Federated target trial emulation using distributed observational data for treatment effect estimation
Abstract Target trial emulation (TTE) aims to estimate treatment effects by simulating randomized controlled trials using real-world observational data. Applying TTE across distributed datasets shows great promise in improving generalizability and power but is always infeasible due to privacy and da...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | npj Digital Medicine |
| Online Access: | https://doi.org/10.1038/s41746-025-01803-y |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849238371252043776 |
|---|---|
| author | Haoyang Li Chengxi Zang Zhenxing Xu Weishen Pan Suraj Rajendran Yong Chen Fei Wang |
| author_facet | Haoyang Li Chengxi Zang Zhenxing Xu Weishen Pan Suraj Rajendran Yong Chen Fei Wang |
| author_sort | Haoyang Li |
| collection | DOAJ |
| description | Abstract Target trial emulation (TTE) aims to estimate treatment effects by simulating randomized controlled trials using real-world observational data. Applying TTE across distributed datasets shows great promise in improving generalizability and power but is always infeasible due to privacy and data-sharing constraints. Here we propose a Federated Learning-based TTE framework, FL-TTE, that enables TTE across multiple sites without sharing patient-level data. FL-TTE incorporates federated protocol design, federated inverse probability of treatment weighting, and a federated Cox proportional hazards model to estimate time-to-event outcomes across heterogeneous data. We validated FL-TTE by emulating Sepsis trials using eICU and MIMIC-IV data from 192 hospitals, and Alzheimer’s trials using INSIGHT Network across five New York City health systems. FL-TTE produced less biased estimates than traditional meta-analysis methods when compared to pooled results and is theoretically supported. Our FL-TTE enables federated treatment effect estimation across distributed and heterogeneous data in a privacy-preserved way. |
| format | Article |
| id | doaj-art-7e5bfdc8f7c54992914937b1fbe047b9 |
| institution | Kabale University |
| issn | 2398-6352 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Digital Medicine |
| spelling | doaj-art-7e5bfdc8f7c54992914937b1fbe047b92025-08-20T04:01:36ZengNature Portfolionpj Digital Medicine2398-63522025-07-018111510.1038/s41746-025-01803-yFederated target trial emulation using distributed observational data for treatment effect estimationHaoyang Li0Chengxi Zang1Zhenxing Xu2Weishen Pan3Suraj Rajendran4Yong Chen5Fei Wang6Department of Population Health Sciences, Weill Cornell MedicineDepartment of Population Health Sciences, Weill Cornell MedicineDepartment of Population Health Sciences, Weill Cornell MedicineDepartment of Population Health Sciences, Weill Cornell MedicineTri-Institutional Computational Biology & Medicine Program, Weill Cornell MedicineDepartment of Biostatistics, Epidemiology, and Informatics, University of Pennsylvania Perelman School of MedicineDepartment of Population Health Sciences, Weill Cornell MedicineAbstract Target trial emulation (TTE) aims to estimate treatment effects by simulating randomized controlled trials using real-world observational data. Applying TTE across distributed datasets shows great promise in improving generalizability and power but is always infeasible due to privacy and data-sharing constraints. Here we propose a Federated Learning-based TTE framework, FL-TTE, that enables TTE across multiple sites without sharing patient-level data. FL-TTE incorporates federated protocol design, federated inverse probability of treatment weighting, and a federated Cox proportional hazards model to estimate time-to-event outcomes across heterogeneous data. We validated FL-TTE by emulating Sepsis trials using eICU and MIMIC-IV data from 192 hospitals, and Alzheimer’s trials using INSIGHT Network across five New York City health systems. FL-TTE produced less biased estimates than traditional meta-analysis methods when compared to pooled results and is theoretically supported. Our FL-TTE enables federated treatment effect estimation across distributed and heterogeneous data in a privacy-preserved way.https://doi.org/10.1038/s41746-025-01803-y |
| spellingShingle | Haoyang Li Chengxi Zang Zhenxing Xu Weishen Pan Suraj Rajendran Yong Chen Fei Wang Federated target trial emulation using distributed observational data for treatment effect estimation npj Digital Medicine |
| title | Federated target trial emulation using distributed observational data for treatment effect estimation |
| title_full | Federated target trial emulation using distributed observational data for treatment effect estimation |
| title_fullStr | Federated target trial emulation using distributed observational data for treatment effect estimation |
| title_full_unstemmed | Federated target trial emulation using distributed observational data for treatment effect estimation |
| title_short | Federated target trial emulation using distributed observational data for treatment effect estimation |
| title_sort | federated target trial emulation using distributed observational data for treatment effect estimation |
| url | https://doi.org/10.1038/s41746-025-01803-y |
| work_keys_str_mv | AT haoyangli federatedtargettrialemulationusingdistributedobservationaldatafortreatmenteffectestimation AT chengxizang federatedtargettrialemulationusingdistributedobservationaldatafortreatmenteffectestimation AT zhenxingxu federatedtargettrialemulationusingdistributedobservationaldatafortreatmenteffectestimation AT weishenpan federatedtargettrialemulationusingdistributedobservationaldatafortreatmenteffectestimation AT surajrajendran federatedtargettrialemulationusingdistributedobservationaldatafortreatmenteffectestimation AT yongchen federatedtargettrialemulationusingdistributedobservationaldatafortreatmenteffectestimation AT feiwang federatedtargettrialemulationusingdistributedobservationaldatafortreatmenteffectestimation |