Implementation of the decision tree method in expert analysis of the medical errors in obstetric practice

Abstract

Aim: To identify expert patterns in cases of improper medical care in obstetric practice based on the analysis of the materials of judicial and investigative cases initiated against obstetrician-gynaecologists in cases of improper performance of their professional duties, using the decision tree method. Materials and methods: A retrospective review of all alleged medical malpractice cases (a total 350) between 2007 and 2016 handled at Ternopil Regional Bu¬reau of Forensic Medical Examination, Chernivtsi Regional Bureau of Forensic Medical Examination and Zhytomir Regional Bureau of Forensic Medical Examination (Ukraine) was performed. Results: Expert commissions confirmed various shortcomings and omissions in provision of medical care in 232 (72.0%) of the investigated cases. Obstetricians were involved in claims in 82 (23.4%) cases. Application of intelligent data processing technology “Data Mining” with the use of the decision tree method revealed that inadequacies with regard to the medical records (attribute usage 100%) were the most informative attribute in the expert assessment of inappropriate medical care in obstetrics. Defects in the provision of obstetric care with a probability (P = 0.71) occur simultaneously both at pre-hospital and hospital levels and with a high probability (P = 0.83) result in severe consequences. Conclusions: The use of modern technologies for data analysis and processing contributes to the formulation of mathematically substantiated statements that significantly enhance the reliability of expert opinions in cases of forensic medical examination attached to dereliction of duties by the medical practitioners.