This paper studies the temporal consistency of health care expenditures in a large state Medicaid program. Predictive machine learning models were used to forecast the expenditures, especially for the high-cost, high-need (HCHN) patients. We systematically tests temporal correlation of patient-level health care expenditures in both the short and long terms. The results suggest that medical expenditures are significantly correlated over multiple periods. Our work demonstrates a prevalent and strong temporal correlation and shows promise for predicting future health care expenditures using machine learning. Temporal correlation is stronger in HCHN patients and their expenditures can be better predicted. Including more past periods is beneficial for better predictive performance. This study shows that there is significant temporal correlation in health care expenditures. Machine learning models can help to accurately forecast the expenditures. These results could advance the field toward precise preventive care to lower overall health care costs and deliver care more efficiently.

Objectives. To examine the association between Colorado’s legalization of recreational cannabis use and opioid-related deaths. Methods. We used an interrupted time-series design (2000–2015) to compare changes in level and slope of monthly opioid-related deaths before and after Colorado stores began selling recreational cannabis. We also describe the percent change in opioid-related deaths by comparing the unadjusted model-smoothed number of deaths at the end of follow-up with the number of deaths just prior to legalization. Results. Colorado’s legalization of recreational cannabis sales and use resulted in a 0.7 deaths per month (b = −0.68; 95% confidence interval = −1.34, −0.03) reduction in opioid-related deaths. This reduction represents a reversal of the upward trend in opioid-related deaths in Colorado. Conclusions. Legalization of cannabis in Colorado was associated with short-term reductions in opioid-related deaths. As additional data become available, research should replicate these analyses in other states with legal recreational cannabis.

Purpose of Review Effective responses to the US opioid overdose epidemic rely on accurate and timely drug overdose mortality data, which are generated from medicolegal death investigations (MDI) and certifications of overdose deaths. We identify nuances of MDI and certification of overdose deaths that can influence drug overdose mortality surveillance, as well as recent research, recommendations, and epidemiological tools for improved identification and quantification of specific drug involvement in overdose mortality. Recent Findings Death certificates are the foundation of drug overdose mortality surveillance. Accordingly, counts and rates of specific drug involvement in overdose deaths are only as accurate as the drug listed on death certificates. Variation in systematic approaches or jurisdictional office policy in drug overdose death certification can lead to bias in mortality rate calculations. Recent research has examined statistical adjustments to improve underreported opioid involvement in overdose deaths. New cause-of-death natural language text analysis tools improve quantification of specific opioid overdose mortality rates. Enhanced opioid overdose surveillance, which combines death certificate data with other MDI-generated data, has the potential to improve understanding of factors and circumstances of opioid overdose mortality. Summary The opioid overdose crisis has brought into focus some of the limitations of US MDI systems for drug overdose surveillance and has given rise to a sense of urgency regarding the pressing need for improvements in our MDI data for public health action and research. Epidemiologists can stimulate positive changes in MDI data quality by demonstrating the critical role of data in guiding public health and safety decisions and addressing the challenges of accurate and timely overdose mortality measures with stakeholders. Education, training, and resources specific to drug overdose surveillance and analysis will be essential as the nation’s overdose crisis continues to evolve.

Deaths involving fentanyl analogs, such as carfentanil, have increased the severity of the opioid overdose epidemic in Florida.