Assessing the Value of Unsupervised Clustering in Predicting Persistent High Health Care Utilizers: Retrospective Analysis of Insurance Claims Data.
Raghav RamachandranMichael J McSheaStephanie N HowsonHoward S BurkomHsien-Yen ChangJonathan P WeinerHadi KharraziPublished in: JMIR medical informatics (2021)
Our study illustrates the value of LCA in identifying subgroups of patients with similar patterns of diagnoses and medications. Our results show that LCA-derived classes can simplify predictive models of PHUs without compromising predictive accuracy. Future studies should investigate the value of LCA-derived classes for predicting PHUs in other health care settings.