AI AND ALTERNATIVE SYMPTOMS IN THE DIAGNOSIS OF MDD: The role of forgiveness, hopelessness, mixity and diminished...

Area of Science:

• Psychiatry
• Medical Informatics
• Artificial Intelligence

Background:

• The integration of artificial intelligence (AI) into clinical practice is rapidly transforming medical assessment.
• Understanding the nuances of patient-reported symptoms is crucial for accurate diagnosis of mental health conditions.

Purpose of the Study:

• To explore the utility of AI in analyzing semi-structured interviews for diagnosing Major Mood Disorders (MMD).
• To identify patient-reported symptoms beyond DSM-5-TR criteria that predict MMD.
• To investigate the relationship between MMD symptoms and factors like forgiveness, hopelessness, and drive.

Main Methods:

• Conducted semi-structured interviews with 43 patients diagnosed with MMD according to DSM-5-TR criteria.
• Utilized trained AI programs to analyze recorded and transcribed interviews.
• Evaluated the predictive value of symptoms not listed in DSM-5-TR and their correlation with psychological factors.

Main Results:

• AI analysis identified somatization, physical oppression, ambivalent/blocked anhedonia, distress, agitated restlessness, mixed states, and subthreshold oscillations as significant predictive factors.
• These AI-identified symptoms showed a positive predictive weight for MMD.
• The study explored correlations with forgiveness, hopelessness, and diminished drive.

Conclusions:

• AI demonstrates potential in enhancing the diagnostic accuracy of Major Mood Disorders by analyzing qualitative patient data.
• Patient-reported symptoms beyond current diagnostic frameworks can offer valuable predictive insights.
• Further research into AI-driven analysis of patient narratives can refine diagnostic criteria and treatment strategies.