BMC Medical Informatics and Decision Making最新文献

{"title":"Development of a big data platform for collecting and utilizing clinical information from the Korea Biobank Network.","authors":"Yun Seon Im, Seol Whan Oh, Ki Hoon Kim, Wona Choi, In Young Choi","doi":"10.1186/s12911-025-03192-4","DOIUrl":"10.1186/s12911-025-03192-4","url":null,"abstract":"<p><strong>Background: </strong>Advanced biobanks increasingly focus on supporting biomedical research through the collection and integration of large-scale biological and clinical datasets. This study aimed to develop a big data platform that enables institutions within the Korea Biobank Network (KBN) to efficiently collect and utilize clinical information using a standardized common data model.</p><p><strong>Methods: </strong>The KBN Biobank Research Information and Digital Image Exchange (BRIDGE) platform was developed to allow 43 biobanks to systemically collect and upload electronic medical records and clinical data. This platform was designed to incorporate automated quality verification and basic statistical preprocessing functionalities, allowing users to analyze data efficiently without complex queries. Additionally, a survey was conducted to evaluate user satisfaction with the platform.</p><p><strong>Results: </strong>Through the KBN BRIDGE platform, institutions collected and integrated clinical information on 39 diseases. A total of 136,473 patients' clinical data, collected by institutions between 2021 and 2023, were uploaded to the KBN common data model, including 43,330 serum samples, 33,352 plasma samples, and 22,279 buffy coat samples. A satisfaction survey conducted among 35 institutional data managers reported an average score of 3.5 out of 5 for the platform.</p><p><strong>Conclusions: </strong>This study developed and demonstrated that the KBN BRIDGE platform enables institutions to systematically collect, integrate, and manage large-scale clinical information across multiple biobanks. Furthermore, through data quality management and preprocessing statistical functions, the platform has shown potential for several research applications. Future improvements in system functionality and clinical information utilization can further enhance the platform's utility across various research fields.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"366"},"PeriodicalIF":3.8,"publicationDate":"2025-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12505599/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145249946","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development and external validation of a machine learning-based predictive model for acute kidney injury in hospitalized children with idiopathic nephrotic syndrome.","authors":"Xuejun Yang, De Zhang, Yan Li, Anshuo Wang, Zongwen Chen, Li Wang, Li Xiao, Sijie Yu, Hongxing Chen, Fanghong Zhang, Mo Wang, Shaojun Li, Haiping Yang, Qiu Li","doi":"10.1186/s12911-025-03203-4","DOIUrl":"10.1186/s12911-025-03203-4","url":null,"abstract":"","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"364"},"PeriodicalIF":3.8,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12505573/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145243790","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Design and implementation of a natural language processing system at the point of care: MiADE (medical information AI data extractor).","authors":"Jennifer Jiang-Kells, James Brandreth, Leilei Zhu, Jack Ross, Yogini Jani, Enrico Costanza, Maisarah Amran, Zeljko Kraljevic, Xi Bai, M M N S Dilan, Jayathri Wijayarathne, Ravi Wickramaratne, Folkert W Asselbergs, Richard J B Dobson, Wai Keong Wong, Anoop D Shah","doi":"10.1186/s12911-025-03195-1","DOIUrl":"10.1186/s12911-025-03195-1","url":null,"abstract":"<p><strong>Background: </strong>Well-organised electronic health records (EHR) are essential for high quality patient care, but EHR user interfaces can be cumbersome for entry of structured information, resulting in the majority of information being in free text rather than a structured form. This makes it difficult to retrieve information for clinical purposes and limits the research potential of the data. Natural language processing (NLP) at the point of care has been suggested as a way of improving data quality and completeness, but there is little evidence as to its effectiveness. We sought to generate such evidence by developing an open source, modular, configurable NLP system called MiADE, which is designed to integrate with an EHR. This paper describes the design of MiADE and the deployment at University College London Hospitals (UCLH), and is intended to benefit those who may wish to develop or implement a similar system elsewhere.</p><p><strong>Results: </strong>The MiADE system includes components to extract diagnoses, medications and allergies from a clinical note, and communicate with an EHR system in real time using Health Level 7 Clinical Document Architecture (HL7 CDA) messaging. This enables NLP results to be displayed to a clinician for verification before saving them to the patient's record. MiADE utilises the MedCAT library (part of the Cogstack family of NLP tools) for named entity recognition (NER) and linking to SNOMED CT, as well as context detection. MedCAT models underwent unsupervised and supervised training on patient notes from UCLH, achieving precision of 83.2% (95% CI 77.0, 88.1), and recall of 85.2% (95% CI 79.1, 89.8) for detection of diagnosis concepts. In simulation testing we found that MiADE reduced the time taken for clinicians to enter structured problem lists by 89%. We have commenced a trial implementation of MiADE at UCLH in live clinical use, integrated with the Epic EHR at UCLH.</p><p><strong>Conclusions: </strong>We have developed an open source point of care NLP system and successfully integrated it with the EHR in live clinical use at a major hospital. Simulation testing has shown that our system significantly reduces the time taken for clinicians to enter structured diagnosis codes.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"365"},"PeriodicalIF":3.8,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12506320/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145243763","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AI-driven prognostics in pediatric bone marrow transplantation: a CAD approach with Bayesian and PSO optimization.","authors":"Mahmoud Badawy, Yousry AbdulAzeem, Hanaa ZainEldin, Hossam Magdy Balaha, Amna Bamaqa, Rasha F El-Agamy, Hanaa A Sayed, Mostafa A Elhosseini","doi":"10.1186/s12911-025-03133-1","DOIUrl":"10.1186/s12911-025-03133-1","url":null,"abstract":"<p><p>Bone marrow transplantation (BMT) is a critical treatment for various hematological diseases in children, offering a potential cure and significantly improving patient outcomes. However, the complexity of matching donors and recipients and predicting post-transplant complications presents significant challenges. In this context, machine learning (ML) and artificial intelligence (AI) serve essential functions in enhancing the analytical processes associated with BMT. This study introduces a novel Computer-Aided Diagnosis (CAD) framework that analyzes critical factors such as genetic compatibility and human leukocyte antigen types for optimizing donor-recipient matches and increasing the success rates of allogeneic BMTs. The CAD framework employs Particle Swarm Optimization for efficient feature selection, seeking to determine the most significant features influencing classification accuracy. This is complemented by deploying diverse machine-learning models to guarantee strong and adaptable analytical capabilities. The Adaptive Tree of Parzen Estimators (TPE), a Bayesian optimization technique, is a key component of the proposed methodology. TPE is instrumental in navigating the complex hyperparameter space to optimize model performance, enhancing the overall effectiveness of the ML algorithms. Besides, the study investigates the impact of various scaling techniques on model performance, including L1 normalization and L2 normalization, ensuring that data preprocessing is optimized for the best possible outcomes. The Local Interpretable Model-Agnostic Explanations (LIME) framework is utilized to enhance model transparency and interpretability, bridging the gap between complex AI algorithms and clinical usability. This study uses a comprehensive dataset titled \"Bone Marrow Transplant: Children, which is the analysis's foundation. The findings, validated by ANOVA and T-tests, reveal significant associations between several factors and survival status, highlighting the importance of Donorage, extcGvHD, PLTrecovery, and survival_time, among others. The optimal CAD framework employs a majority voting ensemble of seven finely-tuned machine learning algorithms, achieving remarkable performance metrics. The proposed CAD framework not only achieves high accuracy (98.07%), Balanced Accuracy (98.08%), precision (98.45%), recall (98.02%), specificity (98.14%), F1 score (98.23%), and Intersection over Union (96.53%) but also offers interpretable insights into the classification procedure, contributing significantly as a comprehensive tool for clinicians in the domain of childhood BMT.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"363"},"PeriodicalIF":3.8,"publicationDate":"2025-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12502543/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145237950","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correction: ABiMed: An intelligent and visual clinical decision support system for medication reviews and polypharmacy management.","authors":"Abdelmalek Mouazer, Romain Léguillon, Nada Boudegzdame, Thibaud Levrard, Yoann Le Bars, Christian Simon, Brigitte Séroussi, Julien Grosjean, Romain Lelong, Catherine Letord, Stéfan Darmoni, Matthieu Schuers, Joël Belmin, Karima Sedki, Sophie Dubois, Hector Falcoff, Rosy Tsopra, Jean-Baptiste Lamy","doi":"10.1186/s12911-025-03219-w","DOIUrl":"10.1186/s12911-025-03219-w","url":null,"abstract":"","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"362"},"PeriodicalIF":3.8,"publicationDate":"2025-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12498431/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145237928","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cross- & multi-lingual medication detection: a transformer-based analysis.","authors":"Lisa Raithel, Johann Frei, Philippe Thomas, Roland Roller, Pierre Zweigenbaum, Sebastian Möller, Frank Kramer","doi":"10.1186/s12911-025-03179-1","DOIUrl":"10.1186/s12911-025-03179-1","url":null,"abstract":"<p><p>Extracting specific information, such as medication mentions, from large unstructured medical texts can be challenging, especially when no annotated corpus exists in the target language for training. To overcome this, leveraging existing machine learning models and datasets is essential, and since most pre-trained resources are in English, adopting multilingual approaches can help transferring between languages. In this work, we investigate the usage of a multi-lingual transformer model in a multi-lingual and cross-lingual setting to extract drug names from medical texts using named entity recognition in four European languages: German, English, French, and Spanish. We report the scores obtained by cross-lingual transfer with several published datasets after fine-tuning a multi-lingual model, aiming to create empirical evidence on how the transfer of \"medical\" knowledge between languages can be expected to benefit various language pairs. We further perform a qualitative error analysis and find that the performance on all languages achieves competitive levels. Conversely, erroneous prediction artifacts are introduced by annotation inconsistencies, differences in annotation guidelines and vague entity labels in general.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"359"},"PeriodicalIF":3.8,"publicationDate":"2025-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12490045/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145211746","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correction: Adaptive questionnaires for facilitating patient data entry in clinical decision support systems: methods and application to STOPP/ START v2.","authors":"Jean-Baptiste Lamy, Abdelmalek Mouazer, Romain Léguillon, Romain Lelong, Stéfan Darmoni, Karima Sedki, Sophie Dubois, Hector Falcoff","doi":"10.1186/s12911-025-03218-x","DOIUrl":"10.1186/s12911-025-03218-x","url":null,"abstract":"","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"361"},"PeriodicalIF":3.8,"publicationDate":"2025-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12492715/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145211740","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Interpretable deep learning model and nomogram for predicting pathological grading of PNETs based on endoscopic ultrasound.","authors":"Shuangyang Mo, Yan Zhang, Ning Liu, Rili Jiang, Nan Yi, Yingwei Wang, Huaying Zhao, Shanyu Qin, Huaiyang Cai","doi":"10.1186/s12911-025-03193-3","DOIUrl":"10.1186/s12911-025-03193-3","url":null,"abstract":"","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"360"},"PeriodicalIF":3.8,"publicationDate":"2025-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12492739/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145211793","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Determining patient eligibility for a physical activity referral scheme through EHR data extraction.","authors":"James Rosemeyer, Jennifer L Trilk, Meenu Jindal, John M Brooks, Lia K McNulty, Mark Stoutenberg","doi":"10.1186/s12911-025-03122-4","DOIUrl":"10.1186/s12911-025-03122-4","url":null,"abstract":"<p><strong>Background: </strong>Physical Activity Referral Schemes (PARS) are an effective treatment option for promoting physical activity and positively impacting patient care. Retrospective evaluation of PARS implementation requires identifying the eligible patient population that was reached. However, during a clinic visit, health care providers (HCPs) may decide that a physical activity referral is not appropriate for various reasons, such as acute illness or recent surgical history. Including patient visits with these health conditions in assessing a PARS may lead to an overestimation of patients eligible for referral.</p><p><strong>Objective: </strong>To develop a process that more accurately determines patient eligibility for a physical activity referral when retrospectively extracting patient visit data from the electronic health record (EHR).</p><p><strong>Methods: </strong>Inclusion criteria were developed to identify patient visits potentially eligible for a physical activity referral based on five chronic conditions. These conditions were highlighted during the standardized training that staff received when implementing the PARS. Development of exclusion criteria incorporated exercise contraindications from published literature, input from practicing HCPs, and refinement by a multidisciplinary healthcare team. Inclusion/exclusion criteria were pooled and mapped to International Classification of Diseases, 10th edition, codes and applied to EHR data.</p><p><strong>Results: </strong>A total of 334 referrals (numerator) were identified from the pool of eligible patient visits meeting the inclusion criteria. In calculating the denominator for our reach estimate, 479,536 patient visits were initially extracted from the EHR. Applying the inclusion criteria, 58% of these visits were PARS-eligible (n = 277,515). The eligible visits further decreased by 23% (n = 63,203) with the application of the exclusion criteria, leaving a total of 214,312 PARS-eligible visits (denominator), a 55% reduction from the initial number of total patient visits.</p><p><strong>Conclusion: </strong>Through this multi-step process, we developed a novel approach for retrospectively identifying patient visits eligible for a physical activity referral that can be applied to extracted EHR data for subsequent evaluation. This process can be used by other healthcare systems and researchers in the assessment of PARS. Ongoing refinement of the exclusion criteria is needed to best reflect the eligible population and provide the most accurate estimate of the overall PARS reach.</p><p><strong>Clinical trial registration: </strong>Not applicable.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"357"},"PeriodicalIF":3.8,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12482721/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145191187","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comprehensive survival analysis of breast cancer patients: a bayesian network approach.","authors":"Khaled Toffaha, Mecit Can Emre Simsekler, Aamna Al Shehhi, Andrei Sleptchenko, Aydah AlAwadhi","doi":"10.1186/s12911-025-03197-z","DOIUrl":"10.1186/s12911-025-03197-z","url":null,"abstract":"<p><strong>Background: </strong>Breast cancer is recognized as one of the leading causes of cancer-related deaths globally. A deeper understanding of the complex interactions between clinical, pathological, and treatment-related factors is essential for improving patient outcomes.</p><p><strong>Methods: </strong>Following comprehensive data cleaning and preprocessing, an analysis was performed on a cohort of 1,980 primary breast cancer samples from the METABRIC database. The dataset was divided into a 75/25 training-testing split, and five-fold cross-validation was applied to the training set to mitigate overfitting. Overall and relapse-free survival were then modeled using four fully parametric distributions: Weibull, Exponential, Log-Normal, and Log-Logistic, along with their corresponding Accelerated Failure Time (AFT) forms, to identify significant prognostic features. Competing models were ranked by the Akaike Information Criterion (AIC) and further validated through Quantile-Quantile (QQ) plots. Finally, the probabilistic relationships among the significant factors selected by the optimal AFT models were explored using a Bayesian Belief Network (BBN), whose structure was learned from the training data using multiple score-based algorithms and refined through expert-driven judgment; all conditional probability parameters were estimated using maximum likelihood.</p><p><strong>Results: </strong>The Weibull model provided the best fit for overall survival, whereas the Log-Normal form was optimal for relapse-free survival, each satisfying their respective error-distribution diagnostics. In the hold-out test set, the Bayesian network achieved an Area Under the Curve (AUC) of 0.880 and an F1-score of 0.779. Age at diagnosis, menopausal status, tumor stage, lymph-node burden, and treatment modality were identified as the most influential predictors, and the learned network clarified their direct and mediated effects on both survival endpoints.</p><p><strong>Conclusion: </strong>Through the integration of validated parametric survival models with a data-driven BBN, this study delivers a comprehensive framework for estimating individualized survival probabilities and visualizing the complex probabilistic relationships that characterize high-risk cancer patient profiles. This approach supports evidence-based, personalized breast cancer management and demonstrates the potential for guiding clinical decision-making and adapting to diverse external patient cohorts.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"349"},"PeriodicalIF":3.8,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12482897/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145191190","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}