BMC Medical Informatics and Decision Making最新文献

{"title":"Beyond labels: determining the true type of blood gas samples in ICU patients through supervised machine learning.","authors":"Johan Helleberg, Anna Sundelin, Johan Mårtensson, Olav Rooyackers, Ragnar Thobaben","doi":"10.1186/s12911-025-03115-3","DOIUrl":"10.1186/s12911-025-03115-3","url":null,"abstract":"<p><strong>Background: </strong>In the Intensive Care Unit (ICU), data stored in patient data management systems (PDMS) is commonly used in clinical practice and research. Parameters from point-of-care arterial blood gas (BG) analysis are used in the diagnosis and definition of syndromes such as sepsis and ARDS, but manual entry of the blood source (arterial or venous) into the PDMS introduces the risk of mislabeling venous samples as arterial. Our study aimed to employ supervised machine learning to accurately identify blood gas samples as arterial or venous using PDMS data.</p><p><strong>Methods: </strong>A retrospective, single-center observational cohort study including all blood gases during 2018 from a Swedish, pediatric and adult general ICU. Chemical parameters from BG analysis and clinical parameters such as mean arterial pressure (MAP) and saturation (SpO2) were utilized as features. A specialist physician in Intensive Care manually determined the true class of each sample through comprehensive retrospective chart review. The samples were split into training, testing and holdout sets. Training was performed using cross-validation in the training set, with forward stepwise feature selection and Bayesian hyperparameter optimization, and accuracy was assessed using area under the precision recall curve (AUCPR) in the test set. The best model was compared to a multivariate logistic regression model (LR) in the holdout set.</p><p><strong>Results: </strong>Among 33,800 samples (30,753 arterial, 3,047 non-arterial) from 691 ICU admissions, 150 (0.44%) were erroneously marked. The best performing algorithm was extreme gradient boosting (XGboost) using 9 features, with an AUCPR of 0.9974 (95% CI 0.9961-0.9984), significantly better than the LR model (AUCPR = 0.9791, 95% CI 0.9651-0.9904).</p><p><strong>Conclusion: </strong>Supervised machine learning demonstrates efficacy in determining blood gas sample type from ICU patients. This approach shows promise for improving the accuracy of research and clinical applications relying on blood gas data.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"275"},"PeriodicalIF":3.8,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12288198/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144706415","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 and discriminant analysis model for predicting benign and malignant pulmonary nodules.","authors":"Zhi Li, Wenjing Zhang, Jinyi Huang, Ling Lu, Dongming Xie, Jinrong Zhang, Jiamin Liang, Yuepeng Sui, Linyuan Liu, Jianjun Zou, Ao Lin, Lei Yang, Fuman Qiu, Zhaoting Hu, Mei Wu, Yibin Deng, Xin Zhang, Jiachun Lu","doi":"10.1186/s12911-025-03067-8","DOIUrl":"10.1186/s12911-025-03067-8","url":null,"abstract":"<p><strong>Background: </strong>Pulmonary Nodules (PNs) are a trend considered as the early manifestation of lung cancer. Among them, PNs that remain stable for more than two years or whose pathological results suggest not being lung cancer are considered benign PNs (BPNs), while PNs that conform to the growth pattern of tumors or whose pathological results indicate lung cancer are considered malignant PNs (MPNs). Currently, more than 90% of PNs detected by screening tests are benign, with a false positive rate of up to 96.4%. While a range of predictive models have been developed for the identification of MPNs, there are still some challenges in distinguishing between BPNs and MPNs.</p><p><strong>Methods: </strong>We included a total of 5197 patients for the case-control study according to the preset exclusion criteria and sample size. Among them, 4735 with BPNs and 2509 with MPNs were randomly divided into training, validation, and test sets according to a 7:1.5:1.5 ratio. Three widely applicable machine learning algorithms (Random Forests, Gradient Boosting Machine, and XGBoost) were used to screen the metrics, and then the corresponding predictive models were constructed using discriminative analysis, and the best performing model was selected as the target model. The model is internally validated with 10-fold cross validation and compared with PKUPH and Block models.</p><p><strong>Results: </strong>We collated information from chest CT examinations performed from 2018 to 2021 in the physical examination population and found that the detection rate of PNs was 21.57% and showed an overall upward trend. The GMU_D model constructed by discriminative analysis based on machine learning screening features had an excellent discriminative performance (AUC = 0.866, 95% CI: 0.858-0.874), and higher accuracy than the PKUPH model (AUC = 0.559, 95% CI: 0.552-0.567) and the Block model (AUC = 0.823, 95% CI: 0.814-0.833). Moreover, the cross-validation results also exhibit excellent performance (AUC = 0.866, 95% CI: 0.858-0.874).</p><p><strong>Conclusion: </strong>The detection rate of PNs was 21.57% in the physical examination population undergoing chest CT. Meanwhile, based on real-world studies of PNs, a greater prediction tool was developed and validated that can be used to accurately distinguish between BPNs and MPNs with the excellent predictive performance and differentiation.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"272"},"PeriodicalIF":3.3,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12275455/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144667164","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":"Application of ChatGPT-based artificial intelligence in the diagnosis and management of polycystic ovary syndrome.","authors":"Yingchun Zhu, Danchen Luo, Xiaoyue Shen, Qingqing Shi, Haining Lv, Simin Zhang, Feihong Ye, Na Kong","doi":"10.1186/s12911-025-03114-4","DOIUrl":"10.1186/s12911-025-03114-4","url":null,"abstract":"<p><p>This study systematically develops and evaluates the application value of the PCOS-GPT system, an artificial intelligence (AI) assistant based on ChatGPT technology, in the diagnosis and management of polycystic ovary syndrome (PCOS). The research explores innovative pathways for AI-enabled PCOS diagnosis and treatment, aiming to provide an adjunctive diagnostic tool for standardized clinical decision support. Methods: An evidence-based PCOS knowledge base was constructed, covering dimensions such as epidemiology, etiology, clinical manifestations, diagnosis, treatment, and prognosis. The PCOS-GPT system was developed using GPT-3.5 pretraining combined with fine-tuning on domain-specific datasets. Using data from 85 patients, the diagnostic and therapeutic performance of PCOS-GPT was evaluated multidimensionally-accuracy, readability, and operability-using diagnoses by three expert physicians as the gold standard. Compared with GPT-4, PCOS-GPT demonstrated advantages in diagnostic accuracy for PCOS (95.63% vs. 96.40%). Conclusion: PCOS-GPT is an intelligent diagnostic and therapeutic support tool with advantages in diagnostic accuracy. It holds promise for improving standardization in diagnosis and treatment, empowering patient self-management, enhancing access to high-quality healthcare resources, and offering comprehensive health management for PCOS patients. This innovation promotes the development of smart healthcare, benefiting women's health.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"271"},"PeriodicalIF":3.3,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12275324/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144667163","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development and external validation of a machine learning model for predicting drug-induced immune thrombocytopenia in a real-world hospital cohort.","authors":"Hoang Van Dung, Vu Manh Tan, Nguyen Thi Dieu, Pham Van Linh, Nguyen Van Khai, Tran Thi Ngan, Nguyen Thi Thu Phuong","doi":"10.1186/s12911-025-03107-3","DOIUrl":"10.1186/s12911-025-03107-3","url":null,"abstract":"<p><strong>Background: </strong>Drug-induced immune thrombocytopenia (DITP) is a rare but potentially life-threatening adverse drug reaction, often underrecognized due to its nonspecific presentation and the lack of real-time diagnostic tools. Early identification of at-risk patients is critical to improving medication safety and preventing severe complications.</p><p><strong>Objective: </strong>To develop and externally validate a machine learning model for predicting the risk of DITP using routinely collected hospital data, and to optimize its clinical applicability through threshold adjustment.</p><p><strong>Methods: </strong>We conducted a retrospective cohort study using electronic medical records from Hai Phong International Hospital (2018-2024) for model development and internal validation. An independent cohort from Hai Phong International Hospital - Vinh Bao (2024) served as external validation. Eligible patients received at least one drug previously implicated in DITP and had serial platelet counts. A Light Gradient Boosting Machine (LightGBM) model was trained on demographic, clinical, laboratory, and pharmacological features. Model performance was assessed using area under the ROC curve (AUC), accuracy, recall, and F1-score. Shapley Additive explanations (SHAP) were used to interpret feature contributions. Threshold tuning and decision curve analysis (DCA) supported clinical applicability.</p><p><strong>Results: </strong>Among 17,546 patients in the training cohort and 1,403 in the external cohort, DITP occurred in 432 (2.46%) and 70 (4.99%) patients, respectively. In internal validation, LightGBM achieved an AUC of 0.860, recall of 0.392, and F1-score of 0.310. External validation confirmed model robustness with an AUC of 0.813 and an F1-score of 0.341 at the optimized threshold (0.09). SHAP analysis identified AST, baseline platelet count, and renal function as key contributors. DCA and clinical impact curves demonstrated potential benefit in supporting real-time risk stratification. Clopidogrel and vancomycin were frequently associated with suspected DITP cases.</p><p><strong>Conclusion: </strong>This externally validated machine learning model enables early identification of hospitalized patients at risk of DITP using data available in routine care. Its integration into electronic medical records may support clinical decision-making, reduce diagnostic delays, and improve pharmacovigilance practices in hospital settings.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"265"},"PeriodicalIF":3.3,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12261740/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144641873","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 estimations of health systems resilience using machine learning.","authors":"Alessandro Jatobá, Paula de Castro-Nunes, Paloma Palmieri, Omara Machado Araujo de Oliveira, Patricia Passos Simões, Valéria da Silva Fonseca, Paulo Victor Rodrigues de Carvalho","doi":"10.1186/s12911-025-03111-7","DOIUrl":"10.1186/s12911-025-03111-7","url":null,"abstract":"<p><p>Operationalizing resilience in public health systems is critical for enhancing adaptive capacity during crises. This study presents a Machine Learning (ML) -based approach to assess resilience of the health system. Using historical data from Brazilian capitals, based on the World Health Organization's six dimensions of resilient health systems, the study aims to predict responses of the system to stressors. A comprehensive dataset was developed through rigorous data collection and preprocessing, followed by splitting the data into training and testing subsets. Various ML algorithms, including regression models and decision trees, were applied to uncover insights into the resilience of health systems over time. Results revealed significant correlations between key indicators-such as outpatient care and availability of healthcare workforce-and the system's resilience. It was shown that expanding these capacities enhances overall resilience. This research highlights the potential of ML in predictive modeling to inform strategic health decision-making, targeting interventions and more effective resource allocation. This study provides a robust framework for evaluating resilience, offering public health managers a valuable tool to strengthen health systems in the face of emerging challenges.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"267"},"PeriodicalIF":3.3,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12261563/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144641876","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":"Advancing shock prediction: leveraging prior knowledge and self-controlled data for enhanced model accuracy and generalizability.","authors":"Cheng-Yu Tsai, Xiu-Rong Huang, Po-Tsun Kuo, Tzu-Tao Chen, Yun-Kai Yeh, Kuan-Yuan Chen, Arnab Majumdar, Chien-Hua Tseng","doi":"10.1186/s12911-025-03108-2","DOIUrl":"10.1186/s12911-025-03108-2","url":null,"abstract":"<p><strong>Objectives: </strong>Timely intervention in shock is vital, as delays over one hour greatly increase mortality. This study aims to develop an enhanced machine learning model that improves predictive performance by utilizing self-controlled data and applying feature engineering informed by medical knowledge to physiological waveforms, enabling the prediction of shock one hour in advance without relying on blood tests.</p><p><strong>Methods: </strong>Patient data and physiological waveforms were obtained from the Medical Information Mart for Intensive Care III (MIMIC-3) database. Shock was defined as a mean arterial pressure ≤ 65 mmHg for more than one minute, combined with serum lactate levels ≥ 2 mmol/L within 12 h before or after the hypotension event. Waveforms used for prediction were extracted from 30 min time-segment before a 1-hour period prior to the event. Self-controlled waveforms were obtained from the same patient either one day before or up to seven days after the shock event.</p><p><strong>Results: </strong>The study included 389 ICU patients who met the shock criteria and had complete physiological waveform data available for analysis. A total of 299 features were derived: 90 from arterial blood pressure (ABP), 89 from electrocardiogram (ECG), 112 from respiratory waveforms (RESP), and 8 from blood oxygen saturation (SpO₂). The weighted ensemble model showed the best performance with an AUC of 0.93 and accuracy of 84.15%, and sensitivity of 79.64% in the testing set. The most predictive features included ECG_HRV_pNN50 (proportion of successive heartbeat intervals differing by more than 50 ms), RESP_Width_Mean (mean width of respiratory waveform), RESP_Cycle_Rate_Mean (mean respiratory cycle rate), ABP_TimeSBP2DBP_SampEn (sample entropy of systolic-diastolic intervals), and ABP_AmplitudeDBP_Median (median amplitude of diastolic peaks).</p><p><strong>Conclusions: </strong>This study demonstrated the feasibility of predicting shock one hour before its onset using only four physiological waveforms, combined with feature engineering based on physiological concepts and self-sampling data. The model achieved a strong AUC and a high sensitivity.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"262"},"PeriodicalIF":3.3,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12261771/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144636221","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":"Accompanying the prostate cancer patient pathway: evaluation of novel clinical decision support software in patients with early diagnosis of prostate cancer.","authors":"Christian Engesser, Maurice Henkel, Aurelien F Stalder, Horn Tobias, Pawel Trotsenko, Viktor Alargkof, Philip Cornford, Helge Seifert, Bram Stieltjes, Christian Wetterauer","doi":"10.1186/s12911-025-03098-1","DOIUrl":"10.1186/s12911-025-03098-1","url":null,"abstract":"<p><strong>Background: </strong>Prostate cancer, the second most prevalent cancer among men with 1.4 million newly diagnosed cases, poses intricate challenges in treatment decision-making due to multifaceted influencing factors. The aim was to assess the efficacy of clinical decision support software (CDSS) in pre-therapeutic prostate cancer management.</p><p><strong>Methods: </strong>This study evaluated the CDSS \"AI Pathway Companion\" by comparing traditional manual methods with software-supported processes in patients diagnosed with localized prostate cancer. The assessment included time analysis, user surveys, and data quality evaluations.</p><p><strong>Results: </strong>The CDSS notably reduced case preparation time (-41.5% overall time), including accessing laboratory and imaging results, as well as data integration tasks. Users' survey indicated heightened satisfaction and improved information quality using the software. Despite limitations in sample size and single-center focus, the study underscored the CDSS's potential to streamline workflows, enhance data quality, and elevate user experience.</p><p><strong>Conclusion: </strong>The study highlights the CDSS's significant impact on consultation preparation time, decision-making efficiency, and user satisfaction in pre-therapeutic prostate cancer management. While showing promise in this setting, further investigations are needed to gauge its effectiveness in advanced stages and post-therapeutic contexts, aligning with evolving healthcare demands for improved efficiency and patient-centered care.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"260"},"PeriodicalIF":3.3,"publicationDate":"2025-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12247362/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144616303","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":"Utilizing machine learning models for predicting outcomes in acute pancreatitis: development and validation in three retrospective cohorts.","authors":"Kaier Gu, Yang Liu","doi":"10.1186/s12911-025-03103-7","DOIUrl":"10.1186/s12911-025-03103-7","url":null,"abstract":"<p><strong>Background: </strong>Acute pancreatitis (AP) is associated with a high readmission rate; however, there is a paucity of models capable of predicting post-discharge outcomes. Furthermore, existing in-hospital prediction models exhibit notable limitations. This study leverages machine learning (ML) technology to develop prognosis prediction models for AP patients, encompassing in-hospital mortality, readmission rates, and post-discharge mortality.</p><p><strong>Methods: </strong>A retrospective analysis was carried out on the clinical and laboratory data of AP patients from three databases (MIMIC database, eICU database, and Wenzhou Hospital in China), and they were divided into a training set and two validation sets. In the training set, key variables were screened using univariate logistic regression and the LASSO method. Six ML algorithms were employed to construct predictive models. The performance of these models was appraised using receiver operating characteristic curves, decision curve analysis, Shapley additive explanations plots, and other relevant metrics. A comparison was made between the predictive capabilities of the ML models and clinical scores. Subsequently, the performance of the machine learning models was subjected to further validation within two external validation sets.</p><p><strong>Results: </strong>A total of 2,559 AP patients were included. There were 12-26 variables selected for model training. Among the six ML models under assessment, the Logistic Regression, Random Forest, and eXtreme Gradient Boosting (XGB) models exhibited relatively superior performance in predicting in-hospital mortality, mortality within 180/365 days after discharge. Findings from the decision curve analysis and two external validation sets further indicated that the XGB model exhibited the optimal performance in predicting the in-hospital mortality of AP patients admitted to the intensive care unit. Specifically, the XGB model demonstrated stability in the area under the curve across different centers, achieved a balance between sensitivity and specificity, and effectively prevented overfitting through regularization mechanisms. These features are highly congruent with the core requirements for robustness in the medical context.</p><p><strong>Conclusions: </strong>By collecting the dynamic variables of patients during their hospitalization and establishing an XGB model, it is conducive to identifying the short-term and long-term prognoses of AP patients and promoting the decision-making of clinicians.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"261"},"PeriodicalIF":3.3,"publicationDate":"2025-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12247377/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144616304","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":"Predicting antiretroviral therapy adherence status of adult HIV-positive patients using machine-learning Northwest, Ethiopia, 2025.","authors":"Kelemua Aschale Yeneakal, Gizaw Hailiye Teferi, Temesgen T Mihret, Abraham Keffale Mengistu, Sefefe Birhanu Tizie, Maru Meseret Tadele","doi":"10.1186/s12911-025-03106-4","DOIUrl":"10.1186/s12911-025-03106-4","url":null,"abstract":"<p><strong>Background: </strong>Adherence with Anti-Retroviral Therapy (ART) reduces viral load, as well as HIV-related morbidity and mortality. Despite the expanded availability of ART, non-adherence remains a series problem, leads increased viral load, a decline CD4 cell count, and the development of drug resistance. HIV care is currently showing promise with the use of machine learning algorithms for early prediction of future non-adherence. However, as to researcher's Knowledge, there was limited research supporting this evidence in the country. Therefore, the primary aim of this study was to predict ART adherence status using machine learning models and to identify the most important predictors of Adherence at Debre Markos comprehensive specialized hospital.</p><p><strong>Methods: </strong>Secondary data was collected from ART database of Debre Markos comprehensive specialized hospital, spanning from 2005 to 2024. The dataset was split into training (80%) and testing (20%) sets. To address class imbalance, the Synthetic Minority Oversampling Technique (SMOTE) was applied to the training data. Seven machine learning algorithms: support vector machine, random forest, decision tree, logistic regression, gradient boosting, K-nearest neighbors, and artificial neural network were trained. The model performance was evaluated using ROC-AUC, F1 score, accuracy, precision, and recall. To identify important predictor we employed feature importance technique.</p><p><strong>Result: </strong>Out of 4640 patients, who were on antiretroviral therapy, 63.56% (n = 2949) were females, with mean age of 41.8 years (SD ± 11.50). The majority age group was between 40 and 59 years (n = 2152) 46.38% and 98.1% of patients had good adherence while 1.9% had poor adherence. Among the machine learning models tested, the gradient boosting algorithm performed better than all other algorithms with (Accuracy = 0.78, Sensitivity = 0.76, F1score = 0.78, AUC = 0.76). Age, regimen, WHO clinical stage, nutritional status, address status, sex, weight, recent CD4 cell count, viral load and ART dose per day were identified as the most important predictors for adherence status.</p><p><strong>Conclusion: </strong>The study developed a gradient boosting model for predicting adherence status. Age, regimen, WHO clinical stage, nutritional status, address status, sex, weight, recent CD4 cell count, viral load and ART dose per day were the most important predictors for adherence status.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"259"},"PeriodicalIF":3.3,"publicationDate":"2025-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12247312/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144607372","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":"Coding mechanisms for main condition in ICD-11.","authors":"Hude Quan, Olafr Steinum, Danielle A Southern, William A Ghali","doi":"10.1186/s12911-025-03069-6","DOIUrl":"10.1186/s12911-025-03069-6","url":null,"abstract":"<p><p>Countries have been routinely abstracting health data from hospital charts and coding conditions using ICD-10. A main condition must be assigned to each admission. However, the definition of main condition is inconsistent across countries, and may be based on (1) the initial reason for admission; (2) the reason for admission, as understood at the end of the hospital stay; and (3) the condition that consumed the most hospital resources or hospital days. Now, ICD-11 standardizes the coding schema for main condition. This paper describes the ICD-11 coding guidelines for main condition and discusses their implications for data comparability.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"21 Suppl 6","pages":"387"},"PeriodicalIF":3.3,"publicationDate":"2025-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12243148/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144607373","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}