BMC Medical Informatics and Decision Making最新文献

{"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}

{"title":"Evolution of clinical Health Information Exchanges to population health resources: a case study of the Indiana network for patient care.","authors":"Karmen S Williams, Saurabh Rahurkar, Shaun J Grannis, Titus K Schleyer, Brian E Dixon","doi":"10.1186/s12911-025-02933-9","DOIUrl":"10.1186/s12911-025-02933-9","url":null,"abstract":"<p><strong>Background: </strong>Motivated by the Triple Aim, US health care policy is expanding its focus from individual patient care to include population health management. Health Information Exchanges are positioned to play an important role in that expansion.</p><p><strong>Objective: </strong>The objective is to describe the evolution of the Indiana Network for Patient Care (INPC) and discuss examples of its innovations that support both population health and clinical applications.</p><p><strong>Methods: </strong>A descriptive analytical approach was used to gather information on the INPC. This included a literature review of recent systematic and scoping reviews, collection of research that used INPC data as a resource, and data abstracted by Regenstrief Data Services to understand the breadth of uses for the INPC as a data resource.</p><p><strong>Results: </strong>Although INPC data are primarily gathered from and used in healthcare settings, their use for population health management and research has increased. By December 2023, the INPC contained nearly 25 million patients, a significant growth from 3.5 million in 2004. This growth was a result of the use of INPC data for population health surveillance, clinical applications for data, disease registries, Patient-Centered Data Homes, non-clinical population health advancements, and accountable care organization connections with Health Information Exchanges.</p><p><strong>Conclusion: </strong>By structuring services on the fundamental building blocks, expanding the focus to population health, and ensuring value in the services provided to the stakeholders, Health Information Exchanges are uniquely positioned to support both population health and clinical applications.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"97"},"PeriodicalIF":3.3,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11849299/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143490841","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 of post-induction hypotension: identifying risk factors and enhancing anesthesia management.","authors":"Ming Chen, Dingyu Zhang","doi":"10.1186/s12911-025-02930-y","DOIUrl":"10.1186/s12911-025-02930-y","url":null,"abstract":"<p><strong>Background: </strong>Post-induction hypotension (PIH) increases surgical complications including myocardial injury, acute kidney injury, delirium, stroke, prolonged hospitalization, and endangerment of the patient's life. Machine learning is an effective tool to analyze large amounts of data and identify perioperative complication factors. This study aims to identify risk factors for PIH and develop predictive models to support anesthesia management.</p><p><strong>Methods: </strong>A dataset of 5406 patients was analyzed using machine learning methods. Logistic regression, random forest, XGBoost, and neural network models were compared. Model performance was evaluated using the area under the receiver operating characteristic curve (AUROC), calibration curves, and decision curve analysis (DCA).</p><p><strong>Results: </strong>The logistic regression model achieved an AUROC of 0.74 (95% CI: 0.71-0.77), outperforming the random forest (AUROC: 0.71), XGBoost (AUROC: 0.72), and neural network (AUROC: 0.72) models. In terms of calibration, logistic regression demonstrated superior performance, as reflected by Brier Scores and calibration curves, followed by XGBoost, random forest, and neural network. Decision curve analysis indicated that the logistic regression model provided the greatest clinical utility among all models. Baseline blood pressure, age, sex, type of surgery, platelet count, and certain anesthesia-inducing drugs were identified as important features.</p><p><strong>Conclusions: </strong>This study provides a valuable tool for personalized preoperative risk assessment and customized anesthesia management, allowing for early intervention and improved patient outcomes. Integration of machine learning models into electronic medical record systems can facilitate real-time risk assessment and prediction.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"96"},"PeriodicalIF":3.3,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11846375/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143476269","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":"User acceptability and perceived impact of a mobile interactive education and support group intervention to improve postnatal health care in northern India: a qualitative study.","authors":"Valentina Cox, Preetika Sharma, Garima Singh Verma, Navneet Gill, Nadia G Diamond-Smith, Mona Duggal, Vijay Kumar, Rashmi Bagga, Jasmeet Kaur, Pushpendra Singh, Alison M El Ayadi","doi":"10.1186/s12911-025-02935-7","DOIUrl":"10.1186/s12911-025-02935-7","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Postnatal care, crucial for preventing and assessing complications after birth, remains low in India. An interactive mHealth community-based postnatal intervention was implemented to promote healthy maternal behaviors through knowledge and social support in rural Northern India. However, there is limited information on how virtual health interventions in resource-constrained settings are perceived by the users and which elements influence their engagement and sustained participation.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;We explored the user perceptions of acceptability and impact of a virtual interactive maternal and child health intervention pilot tested in Punjab State, India, including their perspectives on barriers and facilitators to engage with this intervention.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;This qualitative study was embedded within extensive mixed-method research, and oriented by the Realist Evaluation approach. Sixteen participants were recruited from the parent study. They were identified by purposive sampling to cover diverse levels of attendance and engagement with the intervention. In-depth interviews were conducted by phone. Following translation, a framework analysis was completed to search for the main themes. Feedback was requested from intervention moderators during the process to prioritize local interpretation.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Study participants reported overall satisfaction with the intervention. The mothers appreciated the educational material provided and the communication with other participants and health professionals. Across context, intervention, and actor domains, the barriers most commented on were network and connectivity challenges, lack of time due to household responsibilities, and feeling uncomfortable sharing personal experiences. Family buy-in and support were fundamental for overcoming the high domestic workload and baby care. Another facilitator mentioned was moderators' guidance on using the different intervention modalities. Regarding perceived impact, participants shared that MeSSSSage increased their capability and motivation to breastfeed, seek care as needed, and use contraception according to their preferences. Finally, participants suggested adding more topics to the educational content and adjusting the dynamics within the group calls to improve the intervention.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;This study identifies the high acceptability and perceived impact of a novel postnatal care program in a rural setting, including the users' perceived barriers to engaging with the intervention and possible solutions to overcome them. These findings enable refinement of the ongoing intervention, providing a more robust framing for its scalability and long-term sustainability. On a larger scale, conclusions from this research provide new insights and encouragement to global stakeholders who aspire to improve maternal and neonatal outcomes in low-income and mi","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"93"},"PeriodicalIF":3.3,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11844055/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143467125","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":"Decision tree model for predicting ovarian tumor malignancy based on clinical markers and preoperative circulating blood cells.","authors":"Yingjia Li, Xingping Zhao, Yanhua Zhou, Lina Gong, Enuo Peng","doi":"10.1186/s12911-025-02934-8","DOIUrl":"10.1186/s12911-025-02934-8","url":null,"abstract":"<p><strong>Objective: </strong>Ovarian cancer is a serious malignant tumor threatening women's health. The early diagnosis and effective treatments of ovarian cancer remain inadequate, and about 70% of ovarian cancers are in advanced stages when discovered. This study aimed to use the decision tree method of artificial intelligence machine learning to build a model for predicting the benign and malignant degree of ovarian cancer patients.</p><p><strong>Study design: </strong>A total of 758 patients were included in the study. These patients were diagnosed by B-ultrasound, CT or MR. The clinicopathological features and circulating blood cell indexes were recorded and analyzed. The prediction model of benign and malignant ovarian tumors was constructed by CART decision tree, and the receiver operating characteristic (ROC) curve was drawn to evaluate the predictive value of the decision tree model.</p><p><strong>Results: </strong>It was found that significant predictor variables included age, disease duration, patient general condition and menopausal status, ascites, tumor size, HE4, CA125, ROMA index, and blood routine related indicators (except for basophil count percentage and absolute value). In the constructed decision tree model, ROMA_after was the root node with the maximum information gain. ROMA_after, Mass size (MR/CT), HE4, CA125, platelet number, lymphocyte ratio, white blood cell count, post-menopause, hematocrit and mean platelet volume were important indicators in the decision tree model. The area under the receiver operating characteristic curve of this model for predicting benign and malignant ovarian cancer was 0.86.</p><p><strong>Conclusions: </strong>The decision tree model was successfully constructed based on clinical indicators and preoperative circulating blood cells, and showed better results in predicting benign and malignant ovarian cancer than alone imaging indicators or biomarkers among our data, which means that our model can more accurately predict benign and malignant ovarian cancer.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"94"},"PeriodicalIF":3.3,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11844102/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143466957","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":"Intracranial stenosis prediction using a small set of risk factors in the Tromsø Study.","authors":"Luca Bernecker, Liv-Hege Johnsen, Torgil Riise Vangberg","doi":"10.1186/s12911-025-02896-x","DOIUrl":"10.1186/s12911-025-02896-x","url":null,"abstract":"<p><p>Intracranial atherosclerotic stenosis (ICAS) refers to a narrowing of intracranial arteries due to plaque buildup on the inside of the vessel walls restricting blood flow. Early detection of ICAS is crucial to prevent serious consequences such as stroke. Here we apply three different machine learning methods, such as support vector machines, multi-layer perceptrons and Kolmogorov-Arnold Networks to predict ICAS according to sparse risk factors from blood lipids and demographic data, including smoking habits, age, sex, diabetes, blood pressure lowering and cholesterol-lowering drugs and high-density lipoprotein. We achieved similar performance on classification compared to modern detection algorithms for ICAS in TOF-MRA (time-of-flight magnetic resonance angiography). The prevalence of ICAS in the population is relatively low, which is often case in medicine. While in the medical research community, the issue of low prevalence is established, machine learning-based research in medicine often does not take into account a critical viewpoint of the prevalence in clinical settings of their methods. We showed that with a balanced training/test set an accuracy up to 81% was achievable, while with the inclusion of prevalence, the positive predictive value was at 19% to the prevalence data, changes the performance metrics. Therefore, we highlighted the discrepancy that can arise between the results reported by the models and their clinical relevance. Furthermore, the results demonstrate the predictive potential of limited risk factors, highlighting its potential contribution to a multi-modular classification algorithm based on MRAs.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"95"},"PeriodicalIF":3.3,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11843764/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143466967","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":"Modeling-based design of adaptive control strategy for the effective preparation of 'Disease X'.","authors":"Hao Wang, Weike Zhou, Xia Wang, Yanni Xiao, Sanyi Tang, Biao Tang","doi":"10.1186/s12911-025-02920-0","DOIUrl":"10.1186/s12911-025-02920-0","url":null,"abstract":"<p><p>This study aims at exploring a general and adaptive control strategy to confront the rapid evolution of an emerging infectious disease ('Disease X'), drawing lessons from the management of COVID-19 in China. We employ a dynamic model incorporating age structures and vaccination statuses, which is calibrated using epidemic data. We therefore estimate the cumulative infection rate (CIR) during the first epidemic wave of Omicron variant after China relaxed its zero-COVID policy to be 82.9% (95% CI: 82.3%, 83.5%), with a case fatality rate (CFR) of 0.25% (95% CI: 0.248%, 0.253%). We further show that if the zero-COVID policy had been eased in January 2022, the CIR and CFR would have decreased to 81.64% and 0.205%, respectively, due to a higher level of immunity from vaccination. However, if we ease the zero-COVID policy during the circulation of Delta variant from June 2021, the CIR would decrease to 74.06% while the CFR would significantly increase to 1.065%. Therefore, in the face of a 'Disease X', the adaptive strategies should be guided by multiple factors, the 'zero-COVID-like' policy could be a feasible and effective way for the control of a variant with relative low transmissibility. However, we should ease the strategy as the virus matures into a new variant with much higher transmissibility, particularly when the population is at a high level of immunity.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"92"},"PeriodicalIF":3.3,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11841272/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143457109","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":"Diabetic peripheral neuropathy detection of type 2 diabetes using machine learning from TCM features: a cross-sectional study.","authors":"Zhikui Tian, JiZhong Zhang, Yadong Fan, Xuan Sun, Dongjun Wang, XiaoFei Liu, GuoHui Lu, Hongwu Wang","doi":"10.1186/s12911-025-02932-w","DOIUrl":"10.1186/s12911-025-02932-w","url":null,"abstract":"<p><strong>Aims: </strong>Diabetic peripheral neuropathy (DPN) is the most common complication of diabetes mellitus. Early identification of individuals at high risk of DPN is essential for successful early intervention. Traditional Chinese medicine (TCM) tongue diagnosis, one of the four diagnostic methods, lacks specific algorithms for TCM symptoms and tongue features. This study aims to develop machine learning (ML) models based on TCM to predict the risk of diabetic peripheral neuropathy (DPN) in patients with type 2 diabetes mellitus (T2DM).</p><p><strong>Methods: </strong>A total of 4723 patients were included in the analysis (4430 with T2DM and 293 with DPN). TFDA-1 was used to obtain tongue images during a questionnaire survey. LASSO (least absolute shrinkage and selection operator) logistic regression model with fivefold cross-validation was used to select imaging features, which were then screened using best subset selection. The synthetic minority oversampling technique (SMOTE) algorithm was applied to address the class imbalance and eliminate possible bias. The area under the receiver operating characteristic curve (AUC) was used to evaluate the model's performance. Four ML algorithms, namely logistic regression (LR), random forest (RF), support vector classifier (SVC), and light gradient boosting machine (LGBM), were used to build predictive models for DPN. The importance of covariates in DPN was ranked using classifiers with better performance.</p><p><strong>Results: </strong>The RF model performed the best, with an accuracy of 0.767, precision of 0.718, recall of 0.874, F-1 score of 0.789, and AUC of 0.77. With a value of 0.879, the LGBM model appeared to be the best regarding recall Age, sweating, dark red tongue, insomnia, and smoking were the five most significant RF features. Age, yellow coating, loose teeth, smoking, and insomnia were the five most significant features of the LGBM model.</p><p><strong>Conclusions: </strong>This cross-sectional study demonstrates that the RF and LGBM models can screen for high-risk DPN in T2DM patients using TCM symptoms and tongue features. The identified key TCM-related features, such as age, tongue coating, and other symptoms, may be advantageous in developing preventative measures for T2DM patients.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"90"},"PeriodicalIF":3.3,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11837659/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143448173","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":"Deep learning-based automated guide for defining a standard imaging plane for developmental dysplasia of the hip screening using ultrasonography: a retrospective imaging analysis.","authors":"Kyung-Sik Ahn, Ji Hye Choi, Heejou Kwon, Seoyeon Lee, Yongwon Cho, Woo Young Jang","doi":"10.1186/s12911-025-02926-8","DOIUrl":"10.1186/s12911-025-02926-8","url":null,"abstract":"<p><strong>Background: </strong>We aimed to propose a deep-learning neural network model for automatically detecting five landmarks during a two-dimensional (2D) ultrasonography (US) scan to develop a standard plane for developmental dysplasia of the hip (DDH) screening.</p><p><strong>Method: </strong>A model of global and local networks was developed to detect five landmarks for DDH screening during 2D US. Patients (N = 532) who underwent hip US for DDH screening from January 2016 to December 2021 at a tertiary medical center were enrolled. All datasets were randomly split into training, validation, and test sets in a 70:10:20 ratio for the final assessment of landmark detection. The performance of this model for detecting five landmarks for guiding DDH was analyzed using the root mean square error (RMSE) and dice similarity coefficient.</p><p><strong>Results: </strong>The RMSE value for the five landmarks for diagnosing and classifying DDH using global and local networks was 4.023 ± 3.723. The point results using EfficientNetB2 were 1.69 ± 1.26 (first point), 3.34 ± 2.37 (second point), 2.54 ± 1.61 (third point), 5.92 ± 4.25 (fourth point), and 6.61 ± 4.82 (fifth point).</p><p><strong>Conclusions: </strong>Our deep-learning network model is feasible for detecting five landmarks for DDH using ultrasound images. The primary parameters to determine DDH will be significantly detected by applying the deep-learning model in clinical settings.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"91"},"PeriodicalIF":3.3,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11837398/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143448171","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}