Journal of Biomedical Informatics最新文献

{"title":"Strategies for detecting and mitigating dataset shift in machine learning for health predictions: A systematic review","authors":"Gabriel Ferreira dos Santos Silva ,&nbsp;Fabiano Novaes Barcellos Filho ,&nbsp;Roberta Moreira Wichmann ,&nbsp;Francisco Costa da Silva Junior ,&nbsp;Alexandre Dias Porto Chiavegatto Filho","doi":"10.1016/j.jbi.2025.104902","DOIUrl":"10.1016/j.jbi.2025.104902","url":null,"abstract":"<div><h3>Objective</h3><div>This review aims to provide a comprehensive overview of the literature on methods and techniques for identifying and correcting dataset shift in machine learning (ML) applications for health predictions.</div></div><div><h3>Methods</h3><div>A systematic search was conducted across PubMed, IEEE Xplore, Scopus, and Web of Science, targeting articles published between January 1, 2019, and March 15, 2025. earch strings combined terms related to machine learning, healthcare, and dataset shift. A total of 32 studies were included, and were evaluated based on dataset shift types addressed, detection and correction strategies used, algorithmic choices, and reported impacts on model performance.</div></div><div><h3>Results</h3><div>The review identified a wide range of dataset shift types, with temporal shift and concept drift being the most commonly addressed. Model-based monitoring and statistical tests were the most frequent detection strategies, while retraining and feature engineering were the predominant correction approaches. Most methods demonstrate moderate interpretability, computational feasibility, and generalizability. However, a lack of standardized performance metrics and external validations limited the comparability of results across studies.</div></div><div><h3>Conclusion</h3><div>While several promising approaches for managing dataset shift in health-related ML models have been proposed, no single method emerged as broadly generalizable across use cases. The implementation of these techniques in real-world clinical workflows remains limited. Future research should prioritize prospective evaluations, subgroup-specific analyses (e.g., by race, age, or geographic region), and integration into clinical decision-support systems to ensure robust and equitable ML deployment in healthcare settings. A structured summary table and conceptual pipeline diagram are provided to support practical adoption.</div></div>","PeriodicalId":15263,"journal":{"name":"Journal of Biomedical Informatics","volume":"170 ","pages":"Article 104902"},"PeriodicalIF":4.5,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144926250","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improving large language models for adverse drug reactions named entity recognition via error correction prompt engineering","authors":"Yunfei Zhang,&nbsp;Wei Liao","doi":"10.1016/j.jbi.2025.104893","DOIUrl":"10.1016/j.jbi.2025.104893","url":null,"abstract":"<div><div>The monitoring and analysis of adverse drug reactions (ADRs ) are important for ensuring patient safety and improving treatment outcomes. Accurate identification of drug names, drug components, and ADR entities during named entity recognition (NER) processes is essential for ensuring drug safety and advancing the integration of drug information. Given that existing medical name entity recognition technologies rely on large amounts of manually annotated data for training, they are often less effective when applied to adverse drug reactions due to significant data variability and the high similarity between drug names. This paper proposes a prompt template for ADR that integrates error correction examples. The prompt template includes: 1. Basic prompts with task descriptions, 2. Annotated entity explanations, 3. Annotation guidelines, 4. Annotated samples for few-shot learning, 5. Error correction examples. Additionally, it integrates complex ADR data from the web and constructs a corpus containing three types of entities (drug name, drug components, and adverse drug reactions) using the Begin, Inside, Outside (BIO) annotation method. Finally, we evaluate the effectiveness of each prompt and compare it with the fine-tuned Large Language Model Meta AI (LLaMA) model and the DeepSeek model. Experimental results show that under this prompt template, the F1 score of GPT-3.5 increased from 0.648 to 0.887, and that of GPT-4 increased from 0.757 to 0.921. It is significantly better than the fine-tuned LLaMA model and DeepSeek model. It demonstrates the superiority of the proposed method, and provides a solid foundation for extracting drug-related entity relationships and building knowledge graphs.</div></div>","PeriodicalId":15263,"journal":{"name":"Journal of Biomedical Informatics","volume":"170 ","pages":"Article 104893"},"PeriodicalIF":4.5,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144926249","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SynthMedic: Utilizing large language models for synthetic discharge summary generation, correction and validation","authors":"Georgi Grazhdanski ,&nbsp;Vasil Vasilev ,&nbsp;Sylvia Vassileva ,&nbsp;Dimitar Taskov ,&nbsp;Izabel Antova ,&nbsp;Ivan Koychev ,&nbsp;Svetla Boytcheva","doi":"10.1016/j.jbi.2025.104906","DOIUrl":"10.1016/j.jbi.2025.104906","url":null,"abstract":"<div><h3>Background and Objective:</h3><div>Synthetic clinical texts can improve transparency and reduce bias and costs when training and evaluating specialized language models in the medical domain. Synthetic texts are freely shareable, as they contain no real patient information, and can be customized for a specific task. The objective of this study is to develop a methodology for generating, validating, and correcting synthetic discharge summaries using LLMs without requiring any real patient data.</div></div><div><h3>Methods:</h3><div>The proposed approach uses an LLM to generate synthetic discharge summaries for specific diseases and standard medical references from Merck Manuals to ground the generation in internationally accepted medical practices. We validate the generated summaries using LLMs as well as by human expert validation. In addition, we propose a method for automatic correction of the generated discharge summaries using Knowledge Graphs to ensure medical factual correctness.</div></div><div><h3>Results:</h3><div>The conducted human expert evaluation shows that the generated synthetic discharge summaries are credible and factually accurate when provided with the medical reference context. The generated summaries achieve a System Usability Score of 94.35% based on a comprehensive rubric evaluated by medical professionals and a score of 93.65% on the Faithfulness metric evaluated by an LLM.</div></div><div><h3>Conclusions:</h3><div>The proposed methodology can be utilized to generate high-quality synthetic discharge summaries for various diseases. The generated synthetic corpus consists of 900 discharge summaries in English representing nine socially significant diseases and is publicly available under an open license. The community can take advantage of the corpus and proposed methodology to train complex machine learning models, helping medical professionals in their daily work without using real patient data.</div></div>","PeriodicalId":15263,"journal":{"name":"Journal of Biomedical Informatics","volume":"170 ","pages":"Article 104906"},"PeriodicalIF":4.5,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145080834","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Overcoming data challenges through enriched validation and targeted sampling to measure whole-person health in electronic health records","authors":"Sarah C. Lotspeich ,&nbsp;Sheetal Kedar ,&nbsp;Rabeya Tahir ,&nbsp;Aidan D. Keleghan ,&nbsp;Amelia Miranda ,&nbsp;Stephany N. Duda ,&nbsp;Michael P. Bancks ,&nbsp;Brian J. Wells ,&nbsp;Ashish K. Khanna ,&nbsp;Joseph Rigdon","doi":"10.1016/j.jbi.2025.104904","DOIUrl":"10.1016/j.jbi.2025.104904","url":null,"abstract":"<div><h3>Objective:</h3><div>The allostatic load index (ALI) is a 10-component composite measure of whole-person health, which reflects the multiple interrelated physiological regulatory systems that underlie healthy functioning. Data from electronic health records (EHR) present a huge opportunity to operationalize the ALI in learning health systems; however, these data are prone to missingness and errors. Validation (e.g., through chart reviews) can provide better-quality data, but realistically, only a subset of patients’ data can be validated, and most protocols do not recover missing data.</div></div><div><h3>Methods:</h3><div>Using a representative sample of 1000 patients from the EHR at an extensive learning health system (100 of whom could be validated), we propose methods to design, conduct, and analyze statistically efficient and robust studies of ALI and healthcare utilization. Employing semiparametric maximum likelihood estimation, we robustly incorporate all available patient information into statistical models. Using targeted design strategies, we examine ways to select the most informative patients for validation. Incorporating clinical expertise, we devise a novel validation protocol to promote EHR data quality and completeness.</div></div><div><h3>Results:</h3><div>Chart reviews uncovered few errors (99% matched source documents) and recovered some missing data through auxiliary information in patients’ charts. On average, validation increased the number of non-missing ALI components per patient from 6 to 7. Through simulations based on preliminary data, residual sampling was identified as the most informative strategy for completing our validation study. Incorporating validation data, statistical models indicated that worse whole-person health (higher ALI) was associated with higher odds of engaging in the healthcare system, adjusting for age.</div></div><div><h3>Conclusion:</h3><div>Targeted validation with an enriched protocol can ensure the quality and promote the completeness of EHR data. Findings from our validation study were incorporated into analyses as we operationalize the ALI as a scalable whole-person health measure that predicts healthcare utilization in the learning health system.</div></div>","PeriodicalId":15263,"journal":{"name":"Journal of Biomedical Informatics","volume":"170 ","pages":"Article 104904"},"PeriodicalIF":4.5,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145000662","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prediction of Single-Cell perturbation response based on Direction-Constrained diffusion Schrödinger Bridge","authors":"Yiqing Luo ,&nbsp;Lin Liu ,&nbsp;Yaxin Fu ,&nbsp;Yi Deng ,&nbsp;Lin Tang","doi":"10.1016/j.jbi.2025.104915","DOIUrl":"10.1016/j.jbi.2025.104915","url":null,"abstract":"<div><h3>Objective</h3><div>Predicting transcriptional responses to external perturbations at the single-cell level is essential for understanding gene regulatory networks, drug discovery, and personalized interventions. The exponential increase in perturbation conditions creates data sparsity, making it difficult to capture dynamic responses and necessitating computational modeling.</div></div><div><h3>Methods</h3><div>We present Direction-Constrained Diffusion Schrödinger Bridge (DC-DSB), a generative framework that learns probabilistic trajectories between unperturbed and post-perturbation distributions by minimizing path-space KL divergence. To enhance conditional control, DC-DSB integrates hierarchical representations derived from experimental variables and biological prior knowledge. We further introduce a direction-constrained conditioning strategy that injects condition signals along the biologically relevant perturbation trajectory, thereby improving modeling quality and training stability.</div></div><div><h3>Results</h3><div>DC-DSB improves expression prediction accuracy and generalization to unseen combinations over baselines. By modeling dynamic expression trajectories and co-expression structures under perturbation, DC-DSB enables the discovery of synergistic and antagonistic gene interactions and supports the progressive reconstruction of regulatory pathways.</div></div><div><h3>Conclusion</h3><div>DC-DSB provides a biologically consistent and generalizable framework for single-cell perturbation modeling. Its trajectory-based and condition-aware architecture overcomes the limitations of static mappings and facilitates downstream analyses in gene regulation and drug discovery.</div></div>","PeriodicalId":15263,"journal":{"name":"Journal of Biomedical Informatics","volume":"170 ","pages":"Article 104915"},"PeriodicalIF":4.5,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145118540","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Resource-efficient instruction tuning of large language models for biomedical named entity recognition","authors":"Hui Liu ,&nbsp;Ziyi Chen ,&nbsp;Peilin Li ,&nbsp;Yuan-Zhi Liu ,&nbsp;Xiangtao Liu ,&nbsp;Ronald X. Xu ,&nbsp;Mingzhai Sun","doi":"10.1016/j.jbi.2025.104896","DOIUrl":"10.1016/j.jbi.2025.104896","url":null,"abstract":"<div><h3>Objective:</h3><div>Large language models (LLMs) have exhibited remarkable efficacy in natural language processing (NLP) tasks, with fine-tuning for Biomedical Named Entity Recognition (BioNER) receiving significant research attention. However, the substantial computational demands associated with fine-tuning large-scale models constrain their development and deployment. Consequently, this study investigates parameter-efficient fine-tuning (PEFT) techniques to optimize LLMs for BioNER under limited computational resources. By leveraging these methods, competitive model performance is maintained while preserving in-domain generalization capability.</div></div><div><h3>Methods:</h3><div>In this study, we employed the PEFT method QLoRA to fine-tune the open-source Llama3.1 model, developing the NERLlama3.1 model specifically designed for the BioNER task. First, an LLM instruction tuning dataset was created using BioNER datasets such as NCBI-disease, BC5CDR-chem, and BC2GM-gene. Next, the Llama3.1-8B model was fine-tuned using the QLoRA method on a single 16GB memory GPU. Furthermore, during the inference phase, we introduced a prompt engineering technique called self-consistency NER prompting (SCNP). This approach leverages the diversity of outputs generated by LLMs to significantly enhance NER performance. Finally, we also developed a multi-task BioNER-capable model, NERLlama3.1-MT, to investigate the capability of fine-tuned LLMs in addressing multi-task BioNER scenarios.</div></div><div><h3>Results:</h3><div>The NERLlama3.1 model achieved F1-scores of 0.8977, 0.9402, and 0.8530 on the NCBI-disease, BC5CDR-chemical, and BG2GM-gene datasets, respectively. Furthermore, when evaluated on previously unseen datasets, it attained F1-scores of 0.6867 on BC5CDR-disease, 0.6800 on NLM-chemical, and 0.8378 on NLM-gene. These results demonstrate that NERLlama3.1 not only outperforms fully fine-tuned LLMs but also exhibits superior in-domain generalization capabilities when compared to the BERT-base model. Additionally, this work represents the first exploration of fine-tuning LLMs for multi-task BioNER.</div></div><div><h3>Conclusion:</h3><div>NERLlama3.1 outperformed LLMs fine-tuned with full parameter updates, despite requiring significantly fewer computational resources. Moreover, it exhibited substantially superior in-domain generalization capabilities compared to traditional pre-trained language models. Its low resource demands, high performance, and strong generalization enhance its applicability and utility across diverse clinical BioNER tasks.</div></div>","PeriodicalId":15263,"journal":{"name":"Journal of Biomedical Informatics","volume":"170 ","pages":"Article 104896"},"PeriodicalIF":4.5,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144926248","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Measuring and visualizing healthcare process variability","authors":"Pengfei Yin ,&nbsp;Abel Armas Cervantes ,&nbsp;Daniel Capurro","doi":"10.1016/j.jbi.2025.104918","DOIUrl":"10.1016/j.jbi.2025.104918","url":null,"abstract":"<div><h3>Importance</h3><div>Understanding factors that contribute to clinical variability in patient care is critical, as unwarranted variability can lead to increased adverse events and prolonged hospital stays. Determining when this variability becomes excessive can be a step in optimizing patient outcomes and healthcare efficiency.</div></div><div><h3>Objective</h3><div>Explore the association between clinical variation and clinical outcomes. This study aims to identify the point in time when the relationship between clinical variation and length of stay (LOS) becomes significant.</div></div><div><h3>Methods</h3><div>This cohort study uses MIMIC-IV, a dataset collecting electronic health records of the Beth Israel Deaconess Medical Center in the United States. We focused on adult patients who underwent elective coronary bypass surgery, generating 847 patient observations. Demographic factors such as age, race, insurance type, and the Charlson Comorbidity Index (CCI) were recorded. We performed a variability analysis where patients’ clinical processes are represented as sequences of events. The data was segmented based on the initial day of recorded activity to establish observation windows. Using a regression analysis, we identified the temporal window where variability’s impact on LOS becomes independently significant.</div></div><div><h3>Result</h3><div>Regression analysis revealed that patients in the top 20 % of the variability distance group experienced an 81 % increase in LOS (95 % CI: 1.72 to 1.91, p &lt; 0.001). Insurance types, such as Medicare and Other, were associated with 18 % (95 % CI: 0.73 to 0.92, p &lt; 0.001) and 21 % (95 % CI: 0.71 to 0.88, p &lt; 0.001) decreases in LOS, respectively. Neither age nor race significantly affected LOS, but a higher CCI was associated with a 3.3 % increase in LOS (95 % CI: 1.02 to 1.05, p &lt; 0.001). These findings indicate that higher variability and CCI significantly influence LOS, with insurance type also playing a crucial role.</div></div><div><h3>Conclusion</h3><div>In the studied cohort, patient journeys with greater variability were associated with longer LOS with a dose–response relationship: the higher the variability, the longer LOS. This study presents a standardized way to measure and visualize variability in clinical processes and measure its impact on patient-relevant outcomes.</div></div>","PeriodicalId":15263,"journal":{"name":"Journal of Biomedical Informatics","volume":"170 ","pages":"Article 104918"},"PeriodicalIF":4.5,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145149215","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparing clinical decision support systems for improving follow-up of abnormal cervical cancer screening test results","authors":"Steven J. Atlas ,&nbsp;Timothy E. Burdick ,&nbsp;Adam Wright ,&nbsp;Wenyan Zhao ,&nbsp;Shoshana Hort ,&nbsp;David G. Aman ,&nbsp;Mathan Thillaiyapillai ,&nbsp;E. John Orav ,&nbsp;Amy J. Wint ,&nbsp;Rebecca E. Smith ,&nbsp;Katherine L. Gallagher ,&nbsp;Molly L. Housman ,&nbsp;Frank Y. Chang ,&nbsp;Courtney J. Diamond ,&nbsp;Li Zhou ,&nbsp;Jennifer S. Haas ,&nbsp;Anna N.A. Tosteson","doi":"10.1016/j.jbi.2025.104908","DOIUrl":"10.1016/j.jbi.2025.104908","url":null,"abstract":"<div><h3>Background</h3><div>Many individuals with abnormal cervical cancer screening test results do not receive timely follow-up care. Clinical decision support systems (CDSS) to improve follow-up are challenged by difficulty identifying clinical elements and applying complex guideline recommendations. As part of a multisite trial, two CDSS models were implemented: one used natural language processes to evaluate extracted data outside of the electronic health record (EHR) (System A); the other used commercial EHR functionality using LOINC-defined result fields (System B). This secondary analysis compared the accuracy and trial outcomes among sites using these two CDSS models.</div></div><div><h3>Methods</h3><div>Primary care clinics (32 in System A and 12 in System B) were randomly assigned to usual care, CDSS alone, or CDSS with patient outreach with or without navigation. CDSS identified individuals with overdue abnormal screening results and specified the recommended follow-up and time interval. CDSS accuracy was assessed by manual chart review. Patient outreach consisted of portal/mailed letters plus a single phone call. Navigation included one or more phone calls to address barriers to care. Completion of recommended follow-up at 120 days after enrollment was the primary outcome. Clinic was the unit of randomization, and the patient was the unit of analysis.</div></div><div><h3>Results</h3><div>Between October 2020 and December 2021, 2596 patients with abnormal results were identified by the CDSS. CDSS true positives were 61.3 % in System A and 70.4 % in System B. CDSS alone versus usual care did not improve outcomes in either system. CDSS with patient outreach with or without navigation versus usual care significantly increased follow-up rates in System A (38.2 % or 37.2 % vs 23.5 %, p &lt; 0.001) and System B (25.4 % or 23 % vs. 19.7 %, p = 0.044).</div></div><div><h3>Conclusions</h3><div>Two CDSS models developed to identify overdue abnormal cervical cancer screening test results had moderate accuracy. Both models with patient outreach with or without navigation – but not CDSS alone – increased recommended follow-up. Future CDSS for cervical cancer screening may be improved with open-source tools developed in public–private partnerships.</div></div>","PeriodicalId":15263,"journal":{"name":"Journal of Biomedical Informatics","volume":"170 ","pages":"Article 104908"},"PeriodicalIF":4.5,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145040048","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"PCGMMF: a prediction method for breast cancer prognostic recurrence and metastasis risk based on enhanced multimodal feature fusion","authors":"Wei Du ,&nbsp;Liang Gao ,&nbsp;Xianhua Xu ,&nbsp;Yuhua Yao ,&nbsp;Zhong Li","doi":"10.1016/j.jbi.2025.104907","DOIUrl":"10.1016/j.jbi.2025.104907","url":null,"abstract":"<div><h3>Background</h3><div>Breast cancer is a highly heterogeneous disease with high morbidity and mortality rates. Despite the availability of various treatments, a significant number of patients still face a high probability of recurrence or metastasis, which severely impacts their survival status. Traditional prognostic methods based on single-modality data and machine learning algorithms often fail to adequately capture the complex biological relationships and heterogeneous characteristics of breast cancer, leading to suboptimal prognostic performance. Therefore, there is an urgent need for a more accurate and effective method to predict the risk of recurrence and metastasis in breast cancer prognosis.</div></div><div><h3>Methods</h3><div>In this study, we propose a novel method termed PCGMMF for breast cancer prognostic analysis. This method integrates histopathological images, clinical data, gene expression data, and DNA methylation data through multimodal fusion. We leverage a pre-trained Vision-LSTM model based on transfer learning to extract features from histopathological images. Additionally, we design a comprehensive feature selection strategy that includes support vector machine (SVM), Mantel test, and correlation analysis to filter features from gene expression data and DNA methylation data. Furthermore, to address the high heterogeneity of breast cancer and the independence and intersectionality of multimodal features, we propose a bidirectional attention and self-attention based enhanced multimodal feature fusion module called BSAMF.</div></div><div><h3>Results</h3><div>Through a series of experiments, we evaluate the performance of PCGMMF. When predicting the recurrence and metastasis risk of breast cancer prognosis, PCGMMF achieves an accuracy of 0.903 and an AUC value of 0.924, outperforming other state-of-the-art methods. Furthermore, we provide an interpretability analysis of highly significant regions from histopathological images, which can serve as a reference for clinical practice.</div></div><div><h3>Conclusion</h3><div>PCGMMF offers a robust and innovative solution for breast cancer prognostic analysis by effectively integrating multimodal data and utilizing advanced deep learning techniques. It can effectively conduct breast cancer prognostic analysis and provide significant references for personalized precision treatment and clinical practice.</div></div>","PeriodicalId":15263,"journal":{"name":"Journal of Biomedical Informatics","volume":"170 ","pages":"Article 104907"},"PeriodicalIF":4.5,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145040243","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An optimized code-free AI approach for efficient and accurate literature screening in bone organoid research","authors":"Jiaxu Zheng ,&nbsp;Janak Lal Pathak ,&nbsp;Shangyan Li ,&nbsp;Anqi Li ,&nbsp;Jiechun Fang ,&nbsp;Zonghua Li ,&nbsp;Zhisheng Bi ,&nbsp;Yin Xiao ,&nbsp;Qing Zhang","doi":"10.1016/j.jbi.2025.104911","DOIUrl":"10.1016/j.jbi.2025.104911","url":null,"abstract":"<div><div>The exponential growth of biomedical literature has rendered traditional screening methods inefficient and unsustainable, making knowledge discovery akin to finding a needle in a haystack. While recent advances in artificial intelligence (AI) offer new opportunities for rapid literature retrieval, many clinicians and researchers lack familiarity with these tools. In this study, we optimized LitSuggest, a user-friendly, code-free AI-based literature screening system, and established a standardized operational workflow. Using the field of organoid-based bone tissue engineering as a case study, the optimized system achieved an accuracy of 98.83%, precision of 76.19%, recall of 83.33%, and an F1-score of 79.60%, while reducing manual screening workload by over 90%. Furthermore, we innovatively integrated correlation scoring into literature analysis, revealing that China and the United States are leading contributors to bone organoid regeneration research, and that complex and genetic disease organoid models hold significant research potential. This AI-driven approach enables researchers to focus on high-value literature, improving efficiency while guiding future research in bone organoid regeneration and broader biomedical fields.</div></div>","PeriodicalId":15263,"journal":{"name":"Journal of Biomedical Informatics","volume":"170 ","pages":"Article 104911"},"PeriodicalIF":4.5,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145040290","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}