OBJECTIVE: To develop and test predictive models of discontinuation of behavioral health service use within 12 months in transitional age youth with recent behavioral health service use. DATA SOURCES: Administrative claims for Medicaid beneficiaries aged 15-26 years in Connecticut. STUDY DESIGN: We compared the performance of a decision tree, random forest, and gradient boosting machine learning algorithms to logistic regression in predicting service discontinuation within 12 months among beneficiaries using behavioral health services. DATA EXTRACTION: We identified 33,532 transitional age youth with ≥1 claim for a primary behavioral health diagnosis in 2016 and Medicaid enrollment of ≥11 months in 2016 and ≥11 months in 2017. PRINCIPAL FINDINGS: Classification accuracy for identifying youth who discontinued behavioral health service use was highest for gradient boosting (80%, AUC = 0.86), decision tree (79%, AUC = 0.84), and random forest (79%, AUC = 0.86), as compared with logistic regression (71%, AUC = 0.71). CONCLUSIONS: Predictive models based on Medicaid claims can assist in identifying transitional age youth who are at risk of discontinuing from behavioral health care within 12 months, thus allowing for proactive assessment and outreach to promote continuity of care for younger persons who have behavioral health needs.
OBJECTIVE: To develop and test predictive models of discontinuation of behavioral health service use within 12 months in transitional age youth with recent behavioral health service use. DATA SOURCES: Administrative claims for Medicaid beneficiaries aged 15-26 years in Connecticut. STUDY DESIGN: We compared the performance of a decision tree, random forest, and gradient boosting machine learning algorithms to logistic regression in predicting service discontinuation within 12 months among beneficiaries using behavioral health services. DATA EXTRACTION: We identified 33,532 transitional age youth with ≥1 claim for a primary behavioral health diagnosis in 2016 and Medicaid enrollment of ≥11 months in 2016 and ≥11 months in 2017. PRINCIPAL FINDINGS: Classification accuracy for identifying youth who discontinued behavioral health service use was highest for gradient boosting (80%, AUC = 0.86), decision tree (79%, AUC = 0.84), and random forest (79%, AUC = 0.86), as compared with logistic regression (71%, AUC = 0.71). CONCLUSIONS: Predictive models based on Medicaid claims can assist in identifying transitional age youth who are at risk of discontinuing from behavioral health care within 12 months, thus allowing for proactive assessment and outreach to promote continuity of care for younger persons who have behavioral health needs.
Authors: M Cappelli; S Davidson; J Racek; S Leon; M Vloet; K Tataryn; K Gillis; A Freeland; J Carver; S Thatte; J Lowe Journal: J Behav Health Serv Res Date: 2016-10 Impact factor: 1.505
Authors: Hadi Kharrazi; Winnie Chi; Hsien-Yen Chang; Thomas M Richards; Jason M Gallagher; Susan M Knudson; Jonathan P Weiner Journal: Med Care Date: 2017-08 Impact factor: 2.983
Authors: Kathleen J Pottick; Scott Bilder; Ann Vander Stoep; Lynn A Warner; Mike F Alvarez Journal: J Behav Health Serv Res Date: 2007-11-17 Impact factor: 1.505
Authors: Laura Acion; Diana Kelmansky; Mark van der Laan; Ethan Sahker; DeShauna Jones; Stephan Arndt Journal: PLoS One Date: 2017-04-10 Impact factor: 3.240