Predicting unplanned medical visits among patients with diabetes: translation from machine learning to clinical implementation.

Background: Diabetes is a medical and economic burden in the United States. In this study, a machine learning predictive model was developed to predict unplanned medical visits among patients with diabetes, and findings were used to design a clinical intervention in the sponsoring healthcare organization. This study presents a case study of how predictive analytics can inform clinical actions, and describes practical factors that must be incorporated in order to translate research into clinical practice.

Smoking is associated with a higher risk of unplanned medical visits among adult patients with diabetes, using retrospective electronic medical record data from 2014 to 2016.

Background: Smoking exacerbates the complications of diabetes, but little is known about whether patients with diabetes who smoke have more unplanned medical visits than those who do not smoke. This study examines the association between smoking status and unplanned medical visits among patients with diabetes.

Methods: Data were drawn from electronic medical records (EMR's) from a large healthcare provider in the Northern Plains region of the US, from adult (≥18 years old) patients with type 1 or type 2 diabetes who received care at least once during 2014-16 (N = 62,149).