BMC Medical Informatics and Decision Making最新文献

{"title":"Machine learning techniques in hepatic encephalopathy: a scoping review.","authors":"Fatemeh Kiani, Farkhondeh Asadi, Azamossadat Hosseini, Shahabedin Rahmatizadeh, Farhang Hosseini, Behzad Kiani","doi":"10.1186/s12911-025-03168-4","DOIUrl":"10.1186/s12911-025-03168-4","url":null,"abstract":"","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"323"},"PeriodicalIF":3.8,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12403440/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144944000","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":"Can artificial intelligence with multimodal imaging outperform traditional methods in predicting age-related macular degeneration progression? A systematic review and exploratory meta-analysis.","authors":"Kai-Yang Chen, Hoi-Chun Chan, Chi-Ming Chan","doi":"10.1186/s12911-025-03119-z","DOIUrl":"10.1186/s12911-025-03119-z","url":null,"abstract":"<p><strong>Purpose: </strong>Age-related macular degeneration (AMD) is a leading cause of irreversible vision loss, and its prevalence is expected to rise with aging populations. Early prediction of AMD progression is critical for effective management. This systematic review and meta-analysis evaluate the accuracy, sensitivity, and specificity of artificial intelligence (AI) algorithms in in detecting and predicting progression of AMD.</p><p><strong>Methods: </strong>Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, a systematic review and meta-analysis were conducted from inception to February 7th, 2025. We included five studies that assessed the performance of AI algorithms in predicting AMD progression using multimodal imaging. Data on accuracy, sensitivity, and specificity were extracted, and meta-analysis was performed using Comprehensive Meta-Analysis software version 3.7. Heterogeneity was assessed using the I² statistic.</p><p><strong>Results: </strong>Of the five studies, AI models demonstrated superior accuracy (mean difference: 0.07, 95% CI: 0.07, 0.07; p < 0.00001) and sensitivity (mean difference: 0.08, 95% CI: 0.08, 0.08; p < 0.00001) compared to retinal specialists. Specificity also showed a minimal but significant advantage for AI (mean difference: 0.01, 95% CI: 0.01, 0.01; p < 0.00001). Importantly, heterogeneity was minimal to absent across all analyses (I² = 0-0.42%), supporting the reliability and consistency of pooled findings.</p><p><strong>Conclusion: </strong>AI algorithms outperform retinal specialists in predicting AMD progression, particularly in accuracy and sensitivity. These findings support the potential of AI in AMD prediction; however, given the limited number of included studies, the results should be interpreted as exploratory and in need of validation through future large-scale, prospective studies.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"321"},"PeriodicalIF":3.8,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12400700/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144943966","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":"Enhancing privacy protection of physical examination data through synthetic algorithms based on differential privacy.","authors":"Weili Zhang, Ran Liu, Xinyi Zhu, Xiaojin Yu, Depeng Jiang","doi":"10.1186/s12911-025-03109-1","DOIUrl":"10.1186/s12911-025-03109-1","url":null,"abstract":"<p><strong>Background: </strong>Health physical examinations play a crucial role in early detection of cancer and chronic disease. However, privacy concerns limit the utilization of this kind of data for health interventions and research. Synthetic data methods based on differential privacy are increasingly used to create complete datasets that protect privacy while enabling data analysis and result interpretation. Hence, the use of synthetic algorithms based on differential privacy for privacy protection of physical examination data is a promising research direction.</p><p><strong>Methods: </strong>Three synthetic algorithms, PrivBayes, PeGS, and DP-Gibbs were used to generate complete synthetic datasets that adhere to differential privacy standards using physical examination data composed of categorical data, which compared with the existing algorithm Private-PGM.</p><p><strong>Results: </strong>Compared with the existing algorithm, DP-Gibbs can provide privacy preserving capacity of 4.686 (ε = 0.5), while the existing algorithm only with 2.012. In addition, DP-Gibbs provides 0.620 of precision, 0.539 of F1-score, 0.342 of Kappa Coefficient, and 0.765 of AUC-score. The corresponding statistical results of existing algorithm are 0.520, 0.321, 0.188 and 0.695.</p><p><strong>Conclusions: </strong>The main contributions of this study are the exploration of combination models incorporating different noise forms and Bayesian synthetic algorithms, alongside a comparative analysis against existing algorithms. This study explored the balance between privacy protection and data utility under different levels of privacy protection, and DP-Gibbs offers more stable technical support for de-identifying physical examination data prior to sharing and analysis, which realized the mining and application of a wider range of medical data under the requirements of privacy protection. By leveraging this effective privacy protection technique, clinical researchers can extract valuable insights on diseases and population health from the physical examination data without the risk of leaking private information.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"324"},"PeriodicalIF":3.8,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12403299/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144944054","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":"Comparison of the readability of ChatGPT and Bard in medical communication: a meta-analysis.","authors":"Daphne E DeTemple, Timo C Meine","doi":"10.1186/s12911-025-03035-2","DOIUrl":"10.1186/s12911-025-03035-2","url":null,"abstract":"<p><strong>Background: </strong>To synthesize the results of various studies on the readability of ChatGPT and Bard in medical communication.</p><p><strong>Methods: </strong>Systemic literature research was conducted in PubMed, Ovid/Medline, CINAHL, Web-of-Science, Scopus and GoogleScholar to detect relevant publications (inclusion criteria: original research articles, English language, medical topic, ChatGPT-3.5/-4.0, Bard/Gemini, Flesch Reading Ease Score (FRE), Flesch Kincaid Grade Level (FKGL)). Study quality was analyzed using modified Downs-and-Black checklist (max. 8 points), adapted for studies on large language model. Analysis was performed on text simplification and/or text generation with ChatGPT-3.5/-4.0 versus Bard/Gemini. Meta-analysis was conducted, if outcome parameter was reported ≥ 3 studies. In addition, subgroup-analyses among different chatbot versions were performed. Publication bias was analyzed.</p><p><strong>Results: </strong>Overall, 59 studies with 2342 items were analyzed. Study quality was limited with a mean of 6 points for FRE and 7 points for FKGL. Meta-analysis of text simplification for FRE between ChatGPT-3.5/-4.0 and Bard/Gemini was not significant (mean difference (MD):5.03; 95%-confidence interval (CI):-20.05,30.11; p = 0.48). FKGL of simplified texts of ChatGPT-3.5/-4.0 and Bard/Gemini was borderline significant (MD:-1.59; CI:-3.15,-0.04; p = 0.05) and subgroup-analysis between ChatGPT-4.0 and Bard was not significant (MD:-1.68; CI:-3.53,0.17; p = 0.07). Focused on text acquisition, MD for FRE and FKGL of studies on ChatGPT-3.5/-4.0- and Bard/Gemini-generated texts were significant (MD:-10.36; CI:-13.08,-7.64; p < 0.01 / MD:1.62; CI:1.09,2.15; p < 0.01). Subgroup-analysis of FRE was significant for ChatGPT-3.5 vs. Bard (MD:-16.07, CI:-24.90,-7.25; p < 0.01), ChatGPT-3.5 vs. Gemini (MD:-4.51; CI:-8.73,-0.29: p = 0.04), ChatGPT-4.0 vs. Bard (MD:-12.01, CI:-16.22,-7.81; p < 0.01) and ChatGPT-4.0 vs. Gemini (MD:-7.91, CI:-11.68,-4.15; p < 0.01). Analysis of FKGL in the subgroups was significant for ChatGPT-3.5 vs. Bard (MD:2.85, CI:1.98,3.73; p < 0.01), ChatGPT-3.5 vs. Gemini (MD:1.21, CI:0.50,1.93; p < 0.01) and ChatGPT-4.0 vs. Gemini (MD:1.95, CI:1.05,2.86; p < 0.01), but it was not significant for ChatGPT-4.0 vs. Bard (MD:0.64, CI:-0.46,1.74; p = 0.24). Egger's test was significant in text generation for FRE and FKGL (p < 0.01 / p < 0.01) and in subgroup ChatGPT-4.0 vs. Bard and ChatGPT-4.0 vs. Gemini (p < 0.01 / p = 0.02) for FRE as well as in subgroups ChatGPT-3.5 vs. Bard and ChatGPT-4.0 vs. Gemini for FKGL (p < 0.01 / p < 0.01).</p><p><strong>Conclusion: </strong>Readability of spontaneously generated texts by Bard/Gemini was slightly superior compared to ChatGPT-3.5/-4.0 and readability of simplified texts by ChatGPT-3.5/-4.0 tended to be improved compared to Bard. Results are limited due study quality and publication bias. Standardized reporting could improve study quality and chatbot development.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"325"},"PeriodicalIF":3.8,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12403948/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144943940","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":"Developing multimodal cervical cancer risk assessment and prediction model based on LMIC hospital patient card sheets and histopathological images.","authors":"Kelebet Chane Jemane, Muktar Bedaso Kuyu, Geletaw Sahle Tegenaw","doi":"10.1186/s12911-025-03174-6","DOIUrl":"10.1186/s12911-025-03174-6","url":null,"abstract":"","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"322"},"PeriodicalIF":3.8,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12400732/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144944057","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":"Edge computing with federated learning for early detection of citric acid overdose and adjustment of regional citrate anticoagulation.","authors":"Saroj Mali, Niroj Mali, Feng Zeng, Ling Zhang","doi":"10.1186/s12911-025-03130-4","DOIUrl":"https://doi.org/10.1186/s12911-025-03130-4","url":null,"abstract":"<p><p>Regional citrate anticoagulation (RCA) is critical for extracorporeal anticoagulation in continuous renal replacement therapy done at the bedside. To make patients' data more secure and to help with computer-based monitoring of dosages, we suggest a system that uses machine learning. This system will give early alerts about citric acid overdose and advise changes to how much citrate and calcium gluconate are infused into the patient's body. Citric acid overdose causes significant clinical risks, emphasizing the need for better adaptable anticoagulation procedures that can respond quickly. The study puts forward a new structure that uses edge computing and federated learning to make better citrate anticoagulation procedures. We proposed the resource-aware Federated Learning with Dynamic Client Selection (RAFL-Fed) algorithm in our method. In this setup, every client takes part by training a local model locally and then sending its outcome to a main server. The algorithm chooses clients for each training session depending on their computing resources, which keeps things efficient and scalable. The server collects the client inputs using weighted averages to update the global model. This step is performed repeatedly across many communication cycles, letting the system adjust to changing data trends from different locations. We put RAFL-Fed to the test on the MIMIC-IV dataset, and it outperformed other methods, getting a high accuracy of 0.9615 (IID) and 0.9571 (Non-IID), also with the lowest loss values being 0.2625 and 0.2469 in that order. It also noted the best MAE at 0.1731 (Non-IID) and a bit higher at 0.2081 (IID). Along with the high sensitivity at 0.9968, specificity stood strong as well, measuring 0.9449, plus latency was only 0.123s, which shows how effective it is for early detection of citric acid overdose as well as adjusting in real-time in the regional citrate anticoagulation process. The proposed method shows a promising solution for the real-time monitoring and adjustment of citrate anticoagulation regimens, greatly enhancing patient data security and treatment effectiveness in clinical settings. This method signifies a significant advancement in handling anticoagulation therapy.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"320"},"PeriodicalIF":3.8,"publicationDate":"2025-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12398048/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144944021","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":"New ICD-11 features for coding late sequelae and chronic post-procedural conditions.","authors":"Danielle A Southern, Bastien Boussat, Marie-Annick Le Pogam, William A Ghali","doi":"10.1186/s12911-025-03121-5","DOIUrl":"https://doi.org/10.1186/s12911-025-03121-5","url":null,"abstract":"<p><p>There are many clinical circumstances in life where people live with chronic conditions (or states) that arose from either (1) a prior clinical diagnosis (e.g. a stroke) or (2) a prior healthcare-related event or medical procedure. Unfortunately, capturing such concepts is not straightforward in coded health data. This paper describes the coding rubric for sequelae (also often referred to as 'late effects') in the new ICD-11 coding system and some clinical coding examples. Earlier versions of ICD were constrained, in all but a few exceptions, by the need to combine all aspects of a clinical scenario into a single code. ICD-11 permits the clustering (postcoordination) of multiple codes to describe multifaceted clinical scenarios. This article features both precoordinated (single code) and postcoordinated (multi-code) descriptions of late effect situations where a prior health problem is the remote cause of current symptoms or conditions - i.e. sequelae. The late effect of a prior health problem rubric is yet another example of enhanced ICD-11 features that will improve future health information systems.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"21 Suppl 6","pages":"388"},"PeriodicalIF":3.8,"publicationDate":"2025-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12398000/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144943995","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 validation of a deep learning model for early detection and screening of diabetic retinopathy.","authors":"Feifei Cao, Xitong Guo, Meng Li, ShuJu Li, Xin Peng","doi":"10.1186/s12911-025-03117-1","DOIUrl":"https://doi.org/10.1186/s12911-025-03117-1","url":null,"abstract":"<p><p>Early diagnosis and screening of diabetic retinopathy (DR) are crucial for reducing medical burdens and conserving healthcare resources. This study introduces an advanced AI-assisted recognition system designed to enhance the detection of DR lesions through innovative automatic learning methods. Central to our approach are agnostic text instruction templates, which facilitate zero-shot DR detection by integrating text embeddings with visual information. Our system performs comprehensive lesion detection by leveraging similarity mapping at both the image and patch levels, enabling it to identify a wide range of diabetic retinopathy (DR) lesions without the need for extensive annotated data. This AI-assisted system distinguishes itself from traditional fully supervised models and few-shot learning approaches by addressing the complexities of DR image annotation and safeguarding patient privacy. To validate the system's effectiveness, we conducted extensive experiments across five internal and publicly available test sets, as well as an external test set captured using smartphone devices. Our evaluation involved performance analysis of various pre-training methods, including detailed patch-level visualizations and t-SNE clustering techniques to assess the quality of feature embeddings. The results of our zero-shot experiments reveal that our system outperforms conventional transfer learning-based DR detection methods. This superiority is evident in both the pre-training and testing phases, showcasing the system's ability to deliver accurate and reliable DR lesion detection while circumventing the limitations of traditional approaches.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"315"},"PeriodicalIF":3.8,"publicationDate":"2025-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12382226/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144944060","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":"Symptoms affecting the development of diabetes: analysis of risk factors with data mining.","authors":"Ali Vasfi Aglarci, Feridun Karakurt","doi":"10.1186/s12911-025-03159-5","DOIUrl":"https://doi.org/10.1186/s12911-025-03159-5","url":null,"abstract":"<p><strong>Objective: </strong>Diabetes is one of the most common chronic health threats worldwide. Early detection of diabetes is difficult and diagnosis and treatment processes can be costly. Data mining techniques offer powerful tools for predictive analysis and knowledge extraction from large data sets. This study aims to identify symptoms that collectively influence the development of diabetes by data mining and identify risk parameters for early detection.</p><p><strong>Materials and methods: </strong>The study uses a dataset of 520 patient records collected from Sylhet Diabetes Hospital in Sylhet, Bangladesh. This dataset is based on real-world data from the UCI Machine Learning Repository. The Apriori algorithm, which is widely used in data mining, was applied to analyze the symptoms associated with diabetes using association analysis. The algorithm analyzed the relationships between symptoms based on support, confidence and lift values.</p><p><strong>Results: </strong>The analysis identified eight key symptoms that significantly contribute to diabetes risk when they occur together: gender, polyuria, polydipsia, sudden weight loss, weakness, blurred vision, partial paresis and obesity. The co-occurrence of these symptoms increases the likelihood of developing diabetes by 1.63 times. These findings emphasize the importance of assessing symptoms collectively rather than in isolation.</p><p><strong>Conclusion: </strong>The results of the study emphasize the importance of individuals at risk of diabetes and healthcare professionals to monitor these symptoms and take necessary precautions. The study shows that association rule mining, especially the Apriori algorithm, is a valuable tool for identifying symptom associations and facilitating early diabetes detection. The findings will contribute to early detection of diabetes and prevention of complications related to the disease through simple symptom analysis.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"319"},"PeriodicalIF":3.8,"publicationDate":"2025-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12392476/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144944016","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":"A heart failure classification model from radial artery pulse wave using LSTM neural networks.","authors":"Yi Lyu, Wen-Yue Huang, Hai-Mei Wu, Jing Hong, Yi-Qin Wang, Hai-Xia Yan, Jin Xu","doi":"10.1186/s12911-025-03167-5","DOIUrl":"https://doi.org/10.1186/s12911-025-03167-5","url":null,"abstract":"<p><strong>Background: </strong>Heart failure (HF) represents a pressing global health issue demanding innovative and accessible approaches for early detection. Non-invasive, rapid, and cost-effective techniques utilizing deep learning (DL) hold significant promise for addressing this challenge.</p><p><strong>Methods: </strong>This study included 462 participants categorized into healthy, coronary artery disease (CAD), and HF groups. Raw radial artery pulse wave data underwent preprocessing, including denoising, normalization, and SMOTE-based balancing. Four deep learning algorithms adept at handling sequential data - Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), Gated Recurrent Unit (GRU), and Bidirectional Long Short-Term Memory (Bi-LSTM) - were subsequently applied and evaluated for their classification performance. A 10-fold cross-validation strategy was employed to ensure a robust evaluation of model performance and stability.</p><p><strong>Results: </strong>To robustly evaluate performance and stability, a 10-fold cross-validation was performed. The LSTM model yielded the highest mean accuracy (0.8595 ± 0.0522) and demonstrated strong performance across other key metrics, including a high Area Under the Curve, establishing it as the most effective model in this study. To enhance model interpretability, the SHAP (SHapley Additive exPlanations) framework was utilized to determine global feature importance and explain the final LSTM model's predictions.</p><p><strong>Conclusion: </strong>Our findings strongly suggest that an LSTM-based model analyzing radial artery pulse waves can effectively differentiate between healthy, CAD, and HF states. This approach represents a simple, non-invasive, and cost-effective methodology with significant potential as a valuable strategy to aid in the early screening and detection of HF. Further investigation and broader clinical validation are warranted to confirm the robustness and real-world applicability of this promising tool.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"318"},"PeriodicalIF":3.8,"publicationDate":"2025-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12382015/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144943914","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}