Diagnosis based specialist identification in the hospital

Abstract

Medical specialties provide essential information about which providers have the skills needed to carry out key procedures or make critical judgments. They are useful for training and staffing and provide confidence to patients that their providers have the experience needed to address their problems.

This work evaluates how machine learning classifiers can be trained on treatment histories to recognize medical specialties. Such classifiers can be used to evaluate staffing and workflows and have applications to safety and security. We focus on treatment histories that consist of the patient diagnoses. We find that some specialties, such as a urologist, can be learned with good precision and recall, while other specialties, such as anesthesiology, are less easily recognized. We call the former diagnosis specialties and explore four machine learning techniques for them, which we compare to a naive baseline based on the diagnoses most commonly treated by specialists in a training set. We find that these techniques can improve substantially on the baseline and that the best technique, which uses Latent Dirichlet Allocation (LDA), provides precision and recall above 80% for many diagnosis specialties based on a study with one year of chart accesses and discharge diagnoses from a major hospital. Furthermore, we explored several data mining techniques to discover valid but unlisted diagnosis specialties. We present the diagnosis specialty discoveries and their associated attributes that corroborate the discoveries.