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

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.

[1]  Joseph Finkelstein,et al.  Machine learning approaches to personalize early prediction of asthma exacerbations , 2017, Annals of the New York Academy of Sciences.

[2]  Joseph Finkelstein,et al.  Patient Subjective Assessment of Drug Side Effects in Inflammatory Bowel Disease , 2008, Journal of clinical gastroenterology.

[3]  J A Lovitky.  The National Practitioner Data Bank: coping with the uncertainties. , 2000, Journal of health law.

[4]  Joseph Finkelstein,et al.  Feasibility of a Palmtop-Based Interactive Education to Promote Patient Safety , 2003, AMIA.

[5]  Jeffrey Wood,et al.  Introducing a Comprehensive Informatics Framework to Promote Breast Cancer Risk Assessment and Chemoprevention in the Primary Care Setting , 2017, AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science.

[6]  Joseph Finkelstein,et al.  Use of provider-level dashboards and pay-for-performance in venous thromboembolism prophylaxis. , 2015, Journal of hospital medicine.

[7]  M. Roizen,et al.  Paid Malpractice Claims for Adverse Events in Inpatient and Outpatient Settings , 2012 .

[8]  Joseph Finkelstein,et al.  Analysis of Maryland Poisoning Deaths Using Classification And Regression Tree (CART) Analysis , 2008, AMIA.

[9]  McKenzie Bedra,et al.  Computerized Insulin Order Sets Can Lead to Unanticipated Consequences , 2015, ICIMTH.

[10]  L. Kohn,et al.  To Err Is Human : Building a Safer Health System , 2007 .

[11]  F. Mullan,et al.  The National Practitioner Data Bank. Report from the first year. , 1992, JAMA.