Federated Choquet Regression with LASSO for Outcome Prediction in Multisite Longitudinal Trial Data
ACM Transactions on Computing for Healthcare · 31.01.2026 · 7 (1) · 1-19
DOI: 10.1145/3761824 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Computing for Healthcare, online erschienen am 14.01.2026. Verfasst von Semyon Lomasov und 2 weiteren Autor:innen. Beteiligte Einrichtung: Stanford University, Stanford, California, USA and Yeshiva University, New York, New York, USA. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIDDK NIH HHS, National Institutes of Health, National Science Foundation.
Abstract (Originalsprache)
Aggregating person-level data across multiple clinical study sites is often constrained by privacy regulations, necessitating the development of decentralized modeling approaches in biomedical research. To address this requirement, a federated nonlinear regression algorithm based on the Choquet integral has been introduced for outcome prediction. This approach avoids reliance on prior statistical assumptions about data distribution and captures feature interactions, reflecting the non-additive nature of biomedical data characteristics. This work represents the first theoretical application of Choquet integral regression to multisite longitudinal trial data within a federated learning framework. The Multiple Imputation Choquet Integral Regression with LASSO (MIChoquet-LASSO) algorithm is specifically designed to reduce overfitting and enable variable selection in federated learning settings. Its performance has been evaluated using synthetic datasets, publicly available biomedical datasets, and proprietary longitudinal randomized controlled trial data. Comparative evaluations were conducted against benchmark methods, including OLS regression and Choquet OLS regression, under various scenarios such as model misspecification and both linear and nonlinear data structures in non-federated and federated contexts. MSE was used as the primary performance metric. Results indicate that MIChoquet-LASSO outperforms compared models in handling nonlinear longitudinal data with missing values, particularly in scenarios prone to overfitting. In federated settings, Choquet OLS underperforms, whereas the federated variant of the model, FEDMIChoquet-LASSO, demonstrates consistently better performance. These findings suggest that FEDMIChoquet-LASSO offers a reliable solution for outcome prediction in multisite longitudinal trials, addressing challenges such as missing values, nonlinear relationships, and privacy constraints while maintaining strong performance within the federated learning framework.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Stanford University, Stanford, California, USA and Yeshiva University, New York, New York, USA.
- University of Massachusetts Dartmouth, Dartmouth, Massachusetts, USA and University of Massachusetts Chan Medical School, Worcester, Massachusetts, USA.
- Graduate Computer Science and Engineering, Yeshiva University, New York, New York, USA.
ORCID-Profile: Semyon Lomasov, Hua Fang, Honggang Wang
Förderung
- NIDDK NIH HHS
- National Institutes of Health
- National Science Foundation
Zitieren
APA
Lomasov, S., Fang, H., & Wang, H. (2026). Federated Choquet Regression with LASSO for Outcome Prediction in Multisite Longitudinal Trial Data. ACM Transactions on Computing for Healthcare, 7(1), 1-19. https://doi.org/10.1145/3761824
Vancouver
Lomasov S, Fang H, Wang H. Federated Choquet Regression with LASSO for Outcome Prediction in Multisite Longitudinal Trial Data. ACM Transactions on Computing for Healthcare. 2026;7(1):1-19. doi:10.1145/3761824
BibTeX
@article{Lomasov2026,
author = {Lomasov, Semyon and Fang, Hua and Wang, Honggang},
title = {Federated Choquet Regression with LASSO for Outcome Prediction in Multisite Longitudinal Trial Data},
journal = {ACM Transactions on Computing for Healthcare},
year = {2026},
volume = {7},
number = {1},
pages = {1--19},
doi = {10.1145/3761824}
}
EUVIMED