Machine learning to identify chronic cough from administrative claims data.

Accurate identification of patient populations is an essential component of clinical research, especially for medical conditions such as chronic cough that are inconsistently defined and diagnosed. We aimed to develop and compare machine learning models to identify chronic cough from medical and pharmacy claims data. In this retrospective observational study, we compared 3 machine learning algorithms based on XG Boost, logistic regression, and neural network approaches using a large claims and electronic health record database. Of the 327,423 patients who met the study criteria, 4,818 had chronic cough based on linked claims-electronic health record data. The XG Boost model showed the best performance, achieving a Receiver-Operator Characteristic Area Under the Curve (ROC-AUC) of 0.916. We selected a cutoff that favors a high positive predictive value (PPV) to minimize false positives, resulting in a sensitivity, specificity, PPV, and negative predictive value of 18.0%, 99.6%, 38.7%, and 98.8%, respectively on the held-out testing set (n = 82,262). Logistic regression and neural network models achieved slightly lower ROC-AUCs of 0.907 and 0.838, respectively. The XG Boost and logistic regression models maintained their robust performance in subgroups of individuals with higher rates of chronic cough. Machine learning algorithms are one way of identifying conditions that are not coded in medical records, and can help identify individuals with chronic cough from claims data with a high degree of classification value.

A machine learning-based algorithm to identify U-500R insulin candidates among adults with type 2 diabetes mellitus in US retrospective databases.

OBJECTIVE: To develop a machine learning-based predictive algorithm to identify patients with type 2 diabetes mellitus (T2DM) who are candidates for initiation of U-500R insulin (U-500R). METHODS: A retrospective cohort of patients with T2DM was used from a large US administrative claims and electronic health records (EHR) database affiliated with Optum. Predictor variables derived from the data were used to identify appropriate supervised machine learning models including least absolute shrinkage and selection operator (LASSO) and extreme gradient boosted (XGBoost) methods. Predictive performance was assessed using precision-recall (PR) and receiver operating characteristic (ROC) area under the curve (AUC). The clinical interpretation of the final model was supported by fitting the final set of variables from the LASSO and XGBoost models to a traditional logistic regression model. Model choice was determined by comparing Akaike Information Criterion (AIC), residual deviances, and scaled Brier scores. RESULTS: Among 81,242 patients who met the study eligibility criteria, 577 initiated U-500R and were assigned to the positive class. Predictors of U-500R initiation included overweight/obesity, neuropathy, HbA1c ≥9% and 8%-9%, BUN 23.8 to <112 mg/dl, ALT 35.9-2056.2 U/L, no radiological chest exams, no GFR labs, and gait/mobility abnormalities. The best performing model was the LASSO model with an ROC AUC of 0.776 on the hold-out test set. CONCLUSION: This study successfully developed and validated a machine learning-based algorithm to identify U-500R candidates among patients with T2DM. This may help health care providers and decision-makers to understand important characteristics of patients who could use U-500R therapies which in turn could support policies and guidelines for optimal patient management.

Predicting Response to Bolus Insulin Therapy in Patients With Type 2 Diabetes.

BACKGROUND: The aim of this study was to develop a predictive model to classify people with type 2 diabetes (T2D) into expected levels of success upon bolus insulin initiation. METHODS: Machine learning methods were applied to a large nationally representative insurance claims database from the United States (dNHI database; data from 2007 to 2017). We trained boosted decision tree ensembles (XGBoost) to assign people into Class 0 (never meeting HbA1c goal), Class 1 (meeting but not maintaining HbA1c goal), or Class 2 (meeting and maintaining HbA1c goal) based on the demographic and clinical data available prior to initiating bolus insulin. The primary objective of the study was to develop a model capable of determining at an individual level, whether people with T2D are likely to achieve and maintain HbA1c goals. HbA1c goal was defined at <8.0% or reduction of baseline HbA1c by >1.0%. RESULTS: Of 15 331 people with T2D (mean age, 53.0 years; SD, 8.7), 7800 (50.9%) people met HbA1c goal but failed to maintain that goal (Class 1), 4510 (29.4%) never attained this goal (Class 0), and 3021 (19.7%) people met and maintained this goal (Class 2). Overall, the model's receiver operating characteristic (ROC) was 0.79 with greater performance on predicting those in Class 2 (ROC = 0.92) than those in Classes 0 and 1 (ROC = 0.71 and 0.62, respectively). The model achieved high area under the precision-recall curves for the individual classes (Class 0, 0.46; Class 1, 0.58; Class 2, 0.71). CONCLUSIONS: Predictive modeling using routine health care data reasonably accurately classified patients initiating bolus insulin who would achieve and maintain HbA1c goals, but less so for differentiation between patients who never met and who did not maintain goals. Prior HbA1c was a major contributing parameter for the predictions.