnego lub górnego neuronu ruchowego (pLMN lub pUMN) (HR = 0,32)18
  • Wyższy wyjściowy wynik ALSFRS-R (HR = 0,95)19
  • Dłuższy czas od wystąpienia objawów do diagnozy (HR = 0,97)2021
  • Młodszy wiek w momencie diagnozy22
  • Przewaga objawów górnego neuronu ruchowego23
  • Podwyższony poziom kinazy kreatynowej (CK) w surowicy – wyższe wartości CK związane są z lepszym rokowaniem24

Czynniki o nieustalonym wpływie na rokowanie

  • Płeć25
  • Poziom wykształcenia26
  • Choroby współistniejące (cukrzyca, nadciśnienie)27
  • Wentylacja nieinwazyjna28
  • Gastrostomia29
  • Stosowanie statyn30

Należy zaznaczyć, że choć riluzol nie został ujęty w modelu ENCALS jako zmienna prognostyczna, według metaanalizy Cochrane mediana korzyści przeżycia wynosi około 3 miesiące, co jest znacznie mniejszym efektem niż łączny wpływ innych predyktorów w ENCALS (HR 0,84 vs 15,29).31

Modele prognostyczne w stwardnieniu zanikowym bocznym

W ostatnich latach opracowano kilka modeli prognostycznych umożliwiających bardziej precyzyjną ocenę rokowania u pacjentów z ALS. Najważniejsze z nich to:

Wskaźnik Prognostyczny ALS (API)

Indeks API (ALS Prognostic Index) to prosty algorytm prognostyczny wykorzystujący zmienne, które można zebrać podczas pierwszego spotkania z pacjentem. API generuje wyniki w zakresie od zera do sześciu (wyższe wyniki wskazują na gorsze rokowanie). Klasyfikacja pacjentów do grupy wysokiego ryzyka wiązała się z dodatnią wartością predykcyjną dla złego rokowania wynoszącą 73,3-85,7% oraz ujemną wartością predykcyjną dla dobrego rokowania wynoszącą 93,3-100%.32 Model API uwzględnia następujące czynniki:

  • Miejsce początku choroby
  • Tempo spadku wyniku w skali ALSFRS-R przed pierwszą oceną
  • Obecność dysfunkcji wykonawczej

Prostota i niezawodność tego modelu może poprawić protokoły stratyfikacji w przyszłych badaniach klinicznych.33

Model ENCALS

European Network for the Cure of ALS (ENCALS) to najbardziej uznany model oparty na dowodach, służący do przewidywania rokowania w ALS.34 Został opracowany do przewidywania przeżycia u pacjentów z ALS, którzy nie byli leczeni tracheostomią ani ciągłą wentylacją nieinwazyjną. Model ENCALS uwzględnia zmienne kliniczne, poznawcze i genetyczne do przewidywania przeżycia na podstawie danych ponad 11 000 europejskich pacjentów z ALS z lat 1992-2016.35

Najważniejsze czynniki prognostyczne uwzględnione w ENCALS to:

  • Miejsce początku (rdzeniowe vs opuszkowe)
  • Wiek w momencie wystąpienia osłabienia mięśni lub objawów opuszkowych
  • Czas od wystąpienia osłabienia lub objawów opuszkowych do diagnozy
  • Stopień pewności diagnozy ALS (pewna, prawdopodobna, możliwa)
  • Natężona pojemność życiowa (FVC)
  • Wynik w zrewidowanej skali funkcjonalnej ALS (ALSFRS-R)
  • Obecność otępienia czołowo-skroniowego
  • Obecność mutacji C9orf72

Model ENCALS może przewidywać czas przeżycia w miesiącach i może być wykorzystany do określenia prawdopodobieństwa przeżycia krótszego niż sześć miesięcy, wskazując na kwalifikację do opieki hospicyjnej.36 Przegląd systematyczny porównujący dziewiętnaście modeli predykcyjnych dla przeżycia w ALS wykazał, że tylko ENCALS wykazywał dobrą zdolność dyskryminacyjną, kalibrację i niskie ryzyko błędu.37

Modele oparte na uczeniu maszynowym

W ostatnich latach coraz większą rolę w przewidywaniu prognozy ALS odgrywają modele oparte na uczeniu maszynowym (ML). Rozwija się trend tworzenia dokładnych narzędzi prognostycznych w oparciu o kombinację czynników prognostycznych, z wykorzystaniem nadzorowanych modeli uczenia maszynowego, takich jak lasy losowe, modele regresji, sieci neuronowe z lasami losowymi i algorytmami wzmacniającymi.38

Na podstawie badań z wykorzystaniem uczenia maszynowego wyróżniono trzy odrębne typy predykcji:

  • Prognozowanie progresji choroby – szacowanie stanu pacjenta w określonym momencie w przyszłości (70% badań)
  • Prognozowanie czasu przeżycia – szacowanie prawdopodobieństwa zgonu w określonym przedziale czasowym
  • Prognozowanie potrzeby wsparcia – przewidywanie momentu, kiedy pacjenci będą potrzebować bardziej specjalistycznego wsparcia39

Jednym z nowszych podejść jest wykorzystanie algorytmu UMAP (Uniform Manifold Approximation and Projection) do identyfikacji stref przeżywalności, co umożliwia prognozowanie rocznego przeżycia.40 Innym przykładem jest model sieciowy DBN (Dynamic Bayesian Network), który pozwala na stratyfikację kohort pacjentów i generowanie kohort in silico o określonych charakterystykach.41

Biomarkery zidentyfikowane jako istotne w więcej niż jednym badaniu to: ALSFRS/ALSFRS-R, czas trwania choroby, natężona pojemność życiowa (FVC), wskaźnik masy ciała (BMI), wiek w momencie zachorowania i kreatynina.42

Praktyczne zastosowanie modelowania prognostycznego w ALS

Dokładna prognoza przeżycia dla pacjentów z ALS ma kluczowe znaczenie z kilku powodów:

Znaczenie kliniczne

  • Umożliwia lekarzom i pacjentom planowanie przyszłego leczenia i opieki43
  • Ułatwia podejmowanie decyzji o zastosowaniu inwazyjnych interwencji terapeutycznych44
  • Pomaga w planowaniu opieki paliatywnej i decyzji dotyczących końca życia45
  • Wspiera określenie kryteriów kwalifikacji do opieki hospicyjnej46

Zastosowanie w badaniach klinicznych

  • Umożliwia lepszą stratyfikację pacjentów47
  • Poprawia projektowanie i interpretację wyników badań klinicznych48
  • Pomaga w selekcji pacjentów o określonych charakterystykach przeżycia do badań nad lekami49

Indywidualizacja prognozy

Modele prognostyczne umożliwiają spersonalizowane podejście do określenia prognozy, zamiast informowania pacjenta jedynie o średnim czasie przeżycia wszystkich pacjentów z ALS.50 Na przykład model opracowany przez Knibb i współpracowników może przewidywać medianę przeżycia od 4 lat do zaledwie 8 miesięcy, a nawet mniej u pacjentów z zajęciem układu oddechowego. Rzeczywisty czas przeżycia mieści się między połową a dwukrotnością mediany u około połowy pacjentów.51

Ograniczenia obecnych modeli prognostycznych

Pomimo znaczących postępów w opracowywaniu modeli prognostycznych dla ALS, istnieją pewne ograniczenia, które należy uwzględnić:

  • Niektórzy pacjenci z ALS doświadczają okresów plateau, podczas gdy inni mają szybką progresję, co utrudnia dokładne prognozowanie52
  • Zastosowanie populacyjnych danych prognostycznych do zindywidualizowanej opieki wymaga rozważnego podejścia i złożonych umiejętności komunikacyjnych53
  • Nie wszystkie modele uwzględniają istotne czynniki leczenia, takie jak stosowanie riluzolu, żywienie dojelitowe czy wentylację54
  • Indywidualne przewidywanie rzadko jest wiarygodne, gdy rozważa się wyłącznie zmienne kliniczne i demograficzne55
  • Pomimo postępów badawczych, prawdopodobnie brakuje systemów wspomagania decyzji klinicznych (CDSS), które pomagałyby lekarzom w codziennej pracy nad prognozą choroby ALS56

Perspektywy na przyszłość w prognozowaniu ALS

W połączeniu z dokładną oceną stanu funkcjonalnego, model ENCALS może być pomocnym narzędziem do przewidywania rokowania w ALS. Potrzebne są dalsze badania, aby określić, czy ENCALS oferuje korzyści prognostyczne w porównaniu z oceną kliniczną specjalisty ALS.57

Przyszłe kierunki badań w dziedzinie prognozowania ALS obejmują:

  • Skupienie się na zbieraniu lub ekstrakcji zmiennych specyficznych dla wyniku i zmieniających się w czasie58
  • Opracowanie bardziej zaawansowanych metodologii, które lepiej uwzględniają informacje czasowe dla poprawy wydajności predykcyjnej podejść opartych na sztucznej inteligencji59
  • Rozwój systemów wspomagania decyzji klinicznych (CDSS) wspierających lekarzy w codziennej pracy z pacjentami z ALS60
  • Walidacja istniejących modeli w niezależnych kohortach pacjentów i rozszerzenie ich o inne ważne czynniki prognostyczne61

Kolejne rozdziały

Zapraszamy do dalszego czytania naszego leksykonu.

Wybierz kolejny rozdział z menu poniżej, aby otworzyć nową podstronę kompedium wiedzy i uzyskać szczegółowe informację o leku, substancji lub chorobie.

  1. 09.04.2026
  2. www.leksykon.com.pl

Materiały źródłowe

  • #1 Development and validation of a 1-year survival prognosis estimation model for Amyotrophic Lateral Sclerosis using manifold learning algorithm UMAP | Scientific Reports
    https://www.nature.com/articles/s41598-020-70125-8
    Amyotrophic Lateral Sclerosis (ALS) is an inexorably progressive neurodegenerative condition with no effective disease modifying therapies. The development and validation of reliable prognostic models is a recognised research priority. We present a prognostic model for survival in ALS where result uncertainty is taken into account. […] Mean survival time from disease onset is typically 3 to 5 years, with death occurring secondary to respiratory failure. […] From a clinical perspective, accurate prognostic indicators are indispensable for optimising multidisciplinary care, planning interventions, advising patients on end-of-life decisions, resource allocation, etc. […] Disease heterogeneity is a recognised barrier to successful clinical trials in ALS, and accurate prognosis prediction would improve patient stratification.
  • #2 Predicting clinical events characterizing the progression of amyotrophic lateral sclerosis via machine learning approaches using routine visits data: a feasibility study | BMC Medical Informatics and Decision Making | Full Text
    https://bmcmedinformdecismak.biomedcentral.com/articles/10.1186/s12911-024-02719-5
    The disease typically results in death within a relatively short span of 3-5 years, although survival times can vary widely and depend on many factors including age, site of onset, rate of disease progression, and presence of comorbidities. […] One of the major challenges in treating ALS is the lack of effective prognostic tools for predicting disease progression. […] Overall, the literature concerning the development of predictive models for clinical outcomes of ALS is still limited as most studies focus on the identification of risk factors based on statistical analyses rather than providing a prediction model. […] Hence, in the future, further studies may focus on the collection or extraction of time-varying and outcome-specific variables as well as the development of more sophisticated methodologies able to consider better temporal information to improve the predictive performance of AI-based approaches.
  • #3 Accurate personalized survival prediction for amyotrophic lateral sclerosis patients | Scientific Reports
    https://www.nature.com/articles/s41598-023-47935-7
    The median survival following the onset of symptoms is 25 years, and respiratory failure is commonly the reason for death. However, the interval between the onset of symptoms and death can range from a few months to more than ten years. This range makes it impossible for clinicians to effectively counsel patients on advance care planning, or to select patients with specific survival characteristics for drug trials. […] Our individual survival curve model provides survival probability for all future time points, and also explicitly deals with censored patients. […] Our learned survival prediction model predicts an individual survival curve (ISD) for each ALS patient. The survival distribution can be more useful than single-time prediction (e.g., Surviving 1 year) when planning future patient treatment because the user can query the predicted survival time for arbitrary survival probabilities.
  • #4 A clinical tool for predicting survival in ALS | Journal of Neurology, Neurosurgery & Psychiatry
    https://jnnp.bmj.com/content/87/12/1361
    Amyotrophic lateral sclerosis (ALS) is a progressive and usually fatal neurodegenerative disease. Survival from diagnosis varies considerably. Several prognostic factors are known, including site of onset (bulbar or limb), age at symptom onset, delay from onset to diagnosis and the use of riluzole and non-invasive ventilation (NIV). Clinicians and patients would benefit from a practical way of using these factors to provide an individualised prognosis. […] The rate at which the condition progresses varies greatly, as does the length of time from symptom onset to death, from a few months to more than 10 years. It is therefore difficult to advise a patient on how long they may expect to live, and on the uncertainty in this prediction, and not every patient wants detailed information; nonetheless, for many patients diagnosed with a life-limiting illness, such an estimate is important for providing hope and enabling them to plan their life and its ending, not to mention improving the design and interpretation of clinical trials.
  • #5 Prediction of survival in amyotrophic lateral sclerosis: a nationwide, Danish cohort study | BMC Neurology | Full Text
    https://bmcneurol.biomedcentral.com/articles/10.1186/s12883-021-02187-8
    The median survival time from onset of symptoms until the primary endpoint (death or initiation of invasive mechanical ventilation) was 36 months. The median survival time from time of diagnosis until the primary endpoint was 14 months. […] The covariates FS, age at onset of symptom, and time from onset of symptoms to diagnosis were associated with survival time and analyzed further by stepwise, multivariate regression. […] After dividing the ALS cohort into two groups by the 50% quantile of FS, the median survival time for the group with the slower progression rate (FS ≤ 0.68) was 46.5 months as compared with the group with the faster progression rate (FS > 0.68) (25.2 months). […] In this Danish ALS cohort study, FS, age at onset of disease, and time from onset of symptoms until diagnosis emerged as independent predictors of survival. The study substantiates previous findings of FS as a prognostic biomarker, which is easily implemented by neurologists to guide prognosis and decision-making in the initial phase of the disease. Furthermore, the symptom progression rate may predict survival, whether calculated at the time of diagnosis or later during the course of the disease.
  • #6 Predicting prognosis in amyotrophic lateral sclerosis: a simple algorithm
    https://pmc.ncbi.nlm.nih.gov/articles/PMC4469087/
    The objective of the study was to develop and validate a practical prognostic index for patients with amyotrophic lateral scleroses (ALS) using information available at the first clinical consultation. […] In the Training sub-cohort (n = 117), significant predictors of prognoses were site of disease onset (HR = 1.7, p = 0.012); ALSFRS-R slope prior to first evaluation (HR = 2.8, p 0.0001), and executive dysfunction (HR = 2.11, p = 0.001). […] A simple algorithm using variables that can be gathered at first patient encounter, validated in an independent patient series, reliably predicts prognoses in ALS patients. […] The identification of the key factors that can influence outcome is important for effective timing of medical interventions and for appropriate stratification in clinical trials.
  • #7 Development and validation of a 1-year survival prognosis estimation model for Amyotrophic Lateral Sclerosis using manifold learning algorithm UMAP | Scientific Reports
    https://www.nature.com/articles/s41598-020-70125-8
    Amyotrophic Lateral Sclerosis (ALS) is an inexorably progressive neurodegenerative condition with no effective disease modifying therapies. The development and validation of reliable prognostic models is a recognised research priority. We present a prognostic model for survival in ALS where result uncertainty is taken into account. […] Mean survival time from disease onset is typically 3 to 5 years, with death occurring secondary to respiratory failure. […] From a clinical perspective, accurate prognostic indicators are indispensable for optimising multidisciplinary care, planning interventions, advising patients on end-of-life decisions, resource allocation, etc. […] Disease heterogeneity is a recognised barrier to successful clinical trials in ALS, and accurate prognosis prediction would improve patient stratification.
  • #8 Predicting prognosis in amyotrophic lateral sclerosis: a simple algorithm
    https://pmc.ncbi.nlm.nih.gov/articles/PMC4469087/
    Previously reported negative prognostic indicators in ALS include older age of onset, bulbar onset of disease, and short delay to diagnosis. […] Cognitive impairment, particularly executive dysfunction, has also been shown to be associated with worse prognosis. […] The survival effect of all the three factors persisted on multivariate analyses: (1) non-spinal onset of disease, HR = 1.7 (95 % CI 1.122.63, SE 0.22, p = 0.012); (2) ALSFRS-R slope: HR = 2.8 (95 % 2.003.81, SE = 0.166, p 0.0001); and executive dysfunction: HR = 2.11 (95 % 1.373.28, SE = 0.233, p = 0.001). […] In the validation cohorts, a high-risk classification was associated with a positive predictive value for poor prognosis of 73.385.7 % and a negative predictive value (NPV) for good prognosis of 93.3100 %. […] A simple prognostic index, named the ALS Prognostic Index (or API), was generated (Fig. 1) with possible scores ranging from zero to six (higher scores indicating worse predicted prognosis).
  • #9 Predicting prognosis in amyotrophic lateral sclerosis: a simple algorithm
    https://pmc.ncbi.nlm.nih.gov/articles/PMC4469087/
    Previously reported negative prognostic indicators in ALS include older age of onset, bulbar onset of disease, and short delay to diagnosis. […] Cognitive impairment, particularly executive dysfunction, has also been shown to be associated with worse prognosis. […] The survival effect of all the three factors persisted on multivariate analyses: (1) non-spinal onset of disease, HR = 1.7 (95 % CI 1.122.63, SE 0.22, p = 0.012); (2) ALSFRS-R slope: HR = 2.8 (95 % 2.003.81, SE = 0.166, p 0.0001); and executive dysfunction: HR = 2.11 (95 % 1.373.28, SE = 0.233, p = 0.001). […] In the validation cohorts, a high-risk classification was associated with a positive predictive value for poor prognosis of 73.385.7 % and a negative predictive value (NPV) for good prognosis of 93.3100 %. […] A simple prognostic index, named the ALS Prognostic Index (or API), was generated (Fig. 1) with possible scores ranging from zero to six (higher scores indicating worse predicted prognosis).
  • #10 Predicting prognosis in amyotrophic lateral sclerosis: a simple algorithm
    https://pmc.ncbi.nlm.nih.gov/articles/PMC4469087/
    Previously reported negative prognostic indicators in ALS include older age of onset, bulbar onset of disease, and short delay to diagnosis. […] Cognitive impairment, particularly executive dysfunction, has also been shown to be associated with worse prognosis. […] The survival effect of all the three factors persisted on multivariate analyses: (1) non-spinal onset of disease, HR = 1.7 (95 % CI 1.122.63, SE 0.22, p = 0.012); (2) ALSFRS-R slope: HR = 2.8 (95 % 2.003.81, SE = 0.166, p 0.0001); and executive dysfunction: HR = 2.11 (95 % 1.373.28, SE = 0.233, p = 0.001). […] In the validation cohorts, a high-risk classification was associated with a positive predictive value for poor prognosis of 73.385.7 % and a negative predictive value (NPV) for good prognosis of 93.3100 %. […] A simple prognostic index, named the ALS Prognostic Index (or API), was generated (Fig. 1) with possible scores ranging from zero to six (higher scores indicating worse predicted prognosis).
  • #11 Predictors of survival in patients with amyotrophic lateral sclerosis: A large meta-analysis
    https://pmc.ncbi.nlm.nih.gov/articles/PMC8646173/
    The survival time of amyotrophic lateral sclerosis (ALS) is greatly variable and protective or risk effects of the potential survival predictors are controversial. […] Twenty-five prediction factors, including twenty non-intervenable and five intervenable factors, were associated with ALS survival. Among them, NFL (HR:3.70, 6.80, in serum and CSF, respectively), FTD (HR:2.98), ALSFRS-R change (HR:2.37), respiratory subtype (HR:2.20), executive dysfunction (HR:2.10) and age of onset (HR:1.03) were superior predictors for poor prognosis, but pLMN or pUMN (HR:0.32), baseline ALSFRS-R score (HR:0.95), duration (HR:0.96), diagnostic delay (HR:0.97) were superior predictors for a good prognosis. […] Our study provided a comprehensive and quantitative index for assessing the prognosis for ALS patients, and the identified non-intervenable or intervenable factors will facilitate the development of treatment strategies for ALS.
  • #12 Predictors of survival in patients with amyotrophic lateral sclerosis: A large meta-analysis
    https://pmc.ncbi.nlm.nih.gov/articles/PMC8646173/
    The survival time of amyotrophic lateral sclerosis (ALS) is greatly variable and protective or risk effects of the potential survival predictors are controversial. […] Twenty-five prediction factors, including twenty non-intervenable and five intervenable factors, were associated with ALS survival. Among them, NFL (HR:3.70, 6.80, in serum and CSF, respectively), FTD (HR:2.98), ALSFRS-R change (HR:2.37), respiratory subtype (HR:2.20), executive dysfunction (HR:2.10) and age of onset (HR:1.03) were superior predictors for poor prognosis, but pLMN or pUMN (HR:0.32), baseline ALSFRS-R score (HR:0.95), duration (HR:0.96), diagnostic delay (HR:0.97) were superior predictors for a good prognosis. […] Our study provided a comprehensive and quantitative index for assessing the prognosis for ALS patients, and the identified non-intervenable or intervenable factors will facilitate the development of treatment strategies for ALS.
  • #13 Predictors of survival in patients with amyotrophic lateral sclerosis: A large meta-analysis
    https://pmc.ncbi.nlm.nih.gov/articles/PMC8646173/
    The survival time of amyotrophic lateral sclerosis (ALS) is greatly variable and protective or risk effects of the potential survival predictors are controversial. […] Twenty-five prediction factors, including twenty non-intervenable and five intervenable factors, were associated with ALS survival. Among them, NFL (HR:3.70, 6.80, in serum and CSF, respectively), FTD (HR:2.98), ALSFRS-R change (HR:2.37), respiratory subtype (HR:2.20), executive dysfunction (HR:2.10) and age of onset (HR:1.03) were superior predictors for poor prognosis, but pLMN or pUMN (HR:0.32), baseline ALSFRS-R score (HR:0.95), duration (HR:0.96), diagnostic delay (HR:0.97) were superior predictors for a good prognosis. […] Our study provided a comprehensive and quantitative index for assessing the prognosis for ALS patients, and the identified non-intervenable or intervenable factors will facilitate the development of treatment strategies for ALS.
  • #14 Predictors of survival in patients with amyotrophic lateral sclerosis: A large meta-analysis
    https://pmc.ncbi.nlm.nih.gov/articles/PMC8646173/
    The survival time of amyotrophic lateral sclerosis (ALS) is greatly variable and protective or risk effects of the potential survival predictors are controversial. […] Twenty-five prediction factors, including twenty non-intervenable and five intervenable factors, were associated with ALS survival. Among them, NFL (HR:3.70, 6.80, in serum and CSF, respectively), FTD (HR:2.98), ALSFRS-R change (HR:2.37), respiratory subtype (HR:2.20), executive dysfunction (HR:2.10) and age of onset (HR:1.03) were superior predictors for poor prognosis, but pLMN or pUMN (HR:0.32), baseline ALSFRS-R score (HR:0.95), duration (HR:0.96), diagnostic delay (HR:0.97) were superior predictors for a good prognosis. […] Our study provided a comprehensive and quantitative index for assessing the prognosis for ALS patients, and the identified non-intervenable or intervenable factors will facilitate the development of treatment strategies for ALS.
  • #15 Predictors of survival in patients with amyotrophic lateral sclerosis: A large meta-analysis
    https://pmc.ncbi.nlm.nih.gov/articles/PMC8646173/
    The survival time of amyotrophic lateral sclerosis (ALS) is greatly variable and protective or risk effects of the potential survival predictors are controversial. […] Twenty-five prediction factors, including twenty non-intervenable and five intervenable factors, were associated with ALS survival. Among them, NFL (HR:3.70, 6.80, in serum and CSF, respectively), FTD (HR:2.98), ALSFRS-R change (HR:2.37), respiratory subtype (HR:2.20), executive dysfunction (HR:2.10) and age of onset (HR:1.03) were superior predictors for poor prognosis, but pLMN or pUMN (HR:0.32), baseline ALSFRS-R score (HR:0.95), duration (HR:0.96), diagnostic delay (HR:0.97) were superior predictors for a good prognosis. […] Our study provided a comprehensive and quantitative index for assessing the prognosis for ALS patients, and the identified non-intervenable or intervenable factors will facilitate the development of treatment strategies for ALS.
  • #16 (PDF) Prognosis for patients with amyotrophic lateral sclerosis: development and validation of a personalised prediction model
    https://www.academia.edu/99261305/Prognosis_for_patients_with_amyotrophic_lateral_sclerosis_development_and_validation_of_a_personalised_prediction_model
    In multivariate analysis, predictors of long survival were younger age at diagnosis, longer interval onset-diagnosis and clinical features with predominant upper motor neuron signs. […] The aim of this study was to determine the predictors of disease progression in a group of 832 patients with the diagnosis of definite or probable amyotrophic lateral sclerosis (ALS). […] Age, site of symptom onset, time between first symptom and first examination, total AALS score at first examination, and AALS preslope were significant and independent covariates of disease progression in our population. […] The median survival time from onset to death/tracheostomy was 44 months. […] In the multivariate analysis age at onset, diagnostic delay, phenotypes but not site of onset, presence/absence of dementia, BMI, riluzole use, R-EEC criteria were independent prognostic factors of survival in ALS. […] The significantly greater mortality of older patients proved not to result from a rise in expected mortality only.
  • #17 FF #437 Amyotrophic Lateral Sclerosis: Prognostication in Advanced Illness   | Palliative Care Network of Wisconsin
    https://www.mypcnow.org/fast-fact/amyotrophic-lateral-sclerosis-prognostication-in-advanced-illness-%EF%BF%BC/
    – Site of onset (spinal vs bulbar) […] – Age of onset of muscle weakness or bulbar symptoms […] – Time from onset of weakness or bulbar symptoms to diagnosis […] – Whether the diagnosis of ALS was definite, probable, or possible […] – Forced vital capacity (FVC) […] – The revised ALS Functional Rating Scale (ALSFRS-R) […] – The presence of frontotemporal dementia (cognitive factor) […] – Presence of the C9orf72 mutation (Genetic factor) […] Prognostic evidence for ENCALS and ALS hospice eligibility guidelines: […] – ENCALS has been critiqued since it does not include relevant treatment factors such as riluzole, enteral nutrition, or ventilation as prognostic variables. Yet, the authors note that the median survival benefit of riluzole in a Cochrane meta-analysis was three months. This is substantially smaller than the combined effect of the predictors in ENCAL (HR 0.84 vs 15.29) (5).
  • #18 Predictors of survival in patients with amyotrophic lateral sclerosis: A large meta-analysis
    https://pmc.ncbi.nlm.nih.gov/articles/PMC8646173/
    Among them, the superior predictors for poor prognosis were neurofilament light chain (NFL, both in serum and cerebrospinal fluid), frontotemporal dementia (FTD), changes in amyotrophic lateral sclerosis functional rating scale-revised (ALSFRS-R), respiratory subtype, executive dysfunction and age at onset. But pure lower motor neuron (pLMN) or pure upper motor neuron (pUMN), baseline ALSFRS-R score, duration, diagnostic delay were superior predictors for a good prognosis. […] Our results did not support the involvement of gender, education level, diabetes, hypertension, noninvasive ventilation, gastrostomy, and statins in ALS survival. […] This study provided a detailed summary of survival predictors of ALS which were then graded. Our work may help guide healthcare workers and ALS patients in scheduling disease management and in guiding clinical trials design.
  • #19 Predictors of survival in patients with amyotrophic lateral sclerosis: A large meta-analysis
    https://pmc.ncbi.nlm.nih.gov/articles/PMC8646173/
    Among them, the superior predictors for poor prognosis were neurofilament light chain (NFL, both in serum and cerebrospinal fluid), frontotemporal dementia (FTD), changes in amyotrophic lateral sclerosis functional rating scale-revised (ALSFRS-R), respiratory subtype, executive dysfunction and age at onset. But pure lower motor neuron (pLMN) or pure upper motor neuron (pUMN), baseline ALSFRS-R score, duration, diagnostic delay were superior predictors for a good prognosis. […] Our results did not support the involvement of gender, education level, diabetes, hypertension, noninvasive ventilation, gastrostomy, and statins in ALS survival. […] This study provided a detailed summary of survival predictors of ALS which were then graded. Our work may help guide healthcare workers and ALS patients in scheduling disease management and in guiding clinical trials design.
  • #20 Predictors of survival in patients with amyotrophic lateral sclerosis: A large meta-analysis
    https://pmc.ncbi.nlm.nih.gov/articles/PMC8646173/
    Among them, the superior predictors for poor prognosis were neurofilament light chain (NFL, both in serum and cerebrospinal fluid), frontotemporal dementia (FTD), changes in amyotrophic lateral sclerosis functional rating scale-revised (ALSFRS-R), respiratory subtype, executive dysfunction and age at onset. But pure lower motor neuron (pLMN) or pure upper motor neuron (pUMN), baseline ALSFRS-R score, duration, diagnostic delay were superior predictors for a good prognosis. […] Our results did not support the involvement of gender, education level, diabetes, hypertension, noninvasive ventilation, gastrostomy, and statins in ALS survival. […] This study provided a detailed summary of survival predictors of ALS which were then graded. Our work may help guide healthcare workers and ALS patients in scheduling disease management and in guiding clinical trials design.
  • #21 (PDF) Prognosis for patients with amyotrophic lateral sclerosis: development and validation of a personalised prediction model
    https://www.academia.edu/99261305/Prognosis_for_patients_with_amyotrophic_lateral_sclerosis_development_and_validation_of_a_personalised_prediction_model
    In multivariate analysis, predictors of long survival were younger age at diagnosis, longer interval onset-diagnosis and clinical features with predominant upper motor neuron signs. […] The aim of this study was to determine the predictors of disease progression in a group of 832 patients with the diagnosis of definite or probable amyotrophic lateral sclerosis (ALS). […] Age, site of symptom onset, time between first symptom and first examination, total AALS score at first examination, and AALS preslope were significant and independent covariates of disease progression in our population. […] The median survival time from onset to death/tracheostomy was 44 months. […] In the multivariate analysis age at onset, diagnostic delay, phenotypes but not site of onset, presence/absence of dementia, BMI, riluzole use, R-EEC criteria were independent prognostic factors of survival in ALS. […] The significantly greater mortality of older patients proved not to result from a rise in expected mortality only.
  • #22 (PDF) Prognosis for patients with amyotrophic lateral sclerosis: development and validation of a personalised prediction model
    https://www.academia.edu/99261305/Prognosis_for_patients_with_amyotrophic_lateral_sclerosis_development_and_validation_of_a_personalised_prediction_model
    In multivariate analysis, predictors of long survival were younger age at diagnosis, longer interval onset-diagnosis and clinical features with predominant upper motor neuron signs. […] The aim of this study was to determine the predictors of disease progression in a group of 832 patients with the diagnosis of definite or probable amyotrophic lateral sclerosis (ALS). […] Age, site of symptom onset, time between first symptom and first examination, total AALS score at first examination, and AALS preslope were significant and independent covariates of disease progression in our population. […] The median survival time from onset to death/tracheostomy was 44 months. […] In the multivariate analysis age at onset, diagnostic delay, phenotypes but not site of onset, presence/absence of dementia, BMI, riluzole use, R-EEC criteria were independent prognostic factors of survival in ALS. […] The significantly greater mortality of older patients proved not to result from a rise in expected mortality only.
  • #23 (PDF) Prognosis for patients with amyotrophic lateral sclerosis: development and validation of a personalised prediction model
    https://www.academia.edu/99261305/Prognosis_for_patients_with_amyotrophic_lateral_sclerosis_development_and_validation_of_a_personalised_prediction_model
    In multivariate analysis, predictors of long survival were younger age at diagnosis, longer interval onset-diagnosis and clinical features with predominant upper motor neuron signs. […] The aim of this study was to determine the predictors of disease progression in a group of 832 patients with the diagnosis of definite or probable amyotrophic lateral sclerosis (ALS). […] Age, site of symptom onset, time between first symptom and first examination, total AALS score at first examination, and AALS preslope were significant and independent covariates of disease progression in our population. […] The median survival time from onset to death/tracheostomy was 44 months. […] In the multivariate analysis age at onset, diagnostic delay, phenotypes but not site of onset, presence/absence of dementia, BMI, riluzole use, R-EEC criteria were independent prognostic factors of survival in ALS. […] The significantly greater mortality of older patients proved not to result from a rise in expected mortality only.
  • #24
    https://journals.lww.com/nrronline/fulltext/2021/16030/creatine_kinase_in_the_diagnosis_and_prognostic.36.aspx
    Creatine kinase is a muscle enzyme that has been reported at various levels in different studies involving patients with amyotrophic lateral sclerosis. […] After adjusting for prognostic covariates, higher log creatine kinase values were correlated with higher overall survival in the amyotrophic lateral sclerosis patients. […] Together, our results suggest that serum creatine kinase levels can be used as an independent factor for predicting the prognosis of amyotrophic lateral sclerosis patients. […] Furthermore, serum CK levels were related to overall survival in ALS patients. […] Higher CK levels were associated with a better prognosis, and CK levels decreased as the disease progressed. […] In the present study, we included 582 ALS patients and adjusted for other prognostic factors, and found that higher serum CK levels were associated with better survival.
  • #25 Predictors of survival in patients with amyotrophic lateral sclerosis: A large meta-analysis
    https://pmc.ncbi.nlm.nih.gov/articles/PMC8646173/
    Among them, the superior predictors for poor prognosis were neurofilament light chain (NFL, both in serum and cerebrospinal fluid), frontotemporal dementia (FTD), changes in amyotrophic lateral sclerosis functional rating scale-revised (ALSFRS-R), respiratory subtype, executive dysfunction and age at onset. But pure lower motor neuron (pLMN) or pure upper motor neuron (pUMN), baseline ALSFRS-R score, duration, diagnostic delay were superior predictors for a good prognosis. […] Our results did not support the involvement of gender, education level, diabetes, hypertension, noninvasive ventilation, gastrostomy, and statins in ALS survival. […] This study provided a detailed summary of survival predictors of ALS which were then graded. Our work may help guide healthcare workers and ALS patients in scheduling disease management and in guiding clinical trials design.
  • #26 Predictors of survival in patients with amyotrophic lateral sclerosis: A large meta-analysis
    https://pmc.ncbi.nlm.nih.gov/articles/PMC8646173/
    Among them, the superior predictors for poor prognosis were neurofilament light chain (NFL, both in serum and cerebrospinal fluid), frontotemporal dementia (FTD), changes in amyotrophic lateral sclerosis functional rating scale-revised (ALSFRS-R), respiratory subtype, executive dysfunction and age at onset. But pure lower motor neuron (pLMN) or pure upper motor neuron (pUMN), baseline ALSFRS-R score, duration, diagnostic delay were superior predictors for a good prognosis. […] Our results did not support the involvement of gender, education level, diabetes, hypertension, noninvasive ventilation, gastrostomy, and statins in ALS survival. […] This study provided a detailed summary of survival predictors of ALS which were then graded. Our work may help guide healthcare workers and ALS patients in scheduling disease management and in guiding clinical trials design.
  • #27 Predictors of survival in patients with amyotrophic lateral sclerosis: A large meta-analysis
    https://pmc.ncbi.nlm.nih.gov/articles/PMC8646173/
    Among them, the superior predictors for poor prognosis were neurofilament light chain (NFL, both in serum and cerebrospinal fluid), frontotemporal dementia (FTD), changes in amyotrophic lateral sclerosis functional rating scale-revised (ALSFRS-R), respiratory subtype, executive dysfunction and age at onset. But pure lower motor neuron (pLMN) or pure upper motor neuron (pUMN), baseline ALSFRS-R score, duration, diagnostic delay were superior predictors for a good prognosis. […] Our results did not support the involvement of gender, education level, diabetes, hypertension, noninvasive ventilation, gastrostomy, and statins in ALS survival. […] This study provided a detailed summary of survival predictors of ALS which were then graded. Our work may help guide healthcare workers and ALS patients in scheduling disease management and in guiding clinical trials design.
  • #28 Predictors of survival in patients with amyotrophic lateral sclerosis: A large meta-analysis
    https://pmc.ncbi.nlm.nih.gov/articles/PMC8646173/
    Among them, the superior predictors for poor prognosis were neurofilament light chain (NFL, both in serum and cerebrospinal fluid), frontotemporal dementia (FTD), changes in amyotrophic lateral sclerosis functional rating scale-revised (ALSFRS-R), respiratory subtype, executive dysfunction and age at onset. But pure lower motor neuron (pLMN) or pure upper motor neuron (pUMN), baseline ALSFRS-R score, duration, diagnostic delay were superior predictors for a good prognosis. […] Our results did not support the involvement of gender, education level, diabetes, hypertension, noninvasive ventilation, gastrostomy, and statins in ALS survival. […] This study provided a detailed summary of survival predictors of ALS which were then graded. Our work may help guide healthcare workers and ALS patients in scheduling disease management and in guiding clinical trials design.
  • #29 Predictors of survival in patients with amyotrophic lateral sclerosis: A large meta-analysis
    https://pmc.ncbi.nlm.nih.gov/articles/PMC8646173/
    Among them, the superior predictors for poor prognosis were neurofilament light chain (NFL, both in serum and cerebrospinal fluid), frontotemporal dementia (FTD), changes in amyotrophic lateral sclerosis functional rating scale-revised (ALSFRS-R), respiratory subtype, executive dysfunction and age at onset. But pure lower motor neuron (pLMN) or pure upper motor neuron (pUMN), baseline ALSFRS-R score, duration, diagnostic delay were superior predictors for a good prognosis. […] Our results did not support the involvement of gender, education level, diabetes, hypertension, noninvasive ventilation, gastrostomy, and statins in ALS survival. […] This study provided a detailed summary of survival predictors of ALS which were then graded. Our work may help guide healthcare workers and ALS patients in scheduling disease management and in guiding clinical trials design.
  • #30 Predictors of survival in patients with amyotrophic lateral sclerosis: A large meta-analysis
    https://pmc.ncbi.nlm.nih.gov/articles/PMC8646173/
    Among them, the superior predictors for poor prognosis were neurofilament light chain (NFL, both in serum and cerebrospinal fluid), frontotemporal dementia (FTD), changes in amyotrophic lateral sclerosis functional rating scale-revised (ALSFRS-R), respiratory subtype, executive dysfunction and age at onset. But pure lower motor neuron (pLMN) or pure upper motor neuron (pUMN), baseline ALSFRS-R score, duration, diagnostic delay were superior predictors for a good prognosis. […] Our results did not support the involvement of gender, education level, diabetes, hypertension, noninvasive ventilation, gastrostomy, and statins in ALS survival. […] This study provided a detailed summary of survival predictors of ALS which were then graded. Our work may help guide healthcare workers and ALS patients in scheduling disease management and in guiding clinical trials design.
  • #31 FF #437 Amyotrophic Lateral Sclerosis: Prognostication in Advanced Illness   | Palliative Care Network of Wisconsin
    https://www.mypcnow.org/fast-fact/amyotrophic-lateral-sclerosis-prognostication-in-advanced-illness-%EF%BF%BC/
    – Site of onset (spinal vs bulbar) […] – Age of onset of muscle weakness or bulbar symptoms […] – Time from onset of weakness or bulbar symptoms to diagnosis […] – Whether the diagnosis of ALS was definite, probable, or possible […] – Forced vital capacity (FVC) […] – The revised ALS Functional Rating Scale (ALSFRS-R) […] – The presence of frontotemporal dementia (cognitive factor) […] – Presence of the C9orf72 mutation (Genetic factor) […] Prognostic evidence for ENCALS and ALS hospice eligibility guidelines: […] – ENCALS has been critiqued since it does not include relevant treatment factors such as riluzole, enteral nutrition, or ventilation as prognostic variables. Yet, the authors note that the median survival benefit of riluzole in a Cochrane meta-analysis was three months. This is substantially smaller than the combined effect of the predictors in ENCAL (HR 0.84 vs 15.29) (5).
  • #32 Predicting prognosis in amyotrophic lateral sclerosis: a simple algorithm
    https://pmc.ncbi.nlm.nih.gov/articles/PMC4469087/
    Previously reported negative prognostic indicators in ALS include older age of onset, bulbar onset of disease, and short delay to diagnosis. […] Cognitive impairment, particularly executive dysfunction, has also been shown to be associated with worse prognosis. […] The survival effect of all the three factors persisted on multivariate analyses: (1) non-spinal onset of disease, HR = 1.7 (95 % CI 1.122.63, SE 0.22, p = 0.012); (2) ALSFRS-R slope: HR = 2.8 (95 % 2.003.81, SE = 0.166, p 0.0001); and executive dysfunction: HR = 2.11 (95 % 1.373.28, SE = 0.233, p = 0.001). […] In the validation cohorts, a high-risk classification was associated with a positive predictive value for poor prognosis of 73.385.7 % and a negative predictive value (NPV) for good prognosis of 93.3100 %. […] A simple prognostic index, named the ALS Prognostic Index (or API), was generated (Fig. 1) with possible scores ranging from zero to six (higher scores indicating worse predicted prognosis).
  • #33 Predicting prognosis in amyotrophic lateral sclerosis: a simple algorithm
    https://pmc.ncbi.nlm.nih.gov/articles/PMC4469087/
    The index and prognostic risk group classification procedure were applied to the Irish Training set. […] In all three cohorts the ALS risk groups predicted survival time (log-rank test p 0.0001 in all three cohorts) with no overlap of the 95 % confidence intervals. […] Our study now incorporates for the first time cognitive status into a prognostic model. […] The simplicity and reliability of the model has the potential to improve stratification protocols in future clinical trials.
  • #34 FF #437 Amyotrophic Lateral Sclerosis: Prognostication in Advanced Illness   – Palliative Care Network of Wisconsin
    https://www.mypcnow.org/fast-fact/amyotrophic-lateral-sclerosis-prognostication-in-advanced-illness-%EF%BF%BC/?print=print
    Most patients with ALS have a linear pattern of decline, however, the speed of that decline is quite variable between individuals. Median survival from time of onset has been shown to be three to five years (1). […] The European Network for the Cure of ALS (ENCALS) model is the most recognized evidence-based, disease-specific model to predict prognosis in ALS (3). It was developed to predict survival for patients with ALS who were not treated with a tracheostomy nor continuous non-invasive ventilation. […] The ENCALS model can predict survival time in months and can thus be used to determine survival likelihood less than six months, indicating hospice eligibility. […] In conjunction with a careful assessment of functional status, the ENCALS model can be a helpful tool to predict prognosis in ALS. Further research is needed to determine if ENCALS offers prognostic benefit over clinician gestalt from an ALS specialist.
  • #35 FF #437 Amyotrophic Lateral Sclerosis: Prognostication in Advanced Illness   | Palliative Care Network of Wisconsin
    https://www.mypcnow.org/fast-fact/amyotrophic-lateral-sclerosis-prognostication-in-advanced-illness-%EF%BF%BC/
    Disease-specific prognostication in ALS: The European Network for the Cure of ALS (ENCALS) model is the most recognized evidence-based, disease-specific model to predict prognosis in ALS (3). It was developed to predict survival for patients with ALS who were not treated with a tracheostomy nor continuous non-invasive ventilation. Survival outcomes are reported three ways: as an individualized prognostic estimate (specific patient compared to average patient), prognostic groups (very long, long, intermediate, short, or very short), or as a point estimate within a survival curve. ENCALS uses clinical, cognitive, and genetic variables to predict survival based on data from over 11,000 European patients with ALS from 1992-2016. […] The most relevant prognostic factors from ENCALS include:
  • #36 FF #437 Amyotrophic Lateral Sclerosis: Prognostication in Advanced Illness   | Palliative Care Network of Wisconsin
    https://www.mypcnow.org/fast-fact/amyotrophic-lateral-sclerosis-prognostication-in-advanced-illness-%EF%BF%BC/
    – A systematic review compared nineteen predictor models for survival in ALS. Only ENCALS was shown to have good discrimination and calibration and a low risk of bias (6). […] – The ENCALS model can predict survival time in months and can thus be used to determine survival likelihood less than six months, indicating hospice eligibility. […] – The validity of hospice eligibility criteria in predicting prognosis in ALS is less known. A 2004 study of 97 consecutive ALS patients admitted into hospice from a tertiary ALS center found that although only five met Medicare criteria at the time of enrollment (7). While the mean number of days on hospice was 85, there was wide range: 1-534 days (7). The Medicare criteria have subsequently been revised; however, the sensitivity and specificity of the revised Medicare criteria remain unknown.
  • #37 FF #437 Amyotrophic Lateral Sclerosis: Prognostication in Advanced Illness   | Palliative Care Network of Wisconsin
    https://www.mypcnow.org/fast-fact/amyotrophic-lateral-sclerosis-prognostication-in-advanced-illness-%EF%BF%BC/
    – A systematic review compared nineteen predictor models for survival in ALS. Only ENCALS was shown to have good discrimination and calibration and a low risk of bias (6). […] – The ENCALS model can predict survival time in months and can thus be used to determine survival likelihood less than six months, indicating hospice eligibility. […] – The validity of hospice eligibility criteria in predicting prognosis in ALS is less known. A 2004 study of 97 consecutive ALS patients admitted into hospice from a tertiary ALS center found that although only five met Medicare criteria at the time of enrollment (7). While the mean number of days on hospice was 85, there was wide range: 1-534 days (7). The Medicare criteria have subsequently been revised; however, the sensitivity and specificity of the revised Medicare criteria remain unknown.
  • #38 Development and validation of a 1-year survival prognosis estimation model for Amyotrophic Lateral Sclerosis using manifold learning algorithm UMAP | Scientific Reports
    https://www.nature.com/articles/s41598-020-70125-8
    However, individualised prediction is seldom reliable when clinical and demographic variables are considered alone. […] There is a growing trend to develop accurate prognostic tools based on a combination of prognostic factors, using supervised machine learning models such as random forests, regression models, neural networks with random forests and boosting algorithms. […] The model is easily updated, works with a limited set of features and factors result uncertainty in. […] Taking advantage of the UMAP projection, other prognosis outcomes and different time frames can be explored. […] The primary outcome was 1-year survival. […] The choice of predictors was based on feature completeness after database cross-referencing. […] Patient survival was on average above 75% for all datasets, and 1-year average ALSFRS was above 17 for all datasets.
  • #39 Frontiers | Machine Learning Solutions Applied to Amyotrophic Lateral Sclerosis Prognosis: A Review
    https://www.frontiersin.org/journals/computer-science/articles/10.3389/fcomp.2022.869140/full
    The prognosis of Amyotrophic Lateral Sclerosis (ALS), a complex and rare disease, represents a challenging and essential task to better comprehend its progression and improve patients’ quality of life. […] The studies evaluated and used different ML algorithms, techniques, datasets, sample sizes, biomarkers, and performance metrics. Based on the results, three distinct types of prediction were identified: Disease Progression, Survival Time, and Need for Support. […] The Disease Progression prediction aimed to estimate the patient’s state at a given moment in the future and was the type most addressed by the studies included (70%). The Survival Time prediction aimed to estimate the occurrence of death from a baseline date to a point-time in the future, such as the probability of death after 12 months from symptoms onset. The Need for Support prediction aimed to estimate the moment when patients will need more specialized support.
  • #40 Development and validation of a 1-year survival prognosis estimation model for Amyotrophic Lateral Sclerosis using manifold learning algorithm UMAP | Scientific Reports
    https://www.nature.com/articles/s41598-020-70125-8
    1-year survival rates zones were identified by dividing the UMAP projection space into multiple small square cells. […] These zones were designed to have distinct survival rates. […] The model was compared to logistic regression and random forest models. […] Our study demonstrated the utility of UMAP for survival analysis in ALS. […] We proposed a simple 1-year survival estimation model which fared well against the tested machine learning models although performance metrics could only be grossly approximated. […] Given the available data, 1-year survival was a good proxy of overall survival. […] In conclusion, we have successfully implemented a simple 1-year survival model partially based on a novel non-linear unsupervised learning method.
  • #41 Predicting functional impairment trajectories in amyotrophic lateral sclerosis: a probabilistic, multifactorial model of disease progression | Journal of Neurology
    https://link.springer.com/article/10.1007/s00415-022-11022-0
    The prediction accuracy was assessed by comparing the predicted patients’ prognosis with the real data: different performance metrics confirmed that the proposed models possess good performance in terms of both survival and domain impairment prediction. […] The DBN model also allows patient cohort stratification, i.e., the partitioning of subjects through the identification of variables that affect the velocity of disease progression or survival. […] The developed tool can also be used to generate in silico populations. For example, it is possible to simulate a population of subjects with bulbar onset by sampling the other variables from real data.
  • #42 Frontiers | Machine Learning Solutions Applied to Amyotrophic Lateral Sclerosis Prognosis: A Review
    https://www.frontiersin.org/journals/computer-science/articles/10.3389/fcomp.2022.869140/full
    The biomarkers identified as relevant in more than one study were the ALSFRS/ALSFRS-R, disease duration, Forced Vital Capacity, Body Mass Index, age at onset, and Creatinine. […] The main objective of this study is to investigate ML approaches on ALS prognosis that analyzed less complex biomarkers, which can be potentially applied to develop clinical decision support systems to assist physicians in the real-world ALS clinical setting. […] The studies presented promissory results that can be applied in developing decision support systems. […] Despite the research advances, there is a probable lack of CDSS to assist the physicians in their daily work on ALS disease prognosis.
  • #43 Accurate personalized survival prediction for amyotrophic lateral sclerosis patients | Scientific Reports
    https://www.nature.com/articles/s41598-023-47935-7
    Amyotrophic Lateral Sclerosis (ALS) is a rapidly progressive neurodegenerative disease. Accurately predicting the survival time for ALS patients can help patients and clinicians to plan for future treatment and care. We describe the application of a machine-learned tool that incorporates clinical features and cortical thickness from brain magnetic resonance (MR) images to estimate the time until a composite respiratory failure event for ALS patients, and presents the prediction as individual survival distributions (ISDs). These ISDs provide the probability of survival (none of the respiratory failures) at multiple future time points, for each individual patient. Our learner considers several survival prediction models, and selects the best model to provide predictions. We evaluate our learned model using the mean absolute error margin (MAE-margin), a modified version of mean absolute error that handles data with censored outcomes. We show that our tool can provide helpful information for patients and clinicians in planning future treatment.
  • #44 (PDF) Prognosis for patients with amyotrophic lateral sclerosis: development and validation of a personalised prediction model
    https://www.academia.edu/99261305/Prognosis_for_patients_with_amyotrophic_lateral_sclerosis_development_and_validation_of_a_personalised_prediction_model
    Amyotrophic lateral sclerosis (ALS) is a relentlessly progressive, fatal motor neuron disease with a variable natural history. There are no accurate models that predict the disease course and outcomes, which complicates risk assessment and counselling for individual patients, stratification of patients for trials, and timing of interventions. We therefore aimed to develop and validate a model for predicting a composite survival endpoint for individual patients with ALS. […] The early recognition of fast progression is essential for patients and neurologists to weigh up invasive therapeutic interventions. […] In a prospective, population-based cohort of ALS patients in Rhineland-Palatinate, Germany, we identified significant prognostic factors at time of diagnosis that allow prediction of early death within first 12 months.
  • #45 A clinical tool for predicting survival in ALS | Journal of Neurology, Neurosurgery & Psychiatry
    https://jnnp.bmj.com/content/87/12/1361
    Amyotrophic lateral sclerosis (ALS) is a progressive and usually fatal neurodegenerative disease. Survival from diagnosis varies considerably. Several prognostic factors are known, including site of onset (bulbar or limb), age at symptom onset, delay from onset to diagnosis and the use of riluzole and non-invasive ventilation (NIV). Clinicians and patients would benefit from a practical way of using these factors to provide an individualised prognosis. […] The rate at which the condition progresses varies greatly, as does the length of time from symptom onset to death, from a few months to more than 10 years. It is therefore difficult to advise a patient on how long they may expect to live, and on the uncertainty in this prediction, and not every patient wants detailed information; nonetheless, for many patients diagnosed with a life-limiting illness, such an estimate is important for providing hope and enabling them to plan their life and its ending, not to mention improving the design and interpretation of clinical trials.
  • #46 FF #437 Amyotrophic Lateral Sclerosis: Prognostication in Advanced Illness   | Palliative Care Network of Wisconsin
    https://www.mypcnow.org/fast-fact/amyotrophic-lateral-sclerosis-prognostication-in-advanced-illness-%EF%BF%BC/
    – A systematic review compared nineteen predictor models for survival in ALS. Only ENCALS was shown to have good discrimination and calibration and a low risk of bias (6). […] – The ENCALS model can predict survival time in months and can thus be used to determine survival likelihood less than six months, indicating hospice eligibility. […] – The validity of hospice eligibility criteria in predicting prognosis in ALS is less known. A 2004 study of 97 consecutive ALS patients admitted into hospice from a tertiary ALS center found that although only five met Medicare criteria at the time of enrollment (7). While the mean number of days on hospice was 85, there was wide range: 1-534 days (7). The Medicare criteria have subsequently been revised; however, the sensitivity and specificity of the revised Medicare criteria remain unknown.
  • #47 Development and validation of a 1-year survival prognosis estimation model for Amyotrophic Lateral Sclerosis using manifold learning algorithm UMAP | Scientific Reports
    https://www.nature.com/articles/s41598-020-70125-8
    Amyotrophic Lateral Sclerosis (ALS) is an inexorably progressive neurodegenerative condition with no effective disease modifying therapies. The development and validation of reliable prognostic models is a recognised research priority. We present a prognostic model for survival in ALS where result uncertainty is taken into account. […] Mean survival time from disease onset is typically 3 to 5 years, with death occurring secondary to respiratory failure. […] From a clinical perspective, accurate prognostic indicators are indispensable for optimising multidisciplinary care, planning interventions, advising patients on end-of-life decisions, resource allocation, etc. […] Disease heterogeneity is a recognised barrier to successful clinical trials in ALS, and accurate prognosis prediction would improve patient stratification.
  • #48 A clinical tool for predicting survival in ALS | Journal of Neurology, Neurosurgery & Psychiatry
    https://jnnp.bmj.com/content/87/12/1361
    Amyotrophic lateral sclerosis (ALS) is a progressive and usually fatal neurodegenerative disease. Survival from diagnosis varies considerably. Several prognostic factors are known, including site of onset (bulbar or limb), age at symptom onset, delay from onset to diagnosis and the use of riluzole and non-invasive ventilation (NIV). Clinicians and patients would benefit from a practical way of using these factors to provide an individualised prognosis. […] The rate at which the condition progresses varies greatly, as does the length of time from symptom onset to death, from a few months to more than 10 years. It is therefore difficult to advise a patient on how long they may expect to live, and on the uncertainty in this prediction, and not every patient wants detailed information; nonetheless, for many patients diagnosed with a life-limiting illness, such an estimate is important for providing hope and enabling them to plan their life and its ending, not to mention improving the design and interpretation of clinical trials.
  • #49 Accurate personalized survival prediction for amyotrophic lateral sclerosis patients | Scientific Reports
    https://www.nature.com/articles/s41598-023-47935-7
    The median survival following the onset of symptoms is 25 years, and respiratory failure is commonly the reason for death. However, the interval between the onset of symptoms and death can range from a few months to more than ten years. This range makes it impossible for clinicians to effectively counsel patients on advance care planning, or to select patients with specific survival characteristics for drug trials. […] Our individual survival curve model provides survival probability for all future time points, and also explicitly deals with censored patients. […] Our learned survival prediction model predicts an individual survival curve (ISD) for each ALS patient. The survival distribution can be more useful than single-time prediction (e.g., Surviving 1 year) when planning future patient treatment because the user can query the predicted survival time for arbitrary survival probabilities.
  • #50 Accurate personalized survival prediction for amyotrophic lateral sclerosis patients | Scientific Reports
    https://www.nature.com/articles/s41598-023-47935-7
    Our learned model gives a personalized prediction specific to this patient rather than only telling the patient the average survival time of all ALS patients. Our learned model performs better than the baseline KaplanMeier estimator, which implies that our learned model can effectively discriminate the differences between the patients and provide personalized predictions.
  • #51 A clinical tool for predicting survival in ALS | Journal of Neurology, Neurosurgery & Psychiatry
    https://jnnp.bmj.com/content/87/12/1361
    A practical way of combining the factors to produce a good prediction for a particular individual would be of great use to the clinician and the affected person. […] Riluzole may have a greater effect in younger patients and those with longer delay to diagnosis. A patient’s survival time has a roughly 50% chance of falling between half and twice the predicted median. […] A simple and clinically applicable graphical method of predicting an individual patient’s survival from diagnosis is presented. The model should be validated in an independent cohort, and extended to include other important prognostic factors. […] The model may predict a median survival of as much as 4 years or as little as 8 months, and even less in patients with respiratory involvement. The true survival time falls between half and twice the median in about half of the patients. Pending validation of the model, we propose this as a clinically useful tool.
  • #52 FF #437 Amyotrophic Lateral Sclerosis: Prognostication in Advanced Illness   | Palliative Care Network of Wisconsin
    https://www.mypcnow.org/fast-fact/amyotrophic-lateral-sclerosis-prognostication-in-advanced-illness-%EF%BF%BC/
    Limitations: Some patients with ALS experience plateau periods, others experience rapid progression. Therefore, the clinical application of ENCAL’s population-based prognostic data for individualized care requires thoughtfulness and complex communication skills. Clinician gestalt by an ALS specialist that is aware of the patient’s clinical scenario is crucial for accurate prognostication. […] Bottom Line: In conjunction with a careful assessment of functional status, the ENCALS model can be a helpful tool to predict prognosis in ALS. Further research is needed to determine if ENCALS offers prognostic benefit over clinician gestalt from an ALS specialist.
  • #53 FF #437 Amyotrophic Lateral Sclerosis: Prognostication in Advanced Illness   | Palliative Care Network of Wisconsin
    https://www.mypcnow.org/fast-fact/amyotrophic-lateral-sclerosis-prognostication-in-advanced-illness-%EF%BF%BC/
    Limitations: Some patients with ALS experience plateau periods, others experience rapid progression. Therefore, the clinical application of ENCAL’s population-based prognostic data for individualized care requires thoughtfulness and complex communication skills. Clinician gestalt by an ALS specialist that is aware of the patient’s clinical scenario is crucial for accurate prognostication. […] Bottom Line: In conjunction with a careful assessment of functional status, the ENCALS model can be a helpful tool to predict prognosis in ALS. Further research is needed to determine if ENCALS offers prognostic benefit over clinician gestalt from an ALS specialist.
  • #54 FF #437 Amyotrophic Lateral Sclerosis: Prognostication in Advanced Illness   | Palliative Care Network of Wisconsin
    https://www.mypcnow.org/fast-fact/amyotrophic-lateral-sclerosis-prognostication-in-advanced-illness-%EF%BF%BC/
    – Site of onset (spinal vs bulbar) […] – Age of onset of muscle weakness or bulbar symptoms […] – Time from onset of weakness or bulbar symptoms to diagnosis […] – Whether the diagnosis of ALS was definite, probable, or possible […] – Forced vital capacity (FVC) […] – The revised ALS Functional Rating Scale (ALSFRS-R) […] – The presence of frontotemporal dementia (cognitive factor) […] – Presence of the C9orf72 mutation (Genetic factor) […] Prognostic evidence for ENCALS and ALS hospice eligibility guidelines: […] – ENCALS has been critiqued since it does not include relevant treatment factors such as riluzole, enteral nutrition, or ventilation as prognostic variables. Yet, the authors note that the median survival benefit of riluzole in a Cochrane meta-analysis was three months. This is substantially smaller than the combined effect of the predictors in ENCAL (HR 0.84 vs 15.29) (5).
  • #55 Development and validation of a 1-year survival prognosis estimation model for Amyotrophic Lateral Sclerosis using manifold learning algorithm UMAP | Scientific Reports
    https://www.nature.com/articles/s41598-020-70125-8
    However, individualised prediction is seldom reliable when clinical and demographic variables are considered alone. […] There is a growing trend to develop accurate prognostic tools based on a combination of prognostic factors, using supervised machine learning models such as random forests, regression models, neural networks with random forests and boosting algorithms. […] The model is easily updated, works with a limited set of features and factors result uncertainty in. […] Taking advantage of the UMAP projection, other prognosis outcomes and different time frames can be explored. […] The primary outcome was 1-year survival. […] The choice of predictors was based on feature completeness after database cross-referencing. […] Patient survival was on average above 75% for all datasets, and 1-year average ALSFRS was above 17 for all datasets.
  • #56 Frontiers | Machine Learning Solutions Applied to Amyotrophic Lateral Sclerosis Prognosis: A Review
    https://www.frontiersin.org/journals/computer-science/articles/10.3389/fcomp.2022.869140/full
    The biomarkers identified as relevant in more than one study were the ALSFRS/ALSFRS-R, disease duration, Forced Vital Capacity, Body Mass Index, age at onset, and Creatinine. […] The main objective of this study is to investigate ML approaches on ALS prognosis that analyzed less complex biomarkers, which can be potentially applied to develop clinical decision support systems to assist physicians in the real-world ALS clinical setting. […] The studies presented promissory results that can be applied in developing decision support systems. […] Despite the research advances, there is a probable lack of CDSS to assist the physicians in their daily work on ALS disease prognosis.
  • #57 FF #437 Amyotrophic Lateral Sclerosis: Prognostication in Advanced Illness   | Palliative Care Network of Wisconsin
    https://www.mypcnow.org/fast-fact/amyotrophic-lateral-sclerosis-prognostication-in-advanced-illness-%EF%BF%BC/
    Limitations: Some patients with ALS experience plateau periods, others experience rapid progression. Therefore, the clinical application of ENCAL’s population-based prognostic data for individualized care requires thoughtfulness and complex communication skills. Clinician gestalt by an ALS specialist that is aware of the patient’s clinical scenario is crucial for accurate prognostication. […] Bottom Line: In conjunction with a careful assessment of functional status, the ENCALS model can be a helpful tool to predict prognosis in ALS. Further research is needed to determine if ENCALS offers prognostic benefit over clinician gestalt from an ALS specialist.
  • #58 Predicting clinical events characterizing the progression of amyotrophic lateral sclerosis via machine learning approaches using routine visits data: a feasibility study | BMC Medical Informatics and Decision Making | Full Text
    https://bmcmedinformdecismak.biomedcentral.com/articles/10.1186/s12911-024-02719-5
    The disease typically results in death within a relatively short span of 3-5 years, although survival times can vary widely and depend on many factors including age, site of onset, rate of disease progression, and presence of comorbidities. […] One of the major challenges in treating ALS is the lack of effective prognostic tools for predicting disease progression. […] Overall, the literature concerning the development of predictive models for clinical outcomes of ALS is still limited as most studies focus on the identification of risk factors based on statistical analyses rather than providing a prediction model. […] Hence, in the future, further studies may focus on the collection or extraction of time-varying and outcome-specific variables as well as the development of more sophisticated methodologies able to consider better temporal information to improve the predictive performance of AI-based approaches.
  • #59 Predicting clinical events characterizing the progression of amyotrophic lateral sclerosis via machine learning approaches using routine visits data: a feasibility study | BMC Medical Informatics and Decision Making | Full Text
    https://bmcmedinformdecismak.biomedcentral.com/articles/10.1186/s12911-024-02719-5
    The disease typically results in death within a relatively short span of 3-5 years, although survival times can vary widely and depend on many factors including age, site of onset, rate of disease progression, and presence of comorbidities. […] One of the major challenges in treating ALS is the lack of effective prognostic tools for predicting disease progression. […] Overall, the literature concerning the development of predictive models for clinical outcomes of ALS is still limited as most studies focus on the identification of risk factors based on statistical analyses rather than providing a prediction model. […] Hence, in the future, further studies may focus on the collection or extraction of time-varying and outcome-specific variables as well as the development of more sophisticated methodologies able to consider better temporal information to improve the predictive performance of AI-based approaches.
  • #60 Frontiers | Machine Learning Solutions Applied to Amyotrophic Lateral Sclerosis Prognosis: A Review
    https://www.frontiersin.org/journals/computer-science/articles/10.3389/fcomp.2022.869140/full
    The biomarkers identified as relevant in more than one study were the ALSFRS/ALSFRS-R, disease duration, Forced Vital Capacity, Body Mass Index, age at onset, and Creatinine. […] The main objective of this study is to investigate ML approaches on ALS prognosis that analyzed less complex biomarkers, which can be potentially applied to develop clinical decision support systems to assist physicians in the real-world ALS clinical setting. […] The studies presented promissory results that can be applied in developing decision support systems. […] Despite the research advances, there is a probable lack of CDSS to assist the physicians in their daily work on ALS disease prognosis.
  • #61 A clinical tool for predicting survival in ALS | Journal of Neurology, Neurosurgery & Psychiatry
    https://jnnp.bmj.com/content/87/12/1361
    A practical way of combining the factors to produce a good prediction for a particular individual would be of great use to the clinician and the affected person. […] Riluzole may have a greater effect in younger patients and those with longer delay to diagnosis. A patient’s survival time has a roughly 50% chance of falling between half and twice the predicted median. […] A simple and clinically applicable graphical method of predicting an individual patient’s survival from diagnosis is presented. The model should be validated in an independent cohort, and extended to include other important prognostic factors. […] The model may predict a median survival of as much as 4 years or as little as 8 months, and even less in patients with respiratory involvement. The true survival time falls between half and twice the median in about half of the patients. Pending validation of the model, we propose this as a clinically useful tool.

Zobacz więcej

wentylacja nieinwazyjna neuron ruchowy płyn mózgowo-rdzeniowy sztuczna inteligencja tracheostomia niewydolność oddechowa neurofilament lekki zajęcie układu oddechowego dysfunkcja wykonawcza opieka wielodyscyplinarna opieka paliatywna kinaza kreatynowa opieka hospicyjna gastrostomia riluzol wentylacja mechaniczna uczenie maszynowe żywienie dojelitowe początek opuszkowy zaburzenie poznawcze skala ALSFRS-R wskaźnik masy ciała natężona pojemność życiowa otępienie czołowo-skroniowe stwardnienie zanikowe boczne