Application of machine learning techniques to explore the occurrence of macrophage activation syndrome in Still's disease: results from the GIRRCS AOSD Study Group and the AIDA Network Still's Disease Registry.
Обработка статьи · этапы, ошибки и управление
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Ruscitti Piero, Masedu Francesco, Vitale Antonio, Caggiano Valeria, Di Cola Ilenia, Atzeni Fabiola, Sbalchiero Jessica, Lopalco Giuseppe, Iannone Florenzo, Morrone Maria, Iacono Daniela, Riccio Flavia, Visconti Mariachiara, Gaggiano Carla, Caso Francesco, Emmi Giacomo, Hinojosa-Azaola Andrea, Torres-Ruiz Jiram, Martín-Nares Eduardo, Guggino Giuliana, La Barbera Lidia, Batu Ezgi D, Ozen Seza, Sfikakis Petros P, Navarini Luca, Costa Luisa, Tufan Abdurrahman, Cakir Ibrahim Yahya, Perosa Federico, Hernández-Rodríguez José, Prete Marcella, Dagna Lorenzo, Campochiaro Corrado, Ursini Francesco, Sfriso Paolo, Bindoli Sara, Giardini Henrique A Mayrink, Fotis Lampros, Kourtesi Katerina, Ragab Gaafar, Ghanema Mahmoud, Saad Moustafa Ali, Direskeneli Haner, Karamanakos Anastasios, Conforti Alessandro, La Torre Francesco, Frassi Micol, Govoni Marcello, Parronchi Paola, Sarzi-Puttini Piercarlo, Maggio Maria Cristina, Bugatti Serena, De Stefano Ludovico, Pelizza Jacopo, Bartoloni Elena, Rigante Donato, Iagnocco Annamaria, Viapiana Ombretta, Wiesik-Szewczyk Ewa, Makowska Joanna, Gündüz Özgül Soysal, Erten Şükran, Ogunjimi Benson, Sebastiani Gian Domenico, Del Giudice Emanuela, Biancalana Edoardo, Conti Giovanni, AlMaghlouth Ibrahim A, Breda Luciana, Gidaro Antonio, Barone Patrizia, Olivieri Alma Nunzia, Carubbi Francesco, De Paulis Amato, Chimenti Maria Sole, Lo Gullo Alberto, Tharwat Samar, Thabet Maissa, Moshrif Abdelhfeez, Alessio Maria, Mauro Angela, Suzon Benoit, Pucino Valentina, Boyarchuk Oksana, Kovalchuk Tetiana, Bes Cemal, Deniz Rabia, Al-Mayouf Sulaiman M, Cipriani Paola, Valenti Marco, Balistreri Alberto, Fabiani Claudia, Ciccia Francesco, Montecucco Carlomaurizio, Giacomelli Roberto, Frediani Bruno, Cantarini Luca
Аннотация
METHODS: A multicenter, observational, prospective study was conducted, including patients with Still's disease enrolled in the Gruppo Italiano di Ricerca in Reumatologia Clinica e Sperimentale (GIRRCS) AOSD Study Group and the AutoInflammatory Disease Alliance (AIDA) Network Still's Disease Registry.
RESULTS: A total of 737 patients (age: 35.5 ± 17.8, male sex: 44.7%) with Still's disease were assessed; 11.4% were affected by MAS, and 3% had a poor prognosis. First, random forest imputation was applied to the original dataset. Subsequently, a machine-learning-driven assessment was developed to explore MAS occurrence. Collectively, regression models, an exploration decision tree, and a random forest were applied, suggesting the importance of ferritin, age, C-reactive protein (CRP), and systemic score. A logistic regression model accounting for data leakage concerns was then generated using these variables, and missing values were imputed using random forest imputation. This analysis supported the role of the selected variables, which were further combined across different clinical scenarios to estimate the probability of MAS. The highest risk of MAS was estimated for patients simultaneously characterized by age ≥ 45 years, ferritin ≥ 4,178.10 ng/mL, CRP ≥ 27.15 mg/L, and a systemic score ≥ 7, corresponding to a 34.7% probability of MAS, as well as for those characterized by ferritin ≥ 4,178.10 ng/mL, CRP ≥ 27.15 mg/L, and systemic score ≥ 7, corresponding to a 33.5% probability of MAS.
CONCLUSIONS: A machine-learning-driven prediction of MAS was explored in Still's disease, highlighting the importance of age of onset, hyperferritinaemia, increased CRP, and multiorgan involvement. A combination of these features may suggest a clinician-friendly algorithm for stratifying the probability of MAS during Still's disease.