التفاصيل البيبلوغرافية
| العنوان: |
Machine learning algorithm improves the detection of NASH (NAS-based) and at-risk NASH : A development and validation study |
| المؤلفون: |
LITMUS Investigators, Lee, Jenny, Westphal, Max, Vali, Yasaman, Boursier, Jerome, Petta, Salvatorre, Ostroff, Rachel, Alexander, Leigh, Chen, Yu, Fournier, Celine, Geier, Andreas, Francque, Sven, Wonders, Kristy, Tiniakos, Dina, Bedossa, Pierre, Allison, Mike, Papatheodoridis, Georgios, Cortez-Pinto, Helena, Pais, Raluca, Dufour, Jean-Francois, Leeming, Diana Julie, Harrison, Stephen, Cobbold, Jeremy, Holleboom, Adriaan G., Yki-Järvinen, Hannele, Crespo, Javier, Ekstedt, Mattias, Aithal, Guruprasad P., Bugianesi, Elisabetta, Romero-Gomez, Manuel, Torstenson, Richard, Karsdal, Morten, Yunis, Carla, Schattenberg, Joern M., Schuppan, Detlef, Ratziu, Vlad, Brass, Clifford, Duffin, Kevin, Zwinderman, Koos, Pavlides, Michael, Anstee, Quentin M., Bossuyt, Patrick M. |
| المساهمون: |
Department of Medicine, HUS Internal Medicine and Rehabilitation |
| بيانات النشر: |
John Wiley & Sons Ltd. |
| سنة النشر: |
2024 |
| المجموعة: |
Helsingfors Universitet: HELDA – Helsingin yliopiston digitaalinen arkisto |
| مصطلحات موضوعية: |
General medicine, internal medicine and other clinical medicine |
| الوصف: |
Background and Aims: Detecting NASH remains challenging, while at-risk NASH (steatohepatitis and F >= 2) tends to progress and is of interest for drug development and clinical application. We developed prediction models by supervised machine learning techniques, with clinical data and biomarkers to stage and grade patients with NAFLD.Approach and Results: Learning data were collected in the Liver Investigation: Testing Marker Utility in Steatohepatitis metacohort (966 biopsy-proven NAFLD adults), staged and graded according to NASH CRN. Conditions of interest were the clinical trial definition of NASH (NAS >= 4;53%), at-risk NASH (NASH with F >= 2;35%), significant (F >= 2;47%), and advanced fibrosis (F >= 3;28%). Thirty-five predictors were included. Missing data were handled by multiple imputations. Data were randomly split into training/validation (75/25) sets. A gradient boosting machine was applied to develop 2 models for each condition: clinical versus extended (clinical and biomarkers). Two variants of the NASH and at-risk NASH models were constructed: direct and composite models.Clinical gradient boosting machine models for steatosis/inflammation/ballooning had AUCs of 0.94/0.79/0.72. There were no improvements when biomarkers were included. The direct NASH model produced AUCs (clinical/extended) of 0.61/0.65. The composite NASH model performed significantly better (0.71) for both variants. The composite at-risk NASH model had an AUC of 0.83 (clinical and extended), an improvement over the direct model. Significant fibrosis models had AUCs (clinical/extended) of 0.76/0.78. The extended advanced fibrosis model (0.86) performed significantly better than the clinical version (0.82).Conclusions: Detection of NASH and at-risk NASH can be improved by constructing independent machine learning models for each component, using only clinical predictors. Adding biomarkers only improved the accuracy of fibrosis. ; Peer reviewed |
| نوع الوثيقة: |
article in journal/newspaper |
| وصف الملف: |
application/pdf |
| اللغة: |
English |
| Relation: |
Jenny Lee, Quentin M. Anstee, and Pierre Bedossa conceptualized and designed the study; Jerome Boursier, Salvatore Petta, Kristy Wonders, Dina Tiniakos, Pierre Bedossa, Andreas Geier, Sven Francque, Mike Allison, Georgios Papatheodoridis, Helena Cortez-Pinto, Diana Julie Leeming, Stephen Harrison, Jeremy Cobbold, Michael Pavlides, Adriaan G. Holleboom, Hannele Yki-Jarvinen, Javier Crespo, Morten Karsdal, Rachel Ostroff, Carla Yunis, Clifford Brass, Mattias Ekstedt, Guruprasad P Aithal, Jorn M. Schattenberg, Elisabetta Bugianesi, Manuel Romero-Gomez, Richard Torstenson, Vlad Ratziu, Quentin M. Anstee assisted in data collection; Jenny Lee, Yasaman Vali, Pierre Bedossa, Kristy Wonders, and Quentin M. Anstee accessed and verified the raw data; Jenny Lee performed data analyses and drafted the manuscript; Patrick M Bossuyt supervised the data analyses and Max Westphal, Koos Zwinderman, Jerome Boursier, Yu Chen, Rachel Ostroff, Quentin M. Anstee, and Vlad Ratziu commented on the data analyses; all authors had full access to all the data in the study and had final responsibility for the decision to submit for publication and critically revised the manuscript and approved of the final version.; http://hdl.handle.net/10138/569203; 85163490526; 001116331700007 |
| الاتاحة: |
http://hdl.handle.net/10138/569203 |
| Rights: |
cc_by_nc_nd ; info:eu-repo/semantics/openAccess ; openAccess |
| رقم الانضمام: |
edsbas.52E003E0 |
| قاعدة البيانات: |
BASE |