BMC Medical Informatics and Decision Making最新文献

{"title":"Automated lung cancer classification using intensity-driven RoI selection and transfer learning.","authors":"Syed Thouheed Ahmed, T Y Satheesha, Lakshmi Hassan Nagaraja, Achyut Shankar, Ashwani Kumar, Afifa Salsabil Fathima","doi":"10.1186/s12911-026-03519-9","DOIUrl":"10.1186/s12911-026-03519-9","url":null,"abstract":"<p><p>Lung cancer diagnosis increasingly relies on advanced medical imaging systems and expert interpretation across heterogeneous clinical data sources. However, accurate clinical decision-making remains challenging due to variations in expert judgment and the complexity of extracting discriminative patterns from electronic health records and radiological datasets. To address these challenges, this paper proposes an enhanced lung cancer classification framework that leverages intensity-driven region-of-interest (RoI) selection from publicly available benchmark datasets, including the Lung Image Database Consortium Image Collection (LIDC-IDRI) and The Cancer Imaging Archive (TCIA). The proposed methodology incorporates customized label refinement and precise annotation of vulnerable RoI regions to capture clinically relevant features associated with malignant nodules. A high-dimensional RoI mapping strategy is employed to improve feature representation and discrimination. Furthermore, a feedback-driven optimization mechanism is integrated within a transfer learning framework to iteratively refine model parameters and enhance learning stability. The optimized RoI representations are transferred to customized deep learning models, enabling efficient knowledge reuse and robust decision-making. The proposed approach is implemented using the CoVNet architecture and evaluated under a 60:40 training-testing split. Experimental results demonstrate a classification accuracy of 97.84%, validating the effectiveness of the proposed framework in improving predictive performance for lung cancer classification.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":" ","pages":""},"PeriodicalIF":5.5,"publicationDate":"2026-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13637333/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148403767","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 multicenter machine learning model for predicting ICU mortality in mechanically ventilated patients: development and external validation.","authors":"Yi Zhang, Xu Chen, Xinghan Tian, Hui Zhao","doi":"10.1186/s12911-026-03590-2","DOIUrl":"10.1186/s12911-026-03590-2","url":null,"abstract":"<p><strong>Background: </strong>Accurate early prediction of mortality in mechanically ventilated intensive care unit (ICU) patients remains challenging due to disease heterogeneity and dynamic clinical trajectories. Traditional severity scoring systems have limited flexibility and generalizability. This study aimed to develop and externally validate a machine learning-based model using routinely available clinical variables to predict ICU mortality in mechanically ventilated patients.</p><p><strong>Methods: </strong>A retrospective multicenter cohort study was conducted using the MIMIC database as the development cohort, with external validation performed in the eICU Collaborative Research Database and an independent institutional cohort. Adult ICU patients receiving invasive mechanical ventilation were included. A two-step feature selection strategy combining least absolute shrinkage and selection operator (LASSO) regression and recursive feature elimination was applied to identify robust predictors. Six machine learning algorithms were compared, and a random forest model was selected. Model performance was evaluated using discrimination, calibration, decision curve analysis, time-dependent area under the curve (AUC), and concordance index (C-index). Model interpretability was assessed using SHAP analysis.</p><p><strong>Results: </strong>A total of 21 predictors were selected for model development. The random forest model demonstrated superior overall performance compared with alternative algorithms. In external validation, the model showed favorable early discrimination, with near-perfect AUC values during the first 48 hours in the local cohort and consistently acceptable performance in the eICU cohort. Predictive performance attenuated over time, particularly in the local cohort, whereas temporal stability was observed in the multicenter dataset. Calibration and decision curve analyses supported the reliability and clinical utility of the model. Key predictors included age, markers of respiratory dysfunction, metabolic stress, organ failure, and treatment intensity.</p><p><strong>Conclusions: </strong>The proposed random forest model provides accurate and interpretable admission-time risk stratification for ICU mortality in mechanically ventilated patients. We recommend its use as an admission triage and screening tool for identifying high-risk patients within the first 48 hours of ICU admission. While predictive performance declined over time, the model demonstrated robust early risk stratification and generalizability across independent cohorts, highlighting its potential value for early clinical decision support in critical care settings.</p><p><strong>Clinical trial number: </strong>Not applicable. This study was an observational retrospective cohort study and was not registered as a clinical trial.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":" ","pages":""},"PeriodicalIF":5.5,"publicationDate":"2026-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13628788/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148403774","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":"Leveraging human-centered AI for clinical decision-making: a transparent, accurate rule extractor using non-dominated sorting genetic algorithm.","authors":"Fatemeh Ahouz, Mohammad Bagher Sohrabi, Amin Golabpour","doi":"10.1186/s12911-026-03674-z","DOIUrl":"10.1186/s12911-026-03674-z","url":null,"abstract":"<p><strong>Background: </strong>The advent of health technologies associated with artificial intelligence (AI) is deemed a transformative shift in the delivery of medical care within our lifetime. Nevertheless, there is a communication gap between intelligent models and clinical experts. Transitioning towards Human-Centered AI can serve as a means to bridge this gap.</p><p><strong>Methods: </strong>This study introduces a human-centered rule extraction model based on the Non-Dominated Sorting Genetic Algorithm (NSGA-II), designed to enhance the interpretability and clinical utility of diagnostic tools in healthcare. This model autonomously generates diagnostic rules, adjusts threshold values for variables, and involves clinical experts in evaluating the rules, thereby ensuring the relevance and applicability of extracted rules in real-world settings.</p><p><strong>Results: </strong>Experiments on the WBC, WDBC, and Pima datasets showed that the proposed model outperformed state-of-the-art rule extraction methods in the literature in terms of predictive value accuracy (PVA) and support. On the subset of data covered by the extracted rules, it achieved accuracy comparable to traditional black-box methods without sacrificing interpretability. The extracted rules were clinically evaluated by 13 domain physicians, with all approved rules achieving a content validity index (CVI) of at least 0.85. Additionally, the model provides multiple high-performance alternative diagnostic rules per class, giving clinicians practical flexibility.</p><p><strong>Conclusions: </strong>Our approach emphasizes the importance of multidisciplinary collaboration between AI specialists and healthcare professionals, aiming to build trust in AI-driven diagnostic systems through transparency and clinical validation.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":" ","pages":""},"PeriodicalIF":5.5,"publicationDate":"2026-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13625358/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148403749","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":"Augmenting medical data interpretation with Large Language Models (LLMs): a comparative analysis of patient empowerment, information processing, and technology acceptance.","authors":"Pouyan Esmaeilzadeh","doi":"10.1186/s12911-026-03686-9","DOIUrl":"10.1186/s12911-026-03686-9","url":null,"abstract":"<p><strong>Background: </strong>Medical data interpretation traditionally relies on healthcare professionals as intermediaries, which can limit patient autonomy and engagement. Large Language Models (LLMs) present an opportunity to transform this paradigm by enabling direct patient access to AI-generated interpretations; however, comparative research on their effectiveness across different medical data types and communication modalities remains limited. This study explores how direct LLM-augmented interpretation of medical data, in which patients use an AI system to receive real-time explanations of laboratory and radiological results, compares with healthcare professional-led interpretation across different data modalities, with particular attention to patient comprehension, empowerment, and technology acceptance.</p><p><strong>Methods: </strong>Using a mixed-methods approach with a within-subjects experimental design, 45 demographically diverse participants experienced six scenarios: blood work and medical imaging interpretations delivered via (1) healthcare professional phone consultation, (2) in-person consultation, or (3) LLM interaction through a custom-configured ChatGPT-4o interface (Medical Explainer AI) designed to provide plain-language explanations of findings, highlight abnormal values, contextualize clinical significance, explain medical terminology, and adapt explanation complexity based on user feedback.</p><p><strong>Results: </strong>LLM interaction significantly enhanced diagnostic comprehension (mean difference = 1.3 compared to phone consultation, p < 0.001), reduced cognitive load, increased perceived control, and improved time efficiency. Healthcare professional-led interpretation, particularly in-person, maintained advantages in fostering trust, reducing anxiety, and enhancing confidence in decision-making. The benefits of LLM interaction were more pronounced for blood work than for medical imaging interpretation. Age, education level, and health literacy significantly moderated the effectiveness of different interpretation methods.</p><p><strong>Conclusions: </strong>LLMs offer complementary rather than replacement capabilities for medical data interpretation, excelling in enhancing comprehension, control, and efficiency, while healthcare professionals provide superior relational value through trust, confidence, and emotional support. Implementation strategies should leverage the strengths of both approaches, carefully considering data complexity and patient characteristics to maximize benefits while ensuring equitable access.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":" ","pages":""},"PeriodicalIF":5.5,"publicationDate":"2026-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13625248/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148403755","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":"Generating Alzheimer's narratives using large language models.","authors":"Paula Andrea Perez-Toro, Mahmoud Almizel, Elmar Nöth, Andreas Maier, Tomas Arias-Vergara","doi":"10.1186/s12911-026-03653-4","DOIUrl":"10.1186/s12911-026-03653-4","url":null,"abstract":"<p><strong>Background: </strong>Analyzing semi-spontaneous speech is a promising direction for supporting Alzheimer's disease (AD) assessment, yet progress is limited by the scarcity of annotated clinical data. Large Language Models (LLMs) offer new opportunities to generate synthetic narratives that may resemble speech patterns of both patients with AD and healthy controls during cognitive evaluation tasks such as the Cookie Theft Picture description.</p><p><strong>Methods: </strong>This study evaluates whether models including GPT, T5/Flan-T5, LLaMA, Mistral, and Qwen can generate clinically plausible picture-description narratives under two configurations: Human-to-Bot, where an LLM responds directly to real interviewer prompts, and Bot-to-Bot, where two LLMs simulate both interviewer and participant roles. Models were fine-tuned on transcripts from the DementiaBank Pitt Corpus and assessed using lexical and semantic metrics, as well as human expert ratings. Generated narratives were further used to augment training data for an AD vs. healthy control classifier based on BERT embeddings and an MLP architecture.</p><p><strong>Results: </strong>LLMs differed substantially in their ability to reproduce clinically meaningful and semantically coherent narratives of patient-interviewer interactions. Mistral, LLaMA, and Qwen achieved the strongest automatic evaluation metrics, e.g., BERTScores above 0.90 in the Human-to-Bot condition-and produced narratives rated by human experts as fluent, plausible, and diagnostically informative. When combining real and synthetic narratives for classifier training, the highest F1-score reached 0.84, outperforming models trained on real data alone (F1 = 0.74). Synthetic data generated in Human-to-Bot settings contributed most to diagnostic improvements, whereas Bot-to-Bot interactions exhibited greater variability and reduced clinical realism.</p><p><strong>Conclusion: </strong>LLMs can generate high-quality synthetic narratives that enhance downstream AD classification and show promising clinical plausibility in cognitive assessment contexts. Incorporating LLM-generated data provides a scalable strategy for mitigating data scarcity in dementia research. Future work should focus on improving fully synthetic dialogue quality, expanding multilingual capabilities, and refining evaluation frameworks to better capture clinically relevant linguistic features.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":" ","pages":""},"PeriodicalIF":5.5,"publicationDate":"2026-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13352925/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148403761","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 prediction of postoperative pulmonary infection in patients who underwent thoracoscopic lung cancer resection: a retrospective case-control study.","authors":"Jiajia Ma, Zhengmin Zhang, Bei Xue, Jing Feng, Liping Yao, Hui Chen, Xiaoxin Liu","doi":"10.1186/s12911-026-03698-5","DOIUrl":"10.1186/s12911-026-03698-5","url":null,"abstract":"<p><strong>Background: </strong>Accurate identification of patients at high risk of pulmonary infection after thoracoscopic lung cancer resection is important for timely and targeted preventive measures. Methods for determining the risk of pulmonary infection after thoracoscopic lung cancer resection have not been well studied.</p><p><strong>Methods: </strong>This study was a retrospective case-control research project. The information of 3219 hospitalised patients who underwent thoracoscopic lung cancer resection between January 2019 and December 2023 was obtained from the hospital electronic medical record system. 26 clinical characteristics were obtained from medical and nursing records. The variables were screened using the least absolute contraction and selection operator (LASSO) regression, and the risk prediction models for pulmonary infection after thoracoscopic lung cancer resection was constructed using the following 5 machine learning algorithms: logistic regression model (LR), artificial neural network (ANN), support vector machine (SVM), random forest (RF) and eXtreme gradient boosting (XGB). The model was evaluated using the following metrics: the area under the receiver operator characteristic curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and F1 score (F1). Shapley additive explanation (SHAP) was used to interpret the machine learning models.</p><p><strong>Results: </strong>There were 3219 enrolled patients, 2203 (70%) of whom were assigned to the training cohort and 966 (30%) of whom were assigned to the validation cohort. The AUC range of the five models was 0.883-0.951. The XGB model outperformed the others, with an AUC of 0.951 (95% confidence interval: 0.943-0.964), accuracy of 0.902 (95% confidence interval: 0.886-0.913), sensitivity of 0.927, specificity of 0.864, positive predictive value of 0.898, negative predictive value of 0.824, precision of 0.908, recall of 0.872 and F1 score of 0.815 in the validation group. The model's prediction performance in the 45-65 age group was the best. The AUC of the logistic regression model was 0.948 (95% confidence interval: 0.931-0.957). We transformed the logistic regression model into a nomogram to help clinicians visualise the model and make them more likely to use it to identify the risk of pulmonary infection after thoracoscopic surgery in lung cancer patients.</p><p><strong>Conclusions: </strong>The establishment of a risk prediction model based on machine learning can help clinical nursing staff identify high-risk patients for pulmonary infection after thoracoscopic lung cancer resection.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":" ","pages":""},"PeriodicalIF":5.5,"publicationDate":"2026-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13617690/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148396200","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":"Physicians' preferences for the use of clinical decision support systems in the context of acutely ill children presenting to ambulatory care: a focus group study.","authors":"Hannelore Dillen, Annelien Dankaerts, Daniëlle Snijders, Lennart Verlinden, Laure Wynants, Jan Y Verbakel","doi":"10.1186/s12911-026-03670-3","DOIUrl":"10.1186/s12911-026-03670-3","url":null,"abstract":"<p><strong>Background: </strong>Acutely ill children are at risk of receiving unnecessary antibiotic prescriptions, yet within this context, clinical decision support systems (CDSS) have the potential to improve clinicians' prescribing behaviour. Since the uptake of CDSS is limited, research into the facilitators and barriers to its use and the preferred content and functions is needed to promote its use.</p><p><strong>Methods: </strong>Four focus groups were conducted among Belgian general practitioners, paediatricians, and ear/nose/throat physicians. The groups took place in a university building, a regional hospital, and online, and were semi-structured according to the interview guide. We transcribed recordings and performed reflexive thematic analysis. All participants were asked to provide feedback on the final themes.</p><p><strong>Results: </strong>Twenty-five physicians participated in the study. The analysis produced four themes: (i) Physicians prefer a pragmatic approach completing the CDSS, with as little additional work as possible; (ii) The comprehensive advice given by the CDSS should be concise, unambiguous, and presented clearly; (iii) The CDSS can reduce diagnostic uncertainty, especially by making physicians aware of alarm symptoms of serious illness; (iv) The scope should be determined beforehand, and implementation should consider reliability and technical barriers. Participants proposed several possibilities for the content and functions of the CDSS, which are informed by their workload, clinical uncertainty, and their emphasis on professional autonomy.</p><p><strong>Conclusions: </strong>The results of this study contribute to the development of a user-friendly CDSS for the assessment of acutely ill children in ambulatory care. Physicians prefer a CDSS that is pragmatic to apply and shows clear guidance on diagnostics and disease management, including support to reduce uncertainty regarding illness severity. The implementation of a CDSS plays a pivotal role in enhancing antimicrobial stewardship.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":" ","pages":""},"PeriodicalIF":5.5,"publicationDate":"2026-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13621462/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148396152","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":"An explainable machine learning model for predicting high phosphorus risk in patients on maintenance hemodialysis: a multicenter retrospective study.","authors":"Jiaoyan Chen, Jurong Yang, Mingyue Hou, Jingrong Peng, Yunyan Wang, Kui Xiang","doi":"10.1186/s12911-026-03678-9","DOIUrl":"10.1186/s12911-026-03678-9","url":null,"abstract":"<p><strong>Background: </strong>Hyperphosphatemia is a common complication in hemodialysis and serves as a key marker for evaluating dialysis adequacy. This study aimed to develop an interpretable machine learning (ML) model to predict the risk of hyperphosphatemia in patients undergoing maintenance hemodialysis.</p><p><strong>Methods: </strong>Data from 718 patients receiving maintenance hemodialysis across five hemodialysis centers in Chongqing between May and September 2025 were included. The dataset was split into training (70%) and testing (30%) sets. Univariate and multivariate analyses were used to identify predictors most strongly associated with hyperphosphatemia. Seven ML algorithms were employed to construct predictive models. Model performance was assessed using the area under the curve (AUC), F1 score, precision, accuracy, and recall. SHapley Additive exPlanations (SHAP) were applied to visualize feature importance and interpret individual predictions.</p><p><strong>Results: </strong>The support vector machine (SVM) model demonstrated superior performance (AUC = 0.840). The most influential predictors, in descending order, were PreCr, PreUrea, PreK, PreCO2CP, and PTH. Elevated PreCr, PreUrea, and PreK exert a positive effect on hyperphosphatemia, while estimated PreCO₂CP levels demonstrate a negative effect.</p><p><strong>Conclusions: </strong>The SVM model exhibited relatively high predictive accuracy for hyperphosphatemia risk in hemodialysis patients. This preliminary multicenter retrospective study demonstrated the feasibility of using SVM combined with the SHAP algorithm for risk identification, and the key features identified (PreCr, PreUrea, PreK, PreCO₂CP, PTH) can serve as a set of candidate parameters for future prospective model development.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":" ","pages":""},"PeriodicalIF":5.5,"publicationDate":"2026-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13621611/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148396158","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":"Does clinical documentation reflect how parents and clinicians share decisions about surgery?","authors":"Angele Kelly, Dalia Mitchell, Anne R Links, Mary C Beach, Emily F Boss, Elaine C Thompson","doi":"10.1186/s12911-026-03566-2","DOIUrl":"10.1186/s12911-026-03566-2","url":null,"abstract":"<p><strong>Background: </strong>While use of shared decision-making (SDM) is widely accepted and applied in practice, it is unknown how core elements of SDM are reflected in clinical documentation. This knowledge gap is particularly relevant in the setting of surgery in children, where parents serve as proxy decision-makers.</p><p><strong>Methods: </strong>We analyzed transcribed audio-recorded outpatient encounters and corresponding medical documentation for pediatric patients undergoing evaluation for elective surgery. Visit transcripts and medical record documentation of the corresponding clinical encounter were coded for two core elements of shared decision-making: parental concerns and preferences. We assessed the frequency (visit-level and instance-level) and content of these elements expressed in verbal communication and in clinical documentation.</p><p><strong>Results: </strong>Of 109 visits, concerns and preferences were discussed in nearly half of encounters (Visit level: Concerns n = 46, 42%; Preferences n = 49, 45%). Most verbally-expressed concerns (e.g., \"we're worried about her breathing\"; \"…she sleeps with me. I'm constantly shaking her. She scares me a lot\") focused on symptoms and surgical risk whereas preferences (e.g., \"I would just rather take them out\"; \"I'd definitely rather go the conservative route\") centered on treatment decisions. Of the total unique instances of stated concerns (n = 74) and preferences (n = 62), about half were recorded in the medical record (Instance-level: Concerns n = 34, 46%; Preferences n = 28, 49%).</p><p><strong>Conclusions: </strong>These findings show that parent preferences and concerns that are discussed during pediatric surgical encounters are not routinely reflected in clinical documentation. Thoughtful documentation of family perspectives may enhance transparency, support communication across the health continuum, and contribute to high quality patient- and family-centered care.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":" ","pages":""},"PeriodicalIF":5.5,"publicationDate":"2026-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13643954/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148387439","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":"Establishing development strategies and improvement paths for decision coach competencies in shared decision-making using an integrated accessibility-performance analysis and network relation map approach.","authors":"Shan-Fu Yu, Yi-Chun Lin, Hsing-Tse Yu, Chia-Li Lin","doi":"10.1186/s12911-026-03680-1","DOIUrl":"10.1186/s12911-026-03680-1","url":null,"abstract":"<p><strong>Background: </strong>A decision coach (DC) is a trained healthcare professional who provides non-directive support to patients in health-related decision-making. The decision coach role can be integrated into shared decision-making (SDM) processes, but is not an inherent component of SDM, as both may be applied independently depending on the clinical context. Numerous trained DCs are nurses who have transitioned from their roles as patient educators to knowledgeable, skilled decision facilitators. Thus, developing core competencies has become increasingly crucial for DC training, especially patient-centered care in nursing education. This study aimed to evaluate DC competencies in SDM by examining accessibility, performance, and perceived directional relationships among competency domains.</p><p><strong>Methods: </strong>This mixed-methods study combined a narrative literature review and expert consultations to identify key DC competency criteria. Subsequently, a cross-sectional questionnaire survey was administered to healthcare professionals at two hospitals in Taiwan between April 2023 and February 2024. Accessibility-performance analysis (APA) and the decision-making trial and evaluation laboratory (DEMATEL)-based network relation map (NRM) approach were applied to evaluate competency accessibility, performance, and perceived directional relationships across domains.</p><p><strong>Results: </strong>A total of 149 healthcare professionals, including physicians, nurses, and other clinical staff, completed the valid questionnaires. The reliability of the overall criteria was measured at 0.965. The findings suggest that the professional knowledge (PK) aspect demonstrated perceived directional associations with the outcome evaluation (OE), process management (PM), and guidance skills (GS) aspects within the network structure, whereas the GS aspect was more likely to be associated with other competency domains. Each of the four aspects has a criterion critical to improving DCs' competencies: value (PK1), listening skill (GS2), shared decision-making resources (PM3), and practical decision-making results (OE3).</p><p><strong>Conclusion: </strong>From healthcare professionals' perspectives, professional knowledge was the competency domain most closely associated with perceived directional relationships among other competency aspects within the network structure. The integrated APA-NRM approach delivers evidence-based prioritization and practical pathways for developing DC competencies and guiding training strategies.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":" ","pages":""},"PeriodicalIF":5.5,"publicationDate":"2026-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13613641/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148387390","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}