BMC Medical Informatics and Decision Making最新文献

{"title":"Which explanations do clinicians prefer? A comparative evaluation of XAI understandability and actionability in predicting the need for hospitalization.","authors":"Laura Bergomi, Giovanna Nicora, Marta Anna Orlowska, Chiara Podrecca, Riccardo Bellazzi, Caterina Fregosi, Francesco Salinaro, Marco Bonzano, Giuseppe Crescenzi, Francesco Speciale, Santi Di Pietro, Valentina Zuccaro, Erika Asperges, Paolo Sacchi, Pietro Valsecchi, Elisabetta Pagani, Michele Catalano, Chandra Bortolotto, Lorenzo Preda, Enea Parimbelli","doi":"10.1186/s12911-025-03045-0","DOIUrl":"https://doi.org/10.1186/s12911-025-03045-0","url":null,"abstract":"<p><strong>Background: </strong>This study aims to address the gap in understanding clinicians' attitudes toward explainable AI (XAI) methods applied to machine learning models using tabular data, commonly found in clinical settings. It specifically explores clinicians' perceptions of different XAI methods from the ALFABETO project, which predicts COVID-19 patient hospitalization based on clinical, laboratory, and chest X-ray at time of presentation to the Emergency Department. The focus is on two cognitive dimensions: understandability and actionability of the explanations provided by explainable-by-design and post-hoc methods.</p><p><strong>Methods: </strong>A questionnaire-based experiment was conducted with 10 clinicians from the IRCCS Policlinico San Matteo Foundation in Pavia, Italy. Each clinician evaluated 10 real-world cases, rating predictions and explanations from three XAI tools: Bayesian networks, SHapley Additive exPlanations (SHAP), and AraucanaXAI. Two cognitive statements for each method were rated on a Likert scale, as well as the agreement with the prediction. Two clinicians answered the survey during think-aloud interviews.</p><p><strong>Results: </strong>Clinicians demonstrated generally positive attitudes toward AI, but high compliance rates (86% on average) indicate a risk of automation bias. Understandability and actionability are positively correlated, with SHAP being the preferred method due to its simplicity. However, the perception of methods varies according to specialty and expertise.</p><p><strong>Conclusions: </strong>The findings suggest that SHAP and AraucanaXAI are promising candidates for improving the use of XAI in clinical decision support systems (DSSs), highlighting the importance of clinicians' expertise, specialty, and setting on the selection and development of supportive XAI advice. Finally, the study provides valuable insights into the design of future XAI DSSs.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"269"},"PeriodicalIF":3.3,"publicationDate":"2025-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144648647","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"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":"https://doi.org/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":"","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":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Interpretable prediction of hospital mortality in bleeding critically ill patients based on machine learning and SHAP.","authors":"Bingkui Ren, Yuping Zhang, Siying Chen, Jinglong Dai, Junci Chong, Yifei Zhong, Mengkai Deng, Shaobo Jiang, Zhigang Chang","doi":"10.1186/s12911-025-03101-9","DOIUrl":"https://doi.org/10.1186/s12911-025-03101-9","url":null,"abstract":"<p><strong>Background: </strong>Hemorrhage is a prevalent and critical condition in the intensive care unit (ICU), characterized by high incidence, elevated mortality rates, and substantial therapeutic challenges. Accurate prediction of mortality in patients with hemorrhage is essential for developing personalized prevention and treatment strategies. Nevertheless, the implementation of effective predictive models in clinical practice remains limited, primarily due to the lack of robust and interpretable tools.</p><p><strong>Objective: </strong>This study aimed to develop an interpretable model for predicting mortality risk in critically ill patients with hemorrhage admitted to ICUs. The SHapley Additive exPlanations (SHAP) method was applied to interpret the eXtreme Gradient Boosting (XGBoost)model, identifying key prognostic factors in this population.</p><p><strong>Methods: </strong>In this retrospective cohort study, we derived data from the eICU Collaborative Research Database (eICU-CRD) to develop and evaluate a predictive model. ​Clinical data from the first 24 h of ICU admission were extracted, and the dataset was randomly split into training (80%) and validation (20%) sets. Model performance was compared​ to four other machine learning algorithms using the area under the curve (AUC). ​SHAP was utilized to interpret the XGBoost model. External validation was subsequently performed using data from the ​Chinese REFRAIN cohort, which focuses on hemorrhage and coagulopathy in critically ill patients.​​.</p><p><strong>Trial registration: </strong>The study protocol was retrospectively registered in the Chinese Clinical Trial Registry (ChiCTR) on December 17, 2024 (Registration number ChiCTR2400094140).</p><p><strong>Results: </strong>A total of 10,306 eligible patients with hemorrhage were included. The observed in-hospital mortality rate was 11.5%.Among the five models compared, XGBoost demonstrated the highest predictive performance (AUC = 0.81), whereas logistic regression (LR) showed the lowest generalizability(AUC = 0.726). Decision curve analysis revealed that the XGBoost model provided a greater net benefit than other models at threshold probabilities of 10-30%. SHAP analysis identified the top 15 predictors of mortality, with bilirubin level ranked as the most influential variable.​​ External validation using the REFRAIN cohort confirmed the robustness of model(AUC = 0.776).</p><p><strong>Conclusions: </strong>The interpretable predictive model improves mortality risk stratification in ICU patients with hemorrhage, supporting clinicians in optimizing treatment plans and resource allocation. Enhanced model transparency through SHAP explanations may facilitate clinical adoption by improving trust in model reliability.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"263"},"PeriodicalIF":3.3,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144641874","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"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":"https://doi.org/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":"","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":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep learning-based delineation of whole-body organs at risk empowering adaptive radiotherapy.","authors":"Zi-Hang Chen, Song-Feng Li, Ling-Xin Xu, Meng-Qiu Tian, Feng Li, Yu-Xian Yang, Chen-Fei Wu, Guan-Qun Zhou, Li Lin, Yao Lu, Ying Sun","doi":"10.1186/s12911-025-03062-z","DOIUrl":"https://doi.org/10.1186/s12911-025-03062-z","url":null,"abstract":"<p><strong>Background: </strong>Accurate delineation of organs at risk (OARs) is crucial for precision radiotherapy. Most previous autosegmentation models were only constructed for single anatomical region without evaluation of dosimetric impact. We aimed to validate the clinical practicability of deep-learning (DL) models for autosegmentation of whole-body OARs with respect to delineation accuracy, clinical acceptance and dosimetric impact.</p><p><strong>Methods: </strong>OARs in various anatomical regions, including the head and neck, thorax, abdomen, and pelvis, were automatedly delineated by DL models (DLD) and compared to manual delineations (MD) by an experienced radiation oncologist (RO). The geometric performance was evaluated using the Dice similarity coefficient (DSC) and average surface distance (ASD). RO A corrected DLD to create delineations approved in clinical practice (CPD). RO B graded the accuracy of DLD to assess clinical acceptance. The dosimetric impact was determined by assessing the difference in dosimetric parameters for each OAR in the DLD-based radiotherapy plan (Plan_DLD) and the CPD-based radiotherapy plan (Plan_CPD).</p><p><strong>Results: </strong>The automatic delineation model has a high OAR delineation accuracy, and the median DSCs can reach 0.841 (IQR, 0.791-0.867) in the head and neck OAR, 0.903 (IQR, 0.777-0.932) in thoracic OAR, 0.847 (IQR, 0.834-0.931) in abdominal OAR, 0.916 (IQR, 0.906-0.964) in pelvic OAR. The majority of DL-generated OARs were graded as clinically acceptable with no editing or little editing needed. No significant differences in dosimetric parameters were found by comparing Plan_DLD with Plan_CPD.</p><p><strong>Conclusions: </strong>For OARs of whole bodily regions, DL-based segmentation is fast; DL models perform sufficiently well for clinical practice with respect to delineation accuracy, clinical accepatance and dosimetric impact.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"268"},"PeriodicalIF":3.3,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144641872","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An interpretable machine learning model for predicting bone marrow invasion in patients with lymphoma via ¹⁸F-FDG PET/CT: a multicenter study.","authors":"Xinyu Zhu, Denglu Lu, Yang Wu, Yanqi Lu, Liang He, Yanyun Deng, Xingyu Mu, Wei Fu","doi":"10.1186/s12911-025-03110-8","DOIUrl":"https://doi.org/10.1186/s12911-025-03110-8","url":null,"abstract":"<p><strong>Purpose: </strong>Accurate identification of bone marrow invasion (BMI) is critical for determining the prognosis of and treatment strategies for lymphoma. Although bone marrow biopsy (BMB) is the current gold standard, its invasive nature and sampling errors highlight the necessity for noninvasive alternatives. We aimed to develop and validate an interpretable machine learning model that integrates clinical data, ¹⁸F-fluorodeoxyglucose positron emission tomography/computed tomography (¹⁸F-FDG PET/CT) parameters, radiomic features, and deep learning features to predict BMI in lymphoma patients.</p><p><strong>Methods: </strong>We included 159 newly diagnosed lymphoma patients (118 from Center I and 41 from Center II), excluding those with prior treatments, incomplete data, or under 18 years of age. Data from Center I were randomly allocated to training (n = 94) and internal test (n = 24) sets; Center II served as an external validation set (n = 41). Clinical parameters, PET/CT features, radiomic characteristics, and deep learning features were comprehensively analyzed and integrated into machine learning models. Model interpretability was elucidated via Shapley Additive exPlanations (SHAPs). Additionally, a comparative diagnostic study evaluated reader performance with and without model assistance.</p><p><strong>Results: </strong>BMI was confirmed in 70 (44%) patients. The key clinical predictors included B symptoms and platelet count. Among the tested models, the ExtraTrees classifier achieved the best performance. For external validation, the combined model (clinical + PET/CT + radiomics + deep learning) achieved an area under the receiver operating characteristic curve (AUC) of 0.886, outperforming models that use only clinical (AUC 0.798), radiomic (AUC 0.708), or deep learning features (AUC 0.662). SHAP analysis revealed that PET radiomic features (especially PET_lbp_3D_m1_glcm_DependenceEntropy), platelet count, and B symptoms were significant predictors of BMI. Model assistance significantly enhanced junior reader performance (AUC improved from 0.663 to 0.818, p = 0.03) and improved senior reader accuracy, although not significantly (AUC 0.768 to 0.867, p = 0.10).</p><p><strong>Conclusion: </strong>Our interpretable machine learning model, which integrates clinical, imaging, radiomic, and deep learning features, demonstrated robust BMI prediction performance and notably enhanced physician diagnostic accuracy. These findings underscore the clinical potential of interpretable AI to complement medical expertise and potentially reduce the reliance on invasive BMB for lymphoma staging.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"264"},"PeriodicalIF":3.3,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144641871","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predicting individual hemoglobin abnormalities using longitudinal data in clinical practice.","authors":"Maliheh Namazkhan, Karel Jan van Tuijn, Maurits Kaptein, Remco van Horssen","doi":"10.1186/s12911-025-03085-6","DOIUrl":"https://doi.org/10.1186/s12911-025-03085-6","url":null,"abstract":"<p><strong>Background: </strong>In preventive medicine, the promotion of health and well-being through early detection and intervention is crucial to preventing the development of diseases. This study aims to predict potential abnormalities in hemoglobin levels before they occur, using individualised observations within normal ranges.</p><p><strong>Methods: </strong>We utilise a dataset generated over seven years, comprising 30,000 patients. Multiple prediction models are employed to identify hemoglobin trends within individuals and predict their next-to-measure hemoglobin value based on past measurements. We focus on whether, at a specific point in time, the individual's values are likely to run outside of the individual 'normal' bounds. A Generalised Additive Model is explored as a plausible approach for predicting future individual hemoglobin values. By calculating confidence intervals for predicted hemoglobin values, we evaluate prediction uncertainty, while assessing the percentage of accurate predictions within these intervals to gauge the reliability of our model's prediction.</p><p><strong>Results: </strong>We find that for 88.47% of the cases, our model accurately predicts whether patients' hemoglobin levels will stay within individual 'normal' bounds or deviate from them, demonstrating its effectiveness in identifying 'out-of-normal' measurements.</p><p><strong>Conclusions: </strong>The findings hold practical significance, potentially reducing unnecessary blood draws and preventing the onset of abnormal hemoglobin levels through preventive healthcare interventions or digital lifestyle coaching. Moreover, early detection and intervention can significantly impact individual patients by preventing disease development.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"266"},"PeriodicalIF":3.3,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144641875","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"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}