BMC Medical Informatics and Decision Making最新文献

{"title":"Improving stroke risk prediction by integrating XGBoost, optimized principal component analysis, and explainable artificial intelligence.","authors":"Lesia Mochurad, Viktoriia Babii, Yuliia Boliubash, Yulianna Mochurad","doi":"10.1186/s12911-025-02894-z","DOIUrl":"https://doi.org/10.1186/s12911-025-02894-z","url":null,"abstract":"<p><p>The relevance of the study is due to the growing number of diseases of the cerebrovascular system, in particular stroke, which is one of the leading causes of disability and mortality in the world. To improve stroke risk prediction models in terms of efficiency and interpretability, we propose to integrate modern machine learning algorithms and data dimensionality reduction methods, in particular XGBoost and optimized principal component analysis (PCA), which provide data structuring and increase processing speed, especially for large datasets. For the first time, explainable artificial intelligence (XAI) is integrated into the PCA process, which increases transparency and interpretation, providing a better understanding of risk factors for medical professionals. The proposed approach was tested on two datasets, with accuracy of 95% and 98%. Cross-validation yielded an average value of 0.99, and high values of Matthew's correlation coefficient (MCC) metrics of 0.96 and Cohen's Kappa (CK) of 0.96 confirmed the generalizability and reliability of the model. The processing speed is increased threefold due to OpenMP parallelization, which makes it possible to apply it in practice. Thus, the proposed method is innovative and can potentially improve forecasting systems in the healthcare industry.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"63"},"PeriodicalIF":3.3,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143370559","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Tough choices: the experience of family members of critically ill patients participating in ECMO treatment decision-making: a descriptive qualitative study.","authors":"Xiangying Yang, Yao Lin, Amao Tang, Xiaokang Zeng, Weiying Dai, Qian Zhang, Li Ning","doi":"10.1186/s12911-025-02876-1","DOIUrl":"https://doi.org/10.1186/s12911-025-02876-1","url":null,"abstract":"<p><strong>Background: </strong>ECMO treatment for critically ill patients mostly requires family members to make surrogate decisions. However, the process and experience of family members' participation in decision making have not been well described.</p><p><strong>Purpose: </strong>To explore the experience of family members of critically ill patients who were asked to consent to ECMO treatment and to gain insight into the factors that promote and hinder their decision-making.</p><p><strong>Methods: </strong>A descriptive qualitative study. Data were collected using a semi-structured interview method and analysed using traditional content analysis approaches. The cohort included nineteen family members of critically ill ICU patients from a general hospital in China.</p><p><strong>Results: </strong>Eleven family members consented to ECMO treatment, and 8 refused. 4 themes and 10 subthemes emerged: (1) tough choices: the dilemma in the emergency situation, the guilt and remorse after giving up; (2) rationalisation of decision-making: ethics and morality guide decision-making, expected efficacy influences decision making, and past experience promotes decision making; (3) decision-making methods: independent decision-making, group decision-making, decision making based on patient preferences; (4) influencing factors of decision making: information and communication, social support.</p><p><strong>Conclusion: </strong>The findings provide insights and a basis for promoting efficient ECMO decision-making in clinical practice. It may be difficult to improve the time it takes to make the decision without sacrificing the quality of the decision. Healthcare professionals should provide timely emotional support, informational support, and comprehensive social support to assist them in making efficient decisions while respecting the treatment preferences of the decision-makers.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"65"},"PeriodicalIF":3.3,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143370565","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Causal machine learning models for predicting low birth weight in midwife-led continuity care intervention in North Shoa Zone, Ethiopia.","authors":"Wudneh Ketema Moges, Awoke Seyoum Tegegne, Aweke A Mitku, Esubalew Tesfahun, Solomon Hailemeskel","doi":"10.1186/s12911-025-02917-9","DOIUrl":"https://doi.org/10.1186/s12911-025-02917-9","url":null,"abstract":"<p><strong>Background: </strong>Low birth weight (LBW) is a critical global health issue that affects infants disproportionately, particularly in developing countries. This study adopted causal machine learning (CML) algorithms for predicting LBW in newborns, drawing from midwife-led continuity care (MLCC).</p><p><strong>Methods: </strong>A quasi-experimental study was carried out in the North Shoa Zone of Ethiopia from August 2019 to September 2020. A total of 1166 women were allocated into two groups. The first group, the MLCC group, received all their antenatal, labor, birth, and immediate post-natal care from a single midwife. The second group received care from various staff members at different times throughout their pregnancy and childbirth. In this study, CML was implemented to predict LBW. Data preprocessing, including data cleaning, was conducted. CML was then employed to identify the most suitable classifier for predicting LBW. Gradient boosting algorithms were used to estimate the causal effect of MLCC on LBW. Moreover, meta-learner algorithms were utilized to estimate the individual treatment effect (ITE), the average treatment effect (ATE), and performance. Moreover, meta-learner algorithms were utilized to estimate the individual treatment effect (ITE), the average treatment effect (ATE), and performance.</p><p><strong>Results: </strong>The study results revealed that Causal K-Nearest Neighbors (CKNN) was the most effective classifier based on accuracy and estimated LBW using a 94.52% accuracy, 90.25% precision, 92.57% recall, and an F1 score of 88.2%. Meconium aspiration, perinatal mortality, pregnancy-induced hypertension, vacuum babies in need of resuscitation, and previous surgeries on their reproductive organs were identified as the top five features affecting LBW. The estimated impact of MLCC versus other professional groups on LBW was analyzed using gradient boosting algorithms and was found to be 0.237. The estimated ATE for the S-learner was 0.284, which is lower than the true ATE of 0.216. Additionally, the estimated ITE for both the T-learner and X-learner was less than -0.5, indicating that mothers would not choose to participate in the MLCC program.</p><p><strong>Conclusions: </strong>Based on these findings, the CKNN classifier demonstrated a higher accuracy and effectiveness. The S-learner and R-learner models, utilizing the XGBoost Regressor and BaseSRegressor, provided accurate estimations of ITE for assessing the impact of the MLCC program. Promoting the MLCC program could help stabilize LBW outcomes.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"64"},"PeriodicalIF":3.3,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143370543","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Patients' and plastic surgeons' experiences with an online patient decision aid for breast reconstruction: considerations for nationwide implementation.","authors":"Jacqueline A Ter Stege, Ellen G Engelhardt, Leonie A E Woerdeman, Hester S A Oldenburg, Jacobien M Kieffer, Daniela E E Hahn, Frederieke H van Duijnhoven, Martine A van Huizum, Regina The, Klemens Karssen, Marianne Kuenen, Miranda A Gerritsma, Quinten Pq Ruhe, Irene S Krabbe-Timmerman, Martijne Van't Riet, Nikola An Kimmings, Eveline M L Corten, Kerry A Sherman, Arjen J Witkamp, Eveline M A Bleiker","doi":"10.1186/s12911-024-02832-5","DOIUrl":"https://doi.org/10.1186/s12911-024-02832-5","url":null,"abstract":"<p><strong>Background: </strong>Women diagnosed with breast cancer undergoing a mastectomy often have the option to undergo breast reconstruction (BR). BR decisions are complex and have considerable impact. We developed a patient decision aid (pDA) to support patients' BR decision-making. Here, we assess patients' and physicians' use of the BR pDA and their views on the barriers and facilitators for widespread implementation.</p><p><strong>Methods: </strong>Participants completed a questionnaire, and back-end data of the pDA was analyzed.</p><p><strong>Results: </strong>Of 116 eligible patients, 113 patients accessed the BR pDA (median age: 50 years and 50% were highly educated. Most patients (72%) were satisfied with the pDA and 74% would recommend the BR pDA to other women facing the same choice. Patients' preferences regarding how much, what kind and how to present information varied. Plastic surgeons (N = 22; 71% response) were satisfied with the pDA. Their key factors for implementation included the perceived match between information and clinical practice, costs, impact on patients, and support from peers and management for the tool.</p><p><strong>Conclusions: </strong>As the BR pDA was highly valued by its end users, the identified factors for implementation should be taken into account.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"62"},"PeriodicalIF":3.3,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143363714","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Ontology-based expansion of virtual gene panels to improve diagnostic efficiency for rare genetic diseases.","authors":"Jaemoon Shin, Toyofumi Fujiwara, Hirotomo Saitsu, Atsuko Yamaguchi","doi":"10.1186/s12911-025-02910-2","DOIUrl":"10.1186/s12911-025-02910-2","url":null,"abstract":"<p><strong>Background: </strong>Virtual Gene Panels (VGP) comprising disease-associated causal genes are utilized in the diagnosis of rare genetic diseases to evaluate candidate genes identified by whole-genome and whole-exome sequencing. VGPs generated by the PanelApp software were utilized in a UK 100,000 Genome Project pilot study to filter candidate genes, thus enhancing diagnostic efficiency for rare diseases. However, PanelApp also filtered out disease-causing genes in nearly 50% of the cases.</p><p><strong>Methods: </strong>Here, we propose various methods for optimized approach to design VGPs that significantly improve the diagnostic efficiency by leveraging the hierarchical structure of the Mondo disease ontology, without excluding disease-causing genes. We also performed computational experiments on an evaluation dataset comprising 74 patients to determine the optimal VGP design method.</p><p><strong>Results: </strong>Our results demonstrate that the proposed method can significantly enhance rare disease diagnosis efficiency by automatically identifying candidate genes. The proposed method successfully designed VGPs that improve diagnosis efficiency without excluding disease-causing genes.</p><p><strong>Conclusion: </strong>We have developed novel methods for VGP design that leverage the hierarchical structure of the Mondo disease ontology to improve rare genetic disease diagnosis efficiency. This approach identifies candidate genes without excluding disease-causing genes, and thereby improves diagnostic efficiency.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 Suppl 1","pages":"59"},"PeriodicalIF":3.3,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11800421/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143254614","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":"Healthcare trajectories of aging individuals during their last year of life: application of process mining methods to administrative health databases.","authors":"Delphine Bosson-Rieutort, Alexandra Langford-Avelar, Juliette Duc, Benjamin Dalmas","doi":"10.1186/s12911-025-02898-9","DOIUrl":"10.1186/s12911-025-02898-9","url":null,"abstract":"<p><strong>Context: </strong>World is aging and the prevalence of chronic diseases is raising with age, increasing financial strain on organizations but also affecting patients' quality of life until death. Research on healthcare trajectories has gained importance, as it can help anticipate patients' needs and optimize service organization. In an overburdened system, it is essential to develop automated methods based on comprehensive and reliable and already available data to model and predict healthcare trajectories and future utilization. Process mining, a family of process management and data science techniques used to derive insights from the data generated by a process, can be a solid candidate to provide a useful tool to support decision-making.</p><p><strong>Objective: </strong>We aimed to (1) identify the healthcare baseline trajectories during the last year of life, (2) identify the differences in trajectories according to medical condition, and (3) identify adequate settings to provide a useful output.</p><p><strong>Methods: </strong>We applied process mining techniques on a retrospective longitudinal cohort of 21,255 individuals who died between April 1, 2014, and March 31, 2018, and were at least 66 years or older at death. We used 6 different administrative health databases (emergency visit, hospitalisation, homecare, medical consultation, death register and administrative), to model individuals' healthcare trajectories during their last year of life.</p><p><strong>Results: </strong>Three main trajectories of healthcare utilization were highlighted: (i) mainly accommodating a long-term care center; (ii) services provided by local community centers in combination with a high proportion of medical consultations and acute care (emergency and hospital); and (iii) combination of consultations, emergency visits and hospitalization with no other management by local community centers or LTCs. Stratifying according to the cause of death highlighted that LTC accommodation was preponderant for individuals who died of physical and cognitive frailty. Conversely, services offered by local community centers were more prevalent among individuals who died of a terminal illness. This difference is potentially related to the access to and use of palliative care at the end-of-life, especially home palliative care implementation.</p><p><strong>Conclusion: </strong>Despite some limitations related to data and visual limitations, process mining seems to be a method that is both relevant and simple to implement. It provides a visual representation of the processes recorded in various health system databases and allows for the visualization of the different trajectories of healthcare utilization.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"58"},"PeriodicalIF":3.3,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11796206/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143254420","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":"Digital health data security practices among health professionals in low-resource settings: cross-sectional study in Amhara Region, Ethiopia.","authors":"Ayenew Sisay Gebeyew, Wondwossen Zemene, Binyam Chaklu Tilahun, Nebyu Demeke Mengestie, Berhanu Fikade Endehabtu, Zegeye Regasa Wordofa, Mitiku Kassaw Takillo, Gedefaw Belete Ashagrie, Melaku Molla Sisay","doi":"10.1186/s12911-025-02902-2","DOIUrl":"10.1186/s12911-025-02902-2","url":null,"abstract":"<p><strong>Introduction: </strong>Protecting digital health data from unauthorized access, alteration, and destruction is a crucial aspect of healthcare digitalization. Currently, digital security breaches are becoming more common. Healthcare data breaches have compromised over 50 million medical records per year. In Ethiopia, health digitization has grown gradually. However, there is a limitation of study in digital health security. Studying digital health data security helps individuals protect digital data as a baseline and contributes to developing a digital health security policy.</p><p><strong>Objective: </strong>To assess the practice of healthcare professionals in digital health data security among specialized teaching referral hospitals in Amhara Region, Ethiopia.</p><p><strong>Method: </strong>A cross-sectional study design supplemented by a qualitative purposive sampling method was used to measure the digital data security practices of health professionals. The sample size was determined via single population proportion formula. A simple random sampling technique was used for the study participants. Then, self-administered questionnaires were administered. Multivariable logistic analysis was used to identify associated factors using STATA software. For the qualitative study, key informant interviews were used and analyzed using thematic analysis approach via open-code software.</p><p><strong>Results: </strong>Out of the 423 health professionals, 95.0% were involved in the survey. The finding indicates digital health data security practice of health professionals working at specialized teaching hospitals were 45.0%, CI: (40, 50). Health professionals 41-45-year age group (AOR = 0.107), master's degree (AOR = 2.45), postmaster's degree (AOR = 3.87), time to visit the internet for more than two hours (AOR = 2.46), basic computer training (AOR = 2.77), training in digital data security (AOR = 2.14), and knowledge (AOR = 1.76) were associated with the practice of digital health data security. For the qualitative study, three teams were prepared. The findings indicate digital health data security can be improved through training, advanced knowledge and working with digital security.</p><p><strong>Conclusion: </strong>The practice of digital health data security in specialized teaching hospitals in the Amhara region was inadequate. Therefore, it can be improved through enhancing education status, increasing the time needed to visit the internet, providing computer training, and updating health professionals' knowledge toward digital health data security.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"60"},"PeriodicalIF":3.3,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11796040/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143254056","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":"Examining inclusivity: the use of AI and diverse populations in health and social care: a systematic review.","authors":"John Gabriel O Marko, Ciprian Daniel Neagu, P B Anand","doi":"10.1186/s12911-025-02884-1","DOIUrl":"10.1186/s12911-025-02884-1","url":null,"abstract":"<p><strong>Background: </strong>Artificial intelligence (AI)-based systems are being rapidly integrated into the fields of health and social care. Although such systems can substantially improve the provision of care, diverse and marginalized populations are often incorrectly or insufficiently represented within these systems. This review aims to assess the influence of AI on health and social care among these populations, particularly with regard to issues related to inclusivity and regulatory concerns.</p><p><strong>Methods: </strong>We followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Six leading databases were searched, and 129 articles were selected for this review in line with predefined eligibility criteria.</p><p><strong>Results: </strong>This research revealed disparities in AI outcomes, accessibility, and representation among diverse groups due to biased data sources and a lack of representation in training datasets, which can potentially exacerbate inequalities in care delivery for marginalized communities.</p><p><strong>Conclusion: </strong>AI development practices, legal frameworks, and policies must be reformulated to ensure that AI is applied in an equitable manner. A holistic approach must be used to address disparities, enforce effective regulations, safeguard privacy, promote inclusion and equity, and emphasize rigorous validation.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"57"},"PeriodicalIF":3.3,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11796235/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143254369","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 of an artificial intelligence-based application for the diagnosis of sarcopenia: a retrospective cohort study using the health examination dataset.","authors":"Chang-Won Jeong, Dong-Wook Lim, Si-Hyeong Noh, Sung Hyun Lee, Chul Park","doi":"10.1186/s12911-025-02900-4","DOIUrl":"10.1186/s12911-025-02900-4","url":null,"abstract":"<p><strong>Background: </strong>Medical imaging techniques for diagnosing sarcopenia have been extensively investigated. Studies have proposed using the T-score and patient information as key diagnostic factors. However, these techniques have either been time-consuming or have required separate calculation processes after collecting each parameter. To address this gap, we propose an artificial intelligence (AI)-based web application that automates the collection of data, classification of the lumbar spine 3 (L3) slices, segmentation of the subcutaneous fat, visceral fat, and muscle areas in the classified L3 slices, and quantitative analysis of the segmented areas.</p><p><strong>Methods: </strong>We developed an automated lumbar spine slice classification model using the CNN (EfficientNetV2) algorithm and an automated domain segmentation model to identify the subcutaneous fat, visceral fat, and muscle areas using the U-NET algorithm. These models were used to identify L3 slices from abdominal computed tomography images and divide the images into the three-segmented domains for sarcopenia diagnosis. Additionally, we developed an algorithm for the calculation of T-Score calculated as (measurement value-Young adult mean)/(Young adult SD) using the Aggregation Pipeline by MongoDB, with the mean and standard deviation for skeletal muscle area (SMA), SMA/height², SMA/weight, and SMA/body mass index (BMI) for both sexes and different age groups.</p><p><strong>Results: </strong>The proposed system demonstrated high accuracy and precision, with an overall accuracy of 97.5% in classifying L3 slices and a segmentation accuracy of 92% for muscle, subcutaneous fat, and visceral fat areas. The T-Score-based analysis provided reliable diagnostic thresholds for sarcopenia, facilitating consistent and accurate assessments. Our diagnostic cutoff points for each index were as follows: SMA (-1.0: 152.55, -2.0: 125.89), SMA/height² (-1.0: 38.84, -2.0: 14.50), SMA/weight (-1.0: 2.14, -2.0: 1.89), and SMA/BMI (-1.0: 6.10, -2.0: 5.18) for men; SMA (-1.0: 96.08, -2.0: 76.96), SMA/height² (-1.0: 37.20, -2.0: 29.36), SMA/weight (-1.0: 1.80, -2.0: 1.61), and SMA/BMI (-1.0: 4.56, -2.0: 4.01) for women. SMA/BMI best reflected the loss of muscle mass in healthy populations by age, showing a more remarkable decrease in muscle mass in men than in women. The values for men gradually decreased after their 20s, and that for women gradually decreased after their 40s, which progressed to a more dramatic decline in the 70s for both sexes.</p><p><strong>Conclusion: </strong>This AI-based web application addresses the limitations of previous diagnostic techniques by automatically analyzing medical images for the classification, segmentation, and calculation of T-scores. The study findings provide a more reliable and accurate diagnostic technique for sarcopenia that can consequently impact patient treatment and outcomes.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"61"},"PeriodicalIF":3.3,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11796039/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143255008","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":"Sharing reliable information worldwide: healthcare strategies based on artificial intelligence need external validation. Position paper.","authors":"F Pennestrì, F Cabitza, N Picerno, G Banfi","doi":"10.1186/s12911-025-02883-2","DOIUrl":"10.1186/s12911-025-02883-2","url":null,"abstract":"<p><p>Training machine learning models using data from severe COVID-19 patients admitted to a central hospital, where entire wards are specifically dedicated to COVID-19, may yield predictions that differ significantly from those generated using data collected from patients admitted to a high-volume specialized hospital for orthopedic surgery, where COVID-19 is only a secondary diagnosis. This disparity arises despite the two hospitals being geographically close (within20 kilometers). While machine learning can facilitate rapid public health responses, rigorous external validation and continuous monitoring are essential to ensure reliability and safety.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"56"},"PeriodicalIF":3.3,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11796012/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143187771","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}