Developing a decision support system for early identification of child maltreatment

The third study, currently in progress and funded by the Schusterman Foundation (2023), focuses on the development and implementation of a clinical decision support system to improve the identification of child abuse. In line with existing knowledge in literature, the system will integrate both an active universal screening tool and a passive screening tool—an algorithm based on the predictive model that has been developed. The system will be implemented across all emergency medical services in Jerusalem that are participating in the research (Pediatric Emergency Departments at Shaare Zedek Medical Center, Hadassah Ein Kerem, Hadassah Mount Scopus, and TEREM urgent care clinics).

Figure 1 – Clinical Decision Support System
Developed as part of research grants from the Ministry of Health, the Ministry of Innovation, Science and Technology, the National Digital Agency, and the Schusterman Foundation.
(A) Clinical data from Hadassah Mount Scopus, Hadassah Ein Kerem, Shaare Zedek Medical Center, and TEREM urgent care clinics were merged into a centralized database on the TIMNA infrastructure. Welfare service data from Jerusalem were added to the clinical database to identify cases of child abuse. Part of the data is used to build the predictive model, while another part is used for validation of the model’s performance.
(B) The system will be implemented in emergency care sites and will issue alerts for suspected abuse when the model indicates a risk exceeding a predefined threshold.