Analysis of Factors Related to Domestic Patient Safety Incidents Using Decision Tree Technique.

Abstract

To address the increasing number of patient safety incidents, their scope and extent should be assessed and the situations in which they occur determined. This study employed a decision tree analysis based on patient safety incident cases to identify groups at high risk for adverse patient safety incidents and provide data to develop prevention strategies for minimizing their occurrence or recurrence. In total, 8934 patient safety incidents were analyzed using the "2021 Patient Safety Report Data", which were systematically collected by the Korea Institute for Healthcare Accreditation. A decision tree analysis (Chi-square Automatic Interaction Detection) was employed to identify the characteristics associated with the degree of risk for patient safety incidents. The groups most vulnerable to adverse events were those who experienced healthcare-associated infections (HAI) in long-term care facilities, followed by those experiencing HAI in tertiary hospitals, general hospitals, or clinics, and those experiencing fall-related events in neuropsychiatry departments of tertiary hospitals, general hospitals, or clinics. The most important factor in the degree of harm in patient safety accidents was the type of accident, followed by the type of medical institution, and then the treatment department. Particularly, HAI and falls are the most important factors determining the degree of harm in patient safety accidents.