Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2501.13587 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929687639359488 |
|---|---|
| author | Liu, Yuxuan Han, Jinpei Ramnarayan, Padmanabhan Faisal, A. Aldo |
| author_facet | Liu, Yuxuan Han, Jinpei Ramnarayan, Padmanabhan Faisal, A. Aldo |
| contents | Clinical machine learning deployment across institutions faces significant challenges when patient populations and clinical practices differ substantially. We present a systematic framework for cross-institutional knowledge transfer in clinical time series, demonstrated through pediatric ventilation management between a general pediatric intensive care unit (PICU) and a cardiac-focused unit. Using contrastive predictive coding (CPC) for representation learning, we investigate how different data regimes and fine-tuning strategies affect knowledge transfer across institutional boundaries. Our results show that while direct model transfer performs poorly, CPC with appropriate fine-tuning enables effective knowledge sharing between institutions, with benefits particularly evident in limited data scenarios. Analysis of transfer patterns reveals an important asymmetry: temporal progression patterns transfer more readily than point-of-care decisions, suggesting practical pathways for cross-institutional deployment. Through a systematic evaluation of fine-tuning approaches and transfer patterns, our work provides insights for developing more generalizable clinical decision support systems while enabling smaller specialized units to leverage knowledge from larger centers. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_13587 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Contrastive Representation Learning Helps Cross-institutional Knowledge Transfer: A Study in Pediatric Ventilation Management Liu, Yuxuan Han, Jinpei Ramnarayan, Padmanabhan Faisal, A. Aldo Machine Learning Artificial Intelligence Clinical machine learning deployment across institutions faces significant challenges when patient populations and clinical practices differ substantially. We present a systematic framework for cross-institutional knowledge transfer in clinical time series, demonstrated through pediatric ventilation management between a general pediatric intensive care unit (PICU) and a cardiac-focused unit. Using contrastive predictive coding (CPC) for representation learning, we investigate how different data regimes and fine-tuning strategies affect knowledge transfer across institutional boundaries. Our results show that while direct model transfer performs poorly, CPC with appropriate fine-tuning enables effective knowledge sharing between institutions, with benefits particularly evident in limited data scenarios. Analysis of transfer patterns reveals an important asymmetry: temporal progression patterns transfer more readily than point-of-care decisions, suggesting practical pathways for cross-institutional deployment. Through a systematic evaluation of fine-tuning approaches and transfer patterns, our work provides insights for developing more generalizable clinical decision support systems while enabling smaller specialized units to leverage knowledge from larger centers. |
| title | Contrastive Representation Learning Helps Cross-institutional Knowledge Transfer: A Study in Pediatric Ventilation Management |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2501.13587 |