BMC Medical Informatics and Decision Making最新文献

{"title":"Leveraging machine learning for duration of surgery prediction in knee and hip arthroplasty - a development and validation study.","authors":"Benedikt Langenberger, Daniel Schrednitzki, Andreas Halder, Reinhard Busse, Christoph Pross","doi":"10.1186/s12911-025-02927-7","DOIUrl":"10.1186/s12911-025-02927-7","url":null,"abstract":"<p><strong>Background: </strong>Duration of surgery (DOS) varies substantially for patients with hip and knee arthroplasty (HA/KA) and is a major risk factor for adverse events. We therefore aimed (1) to identify whether machine learning can predict DOS in HA/KA patients using retrospective data available before surgery with reasonable performance, (2) to compare whether machine learning is able to outperform multivariable regression in predictive performance and (3) to identify the most important predictor variables for DOS both in a multi- and single-hospital context.</p><p><strong>Methods: </strong>eXtreme Gradient Boosting (XGBoost) and multivariable linear regression were used for predictions. Both models were applied to both the whole dataset which included multiple hospitals (3,704 patients), and a single-hospital dataset (1,815 patients) of the hospital with the highest case-volumes of our sample. Data was split into training (75%) and test data (25%) for both datasets. Models were trained using 5-fold cross-validation (CV) on the training datasets and applied to test data for performance comparison.</p><p><strong>Results: </strong>On test data in the multi-hospital setting, the mean absolute error (MAE) was 12.13 min (HA) / 13.61 min (KA) for XGBoost. In the single-hospital analysis, performance on test data was MAE 10.87 min (HA) / MAE 12.53 min (KA) for XGBoost. Predictive ability of XGBoost was tended to be better than of regression in all setting, however not statistically significantly. Important predictors for XGBoost were physician experience, age, body mass index, patient reported outcome measures and, for the multi-hospital analysis, the hospital.</p><p><strong>Conclusion: </strong>Machine learning can predict DOS in both a multi-hospital and single-hospital setting with reasonable performance. Performance between regression and machine learning differed slightly, however insignificantly, while larger datasets may improve predictive performance. The study found that hospital indicators matter in the multi-hospital setting despite controlling for various variables, highlighting potential quality differences between hospitals.</p><p><strong>Trial registration: </strong>The study was registered at the German Clinical Trials Register (DRKS) under DRKS00019916.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"106"},"PeriodicalIF":3.3,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11877953/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143540249","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":"Practical applications of methods to incorporate patient preferences into medical decision models: a scoping review.","authors":"Jakub Fusiak, Kousha Sarpari, Inger Ma, Ulrich Mansmann, Verena S Hoffmann","doi":"10.1186/s12911-025-02945-5","DOIUrl":"10.1186/s12911-025-02945-5","url":null,"abstract":"<p><strong>Background: </strong>Algorithms and models increasingly support clinical and shared decision-making. However, they may be limited in effectiveness, accuracy, acceptance, and comprehensibility if they fail to consider patient preferences. Addressing this gap requires exploring methods to integrate patient preferences into model-based clinical decision-making.</p><p><strong>Objectives: </strong>This scoping review aimed to identify and map applications of computational methods for incorporating patient preferences into individualized medical decision models and to report on the types of models where these methods are applied.</p><p><strong>Inclusion criteria: </strong>This review includes articles without restriction on publication date or language, focusing on practical applications. It examines the integration of patient preferences in models for individualized clinical decision-making, drawing on diverse sources, including both white and gray literature, for comprehensive insights.</p><p><strong>Methods: </strong>Following the Joanna Briggs Institute (JBI) methodology, a comprehensive search was conducted across databases such as PubMed, Web of Science, ACM Digital Library, IEEE Xplore, Cochrane Library, OpenGrey, National Technical Reports Library, and the first 20 pages of Google Scholar. Keywords related to patient preferences, medical models, decision-making, and software tools guided the search strategy. Data extraction and analysis followed the JBI framework, with an explorative analysis.</p><p><strong>Results: </strong>From 7074 identified and 7023 screened articles, 45 publications on specific applications were reviewed, revealing significant heterogeneity in incorporating patient preferences into decision-making tools. Clinical applications primarily target neoplasms and circulatory diseases, using methods like Multi-Criteria Decision Analysis (MCDA) and statistical models, often combining approaches. Studies show that incorporating patient preferences can significantly impact treatment decisions, underscoring the need for shared and personalized decision-making.</p><p><strong>Conclusion: </strong>This scoping review highlights a wide range of approaches for integrating patient preferences into medical decision models, underscoring a critical gap in the use of cohesive frameworks that could enhance consistency and clinician acceptance. While the flexibility of current methods supports tailored applications, the limited use of existing frameworks constrains their potential. This gap, coupled with minimal focus on clinician and patient engagement, hinders the real-world utility of these tools. Future research should prioritize co-design with clinicians, real-world testing, and impact evaluation to close this gap and improve patient-centered care.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"109"},"PeriodicalIF":3.3,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11877743/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143540250","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":"Practice, enablers and barriers of health information system accountability framework in Northwest Ethiopia 2023.","authors":"Biniyam Tilahun, Berhanu Fikadie Endehabtu, Amare Minyihun, Tajebew Zayede, Adane Nigusie, Asmamaw Atnafu, Lemma Derseh, Tesfahun Hialemarima, Getasew Amare","doi":"10.1186/s12911-025-02942-8","DOIUrl":"10.1186/s12911-025-02942-8","url":null,"abstract":"<p><strong>Background: </strong>The government of Ethiopia has designed different initiatives for the Health Information Systems (HIS), including an Information Revolution (IR) transformation agenda by 2015. Various interventions and working documents have also been developed and implemented targeting the different aspects of the HIS program. However, there is no nationally designed accountability framework to govern HIS activities. Besides, how health institutions follow and monitor HIS activities is unknown. Therefore, this study aimed to assess the practice and barriers of HIS accountability framework at the selected public health institutions.</p><p><strong>Method: </strong>A descriptive qualitative study design was employed from June 05 to July 12, 2023. Purposively selected informants from public health institutions were recruited for key informant interviews. A prepared pilot-tested semi-structured interview guide was used. The conventional content approach was used to summarize and synthesize the information explored.</p><p><strong>Findings: </strong>The study revealed that most respondents described the concept and advantages of the HIS accountability framework in different ways. The participants believed the HIS accountability framework would help to govern and manage behavioral-related HIS challenges. It was indicated that the framework will help to control the recurrence of HIS errors, enhance the commitment and adherence of health professionals, and improve data handover practice, data security and privacy, data quality, informed decision, and finality quality of care. Lack of national guidelines on the HIS accountability framework, the poor culture of accountability, multiple responsibilities and workload, high staff and leadership turnover, lack of motivation, and security problems were stated barriers to implementation of the HIS accountability framework. It was suggested to create a conducive work environment, engage health professionals and other actors during the intervention development, build the skills on HIS leadership, and have the national HIS accountability framework document to implement the intervention effectively.</p><p><strong>Conclusions: </strong>Even if there is a better understanding of the concept and advantages of the HIS accountability framework, its practice across the system is limited. It would be better to design the HIS accountability framework using a human-centered design/approach by engaging the key HIS actors and understanding their working environment.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"107"},"PeriodicalIF":3.3,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11877924/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143540264","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 evaluation of a whole-chain management system for critical value reporting.","authors":"Dongdong Wu, Feng Zhu, Yifan Sheng, Weiwei Zhang, Hanbo Le, Guoqiang Zhang, Lei Wang, Boer Yan","doi":"10.1186/s12911-025-02936-6","DOIUrl":"10.1186/s12911-025-02936-6","url":null,"abstract":"<p><strong>Background: </strong>Critical value (CV) management is vital for patient safety and shows the quality of critical care. This study aimed to develop a whole-chain management system (WCMS) for CV reporting and evaluate its impact on clinical practice.</p><p><strong>Methods: </strong>A WCMS for CV reporting, considering sample, process and patient population, was developed. A quasi-experimental study was conducted at Zhoushan Hospital. 591 CVs were divided into two groups: the postapplication group (n = 298) and the preapplication group (n = 293). CV quality-related indicators were compared between the two groups, including the timely reporting rate, timely receiving rate, timely treatment rate, completeness of treatment records and closed-loop rate.</p><p><strong>Results: </strong>Before system implementation, the timely treatment rate (93.17%), completeness of treatment records (78.16%), and closed-loop rate (88.05%) were lower than the timely reporting rate (94.54%). After implementation, there were significant differences between the two groups in timely reporting rate (94.54% vs. 97.99%, P < 0.05), timely treatment rate (93.17% vs. 97.65%, P < 0.01), completeness of treatment records (78.16% vs. 94.97%, P < 0.01), and closed-loop rate (88.05% vs. 97.32%, P < 0.01).</p><p><strong>Conclusion: </strong>Implementing the WCMS from sample, process and patient population has improved patient safety. The system's successful integration also shows its potential for use in health information systems of various healthcare facilities.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"104"},"PeriodicalIF":3.3,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11869711/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143522733","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 evaluation of an electronic follow-up questionnaire for patients after percutaneous coronary intervention.","authors":"Hassan Rajabi Moghadam, Parsa Rabbani, Majid Mazouchi, Hossein Akbari, Ehsan Nabovati, Soroosh Rabbani, Parissa Bagheri Toolaroud","doi":"10.1186/s12911-025-02931-x","DOIUrl":"10.1186/s12911-025-02931-x","url":null,"abstract":"<p><strong>Background: </strong>Patient-centered, measurable, and transparent care is essential for improving healthcare outcomes, particularly for patients undergoing percutaneous coronary intervention (PCI) procedures. Electronic follow-up questionnaires offer the potential for efficient and accurate data collection, enhancing the monitoring of patient experiences and outcomes. This study aimed to design and evaluate an electronic follow-up questionnaire tailored for post-PCI patients, focusing on real-time symptom monitoring and data collection.</p><p><strong>Methods: </strong>This developmental study was conducted in 2020 in three phases. In the first phase, a follow-up questionnaire was developed through a needs assessment and expert consultations. Each item's content validity ratio (CVR) and content validity index (CVI) were evaluated to ensure content validity. The finalized questionnaire elements were then reviewed and refined by a panel of ten cardiologists using the Delphi technique. In the second phase, an electronic platform was designed to host the follow-up questionnaire. The tool's effectiveness for post-PCI follow-up was evaluated in the third phase.</p><p><strong>Results: </strong>Cardiologists confirmed all items in the Delphi technique's first round, validating the follow-up questionnaire's content. A total of 41 patients undergoing PCI were enrolled in the study. The most frequently reported symptoms included issues at the catheter insertion site, chest discomfort, digestive complications, and shortness of breath. Of these patients, 21 (51.2%) utilized the electronic follow-up tool. The primary reasons for non-participation were busy schedules, forgetfulness, and perceived recovery. Among the participants, 16 (76.2%) expressed high or very high satisfaction with the tool.</p><p><strong>Conclusion: </strong>The findings suggest that this electronic follow-up questionnaire has the potential to effectively collect clinical data, support academic research, and improve the quality of post-PCI care. However, addressing barriers to patient participation and involving patients in the tool's iterative development will be critical for enhancing its adoption and impact.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"103"},"PeriodicalIF":3.3,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11866665/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143514801","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: FHIR PIT: a geospatial and spatiotemporal data integration pipeline to support subject-level clinical research.","authors":"Karamarie Fecho, Juan J Garcia, Hong Yi, Griffin Roupe, Ashok Krishnamurthy","doi":"10.1186/s12911-025-02940-w","DOIUrl":"10.1186/s12911-025-02940-w","url":null,"abstract":"","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"102"},"PeriodicalIF":3.3,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11863691/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143499429","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":"Detection of COPD exacerbations with continuous monitoring of breathing rate and inspiratory amplitude under oxygen therapy.","authors":"Juliana Alves Pegoraro, Antoine Guerder, Thomas Similowski, Philippe Salamitou, Jesus Gonzalez-Bermejo, Etienne Birmelé","doi":"10.1186/s12911-025-02939-3","DOIUrl":"10.1186/s12911-025-02939-3","url":null,"abstract":"<p><strong>Background: </strong>Chronic Obstructive Pulmonary Disease (COPD) is one of the main causes of morbidity and mortality worldwide. Its management represents real economic and public health burdens, accentuated by periods of acute disease deterioration, called exacerbations. Some researchers have studied the interest of monitoring patients' breathing rate as an indicator of exacerbation, although achieving limited sensitivity and/or specificity. In this study, we look to improve the previously described method, by combining breathing variables, using multiple daily measures, and using an artificial intelligence-based novelty detection approach.</p><p><strong>Methods: </strong>Patients with COPD were monitored with a telemedicine device during their stay in a rehabilitation care center. Daily measures are compared to individually trained reference models based on: i. oxygen therapy duration ii. mean breathing rate, iii. mean inspiratory amplitude, iv. mean breathing rate and mean inspiratory amplitude, v. average distribution of breathing rate and inspiratory amplitude, vi. hidden Markov model (HMM) from a time series of breathing rate and inspiratory amplitude.</p><p><strong>Results: </strong>A set of 16 recordings with exacerbation and 23 recordings without exacerbation was obtained. When using a daily measure of breathing rate, pre-exacerbation periods were identified with a specificity of 50% and a sensitivity of 55.6%. The method based on daily oxygen therapy usage and the method based on time series obtain a sensitivity of 76.8% and 73.2%, respectively, for a fixed specificity of 50%.</p><p><strong>Conclusion: </strong>A single daily measure of breathing rate alone is not sufficient for the detection of pre-exacerbation periods. More complete models also achieve limited performance, equivalent to models based on changes in the duration of therapy usage.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"101"},"PeriodicalIF":3.3,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11863910/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143498251","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: Machine learning to predict virological failure among HIV patients on antiretroviral therapy in the University of Gondar Comprehensive and Specialized Hospital, in Amhara Region, Ethiopia, 2022.","authors":"Daniel Niguse Mamo, Tesfahun Melese Yilma, Makda Fekadie Tewelgne, Yakub Sebastian, Tilahun Bizuayehu, Mequannent Sharew Melaku, Agmasie Damtew Walle","doi":"10.1186/s12911-025-02908-w","DOIUrl":"10.1186/s12911-025-02908-w","url":null,"abstract":"","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"100"},"PeriodicalIF":3.3,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11853309/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143499431","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":"Machine learning-based prediction model for patients with recurrent Staphylococcus aureus bacteremia.","authors":"Yuan Li, Shuang Song, Liying Zhu, Xiaorun Zhang, Yijiao Mou, Maoxing Lei, Wenjing Wang, Zhen Tao","doi":"10.1186/s12911-025-02878-z","DOIUrl":"10.1186/s12911-025-02878-z","url":null,"abstract":"<p><strong>Background: </strong>Staphylococcus aureus bacteremia (SAB) remains a significant contributor to both community-acquired and healthcare-associated bloodstream infections. SAB exhibits a high recurrence rate and mortality rate, leading to numerous clinical treatment challenges. Particularly, since the outbreak of COVID-19, there has been a gradual increase in SAB patients, with a growing proportion of (Methicillin-resistant Staphylococcus aureus) MRSA infections. Therefore, we have constructed and validated a pediction model for recurrent SAB using machine learning. This model aids physicians in promptly assessing the condition and intervening proactively.</p><p><strong>Methods: </strong>The patients data is sourced from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database version 2.2. The patients were divided into training and testing datasets using a 7:3 random sampling ratio. The process of feature selection employed two methods: Recursive Feature Elimination (RFE) and Least Absolute Shrinkage and Selection Operator (LASSO). Prediction models were built using Extreme Gradient Boosting (XGBoost), Random Forest (RF), Logistic Regression (LR), Support Vector Machine (SVM), and Artificial Neural Network (ANN). Model validation included Receiver Operating Characteristic (ROC) analysis, Decision Curve Analysis (DCA), and Precision-Recall Curve (PRC). We utilized SHAP (SHapley Additive exPlanations) values to demonstrate the significance of each feature and explain the XGBoost model.</p><p><strong>Results: </strong>After screening, MRSA, PTT, RBC, RDW, Neutrophils_abs, Sodium, Calcium, Vancomycin concentration, MCHC, MCV, and Prognostic Nutritional Index(PNI) were selected as features for constructing the model. Through combined evaluation using ROC、 DCA and PRC, XGBoost demonstrated the best predictive performance, achieving an AUC value of 0.76 (95% CI: 0.66-0.85) in ROC and 0.56 (95% CI: 0.37-0.75) in PRC. Building a website based on the Xgboost model. SHAP illustrated the feature importance ranking in the XGBoost model and provided examples to explain the XGBoost model.</p><p><strong>Conclusions: </strong>The adoption of XGBoost for model development holds widespread acceptance in the medical domain. The prediction model for recurrent SAB, developed by our team, aids physicians in timely diagnosis and treatment of patients.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"99"},"PeriodicalIF":3.3,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11853511/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143490854","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":"Transforming liver transplant allocation with artificial intelligence and machine learning: a systematic review.","authors":"Lisiane Pruinelli, Kiruthika Balakrishnan, Sisi Ma, Zhigang Li, Anji Wall, Jennifer C Lai, Jesse D Schold, Timothy Pruett, Gyorgy Simon","doi":"10.1186/s12911-025-02890-3","DOIUrl":"10.1186/s12911-025-02890-3","url":null,"abstract":"<p><strong>Background: </strong>The principles of urgency, utility, and benefit are fundamental concepts guiding the ethical and practical decision-making process for organ allocation; however, LT allocation still follows an urgency model.</p><p><strong>Aim: </strong>To identify and analyze data elements used in Machine Learning (ML) and Artificial Intelligence (AI) methods, data sources, and their focus on urgency, utility, or benefit in LT.</p><p><strong>Methods: </strong>A comprehensive search across Ovid Medline and Scopus was conducted for studies published from 2002 to June 2023. Inclusion criteria targeted quantitative studies using ML/AI for candidates, donors, or recipients. Two reviewers assessed eligibility and extracted data, following PRISMA guidelines.</p><p><strong>Results: </strong>A total of 20 papers were included, synthesizing results into five major categories. Eight studies were led by a Spanish team, focusing on donor-recipient matching and proposing machine learning models to predict post- LT survival. Other international studies addressed organ supply-demand issues and developed predictive models to optimize LT outcomes. The studies highlight the potential of ML/AI to enhance LT allocation and outcomes. Despite advancements, limitations included the lack of robust transplant-related benefit models and improvements in urgency models compared to MELD.</p><p><strong>Discussion: </strong>This review highlighted the potential of AI and ML to enhance liver transplant allocation and outcomes. Significant advancements were noted, but limitations such as the need for better urgency models and the absence of a transplant-related benefit model remain. Most studies emphasized utility, focusing on survival outcomes. Future research should address the interpretability and generalizability of these models to improve organ allocation and post-LT survival predictions.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"98"},"PeriodicalIF":3.3,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11852809/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143490855","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}