BMC Medical Informatics and Decision Making最新文献

{"title":"Combining theory and usability testing to inform optimization and implementation of an online primary care depression management tool.","authors":"Nicola McCleary, Justin Presseau, Isabelle Perkins, Brittany Mutsaers, Claire E Kendall, Janet Yamada, Katharine Gillis, Douglas Green","doi":"10.1186/s12911-024-02733-7","DOIUrl":"10.1186/s12911-024-02733-7","url":null,"abstract":"<p><strong>Background: </strong>The 'Ottawa Depression Algorithm' is an evidence-based online tool developed to support primary care professionals care for adults with depression. Uptake of such tools require provider behaviour change. Identifying issues which may impact use of an innovation in routine practice (i.e. barriers to and enablers of behaviour change) informs the selection of implementation strategies that can be deployed with the tool to support use. However, established theory-informed barriers/enablers assessment methods may be less well suited to identifying issues with tool usability. User testing methods can help to determine whether the tool itself is optimally designed. We aimed to integrate these two methodological approaches to i) identify issues impacting the usability of algorithm; and ii) identify barriers to and enablers of algorithm use in routine practice.</p><p><strong>Methods: </strong>We conducted semi-structured interviews with primary care professionals in Ottawa, Canada. To evaluate usability, participants used a written patient scenario to work through the algorithm while verbalizing their thoughts ('Think Aloud'). Participants were then asked about factors influencing algorithm use in routine practice (informed by the Theoretical Domains Framework). We used the codebook approach to thematic analysis to assign statements to pre-specified codes and develop themes pertaining to usability and routine use.</p><p><strong>Results: </strong>We interviewed 20 professionals from seven practices. Usability issues were summarised within five themes: Optimizing content and flow to align with issues faced in practice, Enhancing the most useful algorithm components, Interactivity of the algorithm and embedded tools, Clarity of presence, purpose, or function of components, and Navigational challenges and functionality of links. Barriers to and enablers of routine use were summarised within five themes: Getting to know the algorithm, Alignment with roles and pathways of influence, Integration with current ways of working, Contexts for use, and Anticipated benefits and concerns about patient communication.</p><p><strong>Conclusions: </strong>Whilst the Ottawa Depression Algorithm was viewed as a useful tool, specific usability issues and barriers to use were identified. Supplementing a theory-based barriers/enablers assessment with usability testing provided enhanced insights to inform optimization and implementation of this clinical tool. We have provided a methods guide for others who may wish to apply this approach.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"25"},"PeriodicalIF":3.3,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11734350/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143000503","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":"Derivation and validation of a clinical predictive model for longer duration diarrhea among pediatric patients in Kenya using machine learning algorithms.","authors":"Billy Ogwel, Vincent H Mzazi, Alex O Awuor, Caleb Okonji, Raphael O Anyango, Caren Oreso, John B Ochieng, Stephen Munga, Dilruba Nasrin, Kirkby D Tickell, Patricia B Pavlinac, Karen L Kotloff, Richard Omore","doi":"10.1186/s12911-025-02855-6","DOIUrl":"10.1186/s12911-025-02855-6","url":null,"abstract":"<p><strong>Background: </strong>Despite the adverse health outcomes associated with longer duration diarrhea (LDD), there are currently no clinical decision tools for timely identification and better management of children with increased risk. This study utilizes machine learning (ML) to derive and validate a predictive model for LDD among children presenting with diarrhea to health facilities.</p><p><strong>Methods: </strong>LDD was defined as a diarrhea episode lasting ≥ 7 days. We used 7 ML algorithms to build prognostic models for the prediction of LDD among children < 5 years using de-identified data from Vaccine Impact on Diarrhea in Africa study (N = 1,482) in model development and data from Enterics for Global Health Shigella study (N = 682) in temporal validation of the champion model. Features included demographic, medical history and clinical examination data collected at enrolment in both studies. We conducted split-sampling and employed K-fold cross-validation with over-sampling technique in the model development. Moreover, critical predictors of LDD and their impact on prediction were obtained using an explainable model agnostic approach. The champion model was determined based on the area under the curve (AUC) metric. Model calibrations were assessed using Brier, Spiegelhalter's z-test and its accompanying p-value.</p><p><strong>Results: </strong>There was a significant difference in prevalence of LDD between the development and temporal validation cohorts (478 [32.3%] vs 69 [10.1%]; p < 0.001). The following variables were associated with LDD in decreasing order: pre-enrolment diarrhea days (55.1%), modified Vesikari score(18.2%), age group (10.7%), vomit days (8.8%), respiratory rate (6.5%), vomiting (6.4%), vomit frequency (6.2%), rotavirus vaccination (6.1%), skin pinch (2.4%) and stool frequency (2.4%). While all models showed good prediction capability, the random forest model achieved the best performance (AUC [95% Confidence Interval]: 83.0 [78.6-87.5] and 71.0 [62.5-79.4]) on the development and temporal validation datasets, respectively. While the random forest model showed slight deviations from perfect calibration, these deviations were not statistically significant (Brier score = 0.17, Spiegelhalter p-value = 0.219).</p><p><strong>Conclusions: </strong>Our study suggests ML derived algorithms could be used to rapidly identify children at increased risk of LDD. Integrating ML derived models into clinical decision-making may allow clinicians to target these children with closer observation and enhanced management.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"28"},"PeriodicalIF":3.3,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11737202/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143000571","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":"Causal analysis for multivariate integrated clinical and environmental exposures data.","authors":"Meghamala Sinha, Perry Haaland, Ashok Krishnamurthy, Bo Lan, Stephen A Ramsey, Patrick L Schmitt, Priya Sharma, Hao Xu, Karamarie Fecho","doi":"10.1186/s12911-025-02849-4","DOIUrl":"10.1186/s12911-025-02849-4","url":null,"abstract":"<p><p>Electronic health records (EHRs) provide a rich source of observational patient data that can be explored to infer underlying causal relationships. These causal relationships can be applied to augment medical decision-making or suggest hypotheses for healthcare research. In this study, we explored a large-scale EHR dataset on patients with asthma or related conditions (N = 14,937). The dataset included integrated data on features representing demographic factors, clinical measures, and environmental exposures. The data were accessed via a service named the Integrated Clinical and Environmental Service (ICEES). We estimated underlying causal relationships from the data to identify significant predictors of asthma attacks. We also performed simulated interventions on the inferred causal network to detect the causal effects, in terms of shifts in probability distribution for asthma attacks.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"27"},"PeriodicalIF":3.3,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11736916/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143000501","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 radiomics and deep learning nomogram developed and validated for predicting no-collapse survival in patients with osteonecrosis after multiple drilling.","authors":"Fan Liu, De-Bao Zhang, Shi-Huan Cheng, Gui-Shan Gu","doi":"10.1186/s12911-025-02859-2","DOIUrl":"10.1186/s12911-025-02859-2","url":null,"abstract":"<p><strong>Purpose: </strong>Identifying patients who may benefit from multiple drilling are crucial. Hence, the purpose of the study is to utilize radiomics and deep learning for predicting no-collapse survival in patients with femoral head osteonecrosis.</p><p><strong>Methods: </strong>Patients who underwent multiple drilling were enrolled. Radiomics and deep learning features were extracted from pelvic radiographs and selected by LASSO-COX regression, radiomics and DL signature were then built. The clinical variables were selected through univariate and multivariate Cox regression analysis, and the clinical, radiomics, DL and DLRC model were constructed. Model performance was evaluated using the concordance index (C-index), area under the receiver operating characteristic curve (AUC), net reclassification index (NRI), integrated discrimination improvement (IDI), calibration curves, and Decision Curve Analysis (DCA).</p><p><strong>Results: </strong>A total of 144 patients (212 hips) were included in the study. ARCO classification, bone marrow edema, and combined necrotic angle were identified as independent risk factors for collapse. The DLRC model exhibited superior discrimination ability with higher C-index of 0.78 (95%CI: 0.73-0.84) and AUC values (0.83 and 0.87) than other models. The DLRC model demonstrated superior predictive performance with a higher C-index of 0.78 (95% CI: 0.73-0.84) and area under the curve (AUC) values of 0.83 for 3-year survival and 0.87 for 5-year survival, outperforming other models. The DLRC model also exhibited favorable calibration and clinical utility, with Kaplan-Meier survival curves revealing significant differences in survival rates between high-risk and low-risk cohorts.</p><p><strong>Conclusion: </strong>This study introduces a novel approach that integrates radiomics and deep learning techniques and demonstrates superior predictive performance for no-collapse survival after multiple drilling. It offers enhanced discrimination ability, favorable calibration, and strong clinical utility, making it a valuable tool for stratifying patients into high-risk and low-risk groups. The model has the potential to provide personalized risk assessment, guiding treatment decisions and improving outcomes in patients with osteonecrosis of the femoral head.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"26"},"PeriodicalIF":3.3,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11734477/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143000632","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":"Identifying effective immune biomarkers in alopecia areata diagnosis based on machine learning methods.","authors":"Qingde Zhou, Lan Lan, Wei Wang, Xinchang Xu","doi":"10.1186/s12911-025-02853-8","DOIUrl":"10.1186/s12911-025-02853-8","url":null,"abstract":"<p><strong>Background: </strong>Alopecia areata (AA) is a common non-scarring hair loss disorder associated with autoimmune conditions. However, the pathobiology of AA is not well understood, and there is no targeted therapy available for AA.  METHODS: In this study, differential gene expression analysis, immune status assessment, weighted correlation network analysis (WGCNA), and functional enrichment analysis were performed to identify shared genes associated with both immunological response and AA. Machine learning methods were then used to identify three hub genes as potential diagnostic markers for AA. External validation was performed, and the correlation of hub genes with immune infiltration, immune checkpoint genes, and key marker genes and pathways were evaluated.</p><p><strong>Results: </strong>Three hub genes were identified, which accurately predicted the progression of AA and the immune status. The hub genes were found to be diagnostic markers for AA with high predictive accuracy. External validation confirmed the efficacy of these markers in identifying AA patients.</p><p><strong>Conclusion: </strong>Overall, the study provides a novel approach for the diagnosis, prevention, and treatment of AA. The findings could potentially lead to the development of targeted therapies for AA based on the identified hub genes. The study also highlights the potential of machine learning and bioinformatics analysis in identifying new biomarkers for autoimmune diseases.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"23"},"PeriodicalIF":3.3,"publicationDate":"2025-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11734347/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142982130","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: Which criteria are important in usability evaluation of mHealth applications: an umbrella review.","authors":"Zahra Galavi, Mahdieh Montazeri, Reza Khajouei","doi":"10.1186/s12911-025-02860-9","DOIUrl":"10.1186/s12911-025-02860-9","url":null,"abstract":"","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"22"},"PeriodicalIF":3.3,"publicationDate":"2025-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11731404/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142982908","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":"%diag_test: a generic SAS macro for evaluating diagnostic accuracy measures for multiple diagnostic tests.","authors":"Jacques K Muthusi, Peter W Young, Frankline O Mboya, Samuel M Mwalili","doi":"10.1186/s12911-024-02808-5","DOIUrl":"10.1186/s12911-024-02808-5","url":null,"abstract":"<p><strong>Background: </strong>Measures of diagnostic test accuracy provide evidence of how well a test correctly identifies or rules-out disease. Commonly used diagnostic accuracy measures (DAMs) include sensitivity and specificity, predictive values, likelihood ratios, area under the receiver operator characteristic curve (AUROC), area under precision-recall curves (AUPRC), diagnostic effectiveness (accuracy), disease prevalence, and diagnostic odds ratio (DOR) etc. Most available analysis tools perform accuracy testing for a single diagnostic test using summarized data. We developed a SAS macro for evaluating multiple diagnostic tests using individual-level data that creates a 2 × 2 summary table, AUROC and AUPRC as part of output.</p><p><strong>Methods: </strong>The SAS macro presented here is automated to reduce analysis time and transcription errors. It is simple to use as the user only needs to specify the input dataset, \"standard\" and \"test\" variables and threshold values. It creates a publication-quality output in Microsoft Word and Excel showing more than 15 different accuracy measures together with overlaid AUROC and AUPRC graphics to help the researcher in making decisions to adopt or reject diagnostic tests. Further, it provides for additional variance estimation methods other than the normal distribution approximation.</p><p><strong>Results: </strong>We tested the macro for quality control purposes by reproducing results from published work on evaluation of multiple types of dried blood spots (DBS) as an alternative for human immunodeficiency virus (HIV) viral load (VL) monitoring in resource-limited settings compared to plasma, the gold-standard. Plasma viral load reagents are costly, and blood must be prepared in a reference laboratory setting by a qualified technician. On the other hand, DBS are easy to prepare without these restrictions. This study evaluated the suitability of DBS from venous, microcapillary and direct spotting DBS, hence multiple diagnostic tests which were compared to plasma specimen. We also used the macro to reproduce results of published work on evaluating performance of multiple classification machine learning algorithms for predicting coronary artery disease.</p><p><strong>Conclusion: </strong>The SAS macro presented here is a powerful analytic tool for analyzing data from multiple diagnostic tests. The SAS programmer can modify the source code to include other diagnostic measures and variance estimation methods. By automating analysis, the macro adds value by saving analysis time, reducing transcription errors, and producing publication-quality outputs.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"21"},"PeriodicalIF":3.3,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11730795/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142977760","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":"Mortality and morbidity patterns in Yaoundé, Cameroon: an ICD-11 classification-based analysis.","authors":"Georges Nguefack-Tsague, Fabrice Zobel Lekeumo Cheuyem, Boris Edmond Noah, Valérie Ndobo-Koe, Adidja Amani, Léa Melataguia Mekontchou, Marie Ntep Gweth, Annick Collins Mfoulou Minso Assala, Marie Nicole Ngoufack, Pierre René Binyom","doi":"10.1186/s12911-025-02854-7","DOIUrl":"10.1186/s12911-025-02854-7","url":null,"abstract":"<p><strong>Background: </strong>In Cameroon, like in many other resource-limited countries, data generated by health settings including morbidity and mortality parameters are not always uniform. In the absence of a national guideline necessary for the standardization and harmonization of data, precision of data required for effective decision-making is therefore not guaranteed. The objective of the present study was to assess the reporting style of morbidity and mortality data in healthcare settings.</p><p><strong>Methods: </strong>An institutional-based cross-sectional study was carried out from May to June 2022 at the Yaoundé Central Hospital. A questionnaire was used to assess the need to set up a standard tool to improve the reporting system. Medical records were used to collect mortality and morbidity data which were then compared to the International Statistical Classification of Diseases and Related Health Problems-11 (ICD-11) codification. Data were analyzed using IBM-SPSS version 26.</p><p><strong>Results: </strong>Out of 200 patients' morbidity causes recorded, nearly three-quarter (74.0%) were heterogeneous, and two over five (41.0%) of mortality causes reported were also heterogeneous. Most of respondents stated the need to set up a standard tool for collecting mortality and morbidity data (83.6%). Less than one-fifth (18.2%) of health care providers were able to understand data flow, correctly archived data (36.6%) and used electronic tools for data quality control (40.0%).</p><p><strong>Conclusion: </strong>There were high levels of heterogeneities of morbidity and mortality causes among patients admitted to the Yaoundé Central Hospital in 2021. It is therefore urgent that Cameroon national health authorities implement the ICD-11 to allow the systematic recording, analysis, interpretation and comparison of mortality and morbidity data collected in Yaoundé Central Hospital at different times; and ensure interoperability and reusability of recorded data for medical decision support.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"19"},"PeriodicalIF":3.3,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11730474/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142977763","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":"Natural language processing to identify suicidal ideation and anhedonia in major depressive disorder.","authors":"L Alexander Vance, Leslie Way, Deepali Kulkarni, Emily O C Palmer, Abhijit Ghosh, Melissa Unruh, Kelly M Y Chan, Amey Girdhari, Joydeep Sarkar","doi":"10.1186/s12911-025-02851-w","DOIUrl":"10.1186/s12911-025-02851-w","url":null,"abstract":"<p><strong>Background: </strong>Anhedonia and suicidal ideation are symptoms of major depressive disorder (MDD) that are not regularly captured in structured scales but may be captured in unstructured clinical notes. Natural language processing (NLP) techniques may be used to extract longitudinal data on suicidal behaviors and anhedonia within unstructured clinical notes. This study assessed the accuracy of using NLP techniques on electronic health records (EHRs) to identify these symptoms among patients with MDD.</p><p><strong>Methods: </strong>EHR-derived, de-identified data were used from the NeuroBlu Database (version 23R1), a longitudinal behavioral health real-world database. Mental health clinicians annotated instances of anhedonia and suicidal symptoms in clinical notes creating a ground truth. Interrater reliability (IRR) was calculated using Krippendorff's alpha. A novel transformer architecture-based NLP model was trained on clinical notes to recognize linguistic patterns and contextual cues. Each sentence was categorized into one of four labels: (1) anhedonia; (2) suicidal ideation without intent or plan; (3) suicidal ideation with intent or plan; (4) absence of suicidal ideation or anhedonia. The model was assessed using positive predictive values (PPV), negative predictive values, sensitivity, specificity, F1-score, and AUROC.</p><p><strong>Results: </strong>The model was trained, tested, and validated on 2,198, 1,247, and 1,016 distinct clinical notes, respectively. IRR was 0.80. For anhedonia, suicidal ideation with intent or plan, and suicidal ideation without intent or plan the model achieved a PPV of 0.98, 0.93, and 0.87, an F1-score of 0.98, 0.91, and 0.89 during training and a PPV of 0.99, 0.95, and 0.87 and F1-score of 0.99, 0.95, and 0.89 during validation.</p><p><strong>Conclusions: </strong>NLP techniques can leverage contextual information in EHRs to identify anhedonia and suicidal symptoms in patients with MDD. Integrating structured and unstructured data offers a comprehensive view of MDD's trajectory, helping healthcare providers deliver timely, effective interventions. Addressing current limitations will further enhance NLP models, enabling more accurate extraction of critical clinical features and supporting personalized, proactive mental health care.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"20"},"PeriodicalIF":3.3,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11730826/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142977765","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 value of machine learning for the progression of gestational diabetes mellitus to type 2 diabetes: a systematic review and meta-analysis.","authors":"Meng Zhao, Zhixin Yao, Yan Zhang, Lidan Ma, Wenquan Pang, Shuyin Ma, Yijun Xu, Lili Wei","doi":"10.1186/s12911-024-02848-x","DOIUrl":"10.1186/s12911-024-02848-x","url":null,"abstract":"<p><strong>Background: </strong>This systematic review aims to explore the early predictive value of machine learning (ML) models for the progression of gestational diabetes mellitus (GDM) to type 2 diabetes mellitus (T2DM).</p><p><strong>Methods: </strong>A comprehensive and systematic search was conducted in Pubmed, Cochrane, Embase, and Web of Science up to July 02, 2024. The quality of the studies included was assessed. The risk of bias was assessed through the prediction model risk of bias assessment tool and a graph was drawn accordingly. The meta-analysis was performed using Stata15.0.</p><p><strong>Results: </strong>A total of 13 studies were included in the present review, involving 11,320 GDM patients and 22 ML models. The meta-analysis for ML models showed a pooled C-statistic of 0.82 (95% CI: 0.79 ~ 0.86), a pooled sensitivity of 0.76 (0.72 ~ 0.80), and a pooled specificity of 0.57 (0.50 ~ 0.65).</p><p><strong>Conclusion: </strong>ML has favorable diagnostic accuracy for the progression of GDM to T2DM. This provides evidence for the development of predictive tools with broader applicability.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"18"},"PeriodicalIF":3.3,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11727323/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142977777","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}