Abstract Background To accurately detect individuals’ mental health issues using artificial intelligence and self-report scales, it is crucial to recognize how personal characteristics can affect the detection. This study focuses on the role of alexithymia—a condition where individuals struggle to recognize and articulate emotions and symptoms—in the detection of depression. We aimed to determine whether deep learning models could enhance the accuracy of depression detection in people with alexithymia compared to self-report scales. Methods We analyzed data from 194 patients with major depressive disorder and 105 community controls, employing eight large language models (LLMs) trained on transcript text from clinician-administered structured interviews using the Hamilton Depression Rating Scale (HAMD). Results Here we show that generalized logistic regression analysis indicates a positive relationship between alexithymia and depression. Using the HAMD as the gold standard, individuals with alexithymia show poorer performance on the self-reported Hospital Anxiety and Depression Scale–Depression Subscale (HADS-D) in identifying depression (b = −0.37, p = .002). Four of the eight LLMs (AUCs=0.87-0.89) significantly outperform the HADS-D (AUC = 0.79) in depression detection (p <0.05). Subgroup analysis demonstrates that while LLMs achieve AUCs ranging from 0.79 to 0.96, the HADS-D only reaches an AUC of 0.35 for individuals with alexithymia. Conclusions Our findings reveal that LLMs can potentially outperform self-report scales in detecting depression, particularly in those with alexithymia. These results highlight the importance of considering patient characteristics, such as alexithymia, when detecting depression. Deep learning analyses can enhance the accuracy of clinical assessments for depression and potentially for other mental health disorders.
Building similarity graph...
Analyzing shared references across papers
Loading...
Calvin Lam
Longdi Xian
Rong Huang
Communications Medicine
University of Hong Kong
Chinese University of Hong Kong
Fujian Medical University
Building similarity graph...
Analyzing shared references across papers
Loading...
Lam et al. (Fri,) studied this question.
www.synapsesocial.com/papers/696c79cde45ebfc9113cd53a — DOI: https://doi.org/10.1038/s43856-026-01393-0