BMC Medical Informatics and Decision Making最新文献

{"title":"A study on large-scale disease causality discovery from biomedical literature.","authors":"Shirui Yu, Peng Dong, Junlian Li, Xiaoli Tang, Xiaoying Li","doi":"10.1186/s12911-025-02893-0","DOIUrl":"10.1186/s12911-025-02893-0","url":null,"abstract":"<p><strong>Background: </strong>Biomedical semantic relationship extraction could reveal important biomedical entities and the semantic relationships between them, providing a crucial foundation for the biomedical knowledge discovery, clinical decision making and other artificial intelligence applications. Identifying the causal relationships between diseases is a significant research field, since it expedites the identification of underlying disease pathogenesis mechanisms and promote better disease prevention and treatment. SemRep is an effective tool for semantic relationship extraction in the biomedical field, but it is not accurate enough for disease causality extraction, bringing challenges for downstream tasks. In this study, we proposed an optimization strategy for SemRep to enhance its accuracy in disease causality extraction.</p><p><strong>Methods: </strong>This study aims to optimize disease causality extraction of SemRep tool by constructing a semantic predicate vocabulary that precisely expresses disease causality to support the automatic extraction of disease causality knowledge from biomedical literature. The proposed method invloves the following four steps: Firstly, we obtained a collection of semantic feature words expressing disease causality based on current causality predicate studies and the disease causality pairs extracted from SemMedDB. Then, we constructed a disease causality semantic predicate vocabulary by filtering and evaluating the clue words using quantitative comparisons. Following that, we extracted disease causality pairs from the biomedical literature using 36 semantic predicates with an accuracy greater than 80% for more meaningful knowledge discovery. Finally, we conducted knowledge discovery based on the extracted disease causality triples, which primarily includes unidirectional disease causality, bidirectional disease causality, as well as two specific types of disease causality: primary disease causality and rare disease causality.</p><p><strong>Results: </strong>We obtained a disease causality semantic predicate vocabulary containing 50 textual predicates with an accuracy of above 40%. 36 semantic predicates from the 60% accuracy group were used for disease causality extraction, yielding 259,434 disease causality pairs for subsequent knowledge discovery. Among them, 92,557 types with 176,010 unidirectional disease causality triples, and 6084 types with 83,424 bidirectional disease causality triples were found eventually. Two other types of disease causality, primary disease causality and rare disease causality, were also discovered.</p><p><strong>Conclusions: </strong>The novelty of this research is that the proposed method enhanced the disease causality extraction of SemRep tool, resulting a more accurate and comprehensive disease causality extraction. It also facilitates an automatic disease causality extraction from large-scale biomedical literature. Additionally, a customized extraction of disease ca","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"136"},"PeriodicalIF":3.3,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11916938/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143656227","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":"Prediction of Gestational Diabetes Mellitus (GDM) risk in early pregnancy based on clinical data and ultrasound information: a nomogram.","authors":"Tong Zhu, Lin Tang, Man Qin, Wen-Wen Wang, Ling Chen","doi":"10.1186/s12911-025-02962-4","DOIUrl":"10.1186/s12911-025-02962-4","url":null,"abstract":"<p><strong>Background: </strong>Gestational diabetes mellitus (GDM) is one of the most common complications during pregnancy and has been on a continuous increase in recent years. This study aimed to establish a combined prediction model for the risk of GDM and to provide more reliable reference information for non-invasive assessment of GDM in clinical practice.</p><p><strong>Methods: </strong>This study retrospectively collected clinical data and ultrasound information of 122 pregnant women who underwent fetal nuchal translucency screening, which divided into 36 cases of the GDM group and 86 cases of the non-gestational diabetes mellitus(NGDM) group. The collected clinical data and ultrasound information were analyzed using Student's t-test and Wilcoxon W test for univariate analysis. Independent risk factors for patients with GDM were screened through binary logistic regression analysis. A model was established based on the screened results, and the diagnostic performance of different models was evaluated by drawing the receiver operating characteristic curve(ROC). The optimal prediction model was selected, and the calibration curve and clinical decision curve were drawn to evaluate the goodness of fit and clinical application efficiency of the model.</p><p><strong>Results: </strong>Univariate results showed that age, body mass index(BMI), number of abortions, gravidity, placental volume(PV), vascularization index(VI), flow index(FI), and vascularization flow index(VFI) all had statistically significant differences between the GDM and NGDM groups(p < 0.05). Binary logistic regression analysis showed that BMI, number of abortions, PV, VI, and FI were independent risk factors for the development of GDM in pregnant women (p < 0.05). Based on these results, five prediction models were established in this study. Their area under the ROC curve(AUC) were 0.67, 0.80, 0.80, 0.87, and 0.85, respectively. The model combining clinical data with 30° ultrasound data had the highest AUC, so we constructed a nomogram for this model. The results of its calibration curve showed that the model had a good fit, and the results of the clinical decision curve showed that the model had good clinical application efficiency.</p><p><strong>Conclusion: </strong>The nomogram model combining clinical data with 30° ultrasound data has good accuracy and clinical application value for predicting the risk of GDM.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"138"},"PeriodicalIF":3.3,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11916998/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143656229","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":"Real-world insights of patient voices with age-related macular degeneration in the Republic of Korea and Taiwan: an AI-based Digital Listening study by Semantic-Natural Language Processing.","authors":"Hyewon Jeon, Su-Yeon Yu, Olga Chertkova, Hyejung Yun, Yi Lin Ng, Yan Yoong Lim, Irina Efimenko, Djoubeir Mohamed Makhlouf","doi":"10.1186/s12911-025-02929-5","DOIUrl":"10.1186/s12911-025-02929-5","url":null,"abstract":"<p><strong>Background: </strong>In this era of active online communication, patients increasingly share their healthcare experiences, concerns, and needs across digital platforms. Leveraging these vast repositories of real-world information, Digital Listening enables the systematic collection and analysis of patient voices through advanced technologies. Semantic-NLP artificial intelligence, with its ability to process and extract meaningful insights from large volumes of unstructured online data, represents a novel approach for understanding patient perspectives. This study aimed to demonstrate the utility of Semantic-NLP technology in presenting the needs and concerns of patients with age-related macular degeneration (AMD) in Korea and Taiwan.</p><p><strong>Methods: </strong>Data were collected and analysed over three months from January 2023 using an ontology-based information extraction system (Semantic Hub). The system identified patient \"stories\" and extracted themes from online posts from January 2013 to March 2023, focusing on Korea and Taiwan by filtering the geographic location of users, the language used, and the local online platforms. Extracted texts were structured into knowledge graphs and analysed descriptively.</p><p><strong>Results: </strong>The patient voice was identified in 133,857 messages (9,620 patients) from the Naver online platform in Korea and included internet chat forums focused on macular degeneration. The most important factors for AMD treatments were effectiveness (1,632/3,401 mentions; 48%), price and access to insurance (33%), tolerability (10%) and doctor and clinic recommendations (9%). Treatment burden associated with intravitreal injection of vascular endothelial growth factor inhibitors related to tolerability (254/942 mentions; 27%), financial burden (20%), hospital selection (18%) and emotional burden (14%). In Taiwan, 444 messages were identified from Facebook, YouTube and Instagram. The success of treatment was judged by improvements in visual acuity (20/121 mentions; 16.5%), effect on oedema (10.7%), less distortion (9.1%) and inhibition of angiogenesis (5.8%). Tolerability concerns were rarely mentioned (26/440 mentions; 5.9%).</p><p><strong>Conclusions: </strong>Digital Listening using Semantic-NLP can provide real-world insights from large amounts of internet data quickly and with low human labour cost. This allows healthcare companies to respond to the unmet needs of patients for effective and safe treatment and improved patient quality of life throughout the product lifecycle.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"137"},"PeriodicalIF":3.3,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11916980/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143656231","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":"Presenting a prediction model for HELLP syndrome through data mining.","authors":"Boshra Farajollahi, Mohammadjavad Sayadi, Mostafa Langarizadeh, Ladan Ajori","doi":"10.1186/s12911-025-02904-0","DOIUrl":"10.1186/s12911-025-02904-0","url":null,"abstract":"<p><strong>Background: </strong>The HELLP syndrome represents three complications: hemolysis, elevated liver enzymes, and low platelet count. Since the causes and pathogenesis of HELLP syndrome are not yet fully known and well understood, distinguishing it from other pregnancy-related disorders is complicated. Furthermore, late diagnosis leads to a delay in treatment, which challenges disease management. The present study aimed to present a machine learning (ML) attitude for diagnosing HELLP syndrome based on non-invasive parameters.</p><p><strong>Method: </strong>This cross-sectional study was conducted on 384 patients in Tajrish Hospital, Tehran, Iran, during 2010-2021 in four stages. In the first stage, data elements were identified using a literature review and Delphi method. Then, patient records were gathered, and in the third stage, the dataset was preprocessed and prepared for modeling. Finally, ML models were implemented, and their evaluation metrics were compared.</p><p><strong>Results: </strong>A total of 21 variables were included in this study after the first stage. Among all the ML algorithms, multi-layer perceptron and deep learning performed the best, with an F1 score of more than 99%.In all three evaluation scenarios of 5fold and 10fold cross-validation, the K-nearest neighbors (KNN), random forest (RF), AdaBoost, XGBoost, and logistic regression (LR) had an F1 score of over 0.95, while this value was around 0.90 for support vector machine (SVM), and the lowest values were below 0.90 for decision tree (DT). According to the modeling output, some variables, such as platelet, gestational age, and alanine aminotransferase (ALT), were the most important in diagnosing HELLP syndrome.</p><p><strong>Conclusion: </strong>The present work indicated that ML algorithms can be used successfully in the development of HELLP syndrome diagnosis models. Other algorithms besides DTs have an F1 score above 0.90. In addition, this study demonstrated that biomarker features (among all features) have the most significant impact on the diagnosis of HELLP syndrome.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"135"},"PeriodicalIF":3.3,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11916871/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143647286","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":"Predictive ability of visit-to-visit glucose variability on diabetes complications.","authors":"Xin Rou Teh, Panu Looareesuwan, Oraluck Pattanaprateep, Anuchate Pattanateepapon, John Attia, Ammarin Thakkinstian","doi":"10.1186/s12911-025-02964-2","DOIUrl":"10.1186/s12911-025-02964-2","url":null,"abstract":"<p><strong>Background: </strong>Identification of prognostic factors for diabetes complications are crucial. Glucose variability (GV) and its association with diabetes have been studied extensively but the inclusion of measures of glucose variability (GVs) in prognostic models is largely lacking. This study aims to assess which GVs (i.e., coefficient of variation (CV), standard deviation (SD), and time-varying) are better in predicting diabetic complications, including cardiovascular disease (CVD), diabetic retinopathy (DR), and chronic kidney disease (CKD). The model performance between traditional statistical models (adjusting for covariates) and machine learning (ML) models were compared.</p><p><strong>Methods: </strong>A retrospective cohort of type 2 diabetes (T2D) patients between 2010 and 2019 in Ramathibodi Hospital was created. Complete case analyses were used. Three GVs using HbA1c and fasting plasma glucose (FPG) were considered including CV, SD, and time-varying. Cox proportional hazard regression, ML random survival forest (RSF) and left-truncated, right-censored (LTRC) survival forest were compared in two different data formats (baseline and longitudinal datasets). Adjusted hazard ratios with 95% confidence intervals were used to report the association between three GVs and diabetes complications. Model performance was evaluated using C-statistics along with feature importance in ML models.</p><p><strong>Results: </strong>A total of 40,662 T2D patients, mostly female (61.7%), with mean age of 57.2 years were included. After adjusting for covariates, HbA1c-CV, HbA1c-SD, FPG-CV and FPG-SD were all associated with CVD, DR and CKD, whereas time-varying HbA1c and FPG were associated with DR and CKD only. The CPH and RSF for DR (C-indices: 0.748-0.758 and 0.774-0.787) and CKD models (C-indices: 0.734-0.750 and 0.724-0.740) had modestly better performance than CVD models (C-indices: 0.703-0.730 and 0.698-0.727). Based on RSF feature importance, FPG GV measures ranked higher than HbA1c GV, and both GVs were the most important for DR prediction. Both traditional and ML models had similar performance.</p><p><strong>Conclusions: </strong>We found that GVs based on HbA1c and FPG had comparable performance. Thus, FPG GV may be used as a potential monitoring parameter when HbA1c is unavailable or less accessible.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"134"},"PeriodicalIF":3.3,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11917057/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143647279","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":"Context factors in clinical decision-making: a scoping review.","authors":"Katharina Schuler, Ian-C Jung, Maria Zerlik, Waldemar Hahn, Martin Sedlmayr, Brita Sedlmayr","doi":"10.1186/s12911-025-02965-1","DOIUrl":"10.1186/s12911-025-02965-1","url":null,"abstract":"<p><strong>Background: </strong>Clinical decision support systems (CDSS) frequently exhibit insufficient contextual adaptation, diminishing user engagement. To enhance the sensitivity of CDSS to contextual conditions, it is crucial first to develop a comprehensive understanding of the context factors influencing the clinical decision-making process. Therefore, this study aims to systematically identify and provide an extensive overview of contextual factors affecting clinical decision-making from the literature, enabling their consideration in the future implementation of CDSS.</p><p><strong>Methods: </strong>A scoping review was conducted following the PRISMA-ScR guidelines to identify context factors in the clinical decision-making process. Searches were performed across nine databases: PubMed, APA PsycInfo, APA PsyArticles, PSYINDEX, CINAHL, Scopus, Embase, Web of Science, and LIVIVO. The search strategy focused on combined terms related to contextual factors and clinical decision-making. Included articles were original research articles written in English or German that involved empirical investigations related to clinical decision-making. The identified context factors were categorized using the card sorting method to ensure accurate classification.</p><p><strong>Results: </strong>The data synthesis included 84 publications, from which 946 context factors were extracted. These factors were assigned to six primary entities through card sorting: patient, physician, patient's family, institution, colleagues, and disease treatment. The majority of the identified context factors pertained to individual characteristics of the patient, such as health status and demographic attributes, as well as individual characteristics of the physician, including demographic data, skills, and knowledge.</p><p><strong>Conclusion: </strong>This study provides a comprehensive overview of context factors in clinical decision-making previously investigated in the literature, highlighting the complexity and diversity of contextual influences on the decision-making process. By offering a detailed foundation of identified context factors, this study paves the way for future research to develop more effective, context-sensitive CDSS, enhancing personalized medicine and optimizing clinical outcomes with implications for practice and policy.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"133"},"PeriodicalIF":3.3,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11912758/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143647278","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":"Artificial intelligence-based risk assessment tools for sexual, reproductive and mental health: a systematic review.","authors":"Shifat Islam, Rifat Shahriyar, Abhishek Agarwala, Marzia Zaman, Shamim Ahamed, Rifat Rahman, Moinul H Chowdhury, Farhana Sarker, Khondaker A Mamun","doi":"10.1186/s12911-025-02864-5","DOIUrl":"10.1186/s12911-025-02864-5","url":null,"abstract":"<p><strong>Background: </strong>Artificial intelligence (AI), which emulates human intelligence through knowledge-based heuristics, has transformative impacts across various industries. In the global healthcare sector, there is a pressing need for advanced risk assessment tools due to the shortage of healthcare workers to manage the health needs of the growing population effectively. AI-based tools such as triage systems, symptom checkers, and risk prediction models are poised to democratize healthcare. This systematic review aims to comprehensively assess the current landscape of AI tools in healthcare and identify areas for future research, focusing particularly on sexual reproductive and mental health.</p><p><strong>Methods: </strong>Adhering to PRISMA guidelines, this review utilized data from seven databases: Science Direct, PubMed, SAGE, ACM Digital Library, Springer, IEEE Xplore, and Wiley. The selection process involved a rigorous screening of titles, abstracts, and full-text examinations of peer-reviewed articles published in English from 2018 to 2023. To ensure the quality of the studies, two independent reviewers applied the PROBAST and QUADAS-2 tools to evaluate the risk of bias in prognostic and diagnostic studies, respectively. Data extraction was also independently conducted.</p><p><strong>Results: </strong>Out of 1743 peer-reviewed articles screened, 63 articles (3.61%) met the inclusion criteria and were included in this study. These articles predominantly utilized clinical vignettes, demographic data, and medical data from online sources. Of the studies analyzed, 61.9% focused on sexual and reproductive health, while 38.1% addressed mental health assessment tools. The analysis revealed an increasing trend in research output over the review period and a notable disparity between developed and developing countries. The review highlighted that AI-based systems could outperform traditional clinical methods when implemented correctly.</p><p><strong>Conclusions: </strong>The findings indicate that integrating AI-based models into existing clinical systems can lead to substantial improvements in healthcare delivery and outcomes. However, future research should prioritize obtaining larger and more diverse datasets, including those from underrepresented populations, to reduce biases and disparities. Additionally, for AI-based healthcare interventions to be widely adopted, transparency and ethical considerations must be addressed, ensuring these technologies are used responsibly and effectively in practical scenarios.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"132"},"PeriodicalIF":3.3,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11912754/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143647277","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":"Risk prediction of hyperuricemia based on particle swarm fusion machine learning solely dependent on routine blood tests.","authors":"Min Fang, Chengjie Pan, Xiaoyi Yu, Wenjuan Li, Ben Wang, Huajian Zhou, Zhenying Xu, Genyuan Yang","doi":"10.1186/s12911-025-02956-2","DOIUrl":"10.1186/s12911-025-02956-2","url":null,"abstract":"<p><p>Hyperuricemia has seen a continuous increase in incidence and a trend towards younger patients in recent years, posing a serious threat to human health and highlighting the urgency of using technological means for disease risk prediction. Existing risk prediction models for hyperuricemia typically include two major categories of indicators: routine blood tests and biochemical tests. The potential of using routine blood tests alone for prediction has not yet been explored. Therefore, this paper proposes a hyperuricemia risk prediction model that integrates Particle Swarm Optimization (PSO) with machine learning, which can accurately assess the risk of hyperuricemia by relying solely on routine blood data. In addition, an interpretability method based on Explainable Artificial Intelligence(XAI) is introduced to help medical staff and patients understand how the model makes decisions. This paper uses Cohen's d value to compare the differences in indicators between hyperuricemia and non-hyperuricemia patients and identifies risk factors through multivariate logistic regression. Subsequently, a risk prediction model is constructed based on the parameter optimization of five machine learning models using the PSO algorithm. The accuracy and sensitivity of the proposed particle swarm fusion Stacking model reach 97.8% and 97.6%, marking an improvement in accuracy of over 11% compared to the state-of-the-art models. Finally, a sensitivity analysis of factors affecting the prediction results is conducted using the XAI method. This paper has also developed a Health Portrait Platform that integrates the proposed risk prediction models, enabling real-time online health risk assessment. Since only routine blood test data are used, the new model has better feasibility and scalability, providing a valuable reference for assessing the risk of hyperuricemia occurrence.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"131"},"PeriodicalIF":3.3,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11910002/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143633742","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 model for the early detection of Gestational Diabetes Mellitus.","authors":"Hesham Zaky, Eleni Fthenou, Luma Srour, Thomas Farrell, Mohammed Bashir, Nady El Hajj, Tanvir Alam","doi":"10.1186/s12911-025-02947-3","DOIUrl":"10.1186/s12911-025-02947-3","url":null,"abstract":"<p><strong>Background: </strong>Gestational Diabetes Mellitus (GDM) is one of the most common medical complications during pregnancy. In the Gulf region, the prevalence of GDM is higher than in other parts of the world. Thus, there is a need for the early detection of GDM to avoid critical health conditions in newborns and post-pregnancy complexities of mothers.</p><p><strong>Methods: </strong>In this article, we propose a machine learning (ML)-based techniques for early detection of GDM. For this purpose, we considered clinical measurements taken during the first trimester to predict the onset of GDM in the second trimester.</p><p><strong>Results: </strong>The proposed ensemble-based model achieved high accuracy in predicting the onset of GDM with around 89% accuracy using only the first trimester data. We confirmed biomarkers, i.e., a history of high glucose level/diabetes, insulin and cholesterol, which align with the previous studies. Moreover, we proposed potential novel biomarkers such as HbA1C %, Glucose, MCH, NT pro-BNP, HOMA-IR- (22.5 Scale), HOMA-IR- (405 Scale), Magnesium, Uric Acid. C-Peptide, Triglyceride, Urea, Chloride, Fibrinogen, MCHC, ALT, family history of Diabetes, Vit B12, TSH, Potassium, Alk Phos, FT4, Homocysteine Plasma LC-MSMS, Monocyte Auto.</p><p><strong>Conclusion: </strong>We believe our findings will complement the current clinical practice of GDM diagnosis at an early stage of pregnancy, leading toward minimizing its burden on the healthcare system.Source code is available in GitHub at: https://github.com/H-Zaky/GD.git.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"130"},"PeriodicalIF":3.3,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11905636/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143623583","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":"Pseudonymization tools for medical research: a systematic review.","authors":"Hammam Abu Attieh, Armin Müller, Felix Nikolaus Wirth, Fabian Prasser","doi":"10.1186/s12911-025-02958-0","DOIUrl":"10.1186/s12911-025-02958-0","url":null,"abstract":"<p><strong>Background: </strong>Pseudonymization is an important technique for the secure and compliant use of medical data in research. At its core, pseudonymization is a process in which directly identifying information is separated from medical research data. Due to its importance, a wide range of pseudonymization tools and services have been developed, and researchers face the challenge of selecting an appropriate tool for their research projects. This review aims to address this challenge by systematically comparing existing tools.</p><p><strong>Methods: </strong>A systematic review was performed and is reported according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines where applicable. The search covered PubMed and Web of Science to identify pseudonymization tools documented in the scientific literature. The tools were assessed based on predefined criteria across four key dimensions that describe researchers' requirements: (1) single-center vs. multi-center use, (2) short-term vs. long-term projects, (3) small data vs. big data processing, and (4) integration vs. standalone functionality.</p><p><strong>Results: </strong>From an initial pool of 1,052 papers, 92 were selected for detailed full-text review after the title and abstract screening. This led to the identification of 20 pseudonymization tools, of which 10 met our inclusion criteria and were assessed. The results show that there are differences between the tools that make them more or less suited for research projects differing in regards to the dimensions described above, enabling us to provide targeted recommendations.</p><p><strong>Conclusions: </strong>The landscape of existing pseudonymization tools is heterogeneous, and researchers need to carefully select the appropriate solutions for their research projects. Our findings highlight two Software-as-a-Service-based solutions that enable centralized use without local infrastructure, one tool for retrospective pseudonymization of existing databases, two tools suitable for local deployment in smaller, short-term projects, and two tools well-suited for local deployment in large, multi-center studies.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"128"},"PeriodicalIF":3.3,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11905493/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143613488","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}