Modular Clinical Decision Support Networks (MoDN)-Updatable, interpretable, and portable predictions for evolving clinical environments.

Autor: Trottet C; Intelligent Global Health Research Group, Machine Learning and Optimization Laboratory, Swiss Federal Institute of Technology (EPFL), Lausanne, Switzerland., Vogels T; Intelligent Global Health Research Group, Machine Learning and Optimization Laboratory, Swiss Federal Institute of Technology (EPFL), Lausanne, Switzerland., Keitel K; Division of Pediatric Emergency Medicine, Department of Pediatrics, Inselspital, Bern University Hospital, University of Bern, Switzerland., Kulinkina AV; Digital Health Unit, Swiss Center for International Health, Swiss Tropical and Public Health Institute, Allschwil, Switzerland.; University of Basel, Basel, Switzerland., Tan R; Clinical Research Unit, Swiss Tropical and Public Health Institute, Allschwil, Switzerland.; Ifakara Health Institute, Ifakara, Tanzania.; Center for Primary Care and Public Health (Unisanté), Lausanne, Switzerland., Cobuccio L; Clinical Research Unit, Swiss Tropical and Public Health Institute, Allschwil, Switzerland., Jaggi M; Machine Learning and Optimization Laboratory, Swiss Federal Institute of Technology (EPFL), Lausanne, Switzerland., Hartley MA; Intelligent Global Health Research Group, Machine Learning and Optimization Laboratory, Swiss Federal Institute of Technology (EPFL), Lausanne, Switzerland.; Laboratory of Intelligent Global Health Technologies, Biomedical Informatics and Data Science, Yale School of Medicine, New Haven, CT, USA.
Jazyk: angličtina
Zdroj: PLOS digital health [PLOS Digit Health] 2023 Jul 17; Vol. 2 (7), pp. e0000108. Date of Electronic Publication: 2023 Jul 17 (Print Publication: 2023).
DOI: 10.1371/journal.pdig.0000108
Abstrakt: Clinical Decision Support Systems (CDSS) have the potential to improve and standardise care with probabilistic guidance. However, many CDSS deploy static, generic rule-based logic, resulting in inequitably distributed accuracy and inconsistent performance in evolving clinical environments. Data-driven models could resolve this issue by updating predictions according to the data collected. However, the size of data required necessitates collaborative learning from analogous CDSS's, which are often imperfectly interoperable (IIO) or unshareable. We propose Modular Clinical Decision Support Networks (MoDN) which allow flexible, privacy-preserving learning across IIO datasets, as well as being robust to the systematic missingness common to CDSS-derived data, while providing interpretable, continuous predictive feedback to the clinician. MoDN is a novel decision tree composed of feature-specific neural network modules that can be combined in any number or combination to make any number or combination of diagnostic predictions, updatable at each step of a consultation. The model is validated on a real-world CDSS-derived dataset, comprising 3,192 paediatric outpatients in Tanzania. MoDN significantly outperforms 'monolithic' baseline models (which take all features at once at the end of a consultation) with a mean macro F1 score across all diagnoses of 0.749 vs 0.651 for logistic regression and 0.620 for multilayer perceptron (p < 0.001). To test collaborative learning between IIO datasets, we create subsets with various percentages of feature overlap and port a MoDN model trained on one subset to another. Even with only 60% common features, fine-tuning a MoDN model on the new dataset or just making a composite model with MoDN modules matched the ideal scenario of sharing data in a perfectly interoperable setting. MoDN integrates into consultation logic by providing interpretable continuous feedback on the predictive potential of each question in a CDSS questionnaire. The modular design allows it to compartmentalise training updates to specific features and collaboratively learn between IIO datasets without sharing any data.
Competing Interests: The authors have declared that no competing interests exist.
(Copyright: © 2023 Trottet et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)
Databáze: MEDLINE