Search Articles

View query in Help articles search

Search Results (1 to 2 of 2 Results)

Download search results: CSV END BibTex RIS


Improving the Prediction of Persistent High Health Care Utilizers: Retrospective Analysis Using Ensemble Methodology

Improving the Prediction of Persistent High Health Care Utilizers: Retrospective Analysis Using Ensemble Methodology

Minimum samples to split sets the minimum number of samples at the time of a split, ensuring that each leaf has at least n–1 samples. Minimum samples at leaf is very similar to minimum samples to split but controls samples at the leaf level. In this study, minimum samples at leaf was used to ensure edge cases (ie, unique PHU patterns) were still appropriately populated with training samples.

Stephanie N Howson, Michael J McShea, Raghav Ramachandran, Howard S Burkom, Hsien-Yen Chang, Jonathan P Weiner, Hadi Kharrazi

JMIR Med Inform 2022;10(3):e33212

Assessing the Value of Unsupervised Clustering in Predicting Persistent High Health Care Utilizers: Retrospective Analysis of Insurance Claims Data

Assessing the Value of Unsupervised Clustering in Predicting Persistent High Health Care Utilizers: Retrospective Analysis of Insurance Claims Data

These subpopulations were identified as: (1) otitis media (n=24,992 patients), (2) mental health (n=34,456), (3) musculoskeletal signs and symptoms (n=24,799), and (4) acute upper respiratory infection (URI; n=53,232). Selection process of the study population. JHHC: Johns Hopkins Health Care; EDC: expanded diagnostic cluster. The full study population and each subpopulation contained several predictor variables and the outcome variable.

Raghav Ramachandran, Michael J McShea, Stephanie N Howson, Howard S Burkom, Hsien-Yen Chang, Jonathan P Weiner, Hadi Kharrazi

JMIR Med Inform 2021;9(11):e31442