In 2016, 11.8 million American individuals reported using prescription opioids nonmedically,¹ and an estimated 115 individuals died each day from opioid overdose.^2-4 The annual cost of misuse or abuse of opioids exceeds $78.5 billion, including the costs of health care, lost productivity, substance abuse treatment, and the criminal justice system.⁵

Melanoma, one of the serious forms of skin cancer, is the fifth most common cancer in the United States.¹ In 2018, more than 91 000 individuals were newly diagnosed with melanoma.² Most early-stage melanomas (stages I and II) are curable, with a 5-year survival rate of 98.4%.¹ However, advanced melanoma (stages III and IV) with dacarbazine chemotherapy had a low 3-year survival rate of 12.2%.³ In recent years, immunotherapy with novel immune checkpoint inhibitors (ICIs) has revolutionized treatment approaches for advanced melanoma. Ipilimumab, the first ICI for treatment of advanced melanoma, was introduced to the US market in 2011. Since then, 2 additional ICIs (pembrolizumab and nivolumab) have been approved by the US Food and Drug Administration as a first-line treatment for advanced melanoma.

Background: Quality improvement efforts are frequently tied to patients achieving ≥80% medication adherence. However, there is little empirical evidence that this threshold optimally predicts important health outcomes. Objective: To apply machine learning to examine how adherence to oral hypoglycemic medications is associated with avoidance of hospitalizations, and to identify adherence thresholds for optimal discrimination of hospitalization risk. Methods: A retrospective cohort study of 33,130 non–dual-eligible Medicaid enrollees with type 2 diabetes. We randomly selected 90% of the cohort (training sample) to develop the prediction algorithm and used the remaining (testing sample) for validation. We applied random survival forests to identify predictors for hospitalization and fit survival trees to empirically derive adherence thresholds that best discriminate hospitalization risk, using the proportion of days covered (PDC). Outcomes: Time to first all-cause and diabetes-related hospitalization. Results: The training and testing samples had similar characteristics (mean age, 48 y; 67% female; mean PDC=0.65). We identified 8 important predictors of all-cause hospitalizations (rank in order): prior hospitalizations/emergency department visit, number of prescriptions, diabetes complications, insulin use, PDC, number of prescribers, Elixhauser index, and eligibility category. The adherence thresholds most discriminating for risk of all-cause hospitalization varied from 46% to 94% according to patient health and medication complexity. PDC was not predictive of hospitalizations in the healthiest or most complex patient subgroups. Conclusions: Adherence thresholds most discriminating of hospitalization risk were not uniformly 80%. Machine-learning approaches may be valuable to identify appropriate patient-specific adherence thresholds for measuring quality of care and targeting nonadherent patients for intervention.