Using big data analytics to identify dentists with frequent future malpractice claims

Healthcare spending has been growing at an increasing rate in the US, due in part to medical malpractice costs. Dental malpractice is an area that has not been studied in depth. Using National Practitioner Data Bank (NPDB), we explored the extent of dental malpractice claims and sought to construct a predictive model that can help us identify dental practitioners at risk of performing medical malpractice. Over 1,500 dental malpractice claims were reported annually, and over $1.7 billion being paid out by medical malpractice insurers over the past 15 years. Majority of claims resulted in minor injuries, and the number of major injury claims increased over years. In prediction, we randomly split the data into train (75%) and test (25%) datasets. We trained and tuned models using 5-fold cross validation on the training set. Then, we fitted the model on the test data for performance measures. We used Logistic Regression, Random Forest (RF) and XGBoost and tuned the hypermeters of models accordingly through grid search and cross validation. XGBoost was the best machine learning model to predict the risk of dentists having several malpractice reports. The best performing model had an accuracy of 72.8% with 30.6% F1 score. The NPDB database is a valuable dataset to study dental malpractice claims. Further analysis of information extracted from this dataset is warranted.