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

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.

Evaluation of Fragment Reduction Feasibility When Treating Bony Mallet Finger Using Extension Block K-Wire Technique

PURPOSE: The purpose was to evaluate fragment reduction feasilibty when applying extension block Kirschner-wire technique for bony mallet finger. METHODS: We treated 48 displaced mallet finger fractures by a two extension block Kirschner-wire technique. Among these operation group, we found dorsal rotation of fragment in 18 cases, making it difficult to get anatomical reduction. The patients were divided into two groups. One group of 30 patients did not show dorsal rotation of fragment and anatomical reduction was achieved easily. Another group of 18 patients showed dorsal rotation of fragment and additional methods was applied to achieve anatomical reduction. RESULTS: Joint surface involvement was significant greater in groups showing dorsal rotation of fragment than group which did not show (57.1% and 49.7%, respectively) (p=0.01). The groups whose joint surface involvement more than 50% had higher risk of dorsal rotation of fragment than the group less than 50%, with the odds ratio of 6.11. CONCLUSION: We could encounter the cases which showed dorsal rotation of the fracture fragment when treating the bony mallet finger with extension block K-wire technique especially the joint surface involvement was more than 50%. So if we can evaluate the extents of joint surface involvement and prepare additional method preoperatively when dorsal rotation of fragment is expected, it is possible to get more favorable results.