Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing最新文献_第6页

Automated Evaluation of Large Language Model Response Concordance with Human Specialist Responses on Physician-to-Physician eConsult Cases. 在医生对医生咨询案例中，大型语言模型反应与人类专家反应一致的自动评估。

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing Pub Date : 2026-01-01 DOI: 10.1142/9789819824755_0026

David Jh Wu, Fateme Nateghi Haredasht, David Wu, Vishnu Ravi, Liam G McCoy, Yingjie Weng, Kanav Chopra, Selin S Everett, George Nageeb, Wenyuan Chen, Stephen P Ma, Saloni Kumar Maharaj, Jessica Tran, Leah Rosengaus, Lena Giang, Olivia Jee, Ethan Goh, Jonathan H Chen

{"title":"Automated Evaluation of Large Language Model Response Concordance with Human Specialist Responses on Physician-to-Physician eConsult Cases.","authors":"David Jh Wu, Fateme Nateghi Haredasht, David Wu, Vishnu Ravi, Liam G McCoy, Yingjie Weng, Kanav Chopra, Selin S Everett, George Nageeb, Wenyuan Chen, Stephen P Ma, Saloni Kumar Maharaj, Jessica Tran, Leah Rosengaus, Lena Giang, Olivia Jee, Ethan Goh, Jonathan H Chen","doi":"10.1142/9789819824755_0026","DOIUrl":"10.1142/9789819824755_0026","url":null,"abstract":"Specialist consults in primary care and inpatient settings typically address complex clinical questions beyond standard guidelines. eConsults have been developed as a way for specialist physicians to review cases asynchronously and provide clinical answers without a formal patient encounter. Meanwhile, large language models (LLMs) have approached human-level performance on structured clinical tasks, but their real-world effectiveness requires evaluation, which is bottlenecked by time-intensive manual physician review. To address this, we evaluate two automated methods: LLM-as-judge and a decompose-thenverify framework that breaks down AI answers into verifiable claims against human eConsult responses. Using 40 real-world physician-to-physician eConsults, we compared AI-generated responses to human answers using both physician raters and automated tools. LLM-as-judge outperformed decompose-then-verify, achieving human-level concordance assessment with F1-score of 0.89 (95% CI: 0.750, 0.960) and Cohen's kappa of 0.75 (95% CI 0.47,0.90) , comparable to physician inter-rater agreement κ = 0.69-0.90 (95% CI 0.43-1.0).","PeriodicalId":34954,"journal":{"name":"Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing","volume":"31 ","pages":"372-387"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147310721","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Impact of using PRS-CSx and pruning and thresholding for polygenic partitioning of apparent treatment resistant hypertension. 使用PRS-CSx和剪枝阈值对明显治疗难治性高血压多基因分配的影响

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing Pub Date : 2026-01-01 DOI: 10.1142/9789819824755_0048

Hannah M Seagle, Jeewoo Kim, Alexis T Akerele, Adriana Hung, Jacklyn N Hellwege, Todd L Edwards

{"title":"Impact of using PRS-CSx and pruning and thresholding for polygenic partitioning of apparent treatment resistant hypertension.","authors":"Hannah M Seagle, Jeewoo Kim, Alexis T Akerele, Adriana Hung, Jacklyn N Hellwege, Todd L Edwards","doi":"10.1142/9789819824755_0048","DOIUrl":"10.1142/9789819824755_0048","url":null,"abstract":"Apparent treatment-resistant hypertension (aTRH) is a clinically challenging condition with heterogeneous etiologies. Understanding the biological pathways underlying resistance to antihypertensive treatment could inform targeted therapeutic strategies. To evaluate how methodological choices in SNP selection influence biological inference, we applied two approaches to select aTRH-associated variants for clustering: PRS-CSx and pruning and thresholding (P&T). Using k-means clustering, we grouped aTRH-associated variants based on their association profiles across 91 cardiometabolic-related phenotypes. We then performed pathway and tissue enrichment analyses to evaluate the biological processes represented by each cluster. Both methods identified multiple genetic clusters, but the distribution of variants and biological signals differed. Clustering based on PRS-CSx produced unequally distributed clusters of SNPs and yielded limited tissue enrichment, while P&T-based clustering captured more uniform trends across cardiometabolic traits and broader tissue and pathway enrichment. These results demonstrate that methodological choices in SNP selection influence downstream clustering and biological interpretation. Despite some overlap in identified pathways and tissue enrichment, each approach identified unique biological signals, highlighting the potential of pairing polygenic methods and k-means clustering to elucidate the biological heterogeneity of aTRH and guide future mechanistic studies.","PeriodicalId":34954,"journal":{"name":"Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing","volume":"31 ","pages":"664-678"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147310750","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A random-walk-based learning framework to uncover novel gene candidates for Alzheimer's disease therapy. 一个基于随机行走的学习框架，以发现阿尔茨海默病治疗的新候选基因。

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing Pub Date : 2026-01-01 DOI: 10.1142/9789819824755_0059

Alena Orlenko, Binglan Li, Neda Khanjani, Mythreye Venkatesan, Li Shen, Marylyn D Ritchie, Zhiping Paul Wang, Tayo Obafemi-Ajayi, Jason H Moore

{"title":"A random-walk-based learning framework to uncover novel gene candidates for Alzheimer's disease therapy.","authors":"Alena Orlenko, Binglan Li, Neda Khanjani, Mythreye Venkatesan, Li Shen, Marylyn D Ritchie, Zhiping Paul Wang, Tayo Obafemi-Ajayi, Jason H Moore","doi":"10.1142/9789819824755_0059","DOIUrl":"10.1142/9789819824755_0059","url":null,"abstract":"Identifying repurposable therapeutic targets for Alzheimer's disease (AD) remains challenging due to various clinical and biological factors. This study aimed to identify candidate genes for AD therapy. We hypothesize that gene and disease-specific network properties-learnable from these large-scale biomedical knowledge graphs-can inform implicit gene-AD connections and prioritize repurposable AD drug targets. To evaluate the hypothesis, we focused on druggable genes curated from Drug-Gene Interaction Database and Alzheimer's Knowledge Base (AlzKB). We applied scalable random walk methods to Hetionet to learn unbiased gene and disease embeddings, representative of their topological and semantic network properties. The embeddings were then used to compute gene-AD similarity and derive network-based scores for each gene. To validate the scores, using Alzheimer's Disease Sequencing Project (ADSP) data, we constructed AD classifier models with Tree-based pipeline optimizer 2 (TPOT2), an automated machine learning framework. Models were optimized for performance, model complexity, and high aggregate network-based scores. Network-based scores successfully prioritized diverse feature sets-many not previously associated with AD-that are enriched in biologically meaningful body parts such as brain, and pathways including neuronal signaling, potassium channels, and creatine metabolism. The results suggested that knowledge graphs and network-informed embeddings can capture both known and novel insights into AD mechanisms. Additionally, integrating networkbased scores with feature-set-guided TPOT2 offers a scalable and biologically interpretable framework for AD drug repurposing and discovery.","PeriodicalId":34954,"journal":{"name":"Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing","volume":"31 ","pages":"815-829"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12952682/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147309980","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

LLM Agent Based Protein Function Prediction. 基于LLM代理的蛋白质功能预测。

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing Pub Date : 2026-01-01 DOI: 10.1142/9789819824755_0036

Fernando Zhapa-Camacho, Olga Mashkova, Robert Hoehndorf, Maxat Kulmanov

{"title":"LLM Agent Based Protein Function Prediction.","authors":"Fernando Zhapa-Camacho, Olga Mashkova, Robert Hoehndorf, Maxat Kulmanov","doi":"10.1142/9789819824755_0036","DOIUrl":"10.1142/9789819824755_0036","url":null,"abstract":"Protein function prediction remains a fundamental challenge in computational biology. Here, we present a Large Language Model (LLM) agent-based system that improves protein function prediction performance using knowledge-augmented reasoning and multi-source evidence synthesis.Our approach integrates computational predictions with structured protein metadata, scientific literature, and ontological knowledge through a multi-stage reasoning process. An LLM agent equipped with specialized tools progressively refines functional predictions by querying constraints, cross-referencing evidence, and ensuring biological plausibility. Furthermore, the system provides detailed explanations for each prediction update, documenting the reasoning process and evidence sources.We evaluate our approach against established baseline methods across three Gene Ontology sub-ontologies using four complementary metrics, achieving superior performance in threshold-dependent measures, attaining the lowest Smin scores across all ontologies and the best Fmax for Molecular Function and Cellular Component ontologies. We make our code publicly available at https://github.com/bio-ontology-research-group/go-agent.","PeriodicalId":34954,"journal":{"name":"Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing","volume":"31 ","pages":"508-519"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147310837","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Integrating Polygenic Risk Improves Generative Forecasting of Disease Trajectories. 整合多基因风险改善疾病轨迹的生成预测。

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing Pub Date : 2026-01-01 DOI: 10.1142/9789819824755_0044

Chris German, Suyash Shringarpure, Payam Dibaeinia, James Ashenhurst, Bertram L Koelsch, Adam Auton, Aly A Khan

{"title":"Integrating Polygenic Risk Improves Generative Forecasting of Disease Trajectories.","authors":"Chris German, Suyash Shringarpure, Payam Dibaeinia, James Ashenhurst, Bertram L Koelsch, Adam Auton, Aly A Khan","doi":"10.1142/9789819824755_0044","DOIUrl":"10.1142/9789819824755_0044","url":null,"abstract":"Predicting the longitudinal sequence of diseases an individual will develop over their lifetime is a central challenge in medicine. While recent AI models can process health histories, they have been limited by cohort size and the omission of genetic data. Here we introduce the Next Health Event (NHE) model, a generative transformer trained on the health trajectories of 7.1 million research participants. By using a transformer architecture to integrate demographic data, longitudinal BMI, and polygenic risk scores (PRS) for 297 traits with sequential health history, NHE significantly outperforms baseline models, including XGBoost with the same inputs, in predicting the next diagnosis across 129 conditions (Top-1 accuracy 25.5% vs. 22.3%). Systematic ablation studies reveal that both PRS and longitudinal BMI provide substantial, non-redundant predictive power, whereas self-reported lifestyle information offers limited additional value. The model's predictive accuracy is the same when forecasting prospectively reported incident outcomes vs. combined prospectively and retrospectively reported outcomes (AUROC 0.917), demonstrating its utility for real-world risk assessment. By uniting large-scale health histories with genetics, our work establishes a new framework for predictive health and demonstrates that generative models can effectively forecast individual disease pathways.","PeriodicalId":34954,"journal":{"name":"Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing","volume":"31 ","pages":"600-611"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147310869","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Learning Causally Predictable Outcomes from Psychiatric Longitudinal Data. 从精神病学纵向数据中学习因果预测结果。

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing Pub Date : 2026-01-01 DOI: 10.1142/9789819824755_0012

Eric V Strobl

{"title":"Learning Causally Predictable Outcomes from Psychiatric Longitudinal Data.","authors":"Eric V Strobl","doi":"10.1142/9789819824755_0012","DOIUrl":"10.1142/9789819824755_0012","url":null,"abstract":"Causal inference in longitudinal biomedical data remains a central challenge, especially in psychiatry, where symptom heterogeneity and latent confounding frequently undermine classical estimators. Most existing methods for treatment effect estimation presuppose a fixed outcome variable and address confounding through observed covariate adjustment. However, the assumption of unconfoundedness may not hold for a fixed outcome in practice. To address this foundational limitation, we directly optimize the outcome definition to maximize causal identifiability. Our DEBIAS (Durable Effects with Backdoor-Invariant Aggregated Symptoms) algorithm learns non-negative, clinically interpretable weights for outcome aggregation, maximizing durable treatment effects and empirically minimizing both observed and latent confounding by leveraging the time-limited direct effects of prior treatments in psychiatric longitudinal data. The algorithm also furnishes an empirically verifiable test for outcome unconfoundedness. DEBIAS consistently outperforms state-ofthe- art methods in recovering causal effects for clinically interpretable composite outcomes across comprehensive experiments in depression and schizophrenia. R code is available at https://github.com/ericstrobl/DEBIAS.","PeriodicalId":34954,"journal":{"name":"Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing","volume":"31 ","pages":"158-172"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147310805","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Automated Chest X-ray Report Generation Remains Unsolved. 自动生成胸部x光报告仍未解决。

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing Pub Date : 2026-01-01 DOI: 10.1142/9789819824755_0017

Xiaoman Zhang, Julian Nicolas Acosta, Xiaoli Yang, Subathra Adithan, Luyang Luo, Hong-Yu Zhou, Joshua Miller, Ouwen Huang, Zongwei Zhou, Ibrahim Ethem Hamamci, Shruthi Bannur, Kenza Bouzid, Xi Zhang, Zaiqiao Meng, Aaron Nicolson, Bevan Koopman, Inhyeok Baek, Hanbin Ko, Mercy Prasanna Ranjit, Shaury Srivastav, Sriram Gnana Sambanthan, Pranav Rajpurkar

{"title":"Automated Chest X-ray Report Generation Remains Unsolved.","authors":"Xiaoman Zhang, Julian Nicolas Acosta, Xiaoli Yang, Subathra Adithan, Luyang Luo, Hong-Yu Zhou, Joshua Miller, Ouwen Huang, Zongwei Zhou, Ibrahim Ethem Hamamci, Shruthi Bannur, Kenza Bouzid, Xi Zhang, Zaiqiao Meng, Aaron Nicolson, Bevan Koopman, Inhyeok Baek, Hanbin Ko, Mercy Prasanna Ranjit, Shaury Srivastav, Sriram Gnana Sambanthan, Pranav Rajpurkar","doi":"10.1142/9789819824755_0017","DOIUrl":"10.1142/9789819824755_0017","url":null,"abstract":"Accurate interpretation of chest radiograph images and generation of narrative reports is essential for patient care but places a heavy burden on radiologists and clinical experts. While AI models for automated report generation show promise, standardized evaluation frameworks remain limited. Here we present the ReXrank Challenge V1.0, a competition in the generation of chest radiograph reports utilizing ReXGradient, the largest test dataset consisting of 10,000 studies across 67 sites. The challenge attracted diverse participants from academic institutions, industry, and independent research teams, resulting in 8 new submissions alongside 16 state-of-the-art models previously benchmarked. Through comprehensive evaluation using multiple metrics, we analyzed model performance across various dimensions: differences between normal and abnormal studies, generalization capabilities across healthcare sites, and error rates in identifying clinical findings. This benchmark reveals that automated chest X-ray report generation remains fundamentally unsolved, with significant performance gaps between normal and abnormal studies, where even top-performing models achieve less than 45% error-free reporting on abnormal cases, and substantial variability across healthcare institutions, indicating that robust, clinically-ready systems require continued development before widespread deployment.","PeriodicalId":34954,"journal":{"name":"Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing","volume":"31 ","pages":"236-250"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147310751","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

From Detection to Mitigation: Addressing Bias in Deep Learning Models for Chest X-Ray Diagnosis. 从检测到缓解：解决胸部x射线诊断的深度学习模型中的偏见。

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing Pub Date : 2026-01-01 DOI: 10.1142/9789819824755_0039

Clemence Mottez, Louisa Fay, Maya Varma, Sophie Ostmeier, Curtis Langlotz

{"title":"From Detection to Mitigation: Addressing Bias in Deep Learning Models for Chest X-Ray Diagnosis.","authors":"Clemence Mottez, Louisa Fay, Maya Varma, Sophie Ostmeier, Curtis Langlotz","doi":"10.1142/9789819824755_0039","DOIUrl":"10.1142/9789819824755_0039","url":null,"abstract":"Deep learning models have shown promise in improving diagnostic accuracy from chest X-rays, but they also risk perpetuating healthcare disparities when performance varies across demographic groups. In this work, we present a comprehensive bias detection and mitigation framework targeting sex, age, and race-based disparities when performing diagnostic tasks with chest X-rays. We extend a recent CNN-XGBoost pipeline to support multi-label classification and evaluate its performance across four medical conditions. We show that replacing the final layer of CNN with an eXtreme Gradient Boosting classifier improves the fairness of the subgroup while maintaining or improving the overall predictive performance. To validate its generalizability, we apply the method to different backbones, namely DenseNet-121 and ResNet-50, and achieve similarly strong performance and fairness outcomes, confirming its model-agnostic design. We further compare this lightweight adapter training method with traditional full-model training bias mitigation techniques, including adversarial training, reweighting, data augmentation, and active learning, and find that our approach offers competitive or superior bias reduction at a fraction of the computational cost. Finally, we show that combining eXtreme Gradient Boosting retraining with active learning yields the largest reduction in bias across all demographic subgroups, both in and out of distribution on the CheXpert and MIMIC datasets, establishing a practical and effective path toward equitable deep learning deployment in clinical radiology.","PeriodicalId":34954,"journal":{"name":"Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing","volume":"31 ","pages":"538-550"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147310709","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Higher-order Interaction Matters: Modeling Epidemics via Dynamic Hypergraph Neural Networks. 高阶相互作用问题：通过动态超图神经网络建模流行病。

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing Pub Date : 2026-01-01 DOI: 10.1142/9789819824755_0005

Songyuan Liu, Shengbo Gong, Tianning Feng, Zewen Liu, Max S Y Lau, Wei Jin

{"title":"Higher-order Interaction Matters: Modeling Epidemics via Dynamic Hypergraph Neural Networks.","authors":"Songyuan Liu, Shengbo Gong, Tianning Feng, Zewen Liu, Max S Y Lau, Wei Jin","doi":"10.1142/9789819824755_0005","DOIUrl":"10.1142/9789819824755_0005","url":null,"abstract":"The ongoing need for effective epidemic modeling has driven advancements in capturing the complex dynamics of infectious diseases. Traditional models, such as Susceptible-Infected- Recovered, and graph-based approaches often fail to account for higher-order interactions and the nuanced structure pattern inherent in human contact networks. Higher-order interactions, such as those in schools, workplaces, or public transit, involve simultaneous contact among more than two individuals. This study introduces a novel Human Contact-Tracing Hypergraph Neural Network framework tailored for epidemic modeling called EpiDHGNN, leveraging the capabilities of hypergraphs to model intricate, higher-order relationships from both location and individual level. Both real-world and synthetic epidemic data are used to train and evaluate the model. Results demonstrate that EpiDHGNN consistently outperforms baseline models across various epidemic modeling tasks, such as source detection and forecast, by approximately 12.1% through effectively capturing the higher-order interactions and preserving the complex structure of human interactions. This work underscores the potential of representing human contact data as hypergraphs and employing hypergraphbased methods to improve epidemic modeling, providing reliable insights for public health decision-making.","PeriodicalId":34954,"journal":{"name":"Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing","volume":"31 ","pages":"57-70"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12952669/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147310730","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Detecting PTSD in Clinical Interviews: A Comparative Analysis of NLP Methods and Large Language Models. 临床访谈中PTSD的检测：NLP方法与大型语言模型的比较分析。

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing Pub Date : 2026-01-01 DOI: 10.1142/9789819824755_0019

Feng Chen, Dror Ben-Zeev, Gillian Sparks, Arya Kadakia, Trevor Cohen

{"title":"Detecting PTSD in Clinical Interviews: A Comparative Analysis of NLP Methods and Large Language Models.","authors":"Feng Chen, Dror Ben-Zeev, Gillian Sparks, Arya Kadakia, Trevor Cohen","doi":"10.1142/9789819824755_0019","DOIUrl":"10.1142/9789819824755_0019","url":null,"abstract":"Post-Traumatic Stress Disorder (PTSD) remains under-detected in clinical settings, presenting opportunities for automated detection to identify at-risk patients. This study evaluates natural language processing approaches for binary PTSD classification from clinical interview transcripts using the DAIC-WOZ dataset, which contains semi-structured interviews with standardized psychological assessments. We compared embedding-based methods (SentenceBERT/LLaMA with logistic regression), general and mental health-specific transformer models (BERT/RoBERTa), and large language model prompting strategies (zero-shot/few-shot/chain-ofthought). SentenceBERT embeddings with logistic regression achieved the highest overall performance (AUPRC=0.758±0.128), outperforming domain-specific end-to-end fine-tuning models like Mental-RoBERTa (AUPRC=0.675±0.084 vs. RoBERTa-base 0.599±0.145). Few-shot prompting using DSM-5 criteria and two examples yielded competitive results (AUPRC=0.737). Performance varied significantly across symptom severity and comorbidity status with depression, with higher accuracy for severe PTSD cases and patients with comorbid depression. Our findings highlight the potential of embedding-based methods and LLMs for scalable screening while underscoring the need for improved detection of nuanced presentations.","PeriodicalId":34954,"journal":{"name":"Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing","volume":"31 ","pages":"265-279"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147310746","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0