[EVALUATION OF SCREENING FOR PTSD USING CONSORT AI RECOMMENDATIONS WITH A LARGE LANGUAGE MODEL].

Similar to major natural disasters and large-scale wars, the events of October 7th and the retaliatory Iron Swords war resulted in both direct and indirect exposure of a significant proportion of the population to traumatic events. A major challenge for healthcare systems in such scenarios is the early identification of populations that develop Post Traumatic Stress Disorder (PTSD). The medical literature was reviewed to assess whether language models could be integrated into a screening program for at-risk populations and which tools can be used to evaluate the quality of studies describing screening instruments based on language models. The concept of prompting a large language model to adopt a peer-reviewer persona was also explored to study whether it could be used to assess study quality.