Salvato in:
| Autori principali: | , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2022
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2210.09394 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909660073689088 |
|---|---|
| author | Yoo, Jaesung Choi, Sunghyuk Yang, Ye Seul Kim, Suhyeon Choi, Jieun Lim, Dongkyeong Lim, Yaeji Joo, Hyung Joon Kim, Dae Jung Park, Rae Woong Yoon, Hyeong-Jin Kim, Kwangsoo |
| author_facet | Yoo, Jaesung Choi, Sunghyuk Yang, Ye Seul Kim, Suhyeon Choi, Jieun Lim, Dongkyeong Lim, Yaeji Joo, Hyung Joon Kim, Dae Jung Park, Rae Woong Yoon, Hyeong-Jin Kim, Kwangsoo |
| contents | When a deep learning model is trained sequentially on different datasets, it often forgets the knowledge learned from previous data, a problem known as catastrophic forgetting. This damages the model's performance on diverse datasets, which is critical in privacy-preserving deep learning (PPDL) applications based on transfer learning (TL). To overcome this, we introduce "review learning" (RevL), a low cost continual learning algorithm for diagnosis prediction using electronic health records (EHR) within a PPDL framework. RevL generates data samples from the model which are used to review knowledge from previous datasets. Six simulated institutional experiments and one real-world experiment involving three medical institutions were conducted to validate RevL, using three binary classification EHR data. In the real-world experiment with data from 106,508 patients, the mean global area under the receiver operating curve was 0.710 for RevL and 0.655 for TL. These results demonstrate RevL's ability to retain previously learned knowledge and its effectiveness in real-world PPDL scenarios. Our work establishes a realistic pipeline for PPDL research based on model transfers across institutions and highlights the practicality of continual learning in real-world medical settings using private EHR data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2210_09394 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Review learning: Real world validation of privacy preserving continual learning across medical institutions Yoo, Jaesung Choi, Sunghyuk Yang, Ye Seul Kim, Suhyeon Choi, Jieun Lim, Dongkyeong Lim, Yaeji Joo, Hyung Joon Kim, Dae Jung Park, Rae Woong Yoon, Hyeong-Jin Kim, Kwangsoo Artificial Intelligence Machine Learning When a deep learning model is trained sequentially on different datasets, it often forgets the knowledge learned from previous data, a problem known as catastrophic forgetting. This damages the model's performance on diverse datasets, which is critical in privacy-preserving deep learning (PPDL) applications based on transfer learning (TL). To overcome this, we introduce "review learning" (RevL), a low cost continual learning algorithm for diagnosis prediction using electronic health records (EHR) within a PPDL framework. RevL generates data samples from the model which are used to review knowledge from previous datasets. Six simulated institutional experiments and one real-world experiment involving three medical institutions were conducted to validate RevL, using three binary classification EHR data. In the real-world experiment with data from 106,508 patients, the mean global area under the receiver operating curve was 0.710 for RevL and 0.655 for TL. These results demonstrate RevL's ability to retain previously learned knowledge and its effectiveness in real-world PPDL scenarios. Our work establishes a realistic pipeline for PPDL research based on model transfers across institutions and highlights the practicality of continual learning in real-world medical settings using private EHR data. |
| title | Review learning: Real world validation of privacy preserving continual learning across medical institutions |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2210.09394 |