Predicting opioid use disorder before and after the opioid prescribing peak in the United States: A machine learning tool using electronic healthcare records.

Existing predictive models of opioid use disorder (OUD) may change as the rate of opioid prescribing decreases. Using Veterans Administration's EHR data, we developed machine-learning predictive models of new OUD diagnoses and ranked the importance of patient features based on their ability to predict a new OUD diagnosis in 2000-2012 and 2013-2021. Using patient characteristics, the three separate machine learning techniques were comparable in predicting OUD, achieving an accuracy of >80%.

An Efficient Pipeline for Biophysical Modeling of Neurons.

Automation of the process of developing biophysical conductance-based neuronal models involves the selection of numerous interacting parameters, making the overall process computationally intensive, complex, and often intractable. A recently reported insight about the possible grouping of currents into distinct biophysical modules associated with specific neurocomputational properties also simplifies the process of automated selection of parameters. The present paper adds a new current module to the previous report to design spike frequency adaptation and bursting characteristics, based on user specifications.