Choroba serca – Rokowania, prognozy i postęp choroby

Choroba serca
Rokowania, prognozy i postęp choroby

Niewydolność serca (HF) pozostaje jednym z kluczowych wyzwań kardiologii, charakteryzując się rosnącą częstością występowania i wysoką śmiertelnością. Rokowanie u pacjentów z HF zależy od wielu czynników, w tym wieku (5-letni wskaźnik przeżycia: 79% dla <65 lat vs. 50% dla ≥75 lat), frakcji wyrzutowej lewej komory (LVEF <40% wiąże się z wyższym ryzykiem zgonu), klasy czynnościowej NYHA, biomarkerów takich jak BNP, parametrów nerkowych (GFR), liczby hospitalizacji (HR 3,2; 95% CI 2,8-3,5 po hospitalizacji), ciśnienia tętniczego, parametrów hematologicznych oraz statusu socjoekonomicznego i chorób współistniejących. Metaanaliza z 2019 roku wskazuje na przeżywalność w HF na poziomie 87% po 1 roku, 73% po 2 latach, 57% po 5 latach i 35% po 10 latach. Wydolność fizyczna oceniana testem 6MWT oraz ultrasonografia płuc (LUS) z oceną linii B stanowią istotne narzędzia prognostyczne, a szczytowe VO2 pozostaje złotym standardem w ocenie rokowania.

Prognozy w chorobie serca (Heart disease Prognosis)

Czynniki wpływające na rokowanie
Wskaźniki przeżycia i hospitalizacji
Modele predykcyjne w chorobie serca
Nomogramy i modele predykcji śmiertelności wewnątrzszpitalnej
Wydolność fizyczna a rokowanie
Ultrasonografia płuc w prognozowaniu
Ograniczenia i przyszłe kierunki

Wnioski

Kolejne rozdziały

Prognozy w chorobie serca (Heart disease Prognosis)

Choroba serca, a szczególnie niewydolność serca (HF), stanowi jedno z głównych wyzwań współczesnej kardiologii, będąc jedyną chorobą układu sercowo-naczyniowego o stale rosnącej częstości występowania. Określenie rokowania u pacjentów z chorobą serca jest kluczowe dla podejmowania odpowiednich decyzji terapeutycznych, w tym kwalifikacji do implantacji urządzeń wszczepialnych czy zabiegów chirurgicznych, w tym przeszczepu serca.¹ Celem niniejszego artykułu jest przedstawienie aktualnych metod prognozowania i oceny ryzyka w chorobie serca, ze szczególnym uwzględnieniem niewydolności serca.

Czynniki wpływające na rokowanie

Rokowanie w chorobie serca zależy od wielu czynników, które należy oceniać łącznie, ponieważ żaden pojedynczy marker nie jest wystarczający do precyzyjnej oceny ryzyka.² Do najważniejszych czynników wpływających na rokowanie należą:

Wiek i płeć – metaanaliza z 2019 roku wykazała, że 5-letni wskaźnik przeżycia dla osób poniżej 65 roku życia wynosił około 79%, podczas gdy dla osób w wieku 75 lat i starszych wynosił około 50%³
Frakcja wyrzutowa lewej komory (LVEF) – pacjenci z EF poniżej 40% mogą mieć wyższe ryzyko zgonu z powodu niewydolności serca⁴
Klasa czynnościowa według NYHA – klasyfikacja Nowojorskiego Towarzystwa Kardiologicznego nadal jest przydatna do oceny ciężkości zespołu, tolerancji wysiłku i rokowania u pacjentów z niewydolnością serca⁵
Biomarkery – w tym BNP (peptyd natriuretyczny typu B), który jest jednym z pięciu najważniejszych czynników predykcyjnych ryzyka zgonu⁶
Parametry nerkowe – wskaźnik filtracji kłębuszkowej (GFR) stanowi istotny czynnik rokowniczy⁷
Liczba hospitalizacji – stanowi najważniejszy czynnik predykcyjny w prognozowaniu 3-letniego przeżycia u pacjentów z przewlekłą niewydolnością serca⁸
Ciśnienie tętnicze – zarówno skurczowe, jak i rozkurczowe ciśnienie krwi mają istotne znaczenie rokownicze⁹
Parametry hematologiczne – bezwzględna wartość limfocytów, stężenie albuminy w surowicy, hemoglobina i całkowity cholesterol¹⁰
Status socjoekonomiczny – niski status społeczno-ekonomiczny w wieku dorosłym i dzieciństwie wiąże się z gorszymi wynikami leczenia niewydolności serca¹¹
Choroby współistniejące – obecność chorób współistniejących, takich jak choroba wieńcowa, może wpływać na długość życia¹²

Wskaźniki przeżycia i hospitalizacji

Wskaźniki zachorowalności i śmiertelności po wystąpieniu objawowej niewydolności serca są wysokie, choć zgłaszano różne wskaźniki śmiertelności, co prawdopodobnie odzwierciedla różnice demograficzne, stopień zaawansowania choroby i stosowanie odpowiedniego leczenia.¹³ Metaanaliza z 2019 roku szacuje następujące wskaźniki przeżycia dla niewydolności serca wszystkich typów:

1 rok: 87%
2 lata: 73%
5 lat: 57%
10 lat: 35%¹⁴

Potrzeba hospitalizacji jest ważnym markerem złego rokowania. Badanie danych 7572 pacjentów z przewlekłą niewydolnością serca z obniżoną lub zachowaną frakcją wyrzutową lewej komory w badaniach CHARM wykazało, że śmiertelność wzrosła po hospitalizacjach z powodu niewydolności serca, nawet po skorygowaniu o wyjściowe czynniki predykcyjne zgonu (współczynnik ryzyka [HR] 3,2; 95% CI 2,8-3,5). Zwiększone ryzyko zgonu było najwyższe w ciągu jednego miesiąca od wypisania i stopniowo zmniejszało się z czasem.¹⁵

Modele predykcyjne w chorobie serca

Rozwój modeli predykcyjnych dla oceny ryzyka w chorobie serca stanowi ważny obszar badań, mający na celu bardziej precyzyjne prognozowanie i planowanie leczenia. Obecnie istnieje wiele różnych modeli, wykorzystujących zarówno tradycyjne metody statystyczne, jak i zaawansowane techniki uczenia maszynowego.

Modele oparte na danych klinicznych

Wykorzystując dane dostępne w elektronicznej dokumentacji medycznej, można opracować szereg modeli prognozowania ryzyka złych wyników u pacjentów z niewydolnością serca. Badania wykazały, że stosunkowo prosty model jest równie skuteczny jak bardziej złożony model, ale wszystkie modele prognozują z jedynie umiarkowaną dokładnością.¹⁶ Model ryzyka może być cenny dla priorytetowego traktowania centralnych wysiłków programu zarządzania chorobami, stratyfikując pacjentów według ich bezwzględnego ryzyka złych wyników.¹⁷

Łatwo dostępne dane z elektronicznej dokumentacji medycznej można połączyć, aby przewidzieć ryzyko złych wyników u pacjentów z niewydolnością serca. Model ryzyka pokazał, że pacjenci w najwyższym kwintylu byli około 3 razy bardziej narażeni na złe wyniki niż pacjenci w najniższym kwintylu ryzyka.¹⁸

Mimo zidentyfikowania wielu markerów i modeli złego rokowania, decyzje kliniczne i wytyczne w niewydolności serca nadal opierają się głównie na kilku podstawowych parametrach, takich jak obecność objawów niewydolności serca (klasa NYHA), LVEF oraz czas trwania i morfologia kompleksu QRS.¹⁹

Modele oparte na uczeniu maszynowym

W ostatnich latach uczenie maszynowe stało się cennym narzędziem do diagnozowania i prognozowania chorób serca poprzez analizę danych zdrowotnych.²⁰ Badania wykazały potencjał różnych algorytmów uczenia maszynowego w prognozowaniu ryzyka chorób sercowo-naczyniowych:

Naiwny klasyfikator Bayesa i sieci neuronowe RBF – osiągnęły dokładność 94,78% w przewidywaniu obecności wieńcowej choroby sercowo-naczyniowej²¹
Learning Vector Quantization – osiągnął najwyższą dokładność klasyfikacji wynoszącą 98,78%, ze swoistością 97,1% i czułością 97,91%²²
Perceptron wielowarstwowy (MLP) – wykazał wyższą dokładność przewidywania na poziomie 82,47% w porównaniu z modelem K-NN z wartością dokładności 73,77%²³
Maszyna wektorów nośnych (SVM) – wykazała lepszą wydajność z dokładnością 82,5% spośród wszystkich klasyfikatorów używanych w klasyfikacji chorób serca²⁴

Celem prognozowania chorób sercowo-naczyniowych jest opracowanie dokładnych i wiarygodnych modeli, które mogą ocenić ryzyko rozwoju różnych stanów sercowo-naczyniowych u danej osoby, umożliwiając wczesną interwencję, spersonalizowane leczenie i ostatecznie zmniejszenie obciążenia chorobami serca dla zdrowia publicznego.²⁵

Modele oparte na głębokim uczeniu

Głębokie uczenie stanowi obiecujący kierunek w prognozowaniu chorób sercowo-naczyniowych. System SEER (Survival ElEctRic), oparty na głębokiej konwolucyjnej sieci neuronowej, może dokładnie przewidywać długoterminowe ryzyko śmiertelności sercowo-naczyniowej i chorób na podstawie samego spoczynkowego EKG.²⁶

SEER przewiduje 5-letnią śmiertelność sercowo-naczyniową z obszarem pod krzywą ROC (AUC) wynoszącym 0,83 w zestawie testowym na Uniwersytecie Stanforda oraz z AUC wynoszącym odpowiednio 0,78 i 0,83 podczas niezależnej oceny w Cedars-Sinai Medical Center i Columbia University Irving Medical Center.²⁷ Pacjenci w górnej jednej trzeciej wyniku SEER byli bardziej narażeni na rozwój szeregu incydentów chorób sercowo-naczyniowych.²⁸

Innym przykładem jest model głębokiego uczenia oparty na fotopletyzmografii (PPG-DLS), który przewiduje dziesięcioletnie ryzyko poważnych zdarzeń sercowo-naczyniowych (MACE: zawał mięśnia sercowego bez skutku śmiertelnego, udar i śmierć sercowo-naczyniowa) na podstawie tylko wieku, płci, statusu palenia i PPG jako predyktorów.²⁹ Model ten wykazał wartość C-statystyki 71,1% (95% CI [69,9, 72,4]).³⁰

Nomogramy i modele predykcji śmiertelności wewnątrzszpitalnej

Nomogram jest skutecznym narzędziem do oceny ryzyka. Zapewnia prostą graficzną reprezentację złożonych statystycznych modeli predykcyjnych i jest również odpowiedni do analizy prognostycznej indywidualnych pacjentów.³¹

Wieloczynnikowa analiza logistyczna wykazała, że wiek, rasa, norepinefryna, dopamina, fenylepinefryna, wazopresyna, wentylacja mechaniczna, intubacja, niewydolność wątroby, częstość akcji serca, częstość oddechów, temperatura, skurczowe ciśnienie krwi, luka anionowa, azot mocznikowy we krwi, kreatynina, chlorek, średnia objętość krwinki (MCV), szerokość rozkładu objętości krwinek czerwonych (RDW) i liczba białych krwinek (WBC) są czynnikami prognostycznymi przeżycia pacjentów z niewydolnością serca.³²

Wydolność fizyczna a rokowanie

Pacjenci z niewydolnością serca, którzy wykazują słabą wydolność fizyczną w 6-minutowym teście chodu (6MWT), w Short Physical Performance Battery (SPPB) i w teście prędkości chodu, mają gorsze rokowanie w porównaniu z pacjentami z dobrą wydolnością fizyczną pod względem zwiększonego ryzyka hospitalizacji lub zwiększonego ryzyka śmiertelności.³³

Pacjenci z HFrEF, HFpEF i ostrą niewydolnością serca, którzy wykazali słabą wydolność fizyczną w 6MWT, zgłosili wyższe ryzyko śmiertelności z wszystkich przyczyn [HR=2,29 95%CI (1,86-2,82), p<0,001] niż pacjenci, którzy wykazali dobrą wydolność fizyczną.³⁴

Szczytowe VO2 pozostaje złotym standardem w przewidywaniu wyniku w niewydolności serca.³⁵

Ultrasonografia płuc w prognozowaniu

Ultrasonografia płuc (LUS) pojawiła się jako prosta, szybka i nieinwazyjna metoda dynamicznej oceny zastoju płucnego, który jest głównym czynnikiem prognostycznym i celem terapeutycznym w ostrej niewydolności serca (AHF).³⁶

Obecność linii B przy wypisie jest istotnie związana z wyższym ryzykiem śmiertelności w ciągu 30 dni. Związek między liczbą linii B a statusem życiowym przy wypisie po 30 dniach jest statystycznie istotny z wartością p < 0,001.³⁷ Brak ustąpienia linii B przy wypisie wydaje się być związany z wysokim ryzykiem zdarzeń niepożądanych, takich jak konsultacja w SOR, ponowne przyjęcie z powodu AHF i śmiertelność z wszystkich przyczyn.³⁸

Ograniczenia i przyszłe kierunki

Pomimo identyfikacji wielu markerów i modeli złego rokowania, wszystkie przedstawione modele wykazały jedynie umiarkowane prawdopodobieństwo przewidywania śmierci w niewydolności serca.³⁹ Wciąż trwają badania mające na celu ocenę potencjalnych nowych czynników predykcyjnych.⁴⁰

Głównym ograniczeniem istniejących modeli jest to, że analizowany zestaw danych ma ograniczony zakres atrybutów i wielkość próby.⁴¹ Przyszłe badania mogłyby obejmować analizę statystyczną modelu na rozbieżnych zestawach danych, takich jak zestaw danych UK Biobank, Uniwersytet Federico II, zestaw danych Statlog dla chorób serca i zestaw danych szpitala NEU dla chorób serca.⁴²

Zamiast opracowywać kolejne podobne modele prognozowania ryzyka chorób układu krążenia dla populacji ogólnej, w erze dużych i połączonych zestawów danych, powinniśmy skupić się na zewnętrznej walidacji i bezpośrednim porównaniu obiecujących istniejących modeli ryzyka chorób układu krążenia, dostosowywaniu tych modeli do lokalnych uwarunkowań, badaniu, czy mogą być rozszerzone o nowe predyktory, i wreszcie ilościowym określeniu klinicznego wpływu najbardziej obiecujących modeli.⁴³

Wnioski

Prognozowanie w chorobie serca, szczególnie w niewydolności serca, jest złożonym zagadnieniem wymagającym uwzględnienia wielu czynników. Obecność objawów niewydolności serca, frakcja wyrzutowa lewej komory, biomarkery sercowe, parametry nerkowe, liczba hospitalizacji oraz wydolność fizyczna to najważniejsze czynniki wpływające na rokowanie.

Rozwój modeli prognozowania, zarówno tradycyjnych, jak i opartych na uczeniu maszynowym, oferuje nowe możliwości w stratyfikacji ryzyka pacjentów z chorobą serca. Jednak pomimo postępu technologicznego, wszystkie modele wykazują jedynie umiarkowaną dokładność w przewidywaniu śmiertelności.

Przyszłe badania powinny skupić się na walidacji istniejących modeli i ich adaptacji do lokalnych warunków, a także na badaniu potencjalnych nowych biomarkerów i czynników predykcyjnych, które mogłyby poprawić dokładność prognozowania w chorobie serca.

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.

Materiały źródłowe

#1
https://link.springer.com/article/10.1007/s11845-020-02477-z
Heart failure (HF) is the only cardiovascular disease with an ever increasing incidence. […] The main challenge in the treatment of HF is the availability of reliable prognostic models that would allow patients and doctors to develop realistic expectations about the prognosis and to choose the appropriate therapy and monitoring method. […] Prognosis assessment plays a special role in patients qualified for implantable device therapy or surgical treatment (including heart transplantation). […] This article begins with a review of individual markers that contribute to the risk of unfavorable outcome in HF. […] However, no single risk factor is sufficient to predict prognosis in HF. Results of a few markers must be interpreted together. […] Still it is important to find the most important and valuable panel of a few predictors and there are still ongoing studies assessing potential new ones.
#2
https://link.springer.com/article/10.1007/s11845-020-02477-z
Heart failure (HF) is the only cardiovascular disease with an ever increasing incidence. […] The main challenge in the treatment of HF is the availability of reliable prognostic models that would allow patients and doctors to develop realistic expectations about the prognosis and to choose the appropriate therapy and monitoring method. […] Prognosis assessment plays a special role in patients qualified for implantable device therapy or surgical treatment (including heart transplantation). […] This article begins with a review of individual markers that contribute to the risk of unfavorable outcome in HF. […] However, no single risk factor is sufficient to predict prognosis in HF. Results of a few markers must be interpreted together. […] Still it is important to find the most important and valuable panel of a few predictors and there are still ongoing studies assessing potential new ones.
#3 Congestive heart failure life expectancy: Prognosis and stages
https://www.medicalnewstoday.com/articles/321538
Many factors can affect a persons life expectancy with congestive heart failure (CHF), such as their age, the stage of their condition, and the strength of their heart function. […] Life expectancy with CHF depends on several variables and may be nonlinear. A 2018 review highlights that many physicians feel they cannot confidently predict a persons clinical trajectory in a 6-month time frame. […] A 2019 metaanalysis estimates the following survival rates for all-type heart failure: 1 year: 87%, 2 years: 73%, 5 years: 57%, 10 years: 35%. […] A persons age at diagnosis may affect their outlook. The 2019 meta-analysis reports that the 5-year survival rate for people under age 65 years was around 79%, while the rate was about 50% for those age 75 years and over. […] Additionally, how much blood a persons heart pumps out per beat, known as the ejection fraction (EF), may affect life expectancy.
#4 Congestive heart failure life expectancy: Prognosis and stages
https://www.medicalnewstoday.com/articles/321538
People with an EF under 40% may have a higher risk of dying from CHF. […] The presence of underlying conditions or comorbidities, such as coronary heart disease, can affect a persons life expectancy as well. […] An age-adjusted study from 2021 found that comorbidities are common in people with heart failure and can contribute to higher death rates. […] Research estimates that more than half of all people with congestive heart failure will survive for 5 years after diagnosis. About 35% will survive for 10 years. […] However, in some cases, a person can extend their life expectancy through lifestyle changes, medications, and surgery. […] Life expectancy for the disease varies significantly between individuals. […] Some studies estimate a 5-year survival rate of nearly 50% for a person with heart failure. […] Life expectancy depends on a persons stage and class of CHF and what other complications or health problems they have.
#5
https://link.springer.com/article/10.1007/s11845-020-02477-z
Knowledge of a patients demographic, medical, and clinical data could play an important role in prediction of life expectancy. […] Low socioeconomic status in adulthood and childhood is associated with worsened HF outcomes. […] The New York Heart Association (NYHA) functional classification is still useful for assessing syndrome severity, patients exercise tolerance and prognosis in HF patients. […] Many echocardiographic markers have prognostic value in HF. […] In summary, LV systolic and diastolic function, LA function, and RV function have prognostic value in HFpEF. […] Peak VO2 remains the gold standard in predicting outcome in HF. […] Hospitalization for HF within the last year has been significant risk factor of subsequent hospitalizations. […] All of the presented models have shown only moderate probability in predicting death in HF. […] Despite the identification of many markers and models of poor prognosis, clinical decisions and guidelines in HF are still based mainly on several basic parameters, such as the presence of HF symptoms (NYHA class), LVEF, and the duration and morphology of the QRS complex.
#6 Interpretable prediction of 3-year all-cause mortality in patients with chronic heart failure based on machine learning
https://pmc.ncbi.nlm.nih.gov/articles/PMC10662001/
The goal of this study was to assess the effectiveness of machine learning models and create an interpretable machine learning model that adequately explained 3-year all-cause mortality in patients with chronic heart failure. […] From this study, we can see that the number of hospitalizations, age, glomerular filtration rate, BNP, NYHA cardiac function classification, lymphocyte absolute value, serum albumin, hemoglobin, total cholesterol, pulmonary artery systolic pressure and so on were important for providing an optimal risk assessment and were important predictive factors of chronic heart failure. […] The machine learning-based cardiovascular risk models could be used to accurately assess and stratify the 3-year risk of all-cause mortality among CHF patients. […] The permutation importance showed that the number of hospitalizations, age, glomerular filtration rate, BNP, and NYHA cardiac function classification were the top five important factors.
#7 Interpretable prediction of 3-year all-cause mortality in patients with chronic heart failure based on machine learning
https://pmc.ncbi.nlm.nih.gov/articles/PMC10662001/
The importance of variables based on permutation importance, partial dependence plot and SHAP value showed that number of hospitalizations, age, glomerular filtration rate, BNP, diastolic blood pressure, systolic blood pressure, and NYHA cardiac function classification were the most important factors in predicting survival after 3 years of follow-up in heart failure patients.
#8 Interpretable prediction of 3-year all-cause mortality in patients with chronic heart failure based on machine learning
https://pmc.ncbi.nlm.nih.gov/articles/PMC10662001/
The goal of this study was to assess the effectiveness of machine learning models and create an interpretable machine learning model that adequately explained 3-year all-cause mortality in patients with chronic heart failure. […] From this study, we can see that the number of hospitalizations, age, glomerular filtration rate, BNP, NYHA cardiac function classification, lymphocyte absolute value, serum albumin, hemoglobin, total cholesterol, pulmonary artery systolic pressure and so on were important for providing an optimal risk assessment and were important predictive factors of chronic heart failure. […] The machine learning-based cardiovascular risk models could be used to accurately assess and stratify the 3-year risk of all-cause mortality among CHF patients. […] The permutation importance showed that the number of hospitalizations, age, glomerular filtration rate, BNP, and NYHA cardiac function classification were the top five important factors.
#9 Interpretable prediction of 3-year all-cause mortality in patients with chronic heart failure based on machine learning
https://pmc.ncbi.nlm.nih.gov/articles/PMC10662001/
The importance of variables based on permutation importance, partial dependence plot and SHAP value showed that number of hospitalizations, age, glomerular filtration rate, BNP, diastolic blood pressure, systolic blood pressure, and NYHA cardiac function classification were the most important factors in predicting survival after 3 years of follow-up in heart failure patients.
#10 Interpretable prediction of 3-year all-cause mortality in patients with chronic heart failure based on machine learning
https://pmc.ncbi.nlm.nih.gov/articles/PMC10662001/
The goal of this study was to assess the effectiveness of machine learning models and create an interpretable machine learning model that adequately explained 3-year all-cause mortality in patients with chronic heart failure. […] From this study, we can see that the number of hospitalizations, age, glomerular filtration rate, BNP, NYHA cardiac function classification, lymphocyte absolute value, serum albumin, hemoglobin, total cholesterol, pulmonary artery systolic pressure and so on were important for providing an optimal risk assessment and were important predictive factors of chronic heart failure. […] The machine learning-based cardiovascular risk models could be used to accurately assess and stratify the 3-year risk of all-cause mortality among CHF patients. […] The permutation importance showed that the number of hospitalizations, age, glomerular filtration rate, BNP, and NYHA cardiac function classification were the top five important factors.
#11
https://link.springer.com/article/10.1007/s11845-020-02477-z
Knowledge of a patients demographic, medical, and clinical data could play an important role in prediction of life expectancy. […] Low socioeconomic status in adulthood and childhood is associated with worsened HF outcomes. […] The New York Heart Association (NYHA) functional classification is still useful for assessing syndrome severity, patients exercise tolerance and prognosis in HF patients. […] Many echocardiographic markers have prognostic value in HF. […] In summary, LV systolic and diastolic function, LA function, and RV function have prognostic value in HFpEF. […] Peak VO2 remains the gold standard in predicting outcome in HF. […] Hospitalization for HF within the last year has been significant risk factor of subsequent hospitalizations. […] All of the presented models have shown only moderate probability in predicting death in HF. […] Despite the identification of many markers and models of poor prognosis, clinical decisions and guidelines in HF are still based mainly on several basic parameters, such as the presence of HF symptoms (NYHA class), LVEF, and the duration and morphology of the QRS complex.
#12 Congestive heart failure life expectancy: Prognosis and stages
https://www.medicalnewstoday.com/articles/321538
People with an EF under 40% may have a higher risk of dying from CHF. […] The presence of underlying conditions or comorbidities, such as coronary heart disease, can affect a persons life expectancy as well. […] An age-adjusted study from 2021 found that comorbidities are common in people with heart failure and can contribute to higher death rates. […] Research estimates that more than half of all people with congestive heart failure will survive for 5 years after diagnosis. About 35% will survive for 10 years. […] However, in some cases, a person can extend their life expectancy through lifestyle changes, medications, and surgery. […] Life expectancy for the disease varies significantly between individuals. […] Some studies estimate a 5-year survival rate of nearly 50% for a person with heart failure. […] Life expectancy depends on a persons stage and class of CHF and what other complications or health problems they have.
#13 Prognosis of heart failure – UpToDate
https://www.uptodate.com/contents/prognosis-of-heart-failure
Prognosis of heart failure […] The prognosis of patients with HF with reduced ejection fraction (HFrEF) will be reviewed here. […] Morbidity and mortality rates after the onset of symptomatic HF are high, although variable mortality rates have been reported which likely reflect differences in demographics, disease severity, and the use of appropriate medical therapy. […] The need for hospitalization is an important marker for poor prognosis. The association of nonfatal hospitalization and subsequent mortality rates was studied using data on 7572 chronic HF patients with reduced or preserved LV ejection fraction (LVEF) in the Candesartan in Heart Failure Assessment of Reduction in Mortality and Morbidity (CHARM) trials. Mortality rate was increased after HF hospitalizations, even after adjustment for baseline predictors of death (hazard ratio [HR] 3.2; 95% CI 2.8-3.5). The increased risk of death was highest within one month of discharge and declined progressively over time. […] Outcome with a cardiomyopathy is related to the etiology. […] Mortality and hospitalizations in heart failure show a seasonal variation. […] ACE inhibitor improves survival in advanced HF. […] ACE inhibitor improves survival in moderate HF. […] Enalapril improves outcome in asymptomatic LV dysfunction.
#14 Congestive heart failure life expectancy: Prognosis and stages
https://www.medicalnewstoday.com/articles/321538
Many factors can affect a persons life expectancy with congestive heart failure (CHF), such as their age, the stage of their condition, and the strength of their heart function. […] Life expectancy with CHF depends on several variables and may be nonlinear. A 2018 review highlights that many physicians feel they cannot confidently predict a persons clinical trajectory in a 6-month time frame. […] A 2019 metaanalysis estimates the following survival rates for all-type heart failure: 1 year: 87%, 2 years: 73%, 5 years: 57%, 10 years: 35%. […] A persons age at diagnosis may affect their outlook. The 2019 meta-analysis reports that the 5-year survival rate for people under age 65 years was around 79%, while the rate was about 50% for those age 75 years and over. […] Additionally, how much blood a persons heart pumps out per beat, known as the ejection fraction (EF), may affect life expectancy.
#15 Prognosis of heart failure – UpToDate
https://www.uptodate.com/contents/prognosis-of-heart-failure
Prognosis of heart failure […] The prognosis of patients with HF with reduced ejection fraction (HFrEF) will be reviewed here. […] Morbidity and mortality rates after the onset of symptomatic HF are high, although variable mortality rates have been reported which likely reflect differences in demographics, disease severity, and the use of appropriate medical therapy. […] The need for hospitalization is an important marker for poor prognosis. The association of nonfatal hospitalization and subsequent mortality rates was studied using data on 7572 chronic HF patients with reduced or preserved LV ejection fraction (LVEF) in the Candesartan in Heart Failure Assessment of Reduction in Mortality and Morbidity (CHARM) trials. Mortality rate was increased after HF hospitalizations, even after adjustment for baseline predictors of death (hazard ratio [HR] 3.2; 95% CI 2.8-3.5). The increased risk of death was highest within one month of discharge and declined progressively over time. […] Outcome with a cardiomyopathy is related to the etiology. […] Mortality and hospitalizations in heart failure show a seasonal variation. […] ACE inhibitor improves survival in advanced HF. […] ACE inhibitor improves survival in moderate HF. […] Enalapril improves outcome in asymptomatic LV dysfunction.
#16 Predicting Poor Outcomes in Heart Failure
https://pmc.ncbi.nlm.nih.gov/articles/PMC3267558/
Health plans must prioritize disease management efforts to reduce hospitalization and mortality rates in heart failure patients. […] We developed a risk model to predict the 5-year risk of mortality or hospitalization for heart failure among patients at a large health maintenance organization. […] We observed a 56% five-year risk of hospitalization for heart failure or death (95% confidence interval, 54% to 58%). […] Using data available from electronic health records, we developed a series of risk-prediction models for poor outcomes in patients with heart failure. […] We found that a relatively simple model is as effective as a more complex model, but that all the models predict with only modest accuracy. […] Our prediction model may be valuable for prioritizing centralized disease management program efforts by stratifying patients according to their absolute risk of poor outcomes.
#17 Predicting Poor Outcomes in Heart Failure
https://pmc.ncbi.nlm.nih.gov/articles/PMC3267558/
Health plans must prioritize disease management efforts to reduce hospitalization and mortality rates in heart failure patients. […] We developed a risk model to predict the 5-year risk of mortality or hospitalization for heart failure among patients at a large health maintenance organization. […] We observed a 56% five-year risk of hospitalization for heart failure or death (95% confidence interval, 54% to 58%). […] Using data available from electronic health records, we developed a series of risk-prediction models for poor outcomes in patients with heart failure. […] We found that a relatively simple model is as effective as a more complex model, but that all the models predict with only modest accuracy. […] Our prediction model may be valuable for prioritizing centralized disease management program efforts by stratifying patients according to their absolute risk of poor outcomes.
#18 Predicting Poor Outcomes in Heart Failure
https://pmc.ncbi.nlm.nih.gov/articles/PMC3267558/
Easily accessible data from EMRs can be combined to predict patients at risk of poor outcomes from heart failure. […] The risk model from Model 2 showed that patients in the highest quintile were about 3 times more likely to have the outcome as patients in the lowest quintile of risk. […] Our findings illustrate that the added predictive ability of knowing ejection fraction is small when compared with a model that includes demographics, blood pressure, renal function and anemia status. […] Ejection fraction is an important risk factor, but predicting absolute risk requires a clinician to balance competing risk factors simultaneously.
#19
https://link.springer.com/article/10.1007/s11845-020-02477-z
Knowledge of a patients demographic, medical, and clinical data could play an important role in prediction of life expectancy. […] Low socioeconomic status in adulthood and childhood is associated with worsened HF outcomes. […] The New York Heart Association (NYHA) functional classification is still useful for assessing syndrome severity, patients exercise tolerance and prognosis in HF patients. […] Many echocardiographic markers have prognostic value in HF. […] In summary, LV systolic and diastolic function, LA function, and RV function have prognostic value in HFpEF. […] Peak VO2 remains the gold standard in predicting outcome in HF. […] Hospitalization for HF within the last year has been significant risk factor of subsequent hospitalizations. […] All of the presented models have shown only moderate probability in predicting death in HF. […] Despite the identification of many markers and models of poor prognosis, clinical decisions and guidelines in HF are still based mainly on several basic parameters, such as the presence of HF symptoms (NYHA class), LVEF, and the duration and morphology of the QRS complex.
#20 An active learning machine technique based prediction of cardiovascular heart disease from UCI-repository database | Scientific Reports
https://www.nature.com/articles/s41598-023-40717-1
Heart disease is a significant global cause of mortality, and predicting it through clinical data analysis poses challenges. Machine learning (ML) has emerged as a valuable tool for diagnosing and predicting heart disease by analyzing healthcare data. Previous studies have extensively employed ML techniques in medical research for heart disease prediction. In this study, eight ML classifiers were utilized to identify crucial features that enhance the accuracy of heart disease prediction. […] The motivation behind predicting Cardiovascular Heart Disease lies in its potential to save lives, improves health outcomes, and allocates healthcare resources efficiently. […] The goal of predicting Cardiovascular Heart Disease is to develop accurate and reliable models that can assess an individual’s risk of developing various cardiovascular conditions, enabling early intervention, personalized treatment, and ultimately reducing the burden of heart disease on public health.
#21 An active learning machine technique based prediction of cardiovascular heart disease from UCI-repository database | Scientific Reports
https://www.nature.com/articles/s41598-023-40717-1
The final findings demonstrate that when the learning machine classifiers were put to use, the Naive Bayes and RBF neural networks achieved an accuracy of 94.78% when attempting to forecast the presence of coronary cardiovascular disease. However, the Learning Vector Quantization method achieved the highest categorization accuracy of 98.78%, with a specificity of 97.1% and sensitivity of 97.91%, a precision of 98.07% and 95.31%, and 97.89% F1score and F-measure values, respectively.
#22 An active learning machine technique based prediction of cardiovascular heart disease from UCI-repository database | Scientific Reports
https://www.nature.com/articles/s41598-023-40717-1
The final findings demonstrate that when the learning machine classifiers were put to use, the Naive Bayes and RBF neural networks achieved an accuracy of 94.78% when attempting to forecast the presence of coronary cardiovascular disease. However, the Learning Vector Quantization method achieved the highest categorization accuracy of 98.78%, with a specificity of 97.1% and sensitivity of 97.91%, a precision of 98.07% and 95.31%, and 97.89% F1score and F-measure values, respectively.
#23 Risk prediction of cardiovascular disease using machine learning classifiers
https://www.degruyter.com/document/doi/10.1515/med-2022-0508/html?lang=en
The comparison of results indicates that the MLP model has a higher prediction accuracy of 82.47%, followed by the K-NN model with an accuracy value of 73.77%. […] The constructed MLP model offers consistent accuracy compared to other techniques mentioned and is also capable of predicting other diseases. […] The proposed method can also be used for the classification of other chronic diseases such as breast cancer, liver disease, diabetes mellitus, and thyroid. […] The developed models can be applied to large data sets to predict chronic diseases using IoT and cloud computing techniques. […] The application of ML techniques will vastly aid in preventing fatalities and supplement the efforts of doctors in fighting CVD occurrence among all patient categories of different age groups, genders, and socio-economic backgrounds.
#24 XAI Framework for Cardiovascular Disease Prediction Using Classification Techniques
https://www.mdpi.com/2079-9292/11/24/4086
The SHAP values determine how each attribute contributes to the modelâs prediction. […] The ROC curve train categorizes a patientâs disease condition as either positive or negative, based on the test results and perceives the ideal cut-off value with the best symptomatic performance. […] The efficiency of the proposed XAI-driven ensemble classifiers is better than the conventional classification models. […] The SVM algorithm has exhibited a better performance with an accuracy of 82.5%, among all of the classifiers used in heart disease classification. […] The limitations of the existing models are that the dataset taken has a limited scope of attributes and sample size. […] The future dimension of the research could include the statistical analysis of the model over the divergent datasets, such as the UK Biobank dataset, University Federico II, Statlog heart disease dataset, and the NEU Hospital dataset for heart disease.
#25 An active learning machine technique based prediction of cardiovascular heart disease from UCI-repository database | Scientific Reports
https://www.nature.com/articles/s41598-023-40717-1
Heart disease is a significant global cause of mortality, and predicting it through clinical data analysis poses challenges. Machine learning (ML) has emerged as a valuable tool for diagnosing and predicting heart disease by analyzing healthcare data. Previous studies have extensively employed ML techniques in medical research for heart disease prediction. In this study, eight ML classifiers were utilized to identify crucial features that enhance the accuracy of heart disease prediction. […] The motivation behind predicting Cardiovascular Heart Disease lies in its potential to save lives, improves health outcomes, and allocates healthcare resources efficiently. […] The goal of predicting Cardiovascular Heart Disease is to develop accurate and reliable models that can assess an individual’s risk of developing various cardiovascular conditions, enabling early intervention, personalized treatment, and ultimately reducing the burden of heart disease on public health.
#26 A deep learning-based electrocardiogram risk score for long term cardiovascular death and disease | npj Digital Medicine
https://www.nature.com/articles/s41746-023-00916-6
The electrocardiogram (ECG) is the most frequently performed cardiovascular diagnostic test, but it is unclear how much information resting ECGs contain about long term cardiovascular risk. Here we report that a deep convolutional neural network can accurately predict the long-term risk of cardiovascular mortality and disease based on a resting ECG alone. […] SEER predicts 5-year cardiovascular mortality with an area under the receiver operator characteristic curve (AUC) of 0.83 in a held-out test set at Stanford, and with AUCs of 0.78 and 0.83 respectively when independently evaluated at Cedars-Sinai Medical Center and Columbia University Irving Medical Center. […] SEER can also predict several other cardiovascular conditions such as heart failure and atrial fibrillation. […] SEER was trained using a dataset of resting ECGs from Stanford University Medical Center (Stanford; Supplementary Table 1, Supplementary Fig. 1) and evaluated using ECGs from Stanford, Cedars-Sinai Medical Center (Cedars-Sinai; Supplementary Table 2, Supplementary Fig. 2), and Columbia University Irving Medical Center (Columbia; Supplementary Table 3).
#27 A deep learning-based electrocardiogram risk score for long term cardiovascular death and disease | npj Digital Medicine
https://www.nature.com/articles/s41746-023-00916-6
The electrocardiogram (ECG) is the most frequently performed cardiovascular diagnostic test, but it is unclear how much information resting ECGs contain about long term cardiovascular risk. Here we report that a deep convolutional neural network can accurately predict the long-term risk of cardiovascular mortality and disease based on a resting ECG alone. […] SEER predicts 5-year cardiovascular mortality with an area under the receiver operator characteristic curve (AUC) of 0.83 in a held-out test set at Stanford, and with AUCs of 0.78 and 0.83 respectively when independently evaluated at Cedars-Sinai Medical Center and Columbia University Irving Medical Center. […] SEER can also predict several other cardiovascular conditions such as heart failure and atrial fibrillation. […] SEER was trained using a dataset of resting ECGs from Stanford University Medical Center (Stanford; Supplementary Table 1, Supplementary Fig. 1) and evaluated using ECGs from Stanford, Cedars-Sinai Medical Center (Cedars-Sinai; Supplementary Table 2, Supplementary Fig. 2), and Columbia University Irving Medical Center (Columbia; Supplementary Table 3).
#28 A deep learning-based electrocardiogram risk score for long term cardiovascular death and disease | npj Digital Medicine
https://www.nature.com/articles/s41746-023-00916-6
Among patients in these cohorts with 5 years of followup or a cardiovascular mortality within 5 years, SEER predicted 5-year cardiovascular mortality with areas under the receiver operator characteristic curve (AUC) of 0.83 (95% CI: 0.810.85), 0.78 (0.770.80), and 0.83 (0.820.83) at Stanford, Cedars-Sinai, and Columbia respectively. […] Patients in the top third of the SEER score were at higher risk for developing a range of incident cardiovascular diseases (Fig. 1C). […] SEER achieved a 5-year AUC of 0.67 (0.650.69) and Harrell C-statistic of 0.66 (0.650.68) in predicting hard ASCVD at Stanford and an AUC of 0.63 (0.590.67) and C-statistic of 0.635 (0.620.65), while the PCE achieved a 5-year AUC of 0.71 (0.690.73) and a better Harrell C-statistic of 0.70 (0.690.71) at Stanford and an AUC of 0.66 (0.620.70) and a C-statistic of 0.64 (0.610.67) at Cedars-Sinai. […] SEER is also able to reclassify patients with moderate 10-year ASCVD risk. […] Our risk score, SEER, identifies groups of patients to be up-risked and successfully stratifies intermediate risk patients for risk of ASCVD and cardiovascular mortality.
#29 Predicting cardiovascular disease risk using photoplethysmography and deep learning | PLOS Global Public Health
https://journals.plos.org/globalpublichealth/article?id=10.1371/journal.pgph.0003204
Cardiovascular diseases (CVDs) are responsible for a large proportion of premature deaths in low- and middle-income countries. Early CVD detection and intervention is critical in these populations, yet many existing CVD risk scores require a physical examination or lab measurements, which can be challenging in such health systems due to limited accessibility. […] We developed a deep learning PPG-based CVD risk score (DLS) to predict the probability of having major adverse cardiovascular events (MACE: non-fatal myocardial infarction, stroke, and cardiovascular death) within ten years, given only age, sex, smoking status and PPG as predictors. […] DLS predicts ten-year MACE risk comparable with the office-based refit-WHO score. […] Our study provides a proof-of-concept and suggests the potential of a PPG-based approach strategies for community-based primary prevention in resource-limited regions.
#30 Predicting cardiovascular disease risk using photoplethysmography and deep learning | PLOS Global Public Health
https://journals.plos.org/globalpublichealth/article?id=10.1371/journal.pgph.0003204
We showed that DLS demonstrated non-inferiority to the office-based refit-WHO score. […] The DLS yielded C-statistic of 71.1% (95% CI [69.9, 72.4]). […] Our work focuses on understanding the role that PPG and deep learning can play in settings where equipment access to healthcare is limited, such as community-based screening programs in LMICs. […] This feature improves accessibility for health systems that have limited resources to collect vitals and labs for CVD risk screening and triage. […] Our study found that a deep learning model extracted features that when added to easily extractable clinical and demographic variables (such as smoking status, age and sex), provided statistically significant prognostic information about cardiovascular risk.
#31 Early prediction of in-hospital mortality in patients with congestive heart failure in intensive care unit: a retrospective observational cohort study | BMJ Open
https://bmjopen.bmj.com/content/12/7/e059761
The nomogram, which included these factors, accurately predicted the in-hospital mortality of patients with CHF. The novel nomogram has the potential for use in clinical practice as a tool to predict and assess mortality of patients with CHF in the ICU. […] The 20 independent risk factors for in-hospital mortality of patients with CHF were age, race, norepinephrine, dopamine, phenylephrine, vasopressin, mechanical ventilation, intubation, HepF, heart rate, respiratory rate, temperature, SBP, AG, BUN, creatinine, chloride, MCV, RDW and WCC. […] A nomogram is an effective tool for risk assessment. It provides a simple graphical representation for complex statistical prediction models, and is also suitable for prognostic analysis of individual patients. […] The present multivariate logistic regression indicated that age, race, norepinephrine, dopamine, phenylephrine, vasopressin, mechanical ventilation, intubation, HepF, heart rate, respiratory rate, temperature, SBP, AG, BUN, creatinine, chloride, MCV, RDW and WCC are prognostic factors for survival of patients with CHF.
#32 Early prediction of in-hospital mortality in patients with congestive heart failure in intensive care unit: a retrospective observational cohort study | BMJ Open
https://bmjopen.bmj.com/content/12/7/e059761
The nomogram, which included these factors, accurately predicted the in-hospital mortality of patients with CHF. The novel nomogram has the potential for use in clinical practice as a tool to predict and assess mortality of patients with CHF in the ICU. […] The 20 independent risk factors for in-hospital mortality of patients with CHF were age, race, norepinephrine, dopamine, phenylephrine, vasopressin, mechanical ventilation, intubation, HepF, heart rate, respiratory rate, temperature, SBP, AG, BUN, creatinine, chloride, MCV, RDW and WCC. […] A nomogram is an effective tool for risk assessment. It provides a simple graphical representation for complex statistical prediction models, and is also suitable for prognostic analysis of individual patients. […] The present multivariate logistic regression indicated that age, race, norepinephrine, dopamine, phenylephrine, vasopressin, mechanical ventilation, intubation, HepF, heart rate, respiratory rate, temperature, SBP, AG, BUN, creatinine, chloride, MCV, RDW and WCC are prognostic factors for survival of patients with CHF.
#33 Physical functional performance and prognosis in patients with heart failure: a systematic review and meta-analysis | BMC Cardiovascular Disorders | Full Text
https://bmccardiovascdisord.biomedcentral.com/articles/10.1186/s12872-020-01725-5
Patients with HFrEF and HFpEF who showed a slower gait speed (0.80m/s) also reported a larger risk of All-Cause of Hospitalisation [HR=1.32 95%CI (1.101.57), p=0.002] than patients with a faster gait speed (0.80m/s). […] Patients with HF who showed a poor physical functional performance in the 6MWT also reported an increased risk of the combined endpoint of hospitalisation and mortality for any cause, an increased risk of HF hospitalisation and an increased risk of all-cause of hospitalisation. […] Patients with HF who report a poor physical functional performance in the 6MWT, in the SPPB or in the Gait Speed Test, show worse prognosis than patients who report a good physical functional performance in terms of an increased risk of hospitalisation or an increased risk of mortality.
#34 Physical functional performance and prognosis in patients with heart failure: a systematic review and meta-analysis | BMC Cardiovascular Disorders | Full Text
https://bmccardiovascdisord.biomedcentral.com/articles/10.1186/s12872-020-01725-5
Patients with poor physical functional performance in the Six Minute Walking Test (6MWT), in the Short Physical Performance Battery (SPPB) and in the Gait Speed Test showed worse prognosis in terms of larger risk of hospitalisation or mortality than patients with good physical functional performance. […] The review includes a large number of studies which show a strong relationship between physical functional performance and prognosis in patients with HF. […] Patients with HFrEF, HFpEF and acute HF who showed a poor physical functional performance in the 6MWT reported a larger risk of All-Cause of Mortality [HR=2.29 95%CI (1.862.82), p0.001] than those patients who showed a good physical functional performance. […] Patients with HFrEF and HFpEF who showed a poor physical functional performance in the 6MWT also reported a larger risk of HF Mortality [HR=2.39 95%CI (2.212.59),p0.001] than those patients who showed a good physical functional performance.
#35
https://link.springer.com/article/10.1007/s11845-020-02477-z
Knowledge of a patients demographic, medical, and clinical data could play an important role in prediction of life expectancy. […] Low socioeconomic status in adulthood and childhood is associated with worsened HF outcomes. […] The New York Heart Association (NYHA) functional classification is still useful for assessing syndrome severity, patients exercise tolerance and prognosis in HF patients. […] Many echocardiographic markers have prognostic value in HF. […] In summary, LV systolic and diastolic function, LA function, and RV function have prognostic value in HFpEF. […] Peak VO2 remains the gold standard in predicting outcome in HF. […] Hospitalization for HF within the last year has been significant risk factor of subsequent hospitalizations. […] All of the presented models have shown only moderate probability in predicting death in HF. […] Despite the identification of many markers and models of poor prognosis, clinical decisions and guidelines in HF are still based mainly on several basic parameters, such as the presence of HF symptoms (NYHA class), LVEF, and the duration and morphology of the QRS complex.
#36 Interest of Lung Ultrasound in the Management of Acute Heart Failure in Post-Emergency Service
https://www.mdpi.com/2075-1729/15/5/752
Lung ultrasound (LUS) has emerged as a simple, rapid, and non-invasive method for the dynamic assessment of pulmonary congestion, a major prognostic factor and a therapeutic target in acute heart failure (AHF). […] Pulmonary congestion appears as a major prognostic factor in AHF, and therefore represents an important therapeutic target. […] Monitoring B-lines could be interesting for tracking pulmonary congestion, allowing for treatment in AHF patients and improving their prognosis. […] The presence of B-lines at discharge is significantly associated with a higher risk of mortality at 30-days. […] The relationship between the number of B-lines and the vital status at 30-days discharge is statistically significant with a p-value < 0.001. [...] The lack of clearance of B-lines at discharge seems to be associated with a high risk of adverse events, such as ED consultation, readmission for AHF, and all-cause mortality.
#37 Interest of Lung Ultrasound in the Management of Acute Heart Failure in Post-Emergency Service
https://www.mdpi.com/2075-1729/15/5/752
Lung ultrasound (LUS) has emerged as a simple, rapid, and non-invasive method for the dynamic assessment of pulmonary congestion, a major prognostic factor and a therapeutic target in acute heart failure (AHF). […] Pulmonary congestion appears as a major prognostic factor in AHF, and therefore represents an important therapeutic target. […] Monitoring B-lines could be interesting for tracking pulmonary congestion, allowing for treatment in AHF patients and improving their prognosis. […] The presence of B-lines at discharge is significantly associated with a higher risk of mortality at 30-days. […] The relationship between the number of B-lines and the vital status at 30-days discharge is statistically significant with a p-value < 0.001. [...] The lack of clearance of B-lines at discharge seems to be associated with a high risk of adverse events, such as ED consultation, readmission for AHF, and all-cause mortality.
#38 Interest of Lung Ultrasound in the Management of Acute Heart Failure in Post-Emergency Service
https://www.mdpi.com/2075-1729/15/5/752
Lung ultrasound (LUS) has emerged as a simple, rapid, and non-invasive method for the dynamic assessment of pulmonary congestion, a major prognostic factor and a therapeutic target in acute heart failure (AHF). […] Pulmonary congestion appears as a major prognostic factor in AHF, and therefore represents an important therapeutic target. […] Monitoring B-lines could be interesting for tracking pulmonary congestion, allowing for treatment in AHF patients and improving their prognosis. […] The presence of B-lines at discharge is significantly associated with a higher risk of mortality at 30-days. […] The relationship between the number of B-lines and the vital status at 30-days discharge is statistically significant with a p-value < 0.001. [...] The lack of clearance of B-lines at discharge seems to be associated with a high risk of adverse events, such as ED consultation, readmission for AHF, and all-cause mortality.
#39
https://link.springer.com/article/10.1007/s11845-020-02477-z
Knowledge of a patients demographic, medical, and clinical data could play an important role in prediction of life expectancy. […] Low socioeconomic status in adulthood and childhood is associated with worsened HF outcomes. […] The New York Heart Association (NYHA) functional classification is still useful for assessing syndrome severity, patients exercise tolerance and prognosis in HF patients. […] Many echocardiographic markers have prognostic value in HF. […] In summary, LV systolic and diastolic function, LA function, and RV function have prognostic value in HFpEF. […] Peak VO2 remains the gold standard in predicting outcome in HF. […] Hospitalization for HF within the last year has been significant risk factor of subsequent hospitalizations. […] All of the presented models have shown only moderate probability in predicting death in HF. […] Despite the identification of many markers and models of poor prognosis, clinical decisions and guidelines in HF are still based mainly on several basic parameters, such as the presence of HF symptoms (NYHA class), LVEF, and the duration and morphology of the QRS complex.
#40
https://link.springer.com/article/10.1007/s11845-020-02477-z
Heart failure (HF) is the only cardiovascular disease with an ever increasing incidence. […] The main challenge in the treatment of HF is the availability of reliable prognostic models that would allow patients and doctors to develop realistic expectations about the prognosis and to choose the appropriate therapy and monitoring method. […] Prognosis assessment plays a special role in patients qualified for implantable device therapy or surgical treatment (including heart transplantation). […] This article begins with a review of individual markers that contribute to the risk of unfavorable outcome in HF. […] However, no single risk factor is sufficient to predict prognosis in HF. Results of a few markers must be interpreted together. […] Still it is important to find the most important and valuable panel of a few predictors and there are still ongoing studies assessing potential new ones.
#41 XAI Framework for Cardiovascular Disease Prediction Using Classification Techniques
https://www.mdpi.com/2079-9292/11/24/4086
The SHAP values determine how each attribute contributes to the modelâs prediction. […] The ROC curve train categorizes a patientâs disease condition as either positive or negative, based on the test results and perceives the ideal cut-off value with the best symptomatic performance. […] The efficiency of the proposed XAI-driven ensemble classifiers is better than the conventional classification models. […] The SVM algorithm has exhibited a better performance with an accuracy of 82.5%, among all of the classifiers used in heart disease classification. […] The limitations of the existing models are that the dataset taken has a limited scope of attributes and sample size. […] The future dimension of the research could include the statistical analysis of the model over the divergent datasets, such as the UK Biobank dataset, University Federico II, Statlog heart disease dataset, and the NEU Hospital dataset for heart disease.
#42 XAI Framework for Cardiovascular Disease Prediction Using Classification Techniques
https://www.mdpi.com/2079-9292/11/24/4086
The SHAP values determine how each attribute contributes to the modelâs prediction. […] The ROC curve train categorizes a patientâs disease condition as either positive or negative, based on the test results and perceives the ideal cut-off value with the best symptomatic performance. […] The efficiency of the proposed XAI-driven ensemble classifiers is better than the conventional classification models. […] The SVM algorithm has exhibited a better performance with an accuracy of 82.5%, among all of the classifiers used in heart disease classification. […] The limitations of the existing models are that the dataset taken has a limited scope of attributes and sample size. […] The future dimension of the research could include the statistical analysis of the model over the divergent datasets, such as the UK Biobank dataset, University Federico II, Statlog heart disease dataset, and the NEU Hospital dataset for heart disease.
#43 Prediction models for cardiovascular disease risk in the general population: systematic review | The BMJ
https://www.bmj.com/content/353/bmj.i2416
This review shows that there is an abundance of cardiovascular risk prediction models for the general population. Previous reviews also indicated this but were conducted more than a decade ago, excluded models that were not internally or externally validated, or excluded articles that solely described external validation. […] Most developed prediction models are insufficiently reported to allow external validation by others, let alone to become implemented in clinical guidelines or being used in practice. We believe it is time to stop developing yet another similar CVD risk prediction model for the general population. Rather than developing such new CVD risk prediction models, in this era of large and combined datasets, we should focus on externally validating and comparing head-to-head the promising existing CVD risk models, on tailoring these models to local settings, to investigate whether they may be extended with new predictors, and finally to quantify the clinical impact of the most promising models.