Data mining approaches to identify predictors of frequent malpractice claims against dentists

Abstract

We separated all malpractice records for US dentists into two groups according to the total number of malpractice records (0: less than 5 records, 1: more than 4 records), extracted the first malpractice record of all dental practitioners' and used malpractice allegation group, payment and years between graduation and year of the first record in logistic regression to identify crucial factors for predicting dentists who made more than four malpractice records. Bivariate statistics, cross-correlation and principal component analysis were used to identify predictive features. Resulting model allowed prediction of dentists with frequent malpractice records based on the following characteristics of the first malpractice record: allegation type, payment amount and number of years from graduation to the first malpractice claim. Time between provider graduation year and the first malpractice record as well higher malpractice payment for the first claim were negatively correlated with the total number of malpractice records in individual providers.