Łuszczyca – Rokowania, prognozy i postęp choroby

Łuszczyca
Rokowania, prognozy i postęp choroby

Łuszczyca jest przewlekłą chorobą zapalną skóry, której przebieg i odpowiedź na leczenie są determinowane przez kluczowe czynniki prognostyczne: wiek pacjenta ≥40 lat wiąże się z lepszym rokowaniem (iloraz szans 0,27; 95% CI 0,10-0,72; p = 0,0091), natomiast płeć męska (iloraz szans 2,67; 95% CI 1,02-7,00; p = 0,0459) oraz BMI ≥25 (iloraz szans 2,74; 95% CI 1,01-7,42; p = 0,0480) są czynnikami niekorzystnymi. Pacjenci z ciężką postacią choroby doświadczają obniżonej jakości życia, zwiększonego ryzyka depresji oraz podwyższonej śmiertelności (średnio 3-5 lat wcześniejsza śmierć), głównie z powodu chorób współistniejących, zwłaszcza sercowo-naczyniowych. Leki biologiczne, choć skuteczne, tracą efektywność w 50-65% przypadków w ciągu 5 lat, co wymaga monitorowania i dostosowania terapii.

Prognoza Łuszczycy (Prognosis of Psoriasis)

Czynniki prognostyczne wpływające na przebieg choroby
Jakość życia i śmiertelność w łuszczycy
Predykcja odpowiedzi na leczenie biologiczne
Modele prognostyczne w fototerapii UVB

Miary oceny wyników leczenia łuszczycy

Podstawowe parametry kliniczne
Miary raportowane przez pacjentów
Modele predykcyjne nasilenia łuszczycy

Znaczenie prognostyki w optymalizacji leczenia łuszczycy

Kolejne rozdziały

Prognoza Łuszczycy (Prognosis of Psoriasis)

Łuszczyca jest przewlekłą chorobą zapalną skóry charakteryzującą się okresami zaostrzeń i remisji, co znacząco wpływa na jakość życia pacjentów. Prognozy dotyczące przebiegu choroby oraz odpowiedzi na leczenie są istotnym elementem opieki nad pacjentem z łuszczycą, pozwalającym na dobór optymalnej terapii oraz przewidywanie długoterminowych wyników leczenia.¹²

Czynniki prognostyczne wpływające na przebieg choroby

Wieloletnie obserwacje kliniczne pozwoliły na identyfikację kluczowych czynników prognostycznych, które mają wpływ na długoterminowy przebieg łuszczycy po jej zdiagnozowaniu. Analiza tych czynników jest niezbędna zarówno przy projektowaniu badań klinicznych, jak i przy indywidualnym doborze odpowiedniego podejścia terapeutycznego.³

Zidentyfikowano trzy główne czynniki prognostyczne wpływające na długoterminowe wyniki leczenia łuszczycy:

Wiek pacjenta – pacjenci w wieku ≥40 lat mają znacząco lepsze rokowanie (iloraz szans 0,27, 95% przedział ufności (CI) 0,10-0,72, p = 0,0091)
Płeć męska – stanowi czynnik niekorzystny rokowniczo (iloraz szans 2,67, 95% CI 1,02-7,00, p = 0,0459)
BMI ≥25 – nadwaga i otyłość są związane z gorszym rokowaniem (iloraz szans 2,74, 95% CI 1,01-7,42, p = 0,0480)

⁴

Jakość życia i śmiertelność w łuszczycy

Pacjenci z ciężkimi postaciami łuszczycy doświadczają istotnie obniżonej jakości życia w porównaniu do populacji ogólnej. Około połowa wszystkich pacjentów z łuszczycą doświadcza okresów remisji o zmiennej długości, co powoduje, że jakość życia może znacząco się zmieniać w różnych okresach, w zależności od aktywności choroby.⁵

Szczególnie niepokojącym aspektem jest zwiększone ryzyko depresji wtórnej do łuszczycy. Ponadto, w przypadku ciężkiej łuszczycy, wskaźniki śmiertelności mogą być podwyższone – badania populacyjne wykazały, że pacjenci z ciężką łuszczycą umierają średnio 3-5 lat wcześniej niż osoby z grupy kontrolnej.⁶⁷

Wyższa śmiertelność w ciężkiej łuszczycy jest często związana z chorobami współistniejącymi, szczególnie z chorobami sercowo-naczyniowymi. Dodatkowo, intensywne leczenie ciężkiej łuszczycy może wiązać się z poważnymi działaniami niepożądanymi, które zwiększają ryzyko innych chorób, takich jak nowotwory skóry, chłoniaki czy choroby wątroby.⁸

Predykcja odpowiedzi na leczenie biologiczne

Leki biologiczne stosowane w terapii łuszczycy z czasem tracą skuteczność, co prowadzi do przerwania leczenia. Według metaanalizy danych z rejestrów, ryzyko przerwania terapii biologicznej może wynosić nawet 50-65% w ciągu 5 lat, w zależności od stosowanego leku.⁹

Tradycyjne modele statystyczne oparte na czynnikach ryzyka wykazują ograniczoną wartość predykcyjną (AUC = 0,61), co wskazuje na niską wartość dyskryminacyjną, choć lepszą niż przypadkowe przewidywanie. Bardziej zaawansowane metody uczenia maszynowego znacząco poprawiają możliwości predykcyjne:¹⁰

Algorytm Gradient Boosted Tree osiąga AUC na poziomie 0,85, co wskazuje na doskonałą wydajność algorytmu
Najbardziej efektywne algorytmy uczenia maszynowego są w stanie przewidzieć wyniki leczenia z błędem klasyfikacji poniżej 23%, wykorzystując jedynie podstawowe informacje o pacjencie dostępne dla każdego klinicysty

¹¹¹²

Nawet podstawowe informacje kliniczne (płeć, masa ciała, nazwa leku, wcześniejsza ekspozycja na lek biologiczny) pozwalają przewidzieć ryzyko przerwania leczenia przy użyciu prostego nomogramu, co może wspomóc podejmowanie decyzji klinicznych.¹³

Modele prognostyczne w fototerapii UVB

Opracowano zindywidualizowane modele obliczeniowe, które pozwalają na przewidywanie odpowiedzi na fototerapię UVB. W prospektywnym badaniu klinicznym obejmującym 94 pacjentów, seryjne indywidualne dawki UVB i wartości odpowiedzi klinicznej (wskaźnik PASI) zbierane przez pierwsze trzy tygodnie terapii UVB umożliwiły oszacowanie parametru wrażliwości na UVB i przewidywanie indywidualnego wyniku pacjenta na końcu fototerapii.¹⁴

Model przewiduje całkowite ustąpienie zmian i ewentualną remisję, gdy dynamika modelu spada poniżej stanu przejściowego (tj. przy około 90% ustąpieniu zmian). Wskazuje również, że minimalną liczbę sesji UVB i odpowiednią częstotliwość naświetlań koniecznych do ustąpienia łuszczycy i wywołania remisji można określić na podstawie:¹⁵¹⁶

Parametru wrażliwości na UVB specyficznego dla pacjenta (uvbs)
Rzeczywistych dawek UVB, które zostaną podane

¹⁷

Tego typu modele stanowią istotny krok w kierunku medycyny precyzyjnej w łuszczycy, umożliwiając wczesną ocenę odpowiedzi na terapię UVB i indywidualizację schematów fototerapii w celu poprawy wyników klinicznych.¹⁸¹⁹

Miary oceny wyników leczenia łuszczycy

Ocena nasilenia łuszczycy i jej wpływu na codzienne życie pacjenta jest kluczowa dla personelu medycznego i pacjentów podczas ustalania planu leczenia choroby. W praktyce klinicznej i badaniach naukowych stosuje się kilka różnych miar do oceny fizycznego, emocjonalnego i psychicznego wpływu łuszczycy, a także skuteczności zastosowanego leczenia.²⁰

Podstawowe parametry kliniczne

Body Surface Area (BSA) – miara określająca, jaka część powierzchni skóry jest dotknięta łuszczycą; służy do śledzenia zmian nasilenia choroby u indywidualnego pacjenta w czasie
Psoriasis Area and Severity Index (PASI) – ocenia aktywność choroby, uwzględniając zarówno powierzchnię zajętej skóry (BSA), jak i nasilenie zmian łuszczycowych; PASI 75 (75% poprawa w stosunku do wartości wyjściowej) jest często stosowany jako pierwszorzędowy punkt końcowy w badaniach klinicznych do pomiaru poprawy ogólnego zakresu i nasilenia choroby
Static Physicians Global Assessment (sPGA) – ocenia nasilenie choroby w danym momencie, z uwzględnieniem grubości zmian (określanej także jako stwardnienie), zaczerwienienia (określanego także jako rumień) oraz obecności białych/srebrzystych łusek na skórze (określanej także jako złuszczanie); sPGA 0/1 (oznaczające skórę czystą lub prawie czystą) jest często stosowane jako punkt końcowy w badaniach klinicznych

²¹²²

Miary raportowane przez pacjentów

Miary raportowane przez pacjentów są zgłaszane samodzielnie przy użyciu kwestionariuszy, które rejestrują własną ocenę pacjenta dotyczącą jego łuszczycy, zadowolenia z leczenia lub wpływu na jakość życia. Im wyższy wynik, tym bardziej jakość życia jest uważana za upośledzoną.²³

Modele predykcyjne nasilenia łuszczycy

Opracowano i wewnętrznie zwalidowano model diagnostyczny oparty na algorytmie gradient boosting do przewidywania obecności łuszczycy o nasileniu umiarkowanym do ciężkiego. Model ten wykorzystuje dwa samodzielnie raportowane pomiary kliniczne rejestrowane w duńskiej kohorcie skórnej: BSA i DLQI.²⁴

Model diagnostyczny wykazał akceptowalną zdolność dyskryminacyjną z wartością c-statystyki równą 0,73 [95% CI: 0,71-0,74]. Wewnętrzna walidacja metodą bootstrap nie wykazała istotnego optymizmu w wynikach, z wartością c-statystyki 0,72 [95% CI: 0,70-0,74].²⁵

Wykorzystanie tego narzędzia diagnostycznego umożliwia oszacowanie częstości występowania pacjentów sklasyfikowanych jako cierpiący na łuszczycę o nasileniu umiarkowanym do ciężkiego w rejestrach narodowych, co ma istotne znaczenie dla planowania opieki zdrowotnej i alokacji zasobów.²⁶

Znaczenie prognostyki w optymalizacji leczenia łuszczycy

Zrozumienie czynników prognostycznych i rozwój modeli predykcyjnych w łuszczycy ma kluczowe znaczenie dla optymalizacji terapii i poprawy długoterminowych wyników leczenia. Nowoczesne podejście uwzględniające zarówno klasyczne czynniki rokownicze (wiek, płeć, BMI), jak i zaawansowane modele obliczeniowe (modele uczenia maszynowego, modele dynamiki choroby) pozwala na bardziej precyzyjne prognozowanie przebiegu choroby i odpowiedzi na różne metody leczenia.²⁷²⁸²⁹

Zarówno tradycyjne miary kliniczne (PASI, BSA, sPGA), jak i miary raportowane przez pacjentów, stanowią niezbędne narzędzia do oceny skuteczności leczenia i jego wpływu na jakość życia. Integracja tych miar z zaawansowanymi modelami predykcyjnymi otwiera drogę do bardziej zindywidualizowanego podejścia terapeutycznego, stanowiąc ważny krok w kierunku medycyny precyzyjnej w leczeniu łuszczycy.³⁰³¹³²

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 Azthena logo with the word Azthena
https://www.news-medical.net/health/Psoriasis-Prognosis.aspx
Patients with severe forms of psoriasis may experience a poorer quality of life and overall health outcomes as compared to other members of the general population. […] Approximately half of all patients with psoriasis will experience periods of remission, which can vary greatly in length. […] As a result of the occurrence of both remissions and flare-ups, the quality of life of patients with psoriasis can vary significantly over different time periods, depending on the level of impediment. […] The quality of life for patients with psoriasis can be greatly altered due to the effects of the disease. […] Of particular concern, many patients with psoriasis are affected by depression that is secondary to the condition. […] However, mortality rates may be affected in severe cases of psoriasis.
#2 Prognostic factor analysis for plaque psoriasis – PubMed
https://pubmed.ncbi.nlm.nih.gov/16088154/
Little is known about the long-term prognostic factors which affect clinical outcomes after the diagnosis of psoriasis. […] To identify the prognostic factors which predict long-term outcomes after diagnosis. […] The factors age or =40 [odds ratio 0.27, 95% confidence interval (CI) 0.10-0.72, p = 0.0091], male (odds ratio 2.67, 95% CI 1.02-7.00,p = 0.0459) and BMI or =25 (odds ratio 2.74, 95% CI 1.01-7.42, p = 0.0480) had significant effects on long-term prognosis after diagnosis. […] Three major prognostic factors were identified. The proposed index may be useful in the design of future clinical trials for psoriasis and in the selection of appropriate therapeutic approaches for individual patients.
#3 Prognostic factor analysis for plaque psoriasis – PubMed
https://pubmed.ncbi.nlm.nih.gov/16088154/
Little is known about the long-term prognostic factors which affect clinical outcomes after the diagnosis of psoriasis. […] To identify the prognostic factors which predict long-term outcomes after diagnosis. […] The factors age or =40 [odds ratio 0.27, 95% confidence interval (CI) 0.10-0.72, p = 0.0091], male (odds ratio 2.67, 95% CI 1.02-7.00,p = 0.0459) and BMI or =25 (odds ratio 2.74, 95% CI 1.01-7.42, p = 0.0480) had significant effects on long-term prognosis after diagnosis. […] Three major prognostic factors were identified. The proposed index may be useful in the design of future clinical trials for psoriasis and in the selection of appropriate therapeutic approaches for individual patients.
#4 Prognostic factor analysis for plaque psoriasis – PubMed
https://pubmed.ncbi.nlm.nih.gov/16088154/
Little is known about the long-term prognostic factors which affect clinical outcomes after the diagnosis of psoriasis. […] To identify the prognostic factors which predict long-term outcomes after diagnosis. […] The factors age or =40 [odds ratio 0.27, 95% confidence interval (CI) 0.10-0.72, p = 0.0091], male (odds ratio 2.67, 95% CI 1.02-7.00,p = 0.0459) and BMI or =25 (odds ratio 2.74, 95% CI 1.01-7.42, p = 0.0480) had significant effects on long-term prognosis after diagnosis. […] Three major prognostic factors were identified. The proposed index may be useful in the design of future clinical trials for psoriasis and in the selection of appropriate therapeutic approaches for individual patients.
#5 Azthena logo with the word Azthena
https://www.news-medical.net/health/Psoriasis-Prognosis.aspx
Patients with severe forms of psoriasis may experience a poorer quality of life and overall health outcomes as compared to other members of the general population. […] Approximately half of all patients with psoriasis will experience periods of remission, which can vary greatly in length. […] As a result of the occurrence of both remissions and flare-ups, the quality of life of patients with psoriasis can vary significantly over different time periods, depending on the level of impediment. […] The quality of life for patients with psoriasis can be greatly altered due to the effects of the disease. […] Of particular concern, many patients with psoriasis are affected by depression that is secondary to the condition. […] However, mortality rates may be affected in severe cases of psoriasis.
#6 Azthena logo with the word Azthena
https://www.news-medical.net/health/Psoriasis-Prognosis.aspx
Patients with severe forms of psoriasis may experience a poorer quality of life and overall health outcomes as compared to other members of the general population. […] Approximately half of all patients with psoriasis will experience periods of remission, which can vary greatly in length. […] As a result of the occurrence of both remissions and flare-ups, the quality of life of patients with psoriasis can vary significantly over different time periods, depending on the level of impediment. […] The quality of life for patients with psoriasis can be greatly altered due to the effects of the disease. […] Of particular concern, many patients with psoriasis are affected by depression that is secondary to the condition. […] However, mortality rates may be affected in severe cases of psoriasis.
#7 Azthena logo with the word Azthena
https://www.news-medical.net/health/Psoriasis-Prognosis.aspx
Several studies with a sample population of men and women have shown that patients with severe cases of the disease are linked to death three to five years early than the control group population. […] These factors may also account for the mortality changes noted in patients with severe psoriasis. […] In many cases, a resulting health condition, such as heart disease, is responsible for causing changes in mortality rates for patients with psoriasis. […] In severe cases, the treatments required to control the psoriatic symptoms can have harsh adverse effects and may increase the risk of other health conditions, such as skin cancer, lymphoma, and liver disease.
#8 Azthena logo with the word Azthena
https://www.news-medical.net/health/Psoriasis-Prognosis.aspx
Several studies with a sample population of men and women have shown that patients with severe cases of the disease are linked to death three to five years early than the control group population. […] These factors may also account for the mortality changes noted in patients with severe psoriasis. […] In many cases, a resulting health condition, such as heart disease, is responsible for causing changes in mortality rates for patients with psoriasis. […] In severe cases, the treatments required to control the psoriatic symptoms can have harsh adverse effects and may increase the risk of other health conditions, such as skin cancer, lymphoma, and liver disease.
#9 Machine Learning Model for Predicting Outcomes of Biologic Therapy in Psoriasis | medRxiv
https://www.medrxiv.org/content/10.1101/2021.12.05.21267219.full
Biological agents used for the therapy of psoriasis lose efficacy over time, which leads to discontinuation of the drug. […] The predictive model based on those risk factors had an AUC of 0.61. The best ML model (gradient boosted tree) had an AUC of 0.85. […] A machine learning-based approach, more than a statistical model, accurately predicts the risk of discontinuation of biologic therapy based on simple patient variables available in clinical practice. […] In a meta-analysis of the registry data looking at the risk of discontinuation, discontinuation may be as high as 50-65% over 5 years, depending on the drug. […] We found that even the most basic clinical information (sex, weight, drug name, previous exposure to a biologic) allowed us to predict the risk of discontinuation using a simple nomogram.
#10 Machine Learning Model for Predicting Outcomes of Biologic Therapy in Psoriasis | medRxiv
https://www.medrxiv.org/content/10.1101/2021.12.05.21267219.full
The AUC based on the Cox regression is 0.61, which indicates low discriminatory value, but better than a random guess. […] The most efficient ML algorithms were able to predict the treatment outcomes with less than 23% classification error, only utilizing basic patient information routinely available to every clinician. […] The AUC measured for the Gradient Boosted Tree was 0.85, which is an indicator of excellent performance of the algorithm.
#11 Machine Learning Model for Predicting Outcomes of Biologic Therapy in Psoriasis | medRxiv
https://www.medrxiv.org/content/10.1101/2021.12.05.21267219.full
Biological agents used for the therapy of psoriasis lose efficacy over time, which leads to discontinuation of the drug. […] The predictive model based on those risk factors had an AUC of 0.61. The best ML model (gradient boosted tree) had an AUC of 0.85. […] A machine learning-based approach, more than a statistical model, accurately predicts the risk of discontinuation of biologic therapy based on simple patient variables available in clinical practice. […] In a meta-analysis of the registry data looking at the risk of discontinuation, discontinuation may be as high as 50-65% over 5 years, depending on the drug. […] We found that even the most basic clinical information (sex, weight, drug name, previous exposure to a biologic) allowed us to predict the risk of discontinuation using a simple nomogram.
#12 Machine Learning Model for Predicting Outcomes of Biologic Therapy in Psoriasis | medRxiv
https://www.medrxiv.org/content/10.1101/2021.12.05.21267219.full
The AUC based on the Cox regression is 0.61, which indicates low discriminatory value, but better than a random guess. […] The most efficient ML algorithms were able to predict the treatment outcomes with less than 23% classification error, only utilizing basic patient information routinely available to every clinician. […] The AUC measured for the Gradient Boosted Tree was 0.85, which is an indicator of excellent performance of the algorithm.
#13 Machine Learning Model for Predicting Outcomes of Biologic Therapy in Psoriasis | medRxiv
https://www.medrxiv.org/content/10.1101/2021.12.05.21267219.full
Biological agents used for the therapy of psoriasis lose efficacy over time, which leads to discontinuation of the drug. […] The predictive model based on those risk factors had an AUC of 0.61. The best ML model (gradient boosted tree) had an AUC of 0.85. […] A machine learning-based approach, more than a statistical model, accurately predicts the risk of discontinuation of biologic therapy based on simple patient variables available in clinical practice. […] In a meta-analysis of the registry data looking at the risk of discontinuation, discontinuation may be as high as 50-65% over 5 years, depending on the drug. […] We found that even the most basic clinical information (sex, weight, drug name, previous exposure to a biologic) allowed us to predict the risk of discontinuation using a simple nomogram.
#14 Individualised computational modelling of immune mediated disease onset, flare and clearance in psoriasis | PLOS Computational Biology
https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1010267
Despite increased understanding about psoriasis pathophysiology, currently there is a lack of predictive computational models. […] In a prospective clinical study of 94 patients, serial individual UVB doses and clinical response (Psoriasis Area Severity Index) values collected over the first three weeks of UVB therapy informed estimation of the UVB sensitivity parameter and the prediction of individual patient outcome at the end of phototherapy. […] An important advance of our model is its potential for direct clinical application through early assessment of response to UVB therapy, and for individualised optimisation of phototherapy regimes to improve clinical outcome. […] Our model predicts complete clearance and eventual remission when the model dynamics drops below the transition steady state (i.e., at approximately 90% clearance).
#15 Individualised computational modelling of immune mediated disease onset, flare and clearance in psoriasis | PLOS Computational Biology
https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1010267
Despite increased understanding about psoriasis pathophysiology, currently there is a lack of predictive computational models. […] In a prospective clinical study of 94 patients, serial individual UVB doses and clinical response (Psoriasis Area Severity Index) values collected over the first three weeks of UVB therapy informed estimation of the UVB sensitivity parameter and the prediction of individual patient outcome at the end of phototherapy. […] An important advance of our model is its potential for direct clinical application through early assessment of response to UVB therapy, and for individualised optimisation of phototherapy regimes to improve clinical outcome. […] Our model predicts complete clearance and eventual remission when the model dynamics drops below the transition steady state (i.e., at approximately 90% clearance).
#16 Individualised computational modelling of immune mediated disease onset, flare and clearance in psoriasis | PLOS Computational Biology
https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1010267
Our model indicates that a minimum number of UVB episodes and appropriate irradiation frequency are necessary for clearing psoriasis and inducing remission, depending on the patient-specific UVB sensitivity parameter uvbs (i.e., patient-specific UVB sensitivity to phototherapy), and actual UVB doses that will be administered. […] Together these results support the development of precision medicine in psoriasis.
#17 Individualised computational modelling of immune mediated disease onset, flare and clearance in psoriasis | PLOS Computational Biology
https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1010267
Our model indicates that a minimum number of UVB episodes and appropriate irradiation frequency are necessary for clearing psoriasis and inducing remission, depending on the patient-specific UVB sensitivity parameter uvbs (i.e., patient-specific UVB sensitivity to phototherapy), and actual UVB doses that will be administered. […] Together these results support the development of precision medicine in psoriasis.
#18 Individualised computational modelling of immune mediated disease onset, flare and clearance in psoriasis | PLOS Computational Biology
https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1010267
Despite increased understanding about psoriasis pathophysiology, currently there is a lack of predictive computational models. […] In a prospective clinical study of 94 patients, serial individual UVB doses and clinical response (Psoriasis Area Severity Index) values collected over the first three weeks of UVB therapy informed estimation of the UVB sensitivity parameter and the prediction of individual patient outcome at the end of phototherapy. […] An important advance of our model is its potential for direct clinical application through early assessment of response to UVB therapy, and for individualised optimisation of phototherapy regimes to improve clinical outcome. […] Our model predicts complete clearance and eventual remission when the model dynamics drops below the transition steady state (i.e., at approximately 90% clearance).
#19 Individualised computational modelling of immune mediated disease onset, flare and clearance in psoriasis | PLOS Computational Biology
https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1010267
Our model indicates that a minimum number of UVB episodes and appropriate irradiation frequency are necessary for clearing psoriasis and inducing remission, depending on the patient-specific UVB sensitivity parameter uvbs (i.e., patient-specific UVB sensitivity to phototherapy), and actual UVB doses that will be administered. […] Together these results support the development of precision medicine in psoriasis.
#20 Understanding key psoriasis outcome measures â Bristol Myers Squibb
https://www.bms.com/patient-and-caregivers/patient-resources-by-condition/immunology-resources/understanding-key-psoriasis-outcome-measures.html
The severity of psoriasis and its impact on a persons daily life are important for healthcare providers and patients to understand as they work together to determine a disease management plan. Several different measures are used to evaluate the physical, emotional and mental impact of psoriasis, as well as how effectively a medicine treats the disease. […] Below are definitions for some common measures used to assess both disease severity and how psoriasis may improve after receiving treatment. Some of these measures are used in clinical studies to help evaluate the effectiveness of potential new psoriasis treatments. […] Body Surface Area (BSA) – a measure of how much skin is impacted by psoriasis and can be used to track an individuals psoriasis over time. […] Psoriasis Area and Severity Index (PASI) evaluates psoriasis disease activity, taking into account how much of the BSA is affected and the severity of psoriasis lesions. PASI 75 is often used as a primary endpoint in clinical studies to measure improvements in the overall extent and severity of disease, which is one way to measure success of a treatment.
#21 Understanding key psoriasis outcome measures â Bristol Myers Squibb
https://www.bms.com/patient-and-caregivers/patient-resources-by-condition/immunology-resources/understanding-key-psoriasis-outcome-measures.html
The severity of psoriasis and its impact on a persons daily life are important for healthcare providers and patients to understand as they work together to determine a disease management plan. Several different measures are used to evaluate the physical, emotional and mental impact of psoriasis, as well as how effectively a medicine treats the disease. […] Below are definitions for some common measures used to assess both disease severity and how psoriasis may improve after receiving treatment. Some of these measures are used in clinical studies to help evaluate the effectiveness of potential new psoriasis treatments. […] Body Surface Area (BSA) – a measure of how much skin is impacted by psoriasis and can be used to track an individuals psoriasis over time. […] Psoriasis Area and Severity Index (PASI) evaluates psoriasis disease activity, taking into account how much of the BSA is affected and the severity of psoriasis lesions. PASI 75 is often used as a primary endpoint in clinical studies to measure improvements in the overall extent and severity of disease, which is one way to measure success of a treatment.
#22 Understanding key psoriasis outcome measures â Bristol Myers Squibb
https://www.bms.com/patient-and-caregivers/patient-resources-by-condition/immunology-resources/understanding-key-psoriasis-outcome-measures.html
Static Physicians Global Assessment (sPGA) evaluates the severity of the disease at a given point in time, with psoriasis lesions evaluated for thickness (also referred to as induration), redness (also referred to as erythema) and presence of white/silvery scales on the skin (also referred to as desquamation). […] sPGA 0/1 is often used as an endpoint in clinical trials to measure the effectiveness of a treatment, indicating clear or almost-clear skin. […] Patient-Reported Measures are self-reported using questionnaires that capture a patients own assessment of their psoriasis, satisfaction with treatment or impact on their quality of life. […] The higher the score, the more quality of life is considered impaired.
#23 Understanding key psoriasis outcome measures â Bristol Myers Squibb
https://www.bms.com/patient-and-caregivers/patient-resources-by-condition/immunology-resources/understanding-key-psoriasis-outcome-measures.html
Static Physicians Global Assessment (sPGA) evaluates the severity of the disease at a given point in time, with psoriasis lesions evaluated for thickness (also referred to as induration), redness (also referred to as erythema) and presence of white/silvery scales on the skin (also referred to as desquamation). […] sPGA 0/1 is often used as an endpoint in clinical trials to measure the effectiveness of a treatment, indicating clear or almost-clear skin. […] Patient-Reported Measures are self-reported using questionnaires that capture a patients own assessment of their psoriasis, satisfaction with treatment or impact on their quality of life. […] The higher the score, the more quality of life is considered impaired.
#24 Development and internal validation of a diagnostic prediction model for psoriasis severity | Diagnostic and Prognostic Research | Full Text
https://diagnprognres.biomedcentral.com/articles/10.1186/s41512-023-00141-5
We developed a gradient boosting diagnostic model returning acceptable prediction of patients with moderate-to-severe psoriasis. […] The diagnostic prediction model yielded a bootstrap-corrected discrimination performance: c-statistic equal to 0.73 [95% CI: 0.710.74]. […] The internal validation by bootstrap correction showed no substantial optimism in the results with a c-statistic of 0.72 [95% CI: 0.700.74]. […] The outcome was the severity status of psoriasis, which we defined as a binary variable (mild/moderate-to-severe), based on two self-reported clinical measurements recorded in the Danish Skin Cohort: BSA and DLQI. […] We developed and internally validated a clinical diagnostic prediction model to predict the presence of moderate-to-severe psoriasis in the Danish national registries. […] Using this diagnostic tool, it could be possible to estimate the prevalence of patients categorized as moderate-to-severe psoriasis. […] The gradient boosting machine model obtained an acceptable risk prediction for moderate-to-severe psoriasis patients.
#25 Development and internal validation of a diagnostic prediction model for psoriasis severity | Diagnostic and Prognostic Research | Full Text
https://diagnprognres.biomedcentral.com/articles/10.1186/s41512-023-00141-5
We developed a gradient boosting diagnostic model returning acceptable prediction of patients with moderate-to-severe psoriasis. […] The diagnostic prediction model yielded a bootstrap-corrected discrimination performance: c-statistic equal to 0.73 [95% CI: 0.710.74]. […] The internal validation by bootstrap correction showed no substantial optimism in the results with a c-statistic of 0.72 [95% CI: 0.700.74]. […] The outcome was the severity status of psoriasis, which we defined as a binary variable (mild/moderate-to-severe), based on two self-reported clinical measurements recorded in the Danish Skin Cohort: BSA and DLQI. […] We developed and internally validated a clinical diagnostic prediction model to predict the presence of moderate-to-severe psoriasis in the Danish national registries. […] Using this diagnostic tool, it could be possible to estimate the prevalence of patients categorized as moderate-to-severe psoriasis. […] The gradient boosting machine model obtained an acceptable risk prediction for moderate-to-severe psoriasis patients.
#26 Development and internal validation of a diagnostic prediction model for psoriasis severity | Diagnostic and Prognostic Research | Full Text
https://diagnprognres.biomedcentral.com/articles/10.1186/s41512-023-00141-5
We developed a gradient boosting diagnostic model returning acceptable prediction of patients with moderate-to-severe psoriasis. […] The diagnostic prediction model yielded a bootstrap-corrected discrimination performance: c-statistic equal to 0.73 [95% CI: 0.710.74]. […] The internal validation by bootstrap correction showed no substantial optimism in the results with a c-statistic of 0.72 [95% CI: 0.700.74]. […] The outcome was the severity status of psoriasis, which we defined as a binary variable (mild/moderate-to-severe), based on two self-reported clinical measurements recorded in the Danish Skin Cohort: BSA and DLQI. […] We developed and internally validated a clinical diagnostic prediction model to predict the presence of moderate-to-severe psoriasis in the Danish national registries. […] Using this diagnostic tool, it could be possible to estimate the prevalence of patients categorized as moderate-to-severe psoriasis. […] The gradient boosting machine model obtained an acceptable risk prediction for moderate-to-severe psoriasis patients.
#27 Prognostic factor analysis for plaque psoriasis – PubMed
https://pubmed.ncbi.nlm.nih.gov/16088154/
Little is known about the long-term prognostic factors which affect clinical outcomes after the diagnosis of psoriasis. […] To identify the prognostic factors which predict long-term outcomes after diagnosis. […] The factors age or =40 [odds ratio 0.27, 95% confidence interval (CI) 0.10-0.72, p = 0.0091], male (odds ratio 2.67, 95% CI 1.02-7.00,p = 0.0459) and BMI or =25 (odds ratio 2.74, 95% CI 1.01-7.42, p = 0.0480) had significant effects on long-term prognosis after diagnosis. […] Three major prognostic factors were identified. The proposed index may be useful in the design of future clinical trials for psoriasis and in the selection of appropriate therapeutic approaches for individual patients.
#28 Machine Learning Model for Predicting Outcomes of Biologic Therapy in Psoriasis | medRxiv
https://www.medrxiv.org/content/10.1101/2021.12.05.21267219.full
Biological agents used for the therapy of psoriasis lose efficacy over time, which leads to discontinuation of the drug. […] The predictive model based on those risk factors had an AUC of 0.61. The best ML model (gradient boosted tree) had an AUC of 0.85. […] A machine learning-based approach, more than a statistical model, accurately predicts the risk of discontinuation of biologic therapy based on simple patient variables available in clinical practice. […] In a meta-analysis of the registry data looking at the risk of discontinuation, discontinuation may be as high as 50-65% over 5 years, depending on the drug. […] We found that even the most basic clinical information (sex, weight, drug name, previous exposure to a biologic) allowed us to predict the risk of discontinuation using a simple nomogram.
#29 Individualised computational modelling of immune mediated disease onset, flare and clearance in psoriasis | PLOS Computational Biology
https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1010267
Our model indicates that a minimum number of UVB episodes and appropriate irradiation frequency are necessary for clearing psoriasis and inducing remission, depending on the patient-specific UVB sensitivity parameter uvbs (i.e., patient-specific UVB sensitivity to phototherapy), and actual UVB doses that will be administered. […] Together these results support the development of precision medicine in psoriasis.
#30 Understanding key psoriasis outcome measures â Bristol Myers Squibb
https://www.bms.com/patient-and-caregivers/patient-resources-by-condition/immunology-resources/understanding-key-psoriasis-outcome-measures.html
The severity of psoriasis and its impact on a persons daily life are important for healthcare providers and patients to understand as they work together to determine a disease management plan. Several different measures are used to evaluate the physical, emotional and mental impact of psoriasis, as well as how effectively a medicine treats the disease. […] Below are definitions for some common measures used to assess both disease severity and how psoriasis may improve after receiving treatment. Some of these measures are used in clinical studies to help evaluate the effectiveness of potential new psoriasis treatments. […] Body Surface Area (BSA) – a measure of how much skin is impacted by psoriasis and can be used to track an individuals psoriasis over time. […] Psoriasis Area and Severity Index (PASI) evaluates psoriasis disease activity, taking into account how much of the BSA is affected and the severity of psoriasis lesions. PASI 75 is often used as a primary endpoint in clinical studies to measure improvements in the overall extent and severity of disease, which is one way to measure success of a treatment.
#31 Development and internal validation of a diagnostic prediction model for psoriasis severity | Diagnostic and Prognostic Research | Full Text
https://diagnprognres.biomedcentral.com/articles/10.1186/s41512-023-00141-5
We developed a gradient boosting diagnostic model returning acceptable prediction of patients with moderate-to-severe psoriasis. […] The diagnostic prediction model yielded a bootstrap-corrected discrimination performance: c-statistic equal to 0.73 [95% CI: 0.710.74]. […] The internal validation by bootstrap correction showed no substantial optimism in the results with a c-statistic of 0.72 [95% CI: 0.700.74]. […] The outcome was the severity status of psoriasis, which we defined as a binary variable (mild/moderate-to-severe), based on two self-reported clinical measurements recorded in the Danish Skin Cohort: BSA and DLQI. […] We developed and internally validated a clinical diagnostic prediction model to predict the presence of moderate-to-severe psoriasis in the Danish national registries. […] Using this diagnostic tool, it could be possible to estimate the prevalence of patients categorized as moderate-to-severe psoriasis. […] The gradient boosting machine model obtained an acceptable risk prediction for moderate-to-severe psoriasis patients.
#32 Individualised computational modelling of immune mediated disease onset, flare and clearance in psoriasis | PLOS Computational Biology
https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1010267
Despite increased understanding about psoriasis pathophysiology, currently there is a lack of predictive computational models. […] In a prospective clinical study of 94 patients, serial individual UVB doses and clinical response (Psoriasis Area Severity Index) values collected over the first three weeks of UVB therapy informed estimation of the UVB sensitivity parameter and the prediction of individual patient outcome at the end of phototherapy. […] An important advance of our model is its potential for direct clinical application through early assessment of response to UVB therapy, and for individualised optimisation of phototherapy regimes to improve clinical outcome. […] Our model predicts complete clearance and eventual remission when the model dynamics drops below the transition steady state (i.e., at approximately 90% clearance).