Machine Learning Prediction of Liver Fibrosis in Patients With Metabolic Dysfunction-Associated Steatotic Liver Disease.
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.
Petta Salvatore, Pennisi Grazia, Celsa Ciro, Messaoudi Sofiane, Tsochatzis Emmanuel, Bugianesi Elisabetta, Yoneda Masato, Zheng Ming-Hua, Hagström Hannes, Boursier Jérôme, Calleja José Luis, Boon-Bee Goh George, Chan Wah-Kheong, Gallego-Durán Rocio, Sanyal Arun J, de Lédinghen Victor, Newsome Philip N, Fan Jian-Gao, Castéra Laurent, Lai Michelle, Fournier-Poizat Céline, Lai-Hung Wong Grace, Armandi Angelo, Nakajima Atsushi, Liu Wen-Yue, Shang Ying, de Saint-Loup Marc, Llop Elba, Jun Teh Kevin Kim, Lara-Romero Carmen, Asgharpour Amon, Sau-Wai Chan Mandy, Romero-Gomez Manuel, Lin Huapeng, Kim Seung Up, Cheuk-Fung Yip Terry, Calvaruso Vincenza, Zoncapè Mirko, Che-To Lai Jimmy, Yang Boyu, Lee Hye Won, Di Maria Gabriele, Enea Marco, Contino Salvatore, Wai-Sun Wong Vincent, Cirrincione Giansalvo, Cammà Calogero
Аннотация
METHODS: We developed and validated machine learning models to predict fibrosis stages in more than 3600 biopsy-confirmed patients with metabolic dysfunction-associated steatotic liver disease using 22 clinical features, liver stiffness measurement, and controlled attenuation parameter. Models included Feature Tokenizer Transformer, TabNet variants with distance-aware losses, ordinal Multilayer Perceptron with the COnditional RAnk Logits framework. Three centers were prespecified for geographic external validation. In the remaining centers, we used a stratified 75/25 split into a training pool and an internal random test set, tuned hyperparameters by stratified 10-fold cross-validation on the training pool, and trained 1 model per imputed dataset (M = 5) with an internal 80/20 train-validation split for early stopping and operating-point selection. Performance was pooled across imputations using Rubin's rules and reported for the internal random test set and the held-out centers.
RESULTS: Feature Tokenizer Transformer and TabNet achieved the highest performance in binary tasks: area under the receiver operating characteristic curve = 0.860 and 0.855 (F ≥3 vs 0-F2) and area under the receiver operating characteristic curve = 0.800 and 0.788 (F ≥2 vs 0-F1), significantly outperforming the Fibrosis-4 index. For F ≥3, Feature Tokenizer Transformer had significantly higher area under the receiver operating characteristic curve than liver stiffness measurement (P = .014) but only marginally higher than AGILE3+, and, together with TabNet, the highest accuracy and the lowest gray zone (8.2% and 8.4%, respectively). For multiclass staging, ordinal models performed best with Multilayer Perceptron with the Consistent Rank Logits achieving quadratic weighted kappa = 0.616.
CONCLUSIONS: Deep learning models with ordinal-aware architectures can accurately predict liver fibrosis stages using routinely available clinical data, offering a scalable alternative to biopsy without requiring specialized biomarkers.