Hasil untuk "Psychiatry"

B. Jacobs, H. Praag, F. Gage

D. Weissman, D. Rosielle

General paralysis in married women, arising after syphilitic infection from the husband, is a rare occurrence, but sufficiently numerous cases have at pi'esent been investigated to afford support to the theory that conjugal syphilis (contracted by one from the other partner in married life) is a most potent cause of general paralysis. The subject was first dealt with by Ludwig Acker (1887) and Mendel (1888), both of whom reported cases of general paralysis caused in wives by syphilis contracted from their husbands. Various observers have since then placed similar cases on record, as at present, according to Cullere 1 (1904) no fewer than 40 undoubted cases are known to medical literature. In a recent publication,2 Drs. S. Gamier and A. Santenoise of the Dijon Asylum, give an interesting account of a case of " conjugal general paralysis." The patient was an old woman with a neuropathic family history, her mother having been affected with insane delusions, while a first cousin,

A. Hasan, P. Falkai, T. Wobrock et al.

Max Lamparth, Declan Grabb, Amy Franks et al.

Current medical language model (LM) benchmarks often over-simplify the complexities of day-to-day clinical practice tasks and instead rely on evaluating LMs on multiple-choice board exam questions. In psychiatry especially, these challenges are worsened by fairness and bias issues, since models can be swayed by patient demographics even when those factors should not influence clinical decisions. Thus, we present an expert-created and annotated dataset spanning five critical domains of decision-making in mental healthcare: treatment, diagnosis, documentation, monitoring, and triage. This U.S.-centric dataset - created without any LM assistance - is designed to capture the nuanced clinical reasoning and daily ambiguities mental health practitioners encounter, reflecting the inherent complexities of care delivery that are missing from existing datasets. Almost all base questions with five answer options each have had the decision-irrelevant demographic patient information removed and replaced with variables, e.g., for age or ethnicity, and are available for male, female, or non-binary-coded patients. This design enables systematic evaluations of model performance and bias by studying how demographic factors affect decision-making. For question categories dealing with ambiguity and multiple valid answer options, we create a preference dataset with uncertainties from the expert annotations. We outline a series of intended use cases and demonstrate the usability of our dataset by evaluating sixteen off-the-shelf and six (mental) health fine-tuned LMs on category-specific task accuracy, on the fairness impact of patient demographic information on decision-making, and how consistently free-form responses deviate from human-annotated samples.

Sachin R. Pendse, Darren Gergle, Rachel Kornfield et al.

Throughout history, a prevailing paradigm in mental healthcare has been one in which distressed people may receive treatment with little understanding around how their experience is perceived by their care provider, and in turn, the decisions made by their provider around how treatment will progress. Paralleling this offline model of care, people who seek mental health support from artificial intelligence (AI)-based chatbots are similarly provided little context for how their expressions of distress are processed by the model, and subsequently, any reasoning or theoretical grounding that may underlie model responses. People in severe distress who turn to AI chatbots for support thus find themselves caught between black boxes, contending with unique forms of agony that arise from these intersecting opacities. In this paper, we argue that the distinct psychological state of individuals experiencing severe mental distress uniquely necessitates a higher standard of end-user interpretability in comparison to general AI chatbot use. We propose a reflective interpretability approach to AI-mediated mental health support, which nudges users to engage in an agency-preserving and iterative process of reflection and interpretation of model outputs, towards creating meaning from interactions (rather than accepting outputs as directive instructions). Drawing on interpretability practices from four mental health fields (psychotherapy, crisis intervention, psychiatry, and care authorization), we describe concrete design approaches for reflective interpretability in AI-mediated mental health support, including role induction, prosocial advance directives, intervention titration, and well-defined mechanisms for recourse, alongside a discussion of potential risks and mitigation measures.

Prakrithi Shivaprakash, Diptadhi Mukherjee, Lekhansh Shukla et al.

Background: Large Language Models show promise in psychiatry but are English-centric. Their ability to understand mood states in other languages is unclear, as different languages have their own idioms of distress. Aim: To quantify the ability of language models to faithfully represent phrases (idioms of distress) of four distinct mood states (depression, euthymia, euphoric mania, dysphoric mania) expressed in Indian languages. Methods: We collected 247 unique phrases for the four mood states across 11 Indic languages. We tested seven experimental conditions, comparing k-means clustering performance on: (a) direct embeddings of native and Romanised scripts (using multilingual and Indic-specific models) and (b) embeddings of phrases translated to English and Chinese. Performance was measured using a composite score based on Adjusted Rand Index, Normalised Mutual Information, Homogeneity and Completeness. Results: Direct embedding of Indic languages failed to cluster mood states (Composite Score = 0.002). All translation-based approaches showed significant improvement. High performance was achieved using Gemini-translated English (Composite=0.60) and human-translated English (Composite=0.61) embedded with gemini-001. Surprisingly, human-translated English, further translated into Chinese and embedded with a Chinese model, performed best (Composite = 0.67). Specialised Indic models (IndicBERT and Sarvam-M) performed poorly. Conclusion: Current models cannot meaningfully represent mood states directly from Indic languages, posing a fundamental barrier to their psychiatric application for diagnostic or therapeutic purposes in India. While high-quality translation bridges this gap, reliance on proprietary models or complex translation pipelines is unsustainable. Models must first be built to understand diverse local languages to be effective in global mental health.

Juan Miguel Lopez Alcaraz, Ebenezer Oloyede, David Taylor et al.

Background: Electrocardiogram (ECG) analysis has emerged as a promising tool for detecting physiological changes linked to non-cardiac disorders. Given the close connection between cardiovascular and neurocognitive health, ECG abnormalities may be present in individuals with co-occurring neurocognitive conditions. This highlights the potential of ECG as a biomarker to improve detection, therapy monitoring, and risk stratification in patients with neurocognitive disorders, an area that remains underexplored. Methods: We aim to demonstrate the feasibility to predict neurocognitive disorders from ECG features across diverse patient populations. We utilized ECG features and demographic data to predict neurocognitive disorders defined by ICD-10 codes, focusing on dementia, delirium, and Parkinson's disease. Internal and external validations were performed using the MIMIC-IV and ECG-View datasets. Predictive performance was assessed using AUROC scores, and Shapley values were used to interpret feature contributions. Results: Significant predictive performance was observed for disorders within the neurcognitive disorders. Significantly, the disorders with the highest predictive performance is F03: Dementia, with an internal AUROC of 0.848 (95% CI: 0.848-0.848) and an external AUROC of 0.865 (0.864-0.965), followed by G30: Alzheimer's, with an internal AUROC of 0.809 (95% CI: 0.808-0.810) and an external AUROC of 0.863 (95% CI: 0.863-0.864). Feature importance analysis revealed both known and novel ECG correlates. ECGs hold promise as non-invasive, explainable biomarkers for selected neurocognitive disorders. This study demonstrates robust performance across cohorts and lays the groundwork for future clinical applications, including early detection and personalized monitoring.

Rodrigo M. Carrillo-Larco, Jesus Lovón Melgarejo, Manuel Castillo-Cara et al.

BACKGROUND: Medical large language models (LLMs) have demonstrated remarkable performance in answering medical examinations. However, the extent to which this high performance is transferable to medical questions in Spanish and from a Latin American country remains unexplored. This knowledge is crucial as LLM-based medical applications gain traction in Latin America. AIMS: To build a dataset of questions medical examinations taken by Peruvian physicians pursuing specialty training; to fine-tune a LLM on this dataset; to evaluate and compare the performance in terms of accuracy between vanilla LLMs and the fine-tuned LLM. METHODS: We curated PeruMedQA, a multiple-choice question-answering (MCQA) dataset containing 8,380 questions spanning 12 specialties (2018-2025). We selected ten medical LLMs, including medgemma-4b-it and medgemma-27b-text-it, and developed zero-shot task specific prompts to answer the questions. We employed parameter-efficient fine tuning (PEFT) and low-rand adaptation (LoRA) to fine-tune medgemma-4b-it utilizing all questions except those from 2025 (test set). RESULTS: Medgemma-27b showed the highest accuracy across all specialities, achieving the highest score of 89.29% in Psychiatry; yet, in two specialties, OctoMed-7B exhibited slight superiority: Neurosurgery with 77.27% and 77.38, respectively; and Radiology with 76.13% and 77.39%, respectively. Across specialties, most LLMs with <10 billion parameters exhibited <50% of correct answers. The fine-tuned version of medgemma-4b-it emerged victorious against all LLMs with <10 billion parameters and rivaled a LLM with 70 billion parameters across various examinations. CONCLUSIONS: For medical AI applications and research that require knowledge bases from Spanish-speaking countries and those exhibiting similar epidemiological profile to Peru's, interested parties should utilize medgemma-27b-text-it.

Kleanthis Avramidis, Woojae Jeong, Aditya Kommineni et al.

Identifying physiological and behavioral markers for mental health conditions is a longstanding challenge in psychiatry. Depression and suicidal ideation, in particular, lack objective biomarkers, with screening and diagnosis primarily relying on self-reports and clinical interviews. Here, we investigate eye tracking as a potential marker modality for screening purposes. Eye movements are directly modulated by neuronal networks and have been associated with attentional and mood-related patterns; however, their predictive value for depression and suicidality remains unclear. We recorded eye-tracking sequences from 126 young adults as they read and responded to affective sentences, and subsequently developed a deep learning framework to predict their clinical status. The proposed model included separate branches for trials of positive and negative sentiment, and used 2D time-series representations to account for both intra-trial and inter-trial variations. We were able to identify depression and suicidal ideation with an area under the receiver operating curve (AUC) of 0.793 (95% CI: 0.765-0.819) against healthy controls, and suicidality specifically with 0.826 AUC (95% CI: 0.797-0.852). The model also exhibited moderate, yet significant, accuracy in differentiating depressed from suicidal participants, with 0.609 AUC (95% CI 0.571-0.646). Discriminative patterns emerge more strongly when assessing the data relative to response generation than relative to the onset time of the final word of the sentences. The most pronounced effects were observed for negative-sentiment sentences, that are congruent to depressed and suicidal participants. Our findings highlight eye tracking as an objective tool for mental health assessment and underscore the modulatory impact of emotional stimuli on cognitive processes affecting oculomotor control.

Mohsen Soltanifar, Chel Hee Lee

The concept of concurrent mental health and substance use (MHSU) and its detection in patients has garnered growing interest among psychiatrists and healthcare policymakers over the past four decades. Researchers have proposed various diagnostic methods, including the Data-Driven Diagnostic Method (DDDM), for the identification of MHSU. However, the absence of a standalone statistical software package to facilitate DDDM for large healthcare administrative databases has remained a significant gap. This paper introduces the R statistical software package CMHSU, available on the Comprehensive R Archive Network (CRAN), for the diagnosis of mental health (MH), substance use (SU), and their concurrent status (MHSU). The package implements DDDM using hospital and medical service physician visit counts along with maximum time span parameters for MH, SU, and MHSU diagnoses. A working example using a simulated real-world dataset is presented to examine various analytical aspects, including three key dimensions of MHSU detection based on the DDDM framework, as well as temporal analysis to demonstrate the package's application for healthcare policymakers. Additionally, the limitations of the CMHSU package and potential directions for its future extension are discussed.

Diego D. Díaz-Guerra, Marena de la C. Hernández-Lugo, Yunier Broche-Pérez et al.

IntroductionEvaluating neurocognitive functions and diagnosing psychiatric disorders in older adults is challenging due to the complexity of symptoms and individual differences. An innovative approach that combines the accuracy of artificial intelligence (AI) with the depth of neuropsychological assessments is needed.ObjectivesThis paper presents a novel protocol for AI-assisted neurocognitive assessment aimed at addressing the cognitive, emotional, and functional dimensions of older adults with psychiatric disorders. It also explores potential compensatory mechanisms.MethodologyThe proposed protocol incorporates a comprehensive, personalized approach to neurocognitive evaluation. It integrates a series of standardized and validated psychometric tests with individualized interpretation tailored to the patient’s specific conditions. The protocol utilizes AI to enhance diagnostic accuracy by analyzing data from these tests and supplementing observations made by researchers.Anticipated resultsThe AI-assisted protocol offers several advantages, including a thorough and customized evaluation of neurocognitive functions. It employs machine learning algorithms to analyze test results, generating an individualized neurocognitive profile that highlights patterns and trends useful for clinical decision-making. The integration of AI allows for a deeper understanding of the patient’s cognitive and emotional state, as well as potential compensatory strategies.ConclusionsBy integrating AI with neuro-psychological evaluation, this protocol aims to significantly improve the quality of neurocognitive assessments. It provides a more precise and individualized analysis, which has the potential to enhance clinical decision-making and overall patient care for older adults with psychiatric disorders.

Jiaqi Yao, Jiaqi Yao, Xinjian Lu et al.

BackgroundCompared to single-shell diffusion tensor imaging (DTI), free water (FW) and neurite orientation dispersion and density imaging (NODDI) offer a more comprehensive evaluation of microstructural alterations in cerebral white matter (WM), particularly in detecting crossing fibers. However, research utilizing multi-shell diffusion imaging to investigate thyroid-associated ophthalmopathy (TAO) remains limited. This study employs FW and NODDI to investigate microstructural changes in the white matter of the visual pathways in patients with TAO.MethodsMulti-shell diffusion magnetic resonance imaging (dMRI) scans were performed on 45 patients with TAO and 31 age- and sex-matched healthy controls (HC). Tract-based spatial statistics (TBSS) analysis was conducted using eight FW and NODDI-derived metrics to identify group differences in white matter microstructure. Furthermore, correlations between these microstructural changes and clinical measures were examined.ResultsTBSS analysis revealed that, compared to HC, patients with TAO exhibited lower free-water corrected fractional anisotropy (fwFA) and free-water corrected axial diffusivity (fwAD), while free-water corrected mean diffusivity (fwMD), free-water corrected radial diffusivity (fwRD), and orientation dispersion index (ODI) were significantly increased (p &lt; 0.05, FWE). Notably, ODI demonstrated the highest area under the curve (AUC) among these metrics. Furthermore, fwFA, fwAD, fwMD, fwRD, and ODI showed significant correlations with the Hamilton Anxiety Rating Scale (HAMA), Hamilton Depression Rating Scale (HAMD), and the Graves’ Orbitopathy Quality of Life Questionnaire (GO-QOL2) scores.ConclusionThis study suggests that abnormalities in the white matter microstructure of TAO patients can be detected through the complementary use of FW and NODDI metrics, and it is revealed that these changes may have an impact on mental health.

A. Hasan, P. Falkai, T. Wobrock et al.

Kiran Nijabat

Aims This study focuses on the North Central London Child and Adolescent Mental Health Services (NCL CAMHS) Co-production workstream, initiated to establish co-production as a foundational method for service planning and delivery in the NCL region. To understand what the CAMHS experts by experience members found useful and did not find useful in co-production projects within Barnet Enfield and Haringey Mental Health NHS Trust and NCL wide co-production. Methods Semi-structured interviews conducted with experts by experience within the Barnet Enfield and Haringey (BEH) NHS Trust aimed to explore their co-production experiences, identifying facilitators and barriers. The study employed an inductive thematic analysis, grounded in a constructionist epistemological position, to analyse qualitative responses from semi-structured interviews. Braun and Clarke's (2006) methodology guided the analysis, consisting of six phases. The researchers emphasized reflexivity, reflection, and maintaining coherence, consistency, and flexibility throughout the recursive process. The voices of the lived experience co-production members played a central role in the research, influencing the entire report. Two members of the NCL CAMHS lived experience group served as “Lived Experience Researchers” and received training on coding reliability based on Braun and Clarke's (2006) guidance. Results Thematic analysis revealed several key findings. Recognition of co-production values within the group highlighted the importance of giving voice to service users, valuing their individual experiences, and promoting power-sharing. Facilitators included good team working, valuing diversity, accessible online sessions, and promoting equality through interactions. Conversely, barriers included inconsistent meeting timings, power imbalances, and a consultation-style dominance. Participants expressed the need for more involved projects and recommended a transformation of BEH's co-production strategy. Conclusion Recommendations for BEH include a comprehensive evaluation of their co-production projects on the ladder of participation, emphasizing the importance of higher-level collaborations. Training for staff on co-production principles is crucial for fostering a mindset shift, and the establishment of a dedicated co-production team, including a co-production lead, is advised by service-users who co-produce. These roles can drive co-production projects, provide organizational structure, and facilitate stakeholder engagement.

E. Berne

Sai Krishna Tikka, Sangha Mitra Godi, M Aleem Siddiqui et al.

Repetitive transcranial magnetic stimulation (rTMS) is potentially effective as an augmentation strategy in the treatment of many neuropsychiatric conditions. Several Indian studies have been conducted in this regard. We aimed to quantitatively synthesize evidence from Indian studies assessing efficacy and safety of rTMS across broad range of neuropsychiatric conditions. Fifty two studies- both randomized controlled and non-controlled studies were included for a series of random-effects meta-analyses. Pre-post intervention effects of rTMS efficacy were estimated in “active only” rTMS treatment arms/groups and “active vs sham” (sham-controlled) studies using pooled Standardized Mean Differences (SMDs). The outcomes were ‘any depression’, depression in unipolar/bipolar depressive disorder, depression in obsessive compulsive disorder (OCD), depression in schizophrenia, schizophrenia symptoms (positive, negative, total psychopathology, auditory hallucinations and cognitive deficits), obsessive compulsive symptoms of OCD, mania, craving/compulsion in substance use disorders (SUDs) and migraine (headache severity and frequency). Frequencies and odds ratios (OR) for adverse events were calculated. Methodological quality of included studies, publication bias and sensitivity assessment for each meta-analyses was conducted. Meta-analyses of “active only” studies suggested a significant effect of rTMS for all outcomes, with moderate to large effect sizes, at both end of treatment as well as at follow-up. However, except for migraine (headache severity and frequency) with large effect sizes at end of treatment only and craving in alcohol dependence where moderate effect size at follow-up only, rTMS was not found to be effective for any outcome in the series of “active vs sham” meta-analyses. Significant heterogeneity was seen. Serious adverse events were rare. Publication bias was common and the sham controlled positive results lost significance in sensitivity analysis. We conclude that rTMS is safe and shows positive results in ‘only active’ treatment groups for all the studied neuropsychiatric conditions. However, the sham-controlled evidence for efficacy is negative from India. Conclusion rTMS is safe and shows positive results in “only active” treatment groups for all the studied neuropsychiatric conditions. However, the sham-controlled evidence for efficacy is negative from India.

Mingfeng Zhai, Shugang Cao, Jinwei Yang et al.

Abstract Introduction This study aimed to investigate the long-term prognostic effects of different alteplase doses on patients with acute ischemic stroke (AIS). Methods In this cohort study, we enrolled 501 patients with AIS treated with intravenous thrombolysis with alteplase, with the primary endpoint event of recurrence of ischemic stroke and the secondary endpoint event of death. The effects of different doses of alteplase on recurrence of ischemic stroke and death were analyzed using a Cox proportional risk model. Results Among 501 patients with AIS treated with thrombolysis, 295 patients (58.9%) and 206 patients (41.1%) were treated with low-dose and standard-dose alteplase, respectively. During the study period, 61 patients (12.2%) had a confirmed recurrence of ischemic stroke. Multivariate Cox proportional risk analysis showed that standard-dose alteplase thrombolysis (HR 0.511, 95% CI 0.288–0.905, P = 0.021) was significantly associated with a reduced risk of long-term recurrence of AIS, whereas atrial fibrillation was associated with an increased risk of long-term recurrence of AIS. Thirty-nine (7.8%) patients died during the study period. Multivariate Cox proportional risk analysis showed that age, baseline National Institutes of Health Stroke Scale (NIHSS) score, and symptomatic steno-occlusion were associated with an increased long-term risk of death from AIS. The alteplase dose was not associated with the risk of death from AIS. Conclusions Standard-dose alteplase treatment reduced the risk of long-term recurrence of AIS after hospital discharge and the alteplase dose was not associated with the long-term risk of death from AIS.

P. McGorry, M. Keshavan, Sherilyn Goldstone et al.

A. Ehlis, S. Schneider, T. Dresler et al.

Baihan Lin, Djallel Bouneffouf, Guillermo Cecchi et al.

In this work, we compare different neural topic modeling methods in learning the topical propensities of different psychiatric conditions from the psychotherapy session transcripts parsed from speech recordings. We also incorporate temporal modeling to put this additional interpretability to action by parsing out topic similarities as a time series in a turn-level resolution. We believe this topic modeling framework can offer interpretable insights for the therapist to optimally decide his or her strategy and improve psychotherapy effectiveness.