Using Physiomarkers Obtained from Electronic Health Records, Wearable Devices, and Personal Portable Devices to Develop and Update Machine Learning and Transfer Learning Models to Predict Patient-Centered Outcomes

Chen, Kuan-Fu (PI)
Lin, Chen (CoPI)
Lo, Men Tzung (CoPI)

Department of Artificial Intelligence

Project: National Science and Technology Council › National Science and Technology Council Academic Grants

Abstract

我們預計在這個敗血症世代研究中，使用不同的生物及生理標記，加上不需與病人接觸的遠端光體積變化描記圖法，配合機器學習、聯邦及遷移式學習，發展出可使用在不同規模醫療院所、各年齡層與各種感染部位病人的臨床預測模型，來預測病患為中心的預後：如治療反應、死亡及敗血性休克的發生，進一步減少敗血症引起的併發症，並且為有限醫療資源的妥適應用做指引。

Project IDs

Project ID:PC11107-5268
External Project ID:MOST111-2314-B182-017-MY3

Status	Finished
Effective start/end date	01/08/22 → 31/07/23

Keywords

sepsis
biomarker
clinical prediction rule
emergency department
unsupervised learning
cohort study
machine learning
deep learning
therapy responsiveness
heart rate variability

Access Project

https://www.grb.gov.tw/search/planDetail?id=14508806

Using Physiomarkers Obtained from Electronic Health Records, Wearable Devices, and Personal Portable Devices to Develop and Update Machine Learning and Transfer Learning Models to Predict Patient-Centered Outcomes

Project Details

Abstract

Project IDs

Keywords

Access Project

Fingerprint