Predicting and improving patient-level antibiotic adherence.

Low adherence to prescribed medications causes substantial health and economic burden. We analyzed primary data from electronic medical records of 250,000 random patients from Israel's Maccabi Healthcare services from 2007 to 2017 to predict whether a patient will purchase a prescribed antibiotic. We developed a decision model to evaluate whether an intervention to improve purchasing adherence is warranted for the patient, considering the cost of the intervention and the cost of non-adherence. The best performing prediction model achieved an average area under the receiver operating characteristic curve (AUC) of 0.684, with 82% accuracy in detecting individuals who had less than 50% chance of purchasing a prescribed drug. Using the decision model, an adherence intervention targeted to patients whose predicted purchasing probability is below a specified threshold can increase the number of prescriptions filled while generating significant savings compared to no intervention - on the order of 6.4% savings and 4.0% more prescriptions filled for our dataset. We conclude that analysis of large-scale patient data from electronic medical records can help predict the probability that a patient will purchase a prescribed antibiotic and can provide real-time predictions to physicians, who can then counsel the patient about medication importance. More broadly, in-depth analysis of patient-level data can help shape the next generation of personalized interventions.

Personal and social patterns predict influenza vaccination decision.

BACKGROUND: Seasonal influenza vaccination coverage remains suboptimal in most developed countries, despite longstanding recommendations of public health organizations. The individual's decision regarding vaccination is located at the core of non-adherence. We analyzed large-scale data to identify personal and social behavioral patterns for influenza vaccination uptake, and develop a model to predict vaccination decision of individuals in an upcoming influenza season. METHODS: We analyzed primary data from the electronic medical records of a retrospective cohort of 250,000 individuals between the years 2007 and 2017, collected from 137 clinics. Individuals were randomly sampled from the database of Maccabi Healthcare Services. Maccabi's clients are representative of the Israeli population, reflect all demographic, ethnic, and socioeconomic groups and levels. We used several machine-learning models to predict whether a patient would get vaccinated in the future. Models' performance was evaluated based on the area under the ROC curve. RESULTS: The vaccination decision of an individual can be explained in two dimensions, Personal and social. The personal dimension is strongly shaped by a "default" behavior, such as vaccination timing in previous seasons and general health consumption, but can also be affected by temporal factors such as respiratory illness in the prior year. In the social dimension, a patient is more likely to become vaccinated in a given season if at least one member of his family also became vaccinated in the same season. Vaccination uptake was highly assertive with age, socioeconomic score, and geographic location. An XGBoost-based predictive model achieved an ROC-AUC score of 0.91 with accuracy and recall rates of 90% on the test set. Prediction relied mainly on the patient's individual and household vaccination status in the past, age, number of encounters with the healthcare system, number of prescribed medications, and indicators of chronic illnesses. CONCLUSIONS: Our ability to make an excellent prediction of the patient's decision sets a major step toward personalized influenza vaccination campaigns, and will help shape the next generation of targeted vaccination efforts.