BMC Medical Informatics and Decision Making最新文献

{"title":"LabVis: usability testing of a prototype tool for integrating timeline graphs and clinical notes.","authors":"Torbjørn Torsvik, Andreas Brun, Bjørn Ståle Benjaminsen, Aslak Steinsbekk","doi":"10.1186/s12911-025-03173-7","DOIUrl":"10.1186/s12911-025-03173-7","url":null,"abstract":"","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"337"},"PeriodicalIF":3.8,"publicationDate":"2025-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12465496/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145173671","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":"Leveraging data-driven insights for esophageal and gastric cancer diagnosis.","authors":"Shafaq Zahoor, Irfanud Din, Zaib Unnisa, Sajid Iqbal, Roobaea Alroobaea, Oumaima Saidani, Foong Law","doi":"10.1186/s12911-025-03170-w","DOIUrl":"10.1186/s12911-025-03170-w","url":null,"abstract":"","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"338"},"PeriodicalIF":3.8,"publicationDate":"2025-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12465892/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145173764","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 machine learning model for low bone density screening in older adults using demographic and anthropometric data: findings from 2005 to 2020 NHANES.","authors":"Weiyan Huang, Qimou Pan, Jiewei Peng, Yufeng Wu, Dawei Gao","doi":"10.1186/s12911-025-03177-3","DOIUrl":"10.1186/s12911-025-03177-3","url":null,"abstract":"","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"339"},"PeriodicalIF":3.8,"publicationDate":"2025-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12465568/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145173757","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":"PilOT-Measure: a mobile 3D depth sensing application to support accurate and efficient clinician-led home-based falls risk assessments.","authors":"Zear Ibrahim, Arthur G Money, Anita Atwal, Georgia Spiliotopoulou","doi":"10.1186/s12911-025-03149-7","DOIUrl":"10.1186/s12911-025-03149-7","url":null,"abstract":"<p><strong>Background: </strong>An aging global population, coupled with high levels of assistive equipment abandonment, has propelled increases in falls-related injuries at home. Equipment abandonment occurs, in-part, due to inaccurate measurements of the patient's home taken during the falls risk assessment process. There is an urgent need to explore the value of new digital mobile technologies to help clinicians to take more efficient and effective measurements of patient's home, thereby enhancing the efficacy of falls risk assessments and potentially minimising equipment abandonment.</p><p><strong>Aim: </strong>The aim of this study is to present and evaluate the accuracy and efficiency of PilOT-Measure, a digital mobile 3D depth-sensor-enabled measurement guidance application for use by clinicians carrying out falls risk assessments.</p><p><strong>Methods: </strong>Twenty-one trainee and registered Occupational Therapists took part in this repeated-measures, mixed methods study to evaluate measurement accuracy, task completion time, and overall system usability and user perceptions of the application.</p><p><strong>Results: </strong>For measurement accuracy, PilOT-Measure outperformed current state of the art handheld tape measure and paper-based measurement guidance booklet. For accuracy consistency, the handheld tape measure and booklet was more consistently accurate for six out of 11 cases. However, PilOT-Measure tended to facilitate significantly faster task completion times, suggesting potential task efficiency benefits. In terms of usability, participants favoured PilOT-Measure and saw potential to reduce administrative tasks and support joint decision-making. Concerns about marker placement on reflective surfaces and patient privacy were noted.</p><p><strong>Conclusions: </strong>This study highlights the positive role that mobile depth-sensing technologies can potentially play in improving the efficiency and accuracy of falls risk assessments, hence, reducing levels of equipment abandonment and falls related injuries at home. Future work will focus on improving marker placement, measurement accuracy, and accuracy consistency and explore the potential of using PilOT-Measure as a falls risk patient self-assessment tool.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"332"},"PeriodicalIF":3.8,"publicationDate":"2025-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12462305/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145136528","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: Analysis of endometrial thickness patterns and pregnancy outcomes considering 12,991 fresh IVF cycles.","authors":"ShuJie Liao, Renjie Wang, Cheng Hu, Wulin Pan, Wei Pan, Dongyang Yu, Lei Jin","doi":"10.1186/s12911-025-03185-3","DOIUrl":"10.1186/s12911-025-03185-3","url":null,"abstract":"","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"331"},"PeriodicalIF":3.8,"publicationDate":"2025-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12462213/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145136534","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":"Assisting clinical diagnosis with interpretable fuzzy probabilistic modelling.","authors":"Giulia Capitoli, Marco S Nobile, Emma L Ambags, Vincenzo L'Imperio, Michele Provenzano, Pietro Liò","doi":"10.1186/s12911-025-03183-5","DOIUrl":"10.1186/s12911-025-03183-5","url":null,"abstract":"","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 Suppl 3","pages":"330"},"PeriodicalIF":3.8,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12439376/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145069279","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":"FanFAIR: sensitive data sets semi-automatic fairness assessment.","authors":"Chiara Gallese, Teresa Scantamburlo, Luca Manzoni, Simone Giannerini, Marco S Nobile","doi":"10.1186/s12911-025-03184-4","DOIUrl":"10.1186/s12911-025-03184-4","url":null,"abstract":"","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 Suppl 3","pages":"329"},"PeriodicalIF":3.8,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12427094/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145051696","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":"User experience study to evaluate a clinical decision support system prototype supporting continuous kidney replacement therapy in a simulated ICU environment.","authors":"L-M Kunz, M Metzger, C Schaefer, R Pohlmeier, J Petrovic Vorkapic, Michael Nosch","doi":"10.1186/s12911-025-03165-7","DOIUrl":"10.1186/s12911-025-03165-7","url":null,"abstract":"<p><strong>Background: </strong>The increasing amount of data routinely collected on ICUs poses a challenge for clinicians which is aggravated with data-heavy therapies like Continuous Kidney Replacement Therapy (CKRT). We developed the CKRT Supporting Software Prototype (CKRT-SSP), a clinical decision support system for use before, during and after CKRT. The aim of this user experience (UX) study was to prospectively evaluate CKRT-SSP in terms of usability, user experience, and workload in a simulated ICU setting.</p><p><strong>Methods: </strong>We simulated CKRT treatments in a fully equipped single patient room in the ICU and evaluated CKRT-SSP using validated questionnaires: System Usability Scale (SUS) and User Experience Questionnaire (UEQ). Furthermore, a modified NASA-TLX (task load index) compared the workload before and after using CKRT-SSP. Twelve clinicians and nurses participated in this study.</p><p><strong>Results: </strong>The SUS reached a median value of 87.5 for CKRT-SSP, reflecting excellent usability. In the UEQ, CKRT-SSP scored clearly positive in the attractiveness dimension and the three task-related dimensions of clarity, efficiency, and dependability (95% CI fully > 0.8). For the two non-task-related dimensions, stimulation and novelty, there was a positive trend (mean > 0.8, lower limit of 95% CI < 0.8). The modified NASA-TLX suggests a trend to less total workload with CKRT-SSP which mainly is attributable to less physical demand and less effort.</p><p><strong>Conclusion: </strong>CKRT-SSP is a promising tool for improving the workload in ICUs and the specific application of CKRT. We obtained valuable insights for further user-centric development.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"328"},"PeriodicalIF":3.8,"publicationDate":"2025-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12424209/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145032725","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: Discovery of genes positively modulating treatment effect using potential outcome framework and Bayesian update.","authors":"Youngkeun Lee, Jisoo Kim, Sung Wook Seo","doi":"10.1186/s12911-025-03141-1","DOIUrl":"10.1186/s12911-025-03141-1","url":null,"abstract":"","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"327"},"PeriodicalIF":3.8,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12418669/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145022848","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":"Comparing supervised machine learning algorithms for the prediction of partial arterial pressure of oxygen during craniotomy.","authors":"Andrea S Gutmann, Maximilian M Mandl, Clemens Rieder, Dominik J Hoechter, Konstantin Dietz, Benjamin P Geisler, Anne-Laure Boulesteix, Roland Tomasi, Ludwig C Hinske","doi":"10.1186/s12911-025-03148-8","DOIUrl":"10.1186/s12911-025-03148-8","url":null,"abstract":"<p><strong>Background and objectives: </strong>Brain tissue oxygenation is usually inferred from arterial partial pressure of oxygen (paO₂), which is in turn often inferred from pulse oximetry measurements or other non-invasive proxies. Our aim was to evaluate the feasibility of continuous paO₂ prediction in an intraoperative setting among neurosurgical patients undergoing craniotomies with modern machine learning methods.</p><p><strong>Methods: </strong>Data from routine clinical care of lung-healthy neurosurgical patients were extracted from databases of the respective clinical systems and normalized. We used recursive feature elimination to identify relevant features for the prediction of paO₂. Six machine learning regression algorithms (gradient boosting, k-nearest neighbors, random forest, support vector, neural network, linear model with stochastic gradient descent) and a multivariable linear regression were then tuned and fitted to the selected features. A performance matrix consisting of standard deviation of absolute errors (σ_ae), mean absolute percentage error (MAPE), adjusted R², root mean squared error (RMSE), mean absolute error (MAE) and Spearman's ρ was finally computed based on the test set, and used to compare and rank each algorithm.</p><p><strong>Results: </strong>We analyzed N = 4,581 patients with n = 17,821 observations. Between 5 and 22 features were selected from the analysis of the training dataset comprising 3,436 patients with 13,257 observations. The best algorithm, a regularized linear model with stochastic gradient descent, could predict paO₂ values with σ_ae = 86.4 mmHg, MAPE = 16 %, adjusted R² = 0.77, RMSE = 44 mmHg and Spearman's ρ = 0.83. Further improvement was possible by calibrating the algorithm with the first measured paO₂/FiO₂ (p/F) ratio during surgery.</p><p><strong>Conclusion: </strong>PaO₂ can be predicted by perioperative routine data in neurosurgical patients even before blood gas analysis. The prediction improves further when including the first measured p/F ratio, realizing quasi-continuous paO₂ monitoring.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"326"},"PeriodicalIF":3.8,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12406590/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144991631","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}