JMIR Medical Informatics最新文献

{"title":"Integrating Lymph Node Metastasis and Programmed Death-Ligand 1 Prediction in Non-Small Cell Lung Cancer From a Single PET/CT Scan: Multicenter Radiomics Study.","authors":"Wen Chen, Qiufang Liu, Huiling Peng, Jianping Zhang, Zhihao Chen, Silong Hu, Shaoli Song","doi":"10.2196/86835","DOIUrl":"10.2196/86835","url":null,"abstract":"<p><strong>Background: </strong>Preoperative stratification for non-small cell lung cancer (NSCLC) necessitates separate evaluations of lymph node metastasis (LNM) to guide surgical decisions and of programmed death-ligand 1 (PD-L1) expression to inform immunotherapy.</p><p><strong>Objective: </strong>This study aimed to develop and validate an integrated diagnostic solution that could simultaneously predict both LNM status and PD-L1 expression status from a single, standard-of-care ¹⁸F-fluoro-2-deoxy-D-glucose positron emission tomography/computed tomography (¹⁸F-FDG PET/CT) scan.</p><p><strong>Methods: </strong>In this multicenter study, we segmented primary tumors and peritumoral 15-mm expansion regions from preoperative PET/CT scans of 273 patients (for LNM prediction) and 242 patients (for PD-L1 prediction). A total of 7868 radiomic features from intratumoral and peritumoral regions were extracted. Following rigorous feature selection, 2 independent models were developed using machine learning and tested on a temporal validation cohort (n=45). Model performance was benchmarked against clinicopathological models and nuclear medicine physicians.</p><p><strong>Results: </strong>The integrated model for LNM prediction (PT-IPT-LR) achieved an area under the curve of 0.845 (95% CI 0.716-0.973) in the temporal validation cohort, with a sensitivity of 0.765 (95% CI 0.518-1.000) and a specificity of 0.786 (95% CI 0.602-0.970). The model for PD-L1 expression (PT-IPT-SVM) achieved an area under the curve of 0.776 (95% CI 0.641-0.911) in the temporal validation cohort, with a sensitivity of 0.800 (95% CI 0.609-0.991) and a specificity of 0.650 (95% CI 0.401-0.899). Decision curve analysis confirmed the clinical utility of both models. Critically, we found no significant correlation between the radiomic signatures of LNM and PD-L1, which validates our 2-model approach.</p><p><strong>Conclusions: </strong>We present a radiomics framework that noninvasively integrates prediction of LNM and PD-L1 from a single preoperative PET/CT scan. This tool may enable preoperative stratification, potentially optimizing both surgical and systemic treatment planning for patients with NSCLC in a single step.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"14 ","pages":"e86835"},"PeriodicalIF":5.0,"publicationDate":"2026-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13557200/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148921504","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":"The Promise of Ambient AI Technology in Medical Education: Opportunities and Guardrails.","authors":"Shirin Shafazand, Umar Bowers, Sudha Jayaraman","doi":"10.2196/88725","DOIUrl":"10.2196/88725","url":null,"abstract":"<p><strong>Unlabelled: </strong>Ambient AI technologies, commonly known as AI scribes, are transforming clinical practice by autonomously capturing patient-provider conversations and structuring them into clinical notes. Short-term studies suggest that ambient AI can significantly reduce documentation time and improve job satisfaction. However, as health care systems accelerate the adoption of these tools, the medical education community must seek to answer unresolved questions regarding their full impact on learners. The inevitable integration of ambient AI in teaching hospitals presents both transformative opportunities and significant challenges for medical education. This viewpoint discusses the potential benefits and risks of ambient AI in both undergraduate and graduate medical education and considers its impact on learning and clinical skills acquisition. Robust research studies are urgently needed to navigate this new frontier and ensure that the integration of ambient AI in the clinical learning environment ultimately enriches, rather than diminishes, the practice of medicine.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"14 ","pages":"e88725"},"PeriodicalIF":5.0,"publicationDate":"2026-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13552838/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148914212","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":"Automated Extraction of Postoperative Cancer Recurrence and Metastasis From Computed Tomography (CT) Reports: Semisupervised Deep Learning Study.","authors":"Wonkeun Jo, Bumwoo Park, Ji-Hoon Sim","doi":"10.2196/92937","DOIUrl":"10.2196/92937","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Perioperative computed tomography (CT) imaging is essential for detecting postoperative recurrence and metastasis in cancer patients. However, large-scale automated extraction of oncological outcomes from CT reports remains limited by the unstructured nature of report text and wide variability in reporting styles. Radiology reports frequently contain linguistic ambiguities, including negations, hedging, and expressions conveying diagnostic uncertainty (eg, \"cannot exclude recurrence\" or \"possibly metastatic\"). Manual review is labor-intensive and constrains consistent extraction at scale. The inability to systematically account for diagnostic uncertainty represents a major barrier to reliable automated surveillance systems.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This study aimed to develop a semisupervised deep learning (DL) classification framework that explicitly captures diagnostic uncertainty by classifying postoperative recurrence and metastasis into 3 categories (positive, negative, and uncertain).&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;This retrospective study analyzed 288,076 postoperative CT reports from 86,083 cancer surgery patients at Asan Medical Center (2014-2021). After exact-match deduplication, model training and evaluation used 17,846 unique reports for recurrence and 63,766 for metastasis. Preprocessing identified presumed negatives through keyword filtering and unsupervised clustering. The semisupervised framework incorporated human-in-the-loop validation across 3 cycles-with clinicians reviewing approximately 2000 samples per cycle (&lt;1% of total reports)-and integrated rule-based algorithms (RAs) and medical BERT (MedEmbed and PubMedBERT). A report-level train-validation split was used, as preprocessing reduces each report to sentence-level fragments that preclude patient-level linkage. Performance was evaluated against RAs and multiple BERT variants under both naive and simulated real-world class distributions. Maximum mean discrepancy testing confirmed distributional integrity of the sampled data. Model interpretability was assessed using Integrated Gradients.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;The cohort included 11 cancer types, predominantly gastrointestinal (28,516/86,083, 33.1%), hepatobiliary and pancreas (14,715/86,083, 17.1%), and genitourinary (12,959/86,083, 15.1%). Under simulated conditions, PubMedBERT achieved 92.58% accuracy for recurrence in the multiclass, and MedEmbed achieved 93.25% for metastasis in the binary class. The framework achieved accuracies of 97.33% (multiclass) and 99.33% (binary class) for recurrence and 95.00% (multiclass) and 96.67% (binary class) for metastasis, compared with human intrarater consistencies of 96.88% and 93.80% (recurrence and metastasis, respectively, for multiclass), reflecting concordance with the clinician-derived consensus standard. The framework captured diagnostic uncertainty in 1.4% of recurrence cases and 6.9% of metastasis cases. Notably, the RA o","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"14 ","pages":"e92937"},"PeriodicalIF":5.0,"publicationDate":"2026-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13552650/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148914263","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":"Refining Our Focus by Bridging Theory and Practice for Real-World Impact: An Updated Scope for JMIR Medical Informatics.","authors":"Arriel Benis, Amanda Iannaccio, Andrew J Coristine, Tiffany I Leung","doi":"10.2196/109008","DOIUrl":"10.2196/109008","url":null,"abstract":"<p><strong>Unlabelled: </strong>To align with contemporary trends and place greater focus on persistent and novel challenges in the field, <i>JMIR Medical Informatics</i> has updated its focus and scope. Each submitted work will be evaluated against a stronger criterion for translational impact. Additionally, submissions on AI methods and applications are expected to meet standards of rigor and reporting transparency. In this editorial, we explain further what changed; why; and what this means for prospective authors, reviewers, and readers.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"14 ","pages":"e109008"},"PeriodicalIF":5.0,"publicationDate":"2026-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13544690/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148893090","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":"Developing Country-Specific Charlson Comorbidity Index Mappings for Use With German Administrative Data: Methodological Comparative Study.","authors":"Piotr Paweł Sokołowski, Michael Hagmann, Máté E Maros, Gaetan Kamdje Wabo, Josefine Maria Meerjanssen, Fabian Siegel","doi":"10.2196/93923","DOIUrl":"10.2196/93923","url":null,"abstract":"<p><strong>Background: </strong>The Charlson Comorbidity Index (CCI) is widely used to quantify comorbidity burden in observational research. Applying it to real-world data requires accurate International Classification of Diseases-based mappings. The commonly used mapping does not reflect current German coding standards.</p><p><strong>Objective: </strong>This study aimed to develop year-specific mappings (2004 to 2026) based on the German modification of the International Classification of Diseases, 10th Revision (ICD-10-GM), for the CCI with an open-source implementation and compare them with the commonly used mapping.</p><p><strong>Methods: </strong>For each year, mappings were curated via independent dual review with consensus. In 515,827 inpatient cases from a German tertiary center (2010-2024), year-appropriate mappings and the commonly used mapping were applied, and the results were pooled into 2 corresponding datasets that were subsequently compared. Agreement was assessed using the intraclass correlation coefficient (2-way mixed-effects model for absolute agreement based on single measurement), and the significance of the discordances was measured using the McNemar test.</p><p><strong>Results: </strong>Agreement was very high; 3.1% (16,136/515,827) of cases differed. A single code was present in 48.9% (7896/16,136) of the discordant cases and was intentionally excluded in the new mappings as it was not diagnostic for the category it was assigned to. Discordant results were found in 58.8% (10/17) of the categories (\"peripheral vascular disease,\" \"mild liver disease,\" and \"severe liver disease\") being present in, respectively, 51.7% (8339/16,136), 17.4% (2813/16,136), and 16.4% (2657/16,136) of the discordant cases. After filtering the dataset to only include observations with any diagnosis of a malignant disease, 6.9% (9377/136,607) of cases differed, and 79.3% (7434/9377) of those differences were caused by the \"peripheral vascular disease\" category, suggesting significant discrepancies for specific research questions.</p><p><strong>Conclusions: </strong>We provide transparent, year-specific ICD-10-GM (2004-2026) mappings and an open-source tool for CCI calculation. The mappings align with current German coding practice and enable reproducible, year-appropriate comorbidity adjustment using administrative data.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":" ","pages":"e93923"},"PeriodicalIF":5.0,"publicationDate":"2026-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13586706/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148723356","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":"Markov Decision Process-Based Personalized Follow-Up Planning for Type 2 Diabetes: Retrospective Cohort Study.","authors":"Silei Chen, Tianyi Liu, Zhonghua Sun, Jian Jia, Dong Hang, Wenhong Zhang","doi":"10.2196/88206","DOIUrl":"10.2196/88206","url":null,"abstract":"<p><strong>Background: </strong>Personalized follow-up for type 2 diabetes may improve the alignment between monitoring intensity and patient needs, but operational approaches that jointly consider follow-up timing, modality, expected health benefits, and resource use remain limited.</p><p><strong>Objective: </strong>This study develops a Markov decision process (MDP) framework for personalized follow-up planning, externally validates complementary risk-prediction models, and estimates the projected 12-month cost-effectiveness of model-generated follow-up strategies.</p><p><strong>Methods: </strong>We retrospectively analyzed longitudinal data from 41,398 patients with type 2 diabetes managed in 10 community health centers in Nanjing, China, over the 2015-2024 calendar period. An independent Shanghai cohort included 25,506 patients from 10 communities. We developed least absolute shrinkage and selection operator (LASSO)-Cox models to predict 1-year incident complication and mortality risk and evaluated discrimination in Shanghai. Separately, a 12-cycle finite-horizon MDP used observed action-conditional state transitions with prespecified utility, cost, access, and willingness-to-pay parameters to generate personalized follow-up policies.</p><p><strong>Results: </strong>For an example patient initially without recorded complications (S0), the personalized policy increased annual effectiveness by 0.48 quality-adjusted life days (QALDs; 0.0013 quality-adjusted life years [QALYs]) and cost by 33.46 CNY (1 CNY=US $0.15), yielding an incremental cost-effectiveness ratio (ICER) of 25,499 CNY/QALY. In a heterogeneous simulated cohort of 1000 patients initialized in S0, mean annual effectiveness increased from 313.52 to 314.05 QALDs (0.85896 to 0.86041 QALYs), and mean annual cost increased by 24.67 CNY, yielding an ICER of 17,016 CNY/QALY. External C-indices were 0.778 for incident complications and 0.812 for mortality. Deterministic sensitivity analyses did not materially alter the cost-effectiveness conclusion.</p><p><strong>Conclusions: </strong>The MDP framework generated individualized 12-month follow-up policies with small projected QALY gains at modest incremental program cost, while the complementary risk models demonstrated external discrimination in an independent cohort. As action-conditional transitions were estimated from observational records and several economic parameters were prespecified, the modeled differences represent projections rather than causal treatment effects and require prospective implementation and economic validation before clinical adoption.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"14 ","pages":"e88206"},"PeriodicalIF":5.0,"publicationDate":"2026-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13583495/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148882843","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":"Automatic Kidney Image Segmentation During Robot-Assisted Partial Nephrectomy Using a Deep Learning Model Based on a Multiannotator Dataset: Model Development and Validation Study.","authors":"Gaëlle Margue, Kilian Chandelon, Maxime Pattou, Alice Pitout, Abderrahmane Khaddad, Federico Rubat-Baleuri, Julie Desternes, Laura Richert, Nicolas Bourdel, Adrien Bartoli, Jean-Christophe Bernhard","doi":"10.2196/82540","DOIUrl":"10.2196/82540","url":null,"abstract":"<p><strong>Background: </strong>Augmented reality (AR) has emerged as a promising tool to enhance surgical precision during robot-assisted partial nephrectomy (RAPN), particularly by enabling the intraoperative overlay of 3D anatomical models. However, real-time AR implementation requires robust image segmentation of anatomical structures, such as the kidney, which remains technically challenging in dynamic laparoscopic environments.</p><p><strong>Objective: </strong>This study aimed to develop and validate a large, annotated image dataset to train deep learning models for automated segmentation of the renal parenchyma during RAPN, as a prerequisite for real-time AR guidance.</p><p><strong>Methods: </strong>We conducted a single-center, observational image annotation study using prospectively collected surgical videos from 131 RAPN procedures performed between 2022 and 2024. Patients had localized renal tumors, with 11 presenting with multifocal disease (160 tumors in total). A total of 48,000 frames were extracted based on image sharpness, diversity, and the exclusion of artifacts. A subset of 454 images was annotated by 9 contributors (surgeons, engineers, and nonexperts) after structured training. Interannotator agreement was assessed using the Dice similarity coefficient (DSC) and sensitivity against an expert reference. A convolutional neural network (AlbuNet-34) was trained using 12,546 annotated images and evaluated on a validation set of 3137 images. Model performance was analyzed overall and across surgical phases.</p><p><strong>Results: </strong>Annotators achieved high agreement, with median DSC values ranging from 0.91 to 0.95 and sensitivity consistently more than 0.89. The deep learning model achieved a mean DSC of 0.75 (SD 0.23) and a sensitivity of 0.71 (SD 0.24) on the validation set. Segmentation accuracy varied significantly across surgical phases, with lower performance observed during tumor resection and tumor bed reconstruction due to increased visual complexity.</p><p><strong>Conclusions: </strong>This study demonstrates the feasibility of automated renal parenchyma segmentation using deep learning in real-world intraoperative settings. Although current performance remains below that of expert-level annotations, the creation of a large, annotated dataset and the implementation of a structured multiannotator workflow represent key milestones toward reliable AR-assisted surgery. Ongoing refinements in annotation quality, dataset diversity, and neural network optimization are expected to enhance future real-time AR applications in urology.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"14 ","pages":"e82540"},"PeriodicalIF":5.0,"publicationDate":"2026-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13583486/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148882808","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 Health Informatics System in the South Australian Public Health Network: Implementation Report.","authors":"James Malycha, Jake White, Adam Phillips, Lukah Dykes, Lukasz Wiklendt, Paul Lambert, Adelaide Boylan, Justin Beilby","doi":"10.2196/86564","DOIUrl":"10.2196/86564","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Following 2 decades of electronic medical record (EMR) adoption, most large public health systems hold comprehensive digital clinical data but lack the complementary informatics capability to return those data to clinicians, coders, and operational teams in a usable form. In South Australia (SA), the statewide Sunrise (Altera Digital Health) EMR system has digitized documentation and ordering since 2017; however, tools for back-end data extraction and enriched clinical information displays were not prioritized, and clinical, operational, and research users have reported ongoing difficulties accessing timely data.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;The aim of this study is to describe the development, governance, and deployment of a cloud-native health informatics system (HIS) in the Central Adelaide Local Health Network (CALHN), which serves approximately 40% of SA public patients, and to report implementation outcomes in accordance with the iCHECK-DH (Guidelines and Checklist for the Reporting on Digital Health Implementations) guidelines.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;The HIS comprises 6 architectural layers deployed on Microsoft Azure with Red Hat OpenShift (IBM), extracting Sunrise EMR data in near real time under a read-only model in which all patient data remain within the SA Health network at all times. Implementation proceeded through 5 overlapping phases (2021-2026), governed across 4 domains: technical (security impact assessment, information asset classification, and independent cybersecurity review), clinical (a clinical governance committee that has met quarterly since May 2022), corporate (incorporation of HeartAI Pty Ltd in 2022, with conflicts of interest declared and managed under SA Health policy), and ethical (human research ethics committee [HREC], reference 18079 with subsequent amendments). Development was funded through approximately Aus $1.84 million (Aus $1=US $0.72 as of August 24, 2026) in competitive and institutional grants under a public-private model with CALHN and AusHealth.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Unlabelled: &lt;/strong&gt;Three applications have reached deliberately different stages of maturity. The CALHN Critical Care Informatics System (CCCIS) has been implemented and evaluated: it has been deployed across the 2 CALHN intensive care units (ICUs; 54 beds, approximately 5000 admissions per year) since 2022, is in daily clinical use, and automates the submission of 115 variables to the Australian and New Zealand Intensive Care Society Centre for Outcome and Resource Evaluation (ANZICS CORE) registry. In a formal evaluation by 8 senior intensivists, its mean System Usability Scale score was 76 of 100, and the overall workload was low (NASA Task Load Index: 21/100). CODEXA, an AI-assisted clinical coding application, is in operational validation: models trained on 500,000 episodes and tested on 50,000 held-out episodes achieved a pooled &lt;i&gt;F&lt;/i&gt;&lt;sub&gt;1&lt;/sub&gt;-score of 71% across the full case mix and","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"14 ","pages":"e86564"},"PeriodicalIF":5.0,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13533040/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148876551","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 Call Abandonment in a Health Care Call Center Using Nonpersonal Operational Data: Machine Learning Study.","authors":"Hilmi Al-Shakhshir, Sara Kier, Dan Hoke, Stephanie Hoiriis, Mary-Ellen Vicinus, Ravi Thadhani, Anant Madabhushi","doi":"10.2196/88441","DOIUrl":"10.2196/88441","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Call abandonment is a critical barrier to patient access in health care call centers; yet, predictive modeling efforts are limited by strict privacy regulations that restrict the use of personal or behavioral data. Whether abandonment can be accurately predicted using only anonymized operational metrics remains unclear.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This study evaluated the feasibility, performance, and operational use of machine learning models trained exclusively on nonpersonal, routinely collected call center metrics to predict call abandonment across distinct organizational phases.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;We analyzed 1,037,363 call records from a large academic health care system spanning 4 operational periods marked by workflow changes and skill consolidation. Features included temporal variables, skill identifiers, and rolling operational metrics (in-queue time, occupancy, handle time, after-call work time, and active agents). Random forest and CatBoost models were trained on 3 phases defined as: (T1 [January-April 2023; original workflows], T2 [May-August 2023; post skill consolidation, cross-training, and new workflows], and T3a [September-December 2023; optimized processes]) using 5-fold cross-validation with 3 imbalance-handling strategies (none, class weighting, and synthetic minority oversampling technique). Temporal generalizability was assessed by evaluating all models on all 4 phases, with T3b serving as an unseen holdout set. Performance was evaluated using area under the curve (AUC), precision-recall area under the curve (PR-AUC), Brier score, and calibration error. Shapley additive explanations (SHAP) values quantified feature contributions.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Across all training phases and algorithms, adding operational metrics improved the area under the receiver operating characteristic curve by 0.03-0.13 vs models using only temporal and skill features. The best configuration was a CatBoost model trained on T2 with operational metrics and no imbalance correction (T3b AUC 0.767, PR-AUC 0.068, expected calibration error 0.006, and Brier 0.027). Models trained solely on preintervention data (T1) generalized poorly to postintervention periods when restricted to temporal and skill features (AUC 0.32-0.38) but achieved AUC 0.715 on T3b when operational metrics were included. SHAP analysis consistently identified in-queue time as the dominant predictor, with the number of logged-in agents, hour-of-day, and skill identifiers comprising the remaining top features. Abandonment declined from 8.7% (20,809/238,722) in T1 to 2.8% (8293/300,060) in T3b; model-based analyses of temporal features (day of week and hour of day) showed the highest risk on Mondays and between 11:00 and 16:00. Skill-level analyses showed marked improvement in high-volume imaging teams with high abandonment.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;Models trained on nonpersonal operational data predicted call aba","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"14 ","pages":"e88441"},"PeriodicalIF":5.0,"publicationDate":"2026-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13575546/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148868054","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 Conceptual Model for Ambient AI Adoption: Perspectives From Academia and Industry.","authors":"Joshua Biro, Jesse M Pines, Sudha Jayaraman, Vamsi Chagari, Raj Ratwani","doi":"10.2196/91098","DOIUrl":"10.2196/91098","url":null,"abstract":"<p><strong>Unlabelled: </strong>Ambient AI technologies are increasingly marketed as solutions to reduce clinician burden and improve care efficiency; however, real-world performance varies widely across clinical settings. Health care provider organizations face challenges in determining which aspects of ambient AI performance matter most and how to obtain meaningful information about those aspects from vendors or through internal evaluation. This article presents a shared mental model to guide health system leaders in conceptualizing ambient AI performance across 3 interdependent dimensions: technical, interface, and system level. For each dimension, we outline the types of information relevant to assessment; what vendors should reasonably be expected to provide; and how health care provider organizations can conduct their own evaluations to contextualize, verify, or supplement vendor claims. By integrating both vendor and health system perspectives, this work offers a grounded, practical structure to support organizations of all sizes in understanding and making informed decisions about ambient AI technologies.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"14 ","pages":"e91098"},"PeriodicalIF":5.0,"publicationDate":"2026-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13524215/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148882794","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}