Hasil untuk "Psychiatry"

G. Caplan

Eric R. Kandel

B. Sadock, V. A. Sadock, P. Ruiz

Karl J. Friston, K. Stephan, R. Montague et al.

S.B. Jelsma, M. Zijlmans, I.B. Heijink et al.

Epilepsy surgery is usually based on the removal of a local epileptogenic zone. If epilepsy is considered a network disease, a network approach might be more suitable. Insight into patient-specific epileptic brain networks is necessary to establish network-based surgical strategies.We included epilepsy surgery candidates who underwent diffusion-weighted imaging and intracranial EEG implantation with single pulse electrical stimulation (SPES, 0.2 Hz, 1–8 mA, 1 ms, monophasic stimuli) during presurgical evaluation. We reconstructed structural connectivity using fiber tractography taking intracranial electrodes as nodes. We reconstructed effective connectivity with SPES cortico-cortical evoked responses. We determined the inter-modal similarity between structural and effective connectivity with the Jaccard index, and compared network topologies using degree and betweenness centrality. We constructed a linear multilevel model to evaluate the relation between structural and effective connectivity at subject group level. The seizure onset zone nodes (SOZ), node proximity, and the volume of the electrode contact areas (VEA) were added to the model as possible predictors to accommodate for epilepsy and irregular spatial sampling.We included 13 patients (five with electrocorticography, eight with stereo-EEG). The median Jaccard index was 0.25 (IQR: 0.20–0.29), which means there is a higher overlap than expected by chance (median expected Jaccard index = 0.1 (IQR: 0.07–0.17)) with a considerable amount of connections that did not overlap. The structural connectivity degree showed a significant positive correlation with the effective connectivity degree in 9/13 patients and at group level after accommodating for node proximity (β = 0.13, 95 %-CI = [0.04, 0.21], t(852) = 2.79, p = 0.0054). SOZ and VEA were no significant predictors for the correlation between structural and effective connectivity.We showed a moderate overlap between non-invasive structural (measured with DWI) and invasive effective (measured with SPES) connectivity in epileptic brain networks. This overlap supports using non-invasively determined connectivity along with intracranial EEG to understand the epileptic brain. Future research needs to translate these findings towards network-based surgical strategies.

Alissa A. Valentine, Lauren A. Lepow, Lili Chan et al.

The emergency department (ED) is a high stress environment with increased risk of clinician bias exposure. In the United States, Black patients are more likely than other racial/ethnic groups to obtain their first schizophrenia (SCZ) diagnosis in the ED, a highly stigmatizing disorder. Therefore, understanding the link between clinician bias exposure and psychiatric outcomes is critical for promoting nondiscriminatory decision-making in the ED. This study examines the association between clinician bias exposure and psychiatric diagnosis using a sample of patients with anxiety, bipolar, depression, trauma, and SCZ diagnoses (N=29,005) from a diverse, large medical center. Clinician bias exposure was quantified as the ratio of negative to total number of sentences in psychiatric notes, labeled using a large language model (Mistral). We utilized logistic regression to predict SCZ diagnosis when controlling for patient demographics, risk factors, and negative sentence ratio (NSR). A high NSR significantly increased one's odds of obtaining a SCZ diagnosis and attenuated the effects of patient race. Black male patients with high NSR had the highest odds of being diagnosed with SCZ. Our findings suggest sentiment-based metrics can operationalize clinician bias exposure with real world data and reveal disparities beyond race or ethnicity.

Shuyu Liu, Ruoxi Wang, Ling Zhang et al.

The advent of Large Language Models (LLMs) offers potential solutions to address problems such as shortage of medical resources and low diagnostic consistency in psychiatric clinical practice. Despite this potential, a robust and comprehensive benchmarking framework to assess the efficacy of LLMs in authentic psychiatric clinical environments is absent. This has impeded the advancement of specialized LLMs tailored to psychiatric applications. In response to this gap, by incorporating clinical demands in psychiatry and clinical data, we proposed a benchmarking system, PsychBench, to evaluate the practical performance of LLMs in psychiatric clinical settings. We conducted a comprehensive quantitative evaluation of 16 LLMs using PsychBench, and investigated the impact of prompt design, chain-of-thought reasoning, input text length, and domain-specific knowledge fine-tuning on model performance. Through detailed error analysis, we identified strengths and potential limitations of the existing models and suggested directions for improvement. Subsequently, a clinical reader study involving 60 psychiatrists of varying seniority was conducted to further explore the practical benefits of existing LLMs as supportive tools for psychiatrists of varying seniority. Through the quantitative and reader evaluation, we show that while existing models demonstrate significant potential, they are not yet adequate as decision-making tools in psychiatric clinical practice. The reader study further indicates that, as an auxiliary tool, LLM could provide particularly notable support for junior psychiatrists, effectively enhancing their work efficiency and overall clinical quality. To promote research in this area, we will make the dataset and evaluation framework publicly available, with the hope of advancing the application of LLMs in psychiatric clinical settings.

Bruno Aristimunha, Dung Truong, Pierre Guetschel et al.

Current electroencephalogram (EEG) decoding models are typically trained on small numbers of subjects performing a single task. Here, we introduce a large-scale, code-submission-based competition comprising two challenges. First, the Transfer Challenge asks participants to build and test a model that can zero-shot decode new tasks and new subjects from their EEG data. Second, the Psychopathology factor prediction Challenge asks participants to infer subject measures of mental health from EEG data. For this, we use an unprecedented, multi-terabyte dataset of high-density EEG signals (128 channels) recorded from over 3,000 child to young adult subjects engaged in multiple active and passive tasks. We provide several tunable neural network baselines for each of these two challenges, including a simple network and demographic-based regression models. Developing models that generalise across tasks and individuals will pave the way for ML network architectures capable of adapting to EEG data collected from diverse tasks and individuals. Similarly, predicting mental health-relevant personality trait values from EEG might identify objective biomarkers useful for clinical diagnosis and design of personalised treatment for psychological conditions. Ultimately, the advances spurred by this challenge could contribute to the development of computational psychiatry and useful neurotechnology, and contribute to breakthroughs in both fundamental neuroscience and applied clinical research.

Nadja R. Ging-Jehli, Russell K. Childers, Joshua Lu et al.

How do we learn when to persist, when to let go, and when to shift gears? Gearshift Fellowship (GF) is the prototype of a new Supertask paradigm designed to model how humans and artificial agents adapt to shifting environment demands. Grounded in cognitive neuroscience, computational psychiatry, economics, and artificial intelligence, Supertasks combine computational neurocognitive modeling with serious gaming. This creates a dynamic, multi-mission environment engineered to assess mechanisms of adaptive behavior across cognitive and social contexts. Computational parameters explain behavior and probe mechanisms by controlling the game environment. Unlike traditional tasks, GF enables neurocognitive modeling of individual differences across perceptual decisions, learning, and meta-cognitive levels. This positions GF as a flexible testbed for understanding how cognitive-affective control processes, learning styles, strategy use, and motivational shifts adapt across contexts and over time. It serves as an experimental platform for scientists, a phenotype-to-mechanism intervention for clinicians, and a training tool for players aiming to strengthen self-regulated learning, mood, and stress resilience. Online study (n = 60, ongoing) results show that GF recovers effects from traditional neuropsychological tasks (construct validity), uncovers novel patterns in how learning differs across contexts and how clinical features map onto distinct adaptations. These findings pave the way for developing in-game interventions that foster self-efficacy and agency to cope with real-world stress and uncertainty. GF builds a new adaptive ecosystem designed to accelerate science, transform clinical care, and foster individual growth. It offers a mirror and training ground where humans and machines co-develop together deeper flexibility and awareness.

Jana Weber, Marcel Weber, Juan Miguel Lopez Alcaraz

Background: Depression is a major public health concern, affecting an estimated five percent of the global population. Early and accurate diagnosis is essential to initiate effective treatment, yet recognition remains challenging in many clinical contexts. Speech, language, and behavioral cues collected during patient interviews may provide objective markers that support clinical assessment. Methods: We developed a diagnostic approach that integrates features derived from patient interviews, including speech patterns, linguistic characteristics, and structured clinical information. Separate models were trained for each modality and subsequently combined through multimodal fusion to reflect the complexity of real-world psychiatric assessment. Model validity was assessed with established performance metrics, and further evaluated using calibration and decision-analytic approaches to estimate potential clinical utility. Results: The multimodal model achieved superior diagnostic accuracy compared to single-modality models, with an AUROC of 0.88 and a macro F1-score of 0.75. Importantly, the fused model demonstrated good calibration and offered higher net clinical benefit compared to baseline strategies, highlighting its potential to assist clinicians in identifying patients with depression more reliably. Conclusion: Multimodal analysis of patient interviews using machine learning may serve as a valuable adjunct to psychiatric evaluation. By combining speech, language, and clinical features, this approach provides a robust framework that could enhance early detection of depressive disorders and support evidence-based decision-making in mental healthcare.

Timothy Friesen, Philomène Labilloy, Deven Parekh et al.

Background: Stress and negative affect play significant roles in developing psychosis. Bayesian analyses applied to the conditioned hallucinations (CH) task suggest that hallucinations arise when maladaptive prior beliefs outweigh sensory evidence. Prior weighting is linked to hallucination severity, yet the nature of these priors remains unclear. Negative affect may influence the strength of maladaptive priors. We hypothesized that, under stress, participants will show increased CH rates and prior weighting, with this effect more pronounced in patients. Methods: This study employs a modified CH task using valenced linguistic stimuli and stress and non-stress affective manipulations. The sample for this pilot study included those at risk for psychosis and patients with first episode psychosis (N=12) and healthy controls (N=15). The objective of this study was first to validate this affective version of the CH task and then to demonstrate an effect of affect on CH rates and prior weighting. Results: Replicating past results, patients had higher CH rates (b = 0.061, p < 0.001) and prior weighting (b = 0.097, p < 0.001) for session 1 compared to controls (n=15) across conditions. Further, runs with stress manipulations had higher prior weighting across patients and controls compared to runs with non-stress manipulations (b = 0.054, p = 0.033). Conclusions: This study validates this affective version of the CH task and provides preliminary evidence of a relationship between affective state and prior weighting. Future work will be aimed at confirming and extending these findings, with the objective of developing biomarkers of early psychosis. Key words: Schizophrenia, Affect, Priors, Computational Psychiatry, Clinical High Risk Population, Psychotic Symptoms

Evangelos Sariyanidi, Gokul Nair, Lisa Yankowitz et al.

Computational measurement of human behavior from video has recently become feasible due to major advances in AI. These advances now enable granular and precise quantification of facial expression, head movement, body action, and other behavioral modalities and are increasingly used in psychology, psychiatry, neuroscience, and mental health research. However, mainstream adoption remains slow. Most existing methods and software are developed for engineering audiences, require specialized software stacks, and fail to provide behavioral measurements at a level directly useful for hypothesis-driven research. As a result, there is a large barrier to entry for researchers who wish to use modern, AI-based tools in their work. We introduce Bitbox, an open-source toolkit designed to remove this barrier and make advanced computational analysis directly usable by behavioral scientists and clinical researchers. Bitbox is guided by principles of reproducibility, modularity, and interpretability. It provides a standardized interface for extracting high-level behavioral measurements from video, leveraging multiple face, head, and body processors. The core modules have been tested and validated on clinical samples and are designed so that new measures can be added with minimal effort. Bitbox is intended to serve both sides of the translational gap. It gives behavioral researchers access to robust, high-level behavioral metrics without requiring engineering expertise, and it provides computer scientists a practical mechanism for disseminating methods to domains where their impact is most needed. We expect that Bitbox will accelerate integration of computational behavioral measurement into behavioral, clinical, and mental health research. Bitbox has been designed from the beginning as a community-driven effort that will evolve through contributions from both method developers and domain scientists.

S. Dash, G. Clarke, M. Berk et al.

Zuo-cheng Yang, Bo-wen Xue, Xin-yu Song et al.

ObjectivesThis study aimed to elucidate the influences of 1p/19q co-deletion on structural connectivity alterations in patients with dominant hemisphere insular diffuse gliomas.MethodsWe incorporated 32 cases of left insular gliomas and 20 healthy controls for this study. Using diffusion MRI, we applied correlational tractography, differential tractography, and graph theoretical analysis to explore the potential connectivity associated with 1p/19q co-deletion.ResultsThe study revealed that the quantitative anisotropy (QA) of key deep medial fiber tracts, including the anterior thalamic radiation, superior thalamic radiation, fornix, and cingulum, had significant negative associations with 1p/19q co-deletion (FDR = 4.72 × 10–5). These tracts are crucial in maintaining the integrity of brain networks. Differential analysis further supported these findings (FWER-corrected p &lt; 0.05). The 1p/19q non-co-deletion group exhibited significantly higher clustering coefficients (FDR-corrected p &lt; 0.05) and reduced betweenness centrality (FDR-corrected p &lt; 0.05) in regions around the tumor compared to HC group. Graph theoretical analysis indicated that non-co-deletion patients had increased local clustering and decreased betweenness centrality in peritumoral brain regions compared to co-deletion patients and healthy controls (FDR-corrected p &lt; 0.05). Additionally, despite not being significant through correction, patients with 1p/19q co-deletion exhibited lower trends in weighted average clustering coefficient, transitivity, small worldness, and global efficiency, while showing higher tendencies in weighted path length compared to patients without the co-deletion.ConclusionThe findings of this study underline the significant role of 1p/19q co-deletion in altering structural connectivity in insular glioma patients. These alterations in brain networks could have profound implications for the neural functionality in patients with dominant hemisphere insular gliomas.

Allen Ting Chun Lee, Yishan Luo, Zhaohua Huo et al.

Summary: Background: Having more cognitive activities may prevent dementia, but its evidence of modulating the functional brain network is limited. This randomised controlled trial (RCT) investigated the effect of increased cognitive activity participation on the default mode network (DMN) in older adults who had already been having regular cognitive activity participation and experiencing subjective cognitive decline (SCD). Methods: Community-living Chinese individuals aged 55–75 years with regular practice of Chinese calligraphy and screened positive for SCD (but negative for mild cognitive impairment or dementia) were randomly allocated to either the intervention or control group. Over 6 months, the intervention group doubled their weekly calligraphy practice time, while the control group maintained their usual amount of practice. The primary outcome was functional connectivities (FCs) of DMN, with pre-specified regions of interest including medial prefrontal cortex (mPFC), inferior parietal lobe (IPL), hippocampal formation (HF), posterior cingulate cortex (PCC), and lateral temporal cortex (LTC). FC changes were compared using repeated measures multivariate analysis of variance (MANOVA). This study is registered at the Chinese Clinical Trial Registry, ChiCTR1900024433. Findings: Between 15 January 2020 and 31 December 2021, 112 individuals consented and completed the baseline assessment. The participants, who had a mean age of 66.3 (SD 4.3) years, with 83 (74%) being women, had been practising calligraphy for an average duration of 9.7 years before enrolment and, in the preceding six months, for an average of 3.1 hours per week. 96 (86%) completed the post-intervention fMRI scan. Significant between-group differences were observed in the FCs between mPFC and right LTC (group difference = 0.25 [95% CI = 0.06–0.44], p = 0.009), mPFC and right IPL (0.23 [0.06–0.39]; p = 0.007), left HF and right LTC (0.28 [0.002–0.57]; p = 0.04), and left HF and right IPL (0.34 [0.09–0.60]; p = 0.009). Interpretation: Our findings, which reveal positive neuromodulatory effects with increased calligraphy practice, highlight the importance of engaging more in cognitive activities in late life for better brain health. Funding: Research Grants Council, Hong Kong (grant number 24114519).

Xi Chen, Yang Xu, MingKe You et al.

This study evaluates whether large language models (LLMs) exhibit biases towards medical professionals. Fictitious candidate resumes were created to control for identity factors while maintaining consistent qualifications. Three LLMs (GPT-4, Claude-3-haiku, and Mistral-Large) were tested using a standardized prompt to evaluate resumes for specific residency programs. Explicit bias was tested by changing gender and race information, while implicit bias was tested by changing names while hiding race and gender. Physician data from the Association of American Medical Colleges was used to compare with real-world demographics. 900,000 resumes were evaluated. All LLMs exhibited significant gender and racial biases across medical specialties. Gender preferences varied, favoring male candidates in surgery and orthopedics, while preferring females in dermatology, family medicine, obstetrics and gynecology, pediatrics, and psychiatry. Claude-3 and Mistral-Large generally favored Asian candidates, while GPT-4 preferred Black and Hispanic candidates in several specialties. Tests revealed strong preferences towards Hispanic females and Asian males in various specialties. Compared to real-world data, LLMs consistently chose higher proportions of female and underrepresented racial candidates than their actual representation in the medical workforce. GPT-4, Claude-3, and Mistral-Large showed significant gender and racial biases when evaluating medical professionals for residency selection. These findings highlight the potential for LLMs to perpetuate biases and compromise healthcare workforce diversity if used without proper bias mitigation strategies.

Chih-Wei Song, Yu-Kai Lee, Yin-Te Tsai

With the rapid development of large language models in recent years, there has been an increasing demand for domain-specific Agents that can cater to the unique needs of enterprises and organizations. Unlike general models, which strive for broad coverage, these specialized Agents rely on focused datasets tailored to their intended applications. This research proposes a pipeline that leverages the power of LLMs and the Retrieval-Augmented Generation related framework to construct high-quality instruction datasets for fine-tuning on specific domains using custom document collections. By ingesting domain-specific documents, the pipeline generates relevant and contextually appropriate instructions, thus effectively creating a comprehensive dataset for fine-tuning LLMs on the target domain. This approach overcomes the limitations of traditional dataset creation methods, which often rely on manual curation or web-scraping techniques that may introduce noise and irrelevant data. Notably, our pipeline offers a dynamic solution that can quickly adapt to updates or modifications in the domain-specific document collection, eliminating the need for complete retraining. Additionally, it addresses the challenge of data scarcity by enabling the generation of instruction datasets from a limited set of initial documents, rendering it suitable for unpopular or specialized domains where comprehensive datasets are scarce. As a case study, we apply this approach to the domain of psychiatry, a field requiring specialized knowledge and sensitive handling of patient information. The resulting fine-tuned LLM demonstrates showcases the viability of the proposed approach and underscores its potential for widespread adoption across various industries and domains where tailored, accurate, and contextually relevant language models are indispensable.

Braja Gopal Patra, Lauren A. Lepow, Praneet Kasi Reddy Jagadeesh Kumar et al.

Background: Social support (SS) and social isolation (SI) are social determinants of health (SDOH) associated with psychiatric outcomes. In electronic health records (EHRs), individual-level SS/SI is typically documented as narrative clinical notes rather than structured coded data. Natural language processing (NLP) algorithms can automate the otherwise labor-intensive process of data extraction. Data and Methods: Psychiatric encounter notes from Mount Sinai Health System (MSHS, n=300) and Weill Cornell Medicine (WCM, n=225) were annotated and established a gold standard corpus. A rule-based system (RBS) involving lexicons and a large language model (LLM) using FLAN-T5-XL were developed to identify mentions of SS and SI and their subcategories (e.g., social network, instrumental support, and loneliness). Results: For extracting SS/SI, the RBS obtained higher macro-averaged f-scores than the LLM at both MSHS (0.89 vs. 0.65) and WCM (0.85 vs. 0.82). For extracting subcategories, the RBS also outperformed the LLM at both MSHS (0.90 vs. 0.62) and WCM (0.82 vs. 0.81). Discussion and Conclusion: Unexpectedly, the RBS outperformed the LLMs across all metrics. Intensive review demonstrates that this finding is due to the divergent approach taken by the RBS and LLM. The RBS were designed and refined to follow the same specific rules as the gold standard annotations. Conversely, the LLM were more inclusive with categorization and conformed to common English-language understanding. Both approaches offer advantages and are made available open-source for future testing.

Marcantonio Gagliardi, Marina Bonadeni, Sara Billai et al.

Background. Personality is a primary object of interest in clinical psychology and psychiatry. It is most often measured using questionnaires, which rely on Factor Analysis (FA) to identify essential domains corresponding to highly correlated questions/items that define a (sub)scale. This procedure implies the rigid assignment of each question to one scale - giving the item the same meaning regardless of how the respondent may interpret it - arguably affecting the assessment capability of the instrument. Methods. To test this hypothesis, we use the Attachment-Caregiving Questionnaire (ACQ), a clinical and personality self-report that - through extra-scale information - allows the clinician to infer the possible different meanings subjects attribute to the items. Considering four psychotherapy patients, we compare the scoring of the ACQ provided by expert clinicians to the detailed information gained from therapy and the patients. Results. Our analysis suggests that a question can be interpreted differently - receiving the same score for different (clinically relevant) reasons - potentially impacting personality assessment and clinical decision-making. Moreover, accounting for multiple interpretations requires a specific questionnaire design and a more advanced pattern recognition than FA - which Artificial Intelligence (AI) could provide. Conclusion. Our results indicate that a meaning-sensitive, personalized read of a personality self-report can affect profiling and treatment. Since a machine learning model can mimic the interpretative performance of an expert clinician, our results also imply a novel, AI-oriented approach to inventory design, of which we envision the first implementation steps. More evidence is required to support these preliminary findings.

Alissa A. Valentine, Lauren A. Lepow, Lili Chan et al.

Negative patient descriptions and stigmatizing language can contribute to generating healthcare disparities in two ways: (1) read by patients, they can harm their trust and engagement with the medical center; (2) read by physicians, they may negatively influence their perspective of a future patient. In psychiatry, the patient-clinician therapeutic alliance is a major determinant of clinical outcomes. Therefore, language usage in psychiatric clinical notes may not only create healthcare disparities, but also perpetuate them. Recent advances in NLP systems have facilitated the efforts to detect discriminatory language in healthcare. However, such attempts have only focused on the perspectives of the medical center and its physicians. Considering both physicians and non-physicians' point of view is a more translatable approach to identifying potentially harmful language in clinical notes. By leveraging pre-trained and large language models (PLMs and LLMs), this work aims to characterize potentially harmful language usage in psychiatric notes by identifying the sentiment expressed in sentences describing patients based on the reader's point of view. Extracting 39 sentences from the Mount Sinai Health System containing psychiatric lexicon, we fine-tuned three PLMs (RoBERTa, GatorTron, and GatorTron + Task Adaptation) and implemented zero-shot and few-shot ICL approaches for three LLMs (GPT-3.5, Llama-3.1, and Mistral) to classify the sentiment of the sentences according to the physician or non-physician point of view. Results showed that GPT-3.5 aligned best to physician point of view and Mistral aligned best to non-physician point of view. These results underline the importance of recognizing the reader's point of view, not only for improving the note writing process, but also for the quantification, identification, and reduction of bias in computational systems for downstream analyses.