Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Publication
Articles 1 - 2 of 2
Full-Text Articles in Physical Sciences and Mathematics
Machine Learning Methods For Computational Phenotyping Using Patient Healthcare Data With Noisy Labels, Praveen Kumar
Machine Learning Methods For Computational Phenotyping Using Patient Healthcare Data With Noisy Labels, Praveen Kumar
Computer Science ETDs
Positive and Unlabeled (PU) learning problems abound in many real-world applications. In healthcare informatics, diagnosed patients are considered labeled positive for a specific disease, but being undiagnosed does not mean they can be labeled negative. PU learning can improve classification performance, and estimate the positive fraction, α, among unlabeled samples. However, algorithms based on the Selected Completely At Random (SCAR) assumption are inadequate when the SCAR assumption fails (e.g., severe cases overrepresented), and when class imbalance is substantial. This dissertation presents and evaluates new algorithms to overcome these limitations. The proposed methods outperform the state-of-art for α-estimation, enhance classification performance, …
Applying Data Science And Machine Learning To Understand Health Care Transition For Adolescents And Emerging Adults With Special Health Care Needs, Lisamarie Turk
Nursing ETDs
A problem of classification places adolescents and emerging adults with special health care needs among the most at risk for poor or life-threatening health outcomes. This preliminary proof-of-concept study was conducted to determine if phenotypes of health care transition (HCT) for this vulnerable population could be established. Such phenotypes could support development of future studies that require data classifications as input. Mining of electronic health record data and cluster analysis were implemented to identify phenotypes. Subsequently, a machine learning concept model was developed for predicting acute care and medical condition severity. Three clusters were identified and described (Cluster 1, n …