Healthc Inform Res.  2023 Apr;29(2):168-173. 10.4258/hir.2023.29.2.168.

Feasibility Study of Federated Learning on the Distributed Research Network of OMOP Common Data Model

• Lee GH
• Park J
• Kim J
• Kim Y
• Choi B
• Park RW
• Rhee SY
• Shin SY

• KMID: 2542143
• DOI: http://doi.org/10.4258/hir.2023.29.2.168

Abstract

Objectives
Since protecting patients’ privacy is a major concern in clinical research, there has been a growing need for privacy-preserving data analysis platforms. For this purpose, a federated learning (FL) method based on the Observational Medical Outcomes Partnership (OMOP) common data model (CDM) was implemented, and its feasibility was demonstrated.
Methods
We implemented an FL platform on FeederNet, which is a distributed clinical data analysis platform based on the OMOP CDM in Korea. We trained it through an artificial neural network (ANN) using data from patients who received steroid prescriptions or injections, with the aim of predicting the occurrence of side effects depending on the prescribed dose. The ANN was trained using the FL platform with the OMOP CDMs of Kyung Hee University Medical Center (KHMC) and Ajou University Hospital (AUH).
Results
The area under the receiver operating characteristic curves (AUROCs) for predicting bone fracture, osteonecrosis, and osteoporosis using only data from each hospital were 0.8426, 0.6920, and 0.7727 for KHMC and 0.7891, 0.7049, and 0.7544 for AUH, respectively. In contrast, when using FL, the corresponding AUROCs were 0.8260, 0.7001, and 0.7928 for KHMC and 0.7912, 0.8076, and 0.7441 for AUH, respectively. In particular, FL led to a 14% improvement in performance for osteonecrosis at AUH.
Conclusions
FL can be performed with the OMOP CDM, and FL often shows better performance than using only a single institution's data. Therefore, research using OMOP CDM has been expanded from statistical analysis to machine learning so that researchers can conduct more diverse research.

Keyword

Machine Learning, Deep Learning, Distributed Systems, Privacy, Common Data Element

Figure

• 

  Figure 1 Federated learning sequence diagram.

Reference

References

1. McMahan B, Moore E, Ramage D, Hampson S, y Arcas BA. Communication-efficient learning of deep networks from decentralized data. Proc Mach Learn Res. 2017; 54:1273–82.

2. Bonawitz K, Eichner H, Grieskamp W, Huba D, Ingerman A, Ivanov V, et al. Towards federated learning at scale: System design. In : Proceedings of Machine Learning and Systems (MLSys); 2019 Mar 31–Apr 2; Stanford, CA. p. 374–88.

3. Konecny J, McMahan HB, Yu FX, Richtrik P, Suresh AT, Bacon D. Federated learning: strategies for improving communication efficiency [Internet]. Ithaca (NY): arXiv.org;2016. [cited at 2023 Mar 20]. Available from: https://doi.org/10.48550/arXiv.1610.05492.

4. Xu J, Glicksberg BS, Su C, Walker P, Bian J, Wang F. Federated learning for healthcare informatics. J Healthc Inform Res. 2021; 5(1):1–19. https://doi.org/10.1007/s41666-020-00082-4.

5. Rieke N, Hancox J, Li W, Milletari F, Roth HR, Albarqouni S, et al. The future of digital health with federated learning. NPJ Digit Med. 2020; 3:119. https://doi.org/10.1038/s41746-020-00323-1.

6. Lee GH, Shin SY. Federated learning on clinical benchmark data: performance assessment. J Med Internet Res. 2020; 22(10):e20891. https://doi.org/10.2196/20891.

7. Vaid A, Jaladanki SK, Xu J, Teng S, Kumar A, Lee S, et al. Federated learning of electronic health records to improve mortality prediction in hospitalized patients with COVID-19: machine learning approach. JMIR Med Inform. 2021; 9(1):e24207. https://doi.org/10.2196/24207.

8. Li W, Milletari F, Xu D, Rieke N, Hancox J, Zhu W, et al. Privacy-preserving federated brain tumour segmentation. Suk HI, Liu M, Yan P, Lian C, editors. Machine learning in medical imaging. Cham, Switzerland: Springer;2019. 133–41. https://doi.org/10.1007/978-3-030-32692-0_16.

9. Sheller MJ, Edwards B, Reina GA, Martin J, Pati S, Kotrotsou A, et al. Federated learning in medicine: facilitating multi-institutional collaborations without sharing patient data. Sci Rep. 2020; 10(1):12598. https://doi.org/10.1038/s41598-020-69250-1.

10. Brown JS, Holmes JH, Shah K, Hall K, Lazarus R, Platt R. Distributed health data networks: a practical and preferred approach to multi-institutional evaluations of comparative effectiveness, safety, and quality of care. Med Care. 2010; 48(6 Suppl):S45–51. https://doi.org/10.1097/MLR.0b013e3181d9919f.

11. Hansen RA, Zeng P, Ryan P, Gao J, Sonawane K, Teeter B, et al. Exploration of heterogeneity in distributed research network drug safety analyses. Res Synth Methods. 2014; 5(4):352–70. https://doi.org/10.1002/jrsm.1121.

12. Toh S, Gagne JJ, Rassen JA, Fireman BH, Kulldorff M, Brown JS. Confounding adjustment in comparative effectiveness research conducted within distributed research networks. Med Care. 2013; 51(8 Suppl 3):S4–10. https://doi.org/10.1097/MLR.0b013e31829b1bb1.

13. Observational Health Data Sciences and Informatics (OHDSI) [Internet]. [place unknown]: OHDSI;2022. [cited at 2023 Mar 20]. Available from: https://www.ohdsi.org/.

14. FeederNet: a distributed clinical data analysis platform in Korea [Internet]. Seongnam, Korea: Evidnet;c2022. [cited at 2023 Mar 20]. Available from: https://feedernet.com/member/main.

15. Kim Y, Tian Y, Yang J, Huser V, Jin P, Lambert CG, et al. Comparative safety and effectiveness of alendronate versus raloxifene in women with osteoporosis. Sci Rep. 2020; 10(1):11115. https://doi.org/10.1038/s41598-020-68037-8.

16. Suchard MA, Schuemie MJ, Krumholz HM, You SC, Chen R, Pratt N, et al. Comprehensive comparative effectiveness and safety of first-line antihypertensive drug classes: a systematic, multinational, large-scale analysis. Lancet. 2019; 394(10211):1816–26. https://doi.org/10.1016/S0140-6736(19)32317-7.