Intelligent medicine最新文献

{"title":"The rise of large language models in wearable health sensing","authors":"Vahid Farrahi","doi":"10.1016/j.imed.2025.12.003","DOIUrl":"10.1016/j.imed.2025.12.003","url":null,"abstract":"<div><div>Large language models (LLMs) represent a significant advancement in artificial intelligence (AI), offering versatile tools for natural language generation and understanding. The integration of LLMs into health and medicine is progressing rapidly, coinciding with the rising popularity and accessibility of wearable devices. Modern wearable devices such as smartwatches, heart rate monitors, activity trackers, and smart rings can now continuously monitor and measure various physiological and behavioral data, such as physical activity, motion, heart rate, skin temperature, and sleep. Wearable devices have several applications in biomedical research, health, and medicine. Some of these include self-monitoring, remote patient care, and out-of-clinic assessments. However, the continuous streams of data generated by wearables present significant challenges due to their sheer volume, unique characteristics, and inherent complexity. Although still in its infancy, there is a growing trend toward leveraging pre-trained LLMs to interpret and analyze these wearable-generated data streams for various applications. This opinion piece explores the expanding role of pre-trained LLMs in interpreting, analyzing, and leveraging physiological and behavioral data from wearables and discusses how LLMs offer a promising path forward in this evolving field.</div></div>","PeriodicalId":73400,"journal":{"name":"Intelligent medicine","volume":"6 3","pages":"Pages 285-291"},"PeriodicalIF":7.8,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148544652","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"From prediction to decision: Advancing medical artificial intelligence toward real clinical practice","authors":"Qi Chen,&nbsp;Han Lyu,&nbsp;Dong Li,&nbsp;Zhenchang Wang","doi":"10.1016/j.imed.2026.03.003","DOIUrl":"10.1016/j.imed.2026.03.003","url":null,"abstract":"<div><div>Artificial intelligence (AI) in medicine is advancing steadily toward real clinical practice, not only through improved predictive performance but also through more decision-relevant modeling, evaluation, and interaction. The studies highlighted here illustrate three complementary directions. First, contemporary imaging models—exemplified by three-dimensional vision transformer-based analysis of preoperative chest computed tomography (CT)—are being used to infer clinically consequential phenotypes, advancing from image recognition toward decision support in high-stakes settings such as surgical planning. Second, image-to-biomarker pipelines such as automated quantification of retinal vascular fractal dimension demonstrate how medical images can be transformed into reproducible quantitative markers suitable for population-level analysis and risk stratification. Third, large language models (LLMs) are increasingly being evaluated and positioned as clinical communication and interpretation components, most notably structured assessments in telepharmacy and bilingual patient education move beyond fluency to safety, actionability, empathy, and readability, whereas emerging perspectives consider LLMs as interpretive interfaces for complex and temporally evolving health data, including wearable sensing. At the same time, these advances also expose persistent bottlenecks that limit real-world deployment, particularly the continued dominance of single-task and static formulations, fragmented systems driven by task-specific fine-tuning, limited reasoning over disease trajectories and evolving clinical contexts, and evaluation practices that remain insufficiently coupled to clinical workflows and downstream consequences. We argue that the next stage of medical AI should shift from accuracy-centered prediction toward decision-oriented, practice-ready systems that are robust across settings, clinically aligned in evaluation, and deployable at scale in routine care.</div></div>","PeriodicalId":73400,"journal":{"name":"Intelligent medicine","volume":"6 3","pages":"Pages 241-244"},"PeriodicalIF":7.8,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148544645","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Application of large language models to natural language processing and image analysis tasks in dermatology: A systematic review","authors":"Lian Duan,&nbsp;Ting Li,&nbsp;Bowei Li,&nbsp;Xiaozhen Li,&nbsp;Dafu Fu,&nbsp;Xingyue Yang,&nbsp;Kaiyuan Cao,&nbsp;Hong Cai","doi":"10.1016/j.imed.2025.08.004","DOIUrl":"10.1016/j.imed.2025.08.004","url":null,"abstract":"<div><div>Computer vision (CV) and natural language processing (NLP) are 2 crucial subsets of artificial intelligence (AI). Large language models (LLMs) represent a significant application of deep learning in NLP. LLMs are AI systems with transformer architectures trained on large-scale datasets that are capable of understanding and generating natural language. LLMs have been widely applied in tasks such as text generation and translation. In dermatology, LLMs have been used for various purposes, such as diagnostic assistance, medical practice and decision support, patient communication, and professional education. However, dermatology differs from other medical specialties in that the diagnosis of diseases, selection of treatment methods, and prediction of prognoses rely heavily on the recognition of visual patterns. Therefore, in dermatology, LLMs must simultaneously process dermatological images and natural language. The aim of this study was to systematically review NLP and CV applications of LLMs in dermatology. In accordance with the preferred reporting items for systematic reviews and meta-analyses guidelines, the applications of LLMs in dermatological NLP and image processing tasks were systematically reviewed. After searching the MEDLINE (PubMed), Web of Science, and Scopus databases, a total of 37 original studies were included. The results showed that, in NLP tasks, LLMs demonstrated satisfactory performance in some studies, but most image processing results were not ideal. This review summarized the research findings on the applications of LLMs in dermatological natural language and image analysis, to identify LLMs capable of simultaneously processing text and images as a direction for future development.</div></div>","PeriodicalId":73400,"journal":{"name":"Intelligent medicine","volume":"6 3","pages":"Pages 260-271"},"PeriodicalIF":7.8,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148544647","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluation of artificial intelligence-based tool Covidence in literature screening for guideline updates: A prospective study","authors":"Xiaomei Yao,&nbsp;Ashley Low,&nbsp;Duvaraga Sivajohanathan,&nbsp;Emily T. Vella,&nbsp;Peiyao Wang,&nbsp;Gursharanjit Kaur,&nbsp;Ashirbani Saha,&nbsp;Jonathan Sussman","doi":"10.1016/j.imed.2025.12.006","DOIUrl":"10.1016/j.imed.2025.12.006","url":null,"abstract":"<div><h3>Background</h3><div>Regularly updating literature evidence for clinical practice guidelines (CPGs) is necessary but time intensive. Artificial intelligence (AI) tools, such as Covidence, may accelerate literature screening. We prospectively evaluated the effectiveness and accuracy of two Covidence functions: the auto-marking filter (adopted from Cochrane’s RCT classifier) for identifying randomized controlled trials (RCTs) and machine learning-assisted title and abstract (Stage I) screening in two cancer-related CPGs.</div></div><div><h3>Methods</h3><div>We updated the literature searches for the breast and lung cancer CPGs at the Program in Evidence-Based Care (PEBC), Ontario Health (Cancer Care Ontario). Two methodologists trained the machine learning model by indicating which of the first 25 references were tagged by Covidence’s RCT filter. Main outcomes included workload and time savings, work saved over sampling (WSS), and the impact on whether the original guideline recommendations required changes.</div></div><div><h3>Results</h3><div>A total of 1,270 (breast cancer) and 1,734 (lung cancer) references were imported into Covidence. Among them, 633 breast cancer and 656 lung cancer references were tagged using Covidence’s RCT filter as possible RCTs and required review at Stage I. Covidence’s RCT filter excluded non-RCTs with high accuracy, reducing manual screening by 50.2% (breast cancer) and 62.2% (lung cancer). For Stage I screening, Covidence reduced workload by 48.3% and 55.2% at 95% sensitivity, and by 44.2% and 16.9% at 100% sensitivity, respectively. WSS values aligned with these reductions. Owing to the small number of references screened and time needed to become initially trained to use Covidence, time savings was minimal. At 95% sensitivity, one included reference per CPG was missed, but guideline recommendations remained unchanged.</div></div><div><h3>Conclusion</h3><div>Covidence AI-assisted screening may effectively support updating literature reviews for oncology CPGs by reducing workload without compromising the integrity of the final recommendations. A 95% detection threshold may provide a practical balance between efficiency and accuracy.</div></div>","PeriodicalId":73400,"journal":{"name":"Intelligent medicine","volume":"6 3","pages":"Pages 351-357"},"PeriodicalIF":7.8,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148544584","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The eye as a digital biomarker: Transforming systemic disease assessment","authors":"Yanwu Xu,&nbsp;Emanuele Trucco","doi":"10.1016/j.imed.2026.03.002","DOIUrl":"10.1016/j.imed.2026.03.002","url":null,"abstract":"<div><div>The eye is no longer confined to the study of isolated ophthalmic diseases; instead, it is emerging as a scalable, noninvasive source of biomarkers for systemic health assessment. Advances in ophthalmic imaging and artificial intelligence (AI) have revealed that retinal structure, microvasculature, and neurovascular coupling encode clinically meaningful information about cardiovascular, metabolic, and neurodegenerative disorders. This growing body of evidence challenges the traditional organ-centric view of ophthalmology and positions retinal biomarkers as a foundation for population-level risk stratification and longitudinal disease monitoring. In this Editorial, we argue that the true clinical impact of retinal AI will not be realized through incremental improvements in prediction accuracy, but from a paradigm shift toward clinically validated, human-trustworthy, and interpretable multimodal foundation models for ophthalmology. Despite promising results across multiple systemic diseases, translation remains hindered by substantial modality heterogeneity, insufficient clinical validation, and limited interpretability. These barriers have constrained retinal AI largely to retrospective studies, preventing its adoption as a reliable clinical decision-support tool. We highlight key priorities for the field, including multimodal and longitudinal modeling, biologically grounded feature learning, human-AI collaboration, and rigorous prospective validation. Addressing these challenges is essential for transforming retinal imaging from a diagnostic adjunct into a cornerstone of precision medicine. Ultimately, realizing the full potential of the eye as a window to systemic health will require aligning algorithmic innovation with clinical relevance, interpretability, and trust.</div></div>","PeriodicalId":73400,"journal":{"name":"Intelligent medicine","volume":"6 3","pages":"Pages 245-249"},"PeriodicalIF":7.8,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148544648","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine learning-based prediction of aortic microstructural changes using renal pathological indicators under chronic unpredictable mild stress","authors":"Qi Wang,&nbsp;Donglu Liu,&nbsp;Jinrun Liu,&nbsp;Peijuan Tang,&nbsp;Xuedong Wang,&nbsp;Qian Liu,&nbsp;Bingge Fan,&nbsp;Min Hu,&nbsp;Lingbing Meng","doi":"10.1016/j.imed.2025.06.002","DOIUrl":"10.1016/j.imed.2025.06.002","url":null,"abstract":"<div><h3>Background</h3><div>Chronic psychological stress is an increasingly recognized risk factor for both renal and cardiovascular diseases, yet the mechanisms linking stress exposure to vascular remodeling remain poorly defined. We aimed to investigate whether renal pathological markers can predict abdominal aortic microstructural changes under chronic unpredictable mild stress (CUMS) and to evaluate the predictive value of these markers using machine learning models in both normal and metabolically compromised murine models.</div></div><div><h3>Methods</h3><div>A total of 60 male mice, including 30 wild-type (WT) C57BL/6J and 30 ApoE-deficient mice (ApoE^–/–) were randomized into four groups (<em>n</em> =15 per group): WT+ normal diet (ND), WT + ND + CUMS, ApoE^–/– + western diet (WD), and ApoE^–/– + WD + CUMS. CUMS was administered for 12 weeks. Histopathological assessment of renal and aortic tissues was performed using hematoxylin and eosin (H&amp;E), periodic acid-Schiff (PAS), reticular fiber, and immunohistochemical staining. Expression of sodium-glucose cotransporters (SGLT1 and SGLT2), edema, glycogen content, and abdominal aortic intima-media thickness (AA-IMT) were quantified. Correlation analyses were conducted between renal and vascular parameters. Two machine learning models—support vector machine (SVM) and backpropagation (BP) neural network—were used to evaluate the predictive relationship between renal biomarkers and aortic microstructural alterations.</div></div><div><h3>Results</h3><div>CUMS significantly increased renal SGLT1/SGLT2 expression, edema, and glycogen content in wild-type mice (all <em>P</em> &lt; 0.01), along with increased AA-IMT and reduced aortic diameter (<em>P</em> &lt; 0.05). ApoE^–/– mice exhibited pronounced aortic remodeling under CUMS, despite no further renal deterioration. Correlation analysis showed a strong association between renal and vascular indicators, particularly in the CUMS + ApoE^–/– group. Machine learning models demonstrated robust performance in predicting abdominal aorta diameter (AA-D) and AA-IMT based on SGLT1 and SGLT2 levels (SVM R² for AA-D: 0.79, BP network correlation for AA-IMT: 0.99), identifying these markers as early indicators of stress-induced vascular remodeling.</div></div><div><h3>Conclusion</h3><div>Renal injury biomarkers, particularly SGLT1 and SGLT2, can serve as reliable predictors of abdominal aortic microstructural changes under chronic stress. Integration of machine learning models enhances early risk stratification and provides a novel approach for mechanistic insight into cardiorenal stress responses.</div></div>","PeriodicalId":73400,"journal":{"name":"Intelligent medicine","volume":"6 3","pages":"Pages 336-350"},"PeriodicalIF":7.8,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148544585","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"One-stop automated diagnostic system for active sacroiliitis in three-dimensional magnetic resonance images using artificial intelligent models: a retrospective study","authors":"Xiaojian Ji ,&nbsp;Zhuofeng Li ,&nbsp;Lulu Zeng ,&nbsp;An'an Wang ,&nbsp;Jing Dong ,&nbsp;Lei Sun ,&nbsp;Shiwei Yang ,&nbsp;Jian Zhu ,&nbsp;Feng Huang ,&nbsp;Tao Li ,&nbsp;Jing Zhang ,&nbsp;Kunpeng Li","doi":"10.1016/j.imed.2025.07.005","DOIUrl":"10.1016/j.imed.2025.07.005","url":null,"abstract":"<div><h3>Background</h3><div>Axial spondyloarthritis (axSpA) can potentially progress to ankylosing spondylitis, and diagnostic delay may lead to irreversible structural damage. Although sacroiliac joint magnetic resonance imaging (MRI) can detect bone marrow edema (BME) for early diagnosis, the complex etiologies and reliance on expert interpretation impede efficient identification in chronic low back pain populations. Therefore, we developed an artificial intelligence (AI) system that integrates MRI analysis and automates report generation to facilitate the detection of active sacroiliitis and BME quantification.</div></div><div><h3>Methods</h3><div>This retrospective study analyzed 691 patients (540 with axSpA and 151 with non-spondyloarthritis) from the Chinese People’s Liberation Army General Hospital (2011–2023). Data were split into training and testing cohorts (4:1 ratio), with five-fold cross-validation applied to the training set. The system comprises four modules: (1) image preprocessing (intensity normalization), (2) coarse-to-fine 3D U-Net-based quadrant segmentation, (3) ResNet18-driven edema recognition (depth/intensity classification), and (4) diagnostic report generation using the QWEN large language model.</div></div><div><h3>Results</h3><div>Among 691 patients (335 active sacroiliitis-positive and 356 negative), the AI system achieved Spondyloarthritis Research Consortium of Canada (SPARCC) scores of (15.12±10.73) vs. (0.88±1.13) in positive versus negative groups, respectively. The quadrant segmentation module achieved DICE similarity coefficients above 0.7 on the training, validation, and testing datasets. The edema inflammation, depth, and intensity classifiers exhibited good performance on the testing dataset, with balanced accuracies of 77.54%, 76.26%, and 80.91%, and area under the curve values of 0.85, 0.87, and 0.92, respectively. The intraclass correlation coefficient between SPARCC scores by our system and those by rheumatologists was 0.84 on the testing dataset. At the patient-level, our system achieved 90.81% sensitivity for diagnosis of active sacroiliitis on the testing dataset.</div></div><div><h3>Conclusion</h3><div>The developed automated system enhances axSpA diagnostic efficiency by automating the identification of active sacroiliitis and enabling quantitative assessment of BME.</div></div>","PeriodicalId":73400,"journal":{"name":"Intelligent medicine","volume":"6 2","pages":"Pages 212-218"},"PeriodicalIF":6.9,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147807250","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A retrospective magnetic resonance imaging-based radiomics study for predicting lymph node regression status following neoadjuvant therapy in patients with locally advanced rectal cancer","authors":"Tianxu Ma ,&nbsp;Di Hao ,&nbsp;Ruiqing Liu ,&nbsp;Wentao Xie ,&nbsp;Mingyu Yang ,&nbsp;Junhao Zhang ,&nbsp;Jingnong Liu ,&nbsp;Zhenying Xu ,&nbsp;Rujie Jiang ,&nbsp;Xuejun Liu ,&nbsp;Bo Li ,&nbsp;Yuan Gao ,&nbsp;Maoshen Zhang ,&nbsp;Yun Lu","doi":"10.1016/j.imed.2025.12.005","DOIUrl":"10.1016/j.imed.2025.12.005","url":null,"abstract":"<div><h3>Background</h3><div>Lymph node metastasis (LNM) status serves as a key prognostic marker in patients with locally advanced rectal cancer (LARC). Neoadjuvant chemoradiotherapy (nCRT) can influence lymph node status by inducing regression, with treatment responses exhibiting substantial variability among patients. We aimed to develop and validate a random forest-based radiomics model for non-invasively predicting lymph node regression status following neoadjuvant therapy in patients with LARC using pretreatment magnetic resonance imaging (MRI).</div></div><div><h3>Methods</h3><div>This retrospective study included 285 patients with LARC who were treated with nCRT followed by elective resection at Qingdao University Affiliated Hospital between October 2019 and October 2023. Patients were randomly allocated to training and testing sets in a 7:3 ratio. Baseline characteristics including gender, age, body mass index (BMI), and other 13 clinical variables were compared between the groups, with no significant differences observed (<em>P</em> &gt;0.05). High-resolution T2-weighted MRI scans of the rectal region were collected preoperatively. Regions of interest corresponding to primary tumor lesions were manually delineated on the MRI scans, followed by radiomic feature extraction. Feature selection was performed using the least absolute shrinkage and selection operator (LASSO) regression model. A machine learning random forest predictive model was subsequently constructed, incorporating selected radiomics features and clinical variables.</div></div><div><h3>Results</h3><div>Model performance for predicting lymph node status was assessed using receiver operating characteristic curve analysis, area under the curve (AUC), and calibration curves. Four features were selected from 1,051 radiomic features to construct a radiomics model, achieving an AUC of 0.743 in the test set. Four features were also extracted from 19 clinical parameters to develop a clinical data model, with an AUC of 0.727. Integrating radiomic features and clinical data yielded a combined model with superior performance in the test set (AUC 0.794).</div></div><div><h3>Conclusion</h3><div>The radiomics model derived from pretreatment rectal MRI in patients with LARC demonstrated strong predictive capability for assessing metastatic lymph node responses to nCRT.</div></div>","PeriodicalId":73400,"journal":{"name":"Intelligent medicine","volume":"6 2","pages":"Pages 175-186"},"PeriodicalIF":6.9,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147806776","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A pulmonary nodule is worth 8 × 8 × 8 words: Computed tomography-based 3D vision transformer predicts early-stage high-grade lung adenocarcinoma of micropapillary and/or solid subtypes","authors":"Yin Zhou ,&nbsp;Yiyang Wang ,&nbsp;Cheng Li ,&nbsp;Shanshan Wang ,&nbsp;Yuning Pan ,&nbsp;Weiyu Shen ,&nbsp;Chengbin Lin ,&nbsp;Xinzhong Ruan ,&nbsp;Xianwang Ye ,&nbsp;Zhenya Zhao ,&nbsp;Zizhuo Wang ,&nbsp;Jun Chen ,&nbsp;Chenwei Li ,&nbsp;Hui Liu ,&nbsp;Wentao Fang","doi":"10.1016/j.imed.2025.11.001","DOIUrl":"10.1016/j.imed.2025.11.001","url":null,"abstract":"<div><h3>Background</h3><div>Early-stage high-grade lung invasive adenocarcinoma (IAC) has poor prognosis and is hard to identify using conventional radiological assessment. Current reliance on postoperative histology to identify high-grade subtypes delays risk-adapted surgical planning. Three-dimensional (3D) vision transformers (ViTs) may improve prediction by modeling long-range dependencies in computed tomography (CT) scans. We aimed to develop and validate 3D-ViT and Swin Transformer (SwinT) for preoperative CT-based prediction of early-stage high-grade IAC subtypes (micropapillary/solid), benchmarking against ResNet.</div></div><div><h3>Methods</h3><div>A multicenter cohort of 1028 patients with surgically confirmed early-stage lung adenocarcinoma was divided into training (<em>n</em> = 806), validation (<em>n</em> = 100), and external test (<em>n</em> = 122) sets. 3D-ViT, SwinT, and ResNet models were trained on CT to classify nodules harboring high-grade histologic patterns. A novel decision-aid tool for IAC surgery was provided. Performance was evaluated using area under the curve (AUC), accuracy, sensitivity, specificity, and precision. Attention mapping was performed to interpret 3D-ViT decision-making.</div></div><div><h3>Results</h3><div>The 3D-ViT model achieved AUC values of 0.856 (95% CI: 0.845–0.877) (validation) and 0.806 (95% CI: 0.790–0.816) (testing), compared to 0.854 (95% CI: 0.841–0.872) (validation) and 0.760 (95% CI: 0.743–0.776) (testing) for the ResNet baseline. 3D-ViT showed balanced accuracy, sensitivity, specificity, and precision in the validation set. In external testing, 3D-ViT significantly outperformed ResNet in all metrics with <em>P</em> &lt; 0.01. The SwinT-based AlignSen model from decision-aid tool prioritized sensitivity for high-grade IAC (88.0% validation, 93.4% testing), while maintaining specificity (76.0% validation, 54.1% testing) which significantly outperformed ViT and ResNet-based AlignSen models’ specificity (60.0% and 54% validation, 52.5% and 24.6% testing, respectively). Attention maps highlighted 3D nodule heterogeneity and peripheral irregularities.</div></div><div><h3>Conclusion</h3><div>The 3D-ViT model demonstrated robust accuracy and generalizability in predicting high-grade IAC subtypes using CT images. Integration of preoperative SwinT into clinical workflows may offer a viable alternative to intraoperative pathology subtyping, potentially reducing reliance on frozen sections while optimizing surgical planning.</div></div>","PeriodicalId":73400,"journal":{"name":"Intelligent medicine","volume":"6 2","pages":"Pages 116-131"},"PeriodicalIF":6.9,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147806779","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The performance of Covidence: An artificial intelligence-based tool for title and abstract screening in a breast cancer evidence-based clinical practice guideline","authors":"Xiaomei Yao ,&nbsp;Ashirbani Saha ,&nbsp;Ashley Low ,&nbsp;Shakil Ahmed ,&nbsp;Samya Ali ,&nbsp;Aditya Misra ,&nbsp;Mariam Abdelmalek ,&nbsp;Sharan Saravanan ,&nbsp;Jonathan Sussman","doi":"10.1016/j.imed.2025.12.008","DOIUrl":"10.1016/j.imed.2025.12.008","url":null,"abstract":"<div><h3>Background</h3><div>Clinical practice guidelines (CPGs) support evidence-based care but are time-consuming to develop. We aimed to compare artificial intelligence (AI)-assisted versus manual title and abstract screening (Stage I) in Covidence using data from a published breast-cancer CPG.</div></div><div><h3>Methods</h3><div>This systematic review (SR) included 8,774 articles identified through a medical literature search, after duplicate removal. Three article subsets (<em>n</em> = 500, 1,000, and 2,000) were randomly selected from 8,774 articles to perform 30, 30, and 10 trials, respectively, independent Stage I AI-assisted trials. The primary outcome of each trial is workload savings achieved through AI-assisted identification of 95% and 100% relevant articles (e.g., sensitivity), and 100% of finally-included articles. The secondary outcome is missed finally-included articles when the sensitivity of 95% was reached for each subset.</div></div><div><h3>Results</h3><div>At 95% sensitivity, 100% relevant articles and 100% finally-included articles were identified, median (minimum, maximum) workload savings were 40.7% (4.4%, 59.4%), 25.0% (0.4%, 55.2%), and 57.6% (6.2%, 76.4%) for <em>n</em> = 500; 38.3% (6.2%, 54.0%), 17.3% (0.0%, 39.1%), and 63.9% (0.4%, 77.5%) for <em>n</em> = 1,000; 16.6% (10.8%, 41.8%), 4.4% (0.3%, 20.9%), and 17.9% (0.8%, 64.6%) for <em>n</em> = 2,000, respectively. Covidence’s performance does not improve as the size of the subsets increases for a CPG with multiple complicated research questions. A potential positive correlation between the proportion of relevant articles in initial training of Covidence and workload savings at Stage I across all 70 trials. At 95% sensitivity, five trials missed one article (<em>n</em> = 500); two trials missed two articles and one trial missed one article (<em>n</em> = 1,000); and one trial missed three articles and five trials missed one article (<em>n</em> = 2,000).</div></div><div><h3>Conclusion</h3><div>AI-assistance in Covidence for Stage I screening showed promise and pitfalls in the SR for a breast cancer CPG on a complex topic. Further prospective research is needed to better understand the performance of AI-assistance in Covidence and intricacies of CPG topics.</div></div>","PeriodicalId":73400,"journal":{"name":"Intelligent medicine","volume":"6 2","pages":"Pages 219-225"},"PeriodicalIF":6.9,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147807251","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}