Npj mental health research最新文献

Substance use disorder (SUD) poses a major concern due to its detrimental effects on health and society. SUD identification and treatment depend on a variety of factors such as severity, co-determinants (e.g., withdrawal symptoms), and social determinants of health. Existing diagnostic coding systems used by insurance providers, like the International Classification of Diseases (ICD-10), lack granularity for certain diagnoses, but American clinicians will add this granularity (as that found within the Diagnostic and Statistical Manual of Mental Disorders classification or DSM-5) as supplemental unstructured text in clinical notes. Traditional natural language processing (NLP) methods face limitations in accurately parsing such diverse clinical language. Large language models (LLMs) offer promise in overcoming these challenges by adapting to diverse language patterns. This study investigates the application of LLMs for extracting severity-related information for various SUD diagnoses from clinical notes. We propose a workflow employing zero-shot learning of LLMs with carefully crafted prompts and post-processing techniques. Through experimentation with Flan-T5, an open-source LLM, we demonstrate its superior recall compared to the rule-based approach. Focusing on 11 categories of SUD diagnoses, we show the effectiveness of LLMs in extracting severity information, contributing to improved risk assessment and treatment planning for SUD patients.

Psychedelic therapy has the potential to become a revolutionary and transdiagnostic mental health treatment, yielding enduring benefits that are often attributed to the experiences that coincide with peak psychedelic effects. However, there may be an underrecognized temporal structure to this process that helps explain why psychedelic and related altered states of consciousness can have an initially distressing but ultimately distress-resolving effect. Here we present a qualitative analysis of the self-reported 'come-up' or onset phase, and 'come-down' or falling phase, of the psychedelic experience. Focusing on psilocybin or psilocybin-containing mushroom experience reports submitted to Erowid.org, we use phenomenological, thematic content and word frequency analysis to show that the come-up is more often characterized by negatively valenced feeling states that resemble an acute stress reaction, while the come-down phase is more often characterized by positively valenced feeling states of the sort often observed following recovery from illness or resolution of stress. The therapeutic and theoretical relevance of these findings are discussed.

Treatments for major depressive disorder (MDD) include antidepressant medications and evidence-based psychotherapies, which are approximately equally efficacious. Individual response to treatment, however, is variable, implying individual differences that could allow for prospective differential prediction of treatment response and personalized treatment recommendation. We used machine learning to develop predictor variables that combined demographic and clinical items from a randomized clinical trial. The variables predicted a meaningful proportion of variance in end-of-treatment depression severity for cognitive behavioral therapy (39.7%), escitalopram (32.1%), and duloxetine (67.7%), leading to a high accuracy in predicting remission (71%). Further, we used these variables to simulate treatment recommendation and found that patients who received their recommended treatment had significantly improved depression severity and remission likelihood. Finally, the prediction algorithms and treatment recommendation tool were externally validated in an independent sample. These results represent a highly promising, easily implemented, potential advance for personalized medicine in MDD treatment.

This meta-analysis investigated resting frontal alpha asymmetry (FAA) as a potential biomarker for major depressive disorder (MDD). Studies included articles utilizing FAA measure involving EEG electrodes (F3/F4, F7/F8, or Fp1/Fp2) and covering both MDD and controls. Hedges' d was calculated from FAA means and standard deviations (SDs). A systematic search of PubMed through July 2023 identified 23 studies involving 1928 MDD participants and 2604 controls. The analysis revealed a small but significant grand mean effect size (ES) for FAA (F4 - F3), suggesting limited diagnostic value of FAA in MDD. Despite the presence of high heterogeneity across studies, subgroup analyses did not identify significant differences based on calculation formula, reference montage, age, or depression severity. The findings indicate that FAA may have limited standalone diagnostic utility but could complement existing clinical assessments for MDD, highlighting the need for a multifaceted approach to depression diagnosis and prognosis.

Attention-deficit/hyperactivity disorder (ADHD) presents with symptoms like impulsiveness, inattention, and hyperactivity, often affecting children's academic and social functioning. Non-pharmacological interventions, such as digital cognitive therapy, are emerging as complementary treatments for ADHD. The randomized controlled trial explored the impact of an AI-driven digital cognitive program on impulsiveness, inattentiveness, and neurophysiological markers in 41 children aged 8-12 with ADHD. Participants received either 12 weeks of AI-driven therapy or a placebo intervention. Assessments were conducted pre- and post-intervention and magnetoencephalography (MEG) analyzed brain activity. Results showed significant reductions in impulsiveness and inattentiveness scores in the treatment group, associated with normalized MEG spectral profiles, indicating neuromaturation. Notably, improvements in inhibitory control correlated with spectral profile normalization in the parieto-temporal cortex. Improvements in inhibitory control, linked to normalized spectral profiles, suggest AI-driven digital cognitive therapy can reduce impulsiveness in ADHD children by enhancing neurophysiological efficiency. This emphasizes personalized, technology-driven ADHD treatment, using neurophysiological markers for assessing efficacy.