Proceedings of machine learning research最新文献

{"title":"CaseReportBench: An LLM Benchmark Dataset for Dense Information Extraction in Clinical Case Reports.","authors":"Xiao Yu Cindy Zhang, Carlos R Ferreira, Francis Rossignol, Raymond T Ng, Wyeth Wasserman, Jian Zhu","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Rare diseases, including Inborn Errors of Metabolism (IEM), pose significant diagnostic challenges. Case reports serve as key but computationally underutilized resources to inform diagnosis. Clinical dense information extraction refers to organizing medical information into structured predefined categories. Large Language Models (LLMs) may enable scalable information extraction from case reports but are rarely evaluated for this task. We introduce <b>CaseReportBench</b>, an expert-annotated dataset for dense information extraction of case reports (focusing on IEMs). Using this dataset, we assess various models and promptings, introducing novel strategies of <b>category-specific prompting</b> and <b>subheading-filtered data integration</b>. Zero-shot chain-of-thought offers little advantage over zero-shot prompting. <b>Category-specific prompting</b> improves alignment to benchmark. Open-source <b>Qwen2.5:7B</b> outperforms <b>GPT-4o</b> for this task. Our clinician evaluations show that LLMs can extract clinically relevant details from case reports, supporting rare disease diagnosis and management. We also highlight areas for improvement, such as LLMs' limitations in recognizing negative findings for differential diagnosis. This work advances LLM-driven clinical NLP, paving the way for scalable medical AI applications.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"287 ","pages":"527-542"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12477612/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145202365","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}

{"title":"Contrastive Pretraining for Stress Detection with Multimodal Wearable Sensor Data and Surveys.","authors":"Zeyu Yang, Han Yu, Akane Sano","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Stress adversely affects mental and physical health and underscores the importance of early detection. Some studies have utilized physiological signals from wearable sensors and other information to monitor stress levels in daily life. Recent studies use self-supervised methods due to the high cost of collecting stress labels. However, self-supervised learning using both time series and tabular features such as demographics, traits, and contextual information has been understudied. Therefore, there is a need to further investigate how a model can be effectively trained with different granularity of multimodal data and a limited number of labels. In this study, we introduce a self-supervised multimodal learning approach for stress detection that combines time series and tabular features. Our proposed method presents a promising solution for effectively monitoring stress using multimodal data.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"287 ","pages":"166-178"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12975034/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147438086","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}

{"title":"Caught in the Web of Words: Do LLMs Fall for Spin in Medical Literature?","authors":"Hye Sun Yun, Karen Y C Zhang, Ramez Kouzy, Iain J Marshall, Junyi Jessy Li, Byron C Wallace","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Medical research faces well-documented challenges in translating novel treatments into clinical practice. Publishing incentives encourage researchers to present \"positive\" findings, even when empirical results are equivocal. Consequently, it is well-documented that authors often <i>spin</i> study results, especially in article abstracts. Such spin can influence clinician interpretation of evidence and may affect patient care decisions. In this study, we ask whether the interpretation of trial results offered by Large Language Models (LLMs) is similarly affected by spin. This is important since LLMs are increasingly being used to trawl through and synthesize published medical evidence. We evaluated 22 LLMs and found that they are across the board <i>more</i> susceptible to spin than humans. They might also propagate spin into their outputs: We find evidence, e.g., that LLMs implicitly incorporate spin into plain language summaries that they generate. We also find, however, that LLMs are generally capable of recognizing spin, and can be prompted in a way to mitigate spin's impact on LLM outputs.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"287 ","pages":"458-479"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12622377/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145552263","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}

{"title":"KEEP: Integrating Medical Ontologies with Clinical Data for Robust Code Embeddings.","authors":"Ahmed Elhussein, Paul Meddeb, Abigail Newbury, Jeanne Mirone, Martin Stoll, Gamze Gürsoy","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Machine learning in healthcare requires effective representation of structured medical codes, but current methods face a trade-off: knowledge graph-based approaches capture formal relationships but miss real-world patterns, while data-driven methods learn empirical associations but often overlook structured knowledge in medical terminologies. We present KEEP (Knowledge-preserving and Empirically refined Embedding Process), an efficient framework that bridges this gap by combining knowledge graph embeddings with adaptive learning from clinical data. KEEP first generates embeddings from knowledge graphs, then employs regularized training on patient records to adaptively integrate empirical patterns while preserving ontological relationships. Importantly, KEEP produces final embeddings without task-specific axillary or end-to-end training enabling KEEP to support multiple downstream applications and model architectures. Evaluations on structured EHR from UK Biobank and MIMIC-IV demonstrate that KEEP outperforms both traditional and Language Model-based approaches in capturing semantic relationships and predicting clinical outcomes. Moreover, KEEP's minimal computational requirements make it particularly suitable for resource-constrained environments.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"287 ","pages":"43-62"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13356279/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148431705","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}

{"title":"Predicting Partially Observed Long-Term Outcomes with Adversarial Positive-Unlabeled Domain Adaptation.","authors":"Mengying Yan, Meng Xia, Wei A Huang, Chuan Hong, Benjamin A Goldstein, Matthew M Engelhard","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Predicting long-term clinical outcomes often requires large-scale training data with sufficiently long follow-up. However, in electronic health records (EHR) data, long-term labels may not be available for contemporary patient cohorts. Given the dynamic nature of clinical practice, models that rely on historical training data may not perform optimally. In this work, we frame the problem as a positive-unlabeled domain adaptation task, where we seek to adapt from a fully labeled source domain (e.g., historical data) to a partially labeled target domain (e.g., contemporary data). We propose an adversarial framework that includes three core components: (1) Overall Alignment, to match feature distributions between source and target domains; (2) Partial Alignment, to map source negatives to unlabeled target samples; and (3) Conditional Alignment, to address conditional shift using available positive labels in the target domain. We evaluate our method on a benchmark digit classification task (SVHN-MNIST), and two real-world EHR applications: prediction of one-year mortality post COVID-19, and long-term prediction of neurodevelopmental conditions (NDC) in children. In all settings, our approach consistently outperforms baseline models and, in most cases, achieves performance close to an oracle model trained with fully observed labels.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"287 ","pages":"672-690"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12779109/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145936701","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}

{"title":"Scalable Inference for Bayesian Multinomial Logistic-Normal Dynamic Linear Models.","authors":"Manan Saxena, Tinghua Chen, Justin D Silverman","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Many scientific fields collect longitudinal count compositional data. Each observation is a multivariate count vector, where the total counts are arbitrary, and the information lies in the relative frequency of the counts. Multiple authors have proposed Bayesian Multinomial Logistic-Normal Dynamic Linear Models (MLN-DLMs) as a flexible approach to modeling these data. However, adoption of these methods has been limited by computational challenges. This article develops an efficient and accurate approach to posterior state estimation, called Fenrir. Our approach relies on a novel algorithm for MAP estimation and an accurate approximation to a key posterior marginal of the model. As there are no equivalent methods against which we can compare, we also develop an optimized Stan implementation of MLN-DLMs. Our experiments suggest that Fenrir can be three orders of magnitude more efficient than Stan and can even be incorporated into larger sampling schemes for joint inference of model hyperparameters. Our methods are made available to the community as a user-friendly software library written in C++ with an R interface.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"258 ","pages":"442-450"},"PeriodicalIF":0.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12774479/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145919262","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}

{"title":"Harnessing Causality in Reinforcement Learning With Bagged Decision Times.","authors":"Daiqi Gao, Hsin-Yu Lai, Predrag Klasnja, Susan A Murphy","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>We consider reinforcement learning (RL) for a class of problems with bagged decision times. A bag contains a finite sequence of consecutive decision times. The transition dynamics are non-Markovian and non-stationary within a bag. All actions within a bag jointly impact a single reward, observed at the end of the bag. For example, in mobile health, multiple activity suggestions in a day collectively affect a user's daily commitment to being active. Our goal is to develop an online RL algorithm to maximize the discounted sum of the bag-specific rewards. To handle non-Markovian transitions within a bag, we utilize an expert-provided causal directed acyclic graph (DAG). Based on the DAG, we construct states as a dynamical Bayesian sufficient statistic of the observed history, which results in Markov state transitions within and across bags. We then formulate this problem as a periodic Markov decision process (MDP) that allows non-stationarity within a period. An online RL algorithm based on Bellman equations for stationary MDPs is generalized to handle periodic MDPs. We show that our constructed state achieves the maximal optimal value function among all state constructions for a periodic MDP. Finally, we evaluate the proposed method on testbed variants built from real data in a mobile health clinical trial.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"258 ","pages":"658-666"},"PeriodicalIF":0.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12974610/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147438040","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}

{"title":"Stabilized Inverse Probability Weighting via Isotonic Calibration.","authors":"Lars van der Laan, Ziming Lin, Marco Carone, Alex Luedtke","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Inverse weighting with an estimated propensity score is widely used by estimation methods in causal inference to adjust for confounding bias. However, directly inverting propensity score estimates can lead to instability, bias, and excessive variability due to large inverse weights, especially when treatment overlap is limited. In this work, we propose a post-hoc calibration algorithm for inverse propensity weights that generates well-calibrated, stabilized weights from user-supplied, cross-fitted propensity score estimates. Our approach employs a variant of isotonic regression with a loss function specifically tailored to the inverse propensity weights. Through theoretical analysis and empirical studies, we demonstrate that isotonic calibration improves the performance of doubly robust estimators of the average treatment effect.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"275 ","pages":"139-173"},"PeriodicalIF":0.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13061341/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147647881","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}

{"title":"Integrating Social Determinants of Health in a Multi-Modal Deep Clustering Survival Model for Injury-Risk in Alzheimer's and Related Dementia Patients.","authors":"Kazi Noshin, Mary Regina Boland, Bojian Hou, Weiqing He, Victoria Lu, Li Shen, Aidong Zhang","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>As our population ages, the prevalence of Alzheimer's Disease and Related Dementias (ADRD) and its associated burdens continue to rise. Social Determinants of Health (SDOH) significantly influence both ADRD development and progression. Using Electronic Health Records (EHR) from a quaternary care academic medical center in a diverse urban setting, we investigated SDOH's impact on multi-modal deep clustering survival machines. Our findings revealed that SDOH improved model performance across feature selection methods (DeepCox roll-out vs. SHAP DeepExplainer) and EHR clinical modalities (medication vs. laboratory). Additionally, Laboratory features proved more informative than medications for predicting injury-fall risk. Our results highlight SDOH's crucial role in ADRD progression, particularly regarding injury-fall risk. We found that feature importance varied by selection method when analyzing multi-modality EHR data, with education emerging as a key SDOH factor among our top 10 features, underscoring its significance in ADRD progression.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"281 ","pages":"155-164"},"PeriodicalIF":0.0,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13004619/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147500696","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}

{"title":"A Physics-Augmented Deep Learning Framework for Classifying Single Molecule Force Spectroscopy Data.","authors":"Cailong Hua, Sivaraman Rajaganapathy, Rebecca A Slick, Joseph Vavra, Joseph M Muretta, James M Ervasti, Murti V Salapaka","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Deciphering protein folding and unfolding pathways under tension is essential for deepening our understanding of fundamental biological mechanisms. Such insights hold the promise of developing treatments for a range of debilitating and fatal conditions, including muscular disorders like Duchenne Muscular Dystrophy and neurodegenerative diseases such as Parkinson's disease. Single molecule force spectroscopy (SMFS) is a powerful technique for investigating forces involved in protein domains folding and unfolding. However, SMFS trials often involve multiple protein molecules, necessitating filtering to isolate measurements from single-molecule trials. Currently, manual visual inspection is the primary method for classifying single-molecule data; a process that is both time-consuming and requires significant expertise. Here, we both apply state-of-the-art machine learning models and present a novel deep learning model tailored to SMFS data. The proposed model employs a dual-branch fusion strategy; one branch integrates the physics of protein molecules, and the other operates independently of physical constraints. This model automates the isolation of single-molecule measurements, significantly enhancing data processing efficiency. To train and validate our approach, we developed a physics-based Monte Carlo engine to simulate force spectroscopy datasets, including trials involving single molecules, multiple molecules, and no molecules. Our model achieves state-of-the-art performance, outperforming five baseline methods on both simulated and experimental datasets. It attains nearly 100% accuracy across all simulated datasets and an average accuracy of 79.6 ± 5.2% on experimental datasets, using only ~30 training samples, surpassing baseline methods by 11.4%. Notably, even without expert annotations on experimental data, the model achieves an average accuracy of 72.0 ± 5.9% when pre-trained on corresponding simulated datasets. With our deep learning approach, the time required to extract meaningful statistics from single-molecule SMFS trials is reduced from a day to under an hour. This work results in SMFS experimental datasets from four important protein molecules crucial to many biological pathways. To support further research, we have made our datasets publicly available and provided a Python-based toolbox (https://github.com/SalapakaLab-SIMBioSys/SMFS-Identification).</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"267 ","pages":"24950-24974"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13484019/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148802820","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}