Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.03489 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909525544534016 |
|---|---|
| author | Sharma, Gaurang Moradi, Elaheh Pajula, Juha Hilvo, Mika Tohka, Jussi |
| author_facet | Sharma, Gaurang Moradi, Elaheh Pajula, Juha Hilvo, Mika Tohka, Jussi |
| contents | Dementia is a progressive condition that impairs an individual's cognitive health and daily functioning, with mild cognitive impairment (MCI) often serving as its precursor. The prediction of MCI to dementia conversion has been well studied, but previous studies have almost always focused on traditional Machine Learning (ML) based methods that require sharing sensitive clinical information to train predictive models. This study proposes a privacy-enhancing solution using Federated Learning (FL) to train predictive models for MCI to dementia conversion without sharing sensitive data, leveraging socio demographic and cognitive measures. We simulated and compared two network architectures, Peer to Peer (P2P) and client-server, to enable collaborative learning. Our results demonstrated that FL had comparable predictive performance to centralized ML, and each clinical site showed similar performance without sharing local data. Moreover, the predictive performance of FL models was superior to site specific models trained without collaboration. This work highlights that FL can eliminate the need for data sharing without compromising model efficacy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_03489 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Federated Learning for Predicting Mild Cognitive Impairment to Dementia Conversion Sharma, Gaurang Moradi, Elaheh Pajula, Juha Hilvo, Mika Tohka, Jussi Machine Learning Dementia is a progressive condition that impairs an individual's cognitive health and daily functioning, with mild cognitive impairment (MCI) often serving as its precursor. The prediction of MCI to dementia conversion has been well studied, but previous studies have almost always focused on traditional Machine Learning (ML) based methods that require sharing sensitive clinical information to train predictive models. This study proposes a privacy-enhancing solution using Federated Learning (FL) to train predictive models for MCI to dementia conversion without sharing sensitive data, leveraging socio demographic and cognitive measures. We simulated and compared two network architectures, Peer to Peer (P2P) and client-server, to enable collaborative learning. Our results demonstrated that FL had comparable predictive performance to centralized ML, and each clinical site showed similar performance without sharing local data. Moreover, the predictive performance of FL models was superior to site specific models trained without collaboration. This work highlights that FL can eliminate the need for data sharing without compromising model efficacy. |
| title | Federated Learning for Predicting Mild Cognitive Impairment to Dementia Conversion |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2503.03489 |