SEARCH · Search PubMed

Results for “digital learning”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

174 records · Page 6Linked to original sources

PubMed2026

The effects of visuomotor training and tDCS stimulation on visuomotor integration and visual processing: an electrophysiological approach.

BACKGROUND: Visuomotor integration coordinates visual and motor cortical activity to produce goal-directed responses and can be indexed by Rolandic Mu-rhythm suppression and visual evoked potential (VEP) P100 parameters. Perceptual-motor training improves visuomotor performance, and transcranial direct current stimulation (tDCS) over primary motor cortex (M1) has been reported to enhance motor learning when paired with training. This study examined whether anodal M1 tDCS augments the effects of Senaptec visuomotor training in healthy adults. METHODS: Sixty participants were randomized to active anodal tDCS (five 10-minute sessions, 1 mA; n = 31) or sham (n = 29) over M1 immediately before each Senaptec training session; 53 completed all sessions and post-testing. Outcomes were Mu-suppression ratios, VEP P100 latency and amplitude, and Senaptec measures of visual sensitivity and visuomotor control. RESULTS: Active tDCS produced no augmentation of any outcome, with no significant group × time interaction for any measure, consistent across composite and task-level analyses. Training alone produced no change in Mu suppression or visuomotor control. By contrast, both groups showed significant training-related gains in visual sensitivity, including near-far quickness and stereopsis, accompanied by shorter P100 latencies and larger amplitudes, indicating more efficient early visual processing. CONCLUSIONS: A clear dissociation emerged: training produced robust improvements in early visual processing, whereas neither tDCS nor training altered sensorimotor (Mu) or visuomotor-control measures. The tDCS results should be interpreted cautiously given the modest dose and limited power to detect small effects, rather than as evidence of inefficacy. Tablet-based perceptual training enhanced visual processing independent of neuromodulation.

Humans↗

PubMed2026

Multidisciplinary mHealth Rehabilitation for Patients With Abdominal Cancer Who Are Receiving Chemoradiotherapy: Randomized Phase II Trial.

BACKGROUND: Concurrent chemoradiotherapy (CCRT) for abdominal cancer frequently induces muscle loss, weight loss, and malnutrition. OBJECTIVE: This exploratory randomized phase II trial evaluated whether a multidisciplinary, mobile health (mHealth)-based multimodal rehabilitation program could preserve handgrip strength and muscle mass in patients with abdominal cancer undergoing CCRT. METHODS: In this prospective, multicenter, randomized, open-label phase II trial (NCT05325554), 111 eligible patients with abdominal malignancies scheduled for CCRT were randomly assigned (1:1) to receive either multidisciplinary mHealth rehabilitation care (MRC; n=57) or standard care (SC; n=54). The MRC program was delivered by a dedicated multidisciplinary team using the AiNST mHealth platform and wearable heart rate monitors. The primary end point was handgrip strength at the end of CCRT (analyzed with analysis of covariance adjusting for baseline). Secondary end points were exploratory and analyzed without multiplicity adjustment; sensitivity analysis using false discovery rate (FDR) correction was performed. RESULTS: Between February 2022 and April 2023, 111 patients were enrolled. Adherence was high (n=93, 83.9% achieved exercise targets). After adjusting for baseline handgrip strength, the MRC group had significantly higher handgrip strength at the end of CCRT than the SC group (adjusted mean difference 4.87 kg, 95% CI 3.36-6.38; P<.001). Exploratory analyses of secondary end points (without multiplicity adjustment) showed that the MRC group also had better preservation of body weight (P=.005), skeletal muscle mass (P<.001), serum albumin (P=.009), prealbumin (P=.02), and lower rates of hematological toxicity (P<.05), as well as improved psychological status (distress thermometer [DT] and Hospital Anxiety and Depression Scale [HADS]) and nutritional scores (Nutritional Risk Screening 2002 [NRS-2002] and Patient-Generated Subjective Global Assessment [PG-SGA]) at the end of CCRT (all P<.05). All nominally significant secondary end points remained significant after FDR correction (q<.05). These findings are preliminary and should be interpreted with caution due to the open-label design, population heterogeneity, and exploratory secondary analyses. CONCLUSIONS: In this exploratory phase II trial, a multidisciplinary, mHealth-based multimodal rehabilitation program was associated with better preservation of handgrip strength, muscle mass, and nutritional status, as well as lower rates of certain treatment toxicities, compared with SC. However, definitive conclusions are limited by the open-label design, heterogeneity of tumor types, and short follow-up. Larger, blinded phase III trials are needed to confirm these findings.

Humans↗

PubMed2026

The Role of Artificial Intelligence for Intimate Partner Violence Prevention: A Systematic Review.

INTRODUCTION: Intimate partner violence (IPV), encompassing physical, sexual, emotional and economic abuse, remains a pervasive global health concern. Traditional prevention efforts face obstacles such as underreporting, delayed detection and limited personalised support. Emerging artificial intelligence (AI) approaches offer new opportunities to enhance IPV prevention. AIM: This systematic review maps and synthesises evidence on AI-driven tools in IPV prevention based on studies published between 2004 and 2024. METHODS: Following PRISMA 2020 guidelines and PROSPERO registration, we searched PubMed, Embase, CINAHL, PsycINFO, IEEE Xplore and Web of Science. Eligible studies explicitly evaluated AI technologies targeting IPV prediction, screening, intervention or support delivery. Study quality was appraised using the Mixed Methods Appraisal Tool (MMAT). RESULTS: Of 1304 records initially identified, 41 studies met eligibility criteria. AI applications ranged from machine learning (ML) for risk prediction and natural language processing (NLP) for IPV detection in clinical and social media data, to image analysis for forensic evaluation and chatbot-based support. Predictive modelling demonstrated strong discriminative performance, while NLP-based screening detected IPV with notable sensitivity. Chatbots showed feasibility and user acceptability, but evidence of their direct impact on reducing IPV incidence was limited, with one randomised controlled trial showing a modest reduction. Key challenges identified included algorithmic bias, data privacy risks and barriers to integration across health and social care systems. DISCUSSION: AI-informed interventions show promise for improving IPV detection, risk assessment, and scalable support, but questions remain about long-term effectiveness, ethical fairness, transparency and equitable implementation. Future interdisciplinary research should address these concerns to responsibly deploy AI in IPV prevention. RELEVANCE TO CLINICAL PRACTICE: The findings highlight the importance of trauma-informed, culturally responsive care and provider training in AI applications. Nurse-led innovation and policy advocacy will be crucial for safe, equitable integration of AI in IPV prevention.

Artificial Intelligence↗

PubMed2026

Mining Stored-Specimen Studies for Information about Cancer Natural History.

The advent of new multicancer early detection tests and publication of early diagnostic results have generated expectations of clinical benefit from multicancer screening. The clinical benefit of a cancer screening test depends critically on disease natural history, which is typically learned from prospective screening studies. Retrospective studies of stored blood specimens are important in learning about a test's preclinical diagnostic performance but have rarely been used to infer natural history. The extent to which these studies might be harnessed to also learn natural history is discussed in the context of an article in this issue that infers the combined natural history of a range of cancers targeted by a multicancer early detection test using a case-control subsample of specimens from a large cohort study. The critical question concerns the identifiability of key transition rates in multistate models of natural history alongside state-specific sensitivities. The article suggests that these parameters are estimable within a Bayesian framework that leverages prior information about test sensitivity from diagnostic studies. We offer a heuristic discussion of identifiability in this setting and encourage formal study to determine the extent to which models with varying degrees of complexity may be learned from stored-specimen studies. See related article by Dai et al., p. 1535.

Humans↗

PubMed2026

Ensemble DNA methylation clock demonstrates Immune-metabolic aging signatures associated with mortality.

Aging is a multifactorial process that is best described in terms of the progressive acquisition of multiple layers of phenotypic changes, such as epigenetic modifications, inflammation, and metabolic dysregulation. DNA methylation clocks have been extensively used to construct epigenetic clocks based on the DNAm profiles that can be used to estimate biological age and predict age-associated outcomes. Nevertheless, the vast majority of clocks constructed so far have been based on linear models, which are unlikely to fully account for the heterogeneity and non-linearity of survival-related DNAm signatures. In this work, we constructed a heterogeneous stacked ensemble survival model based on DNAm data obtained from the Framingham Heart Study. We first identified 190 CpG loci using elastic net Cox regression and subsequently constructed a survival prediction model based on the fusion of five complementary survival models by means of a neural network meta-learner. The prediction power of the survival model was evaluated in an external validation cohort, where we observed strong performance for predicting all-cause mortality that significantly exceeded PhenoAge and was statistically comparable to GrimAge. These performance estimates were derived in cohorts of European ancestry and externally validated in postmenopausal women aged 50-79 years, and should therefore be interpreted as applicable only to demographically similar populations.

Humans↗

PubMed2026

Nature-based meaning-focused photography intervention enhances subjective well-being: A three-arm randomized controlled study.

Gaining meaning from nature contact can promote subjective well-being. However, few studies have validated the effectiveness of nature-based meaning interventions in enhancing subjective well-being. This study consisted of a 7-day online intervention to examine the effects of nature-based meaning-focused photography on well-being by comparing a photo-only group, a photo + writing group, and a waiting list control group and how meaning in life mediates the relationship between nature contact and well-being. A pre-registered three-arm randomized controlled trial (groups: photo + writing group vs. photo-only group vs. control group) * (time: pre-test vs. post-test vs. 1-month follow-up) was conducted with 219 college students. In the photo + writing group, participants captured nature scenes and wrote 100-word reflections. The photo-only group only took nature photos. The primary outcomes were meaning in life and well-being, and the secondary outcome was life satisfaction. A conservative Bayesian causal forest analysis based on machine learning was used to detect both treatment and heterogeneous intervention effects. Compared with the control group, the photo + writing group showed positive effects on meaning in life, subjective well-being, and life satisfaction, with average treatment effects of 0.36, 0.27, and 0.66 standard deviations (SD), respectively. The photo-only group also showed generally positive effects on these outcomes, with average treatment effects of 0.27, 0.24, and 0.54 SD, respectively. However, these effects were not sustained after 1 month. The intervention was especially beneficial for participants from lower subjective socioeconomic status, with limited prior nature exposure, or lower baseline psychological well-being. Importantly, enhanced meaning in life helped explain how the intervention improved well-being and life satisfaction. This study also demonstrated that combining nature-based photography and reflective writing can improve well-being.

Humans↗

PubMed2025

Application of causal discovery of factors driving dissolved oxygen in estuarine environments.

Dissolved oxygen (DO) concentrations in estuarine bottom waters are a manifestation of multiple, interacting physical and biogeochemical processes, yet identifying their independent contributions remains challenging. Here, we analyze monthly water quality monitoring data from eight stations across Long Island Sound from 1994 to 2022 using a causal discovery framework (PCMCI+) and transformation of forcing variables. Our goal is to identify and isolate variables that causally influence bottom DO and improve predictive models by minimizing overfitting and multicollinearity. PCMCI+ reveals surface-layer temperature as the most important and consistent negative driver of bottom DO, followed by stratification. Wind events exhibit only brief relief by advection and mixing, while river discharge shows no direct causal link to DO, making it less influential than previously thought. Biogeochemical variables, including chlorophyll-a (Chl-a), nitrate and nitrite, and particulate carbon, influence DO through both contemporaneous and time-lagged pathways, often with signs that shift depending on the process. The derived models were evaluated by comparing skill scores, mean squared error, and Akaike Information Criterion. Both model types perform well, with coefficient of determination values exceeding 0.90 at multiple stations using only 3-5 predictors. Our analysis reveals that the best causal predictors are surface-layer temperature, stratification, Chl-a, and particle carbon. This approach provides a scalable framework for improving prediction models and understanding the mechanistic links that control the seasonal variability of DO in estuarine systems.

Estuaries↗

PubMed2026

Effectiveness of an AI-based home exercise app for rehabilitation of rotator cuff-related shoulder pain: A randomized controlled trial.

BACKGROUND: Rotator cuff-related shoulder pain contributes to disability and healthcare use. Although therapeutic exercise is first-line treatment, limited supervision and adherence may reduce its effectiveness; digital rehabilitation with real-time feedback may address these limitations. OBJECTIVES: To evaluate the effectiveness of adding a digital rehabilitation program to standard physiotherapy on pain, function, fear-avoidance beliefs, and healthcare utilization. DESIGN: Single-center, assessor-blinded, randomized controlled trial with two parallel groups. METHOD: Forty-six adults (mean age 59 years) with rotator cuff-related shoulder pain were randomized to 12 weeks of conventional physiotherapy or physiotherapy plus an AI-based digital rehabilitation program using computer vision for real-time feedback and performance monitoring. Outcomes were assessed at baseline and at 2, 4, and 12 weeks. Pain intensity (NPRS) was primary outcome; secondary outcomes included upper limb function (QuickDASH), fear-avoidance beliefs (FABQ), and post-intervention healthcare utilization. Analyses followed an intention-to-treat approach. RESULTS: Pain reduction exceeded the MCID (1.3) at 4 and 12 weeks. Between-group differences favoured the intervention at Weeks 2 and 4 (MD -0.7; 95% CI -1.13 to -0.14 and MD -1.01; 95% CI -1.8 to -0.2, respectively). Upper limb function improved more at Week 4 (MD -7.3; 95% CI -12.3 to -2.2). FABQ scores decreased more at Week 12 (MD -7.6; 95% CI -14 to -0.5). Fewer participants in the experimental group required post-intervention healthcare (3 vs 10; p = 0.02). CONCLUSION: Adding AI-based home exercise app to conventional treatment improve pain and may improve function and reduce healthcare utilization in rotator cuff-related shoulder pain.

Humans↗

PubMed2026

Artificial Intelligence Technologies in Nursing Clinical Decision-Making: An Umbrella Review.

AIM: To describe contemporary peer-reviewed literature on artificial intelligence in nurses' clinical decision-making. METHODS: An umbrella review of literature reviews. DATA SOURCES: Four major databases were searched for reviews published between 2019 and 2024. RESULTS: Sixteen literature reviews reported on 965 nursing artificial intelligence primary studies. The studies focused on technology development and emerging performance evaluations, whilst real-world testing or implementation in nursing clinical settings was rare. Rigorous comparative analyses were lacking. While artificial intelligence demonstrates promise in decision-making, challenges such as a lack of controlled studies, algorithmic bias, limited reproducibility and insufficient clinical trials hinder its practical impact. Ethical concerns, transparency and patient data privacy issues pose barriers to AI integration in nursing practice. Ethical and legal guidelines for patient privacy are needed and should be taught along with AI literacy training for nurses. CONCLUSIONS: Artificial intelligence has the potential to enhance clinical nursing decision-making, although evidence is limited by too few examples of nurse participation during development. Underutilisation in administrative nursing functions hinders implementation. Nurses should assume a central role in the design and development of AI applications to ensure that these technologies address the realities of nursing practice. With such improvements, artificial intelligence can transform nursing practice, improve nurses' clinical decision-making and ultimately enhance consumer healthcare outcomes. PATIENT OR PUBLIC INVOLVEMENT: No Patient or Public Involvement. REPORTING METHOD: While there is no reporting checklist for umbrella reviews, the PRISMA guide for systematic reviews was followed.

Artificial Intelligence↗

PubMed2026

What Constitutes Effective Support and Provision Within Day Service Centres for People With Intellectual Disabilities? A Systematic Review of Qualitative Research.

BACKGROUND: This review aimed to investigate the effectiveness and quality of support and provision within day service centres for people with intellectual disabilities. METHOD: The International Bibliography of the Social Sciences, Scopus and PsycInfo databases were searched in August 2024, and the results were reported according to the PRISMA guidelines. Peer-reviewed, English-language, qualitative studies that investigated the effectiveness of day service provision for people with intellectual disabilities in non-residential settings were considered for review. Methodological quality of the included studies was assessed using the JBI Critical Appraisal Tool for qualitative research. Qualitative themes were identified through thematic analysis and synthesised using the ConQual approach. RESULTS: Fourteen studies were included and four key themes emerged: 'perceptions of service quality'; 'community-orientation, integration, and empowerment'; 'challenging behaviours and safety'; and 'staff-centred factors and job satisfaction'. Confidence in the evidence was 'very low' for 3/4 themes, while there was 'moderate' confidence in the evidence related to the theme 'perceptions of service quality'. CONCLUSIONS: Day service centres for people with intellectual disabilities may enhance their effectiveness and quality of provision by concentrating on promoting communication, engagement, relationships, social networks and community integration. Addressing the methodological shortcomings and incomplete reporting of related research in future would contribute to improvements in overall confidence in the evidence base. This can then be better used to inform and further enhance day service provision for people with intellectual disabilities.

Humans↗

PubMed2026

Bioprospecting microbial genomes to expand the biocatalytic toolbox of rubber oxygenases.

A set of rubber oxygenases was discovered through phylogenetic analysis and AI-based structural modeling of complexes of the putative enzymes with a substrate mimicking cis-1,4-polyisoprene. Sixteen candidate proteins were selected from thermophilic microorganisms, all sequence-related to the Latex clearing protein from Streptomyces sp. K30 (LcpK30). Sequence truncation and solubility tags were then evaluated to enhance protein expression, with the SUMO tag proving to be the most effective. Including LcpK30, nine heme-containing oxygenases were successfully expressed in E. coli NEB 10-beta cells, purified (35-157 mg L-1 yield) and characterized. Steady-state kinetics revealed significant rubber latex-degrading properties for six of them, with the truncated SUMO-fused LcpK30 (SUMO-LcpK30T) showing activity in agreement with literature. Notably, the catalytic efficiencies of all the expressed homologs lay within one order of magnitude and the oxygenase from Thermomonospora echinospora was found to be particularly promising in terms of activity, especially at high latex concentrations (more than 1% w/v). The analysis of reaction mixtures by both HPLC and HPLC-MS confirmed the oxidation of cis-1,4-polyisoprene to form the expected isoprenoid oligomers (n = 2-12), whose distribution was consistent with the usual endo-type cleavage pattern in all but one case. This bioprospecting effort afforded a platform of new rubber-degrading enzymes with diverse efficiencies and product profiles, capable of adapting to targeted applications.

Oxygenases↗

PubMed2026

Clinical accuracy and short-term outcomes of intraoral photogrammetry for complete-arch implant rehabilitation: A retrospective multicentre study on 35 patients.

OBJECTIVES: To evaluate the clinical accuracy and short-term outcomes of complete-arch implant-supported fixed dental prostheses (ISFDPs) fabricated using an intraoral photogrammetry (IPG) based digital workflow in completely edentulous patients. METHODS: This multicenter retrospective clinical study included 35 patients rehabilitated with 52 complete-arch ISFDPs (10 FP1, 18 FP2 and 24 FP3 restorations) supported by 221 implants. All definitive prostheses were designed and fabricated using a fully digital workflow initiated by IPG acquisition with the Aoralscan Elite IPG® (SHINING 3D). The primary outcome was clinical accuracy, assessed at definitive prosthesis delivery through evaluation of passive fit using the Sheffield test and radiographic verification. Secondary outcomes included biologic and prosthetic complications, as well as implant and prosthesis survival rates during the follow-up. RESULTS: Passive fit was achieved in all definitive restorations (100%). Radiographic evaluation confirmed accurate marginal adaptation at the implant-prosthesis interface in all cases. No statistically significant differences in clinical accuracy were observed according to treated arch, number of supporting implants, or prosthetic design (P > .05). During a mean follow-up period of 12.1 ± 3.5 months, biologic and prosthetic complications were limited and generally minor. Implant survival was 99.5%, and prosthesis survival was 100%. CONCLUSIONS: Within the limitations of this retrospective clinical study, the IPG based workflow demonstrated high clinical accuracy and predictable short-term outcomes for complete-arch implant rehabilitation, consistently enabling passive fit and favorable prosthetic performance. CLINICAL RELEVANCE: IPG may represent a clinically reliable and predictable approach for complete-arch digital implant impression acquisition. The high rates of passive fit, together with the low incidence of biologic and prosthetic complications observed in this multicenter clinical study, support the use of IPG based workflows for the fabrication of complete-arch ISFDPs.

Humans↗

PubMed2026

AI echo INSIGHT study: A prospective blinded randomized trial of artificial intelligence echocardiogram interpretation.

BACKGROUND: Transthoracic echocardiography (TTE) is the most commonly performed cardiac imaging modality with over 30 million studies annually. Demand for timely expert interpretation continues to outpace capacity, creating diagnostic delays and inter-observer variability that impact patient care. Recent research has suggested computer vision artificial intelligence (AI) models can generate accurate preliminary comprehensive TTE reports, however, prospective evaluation is needed to determine whether AI-assisted TTE interpretation can improve clinician efficiency while preserving diagnostic accuracy. METHODS: AI ECHO INSIGHT is a prospective randomized blinded clinical trial conducted at Kaiser Permanente Northern California that will evaluate 1200 historical TTE studies (1000 consecutive unselected studies plus 200 with moderate or greater valvular disease) interpreted using three workflows: (1) AI-generated preliminary report finalized by a blinded cardiologist (AI-assisted); (2) cardiologist-generated preliminary report finalized by a blinded cardiologist (cardiologist-assisted); and (3) sonographer-generated preliminary report finalized by a blinded cardiologist (sonographer-assisted). The primary outcome is the rate of substantial change between preliminary and final reports, comparing the AI-assisted workflow to the pooled cardiologist-assisted and sonographer-assisted workflows. Secondary outcomes include cardiologist interpretation time for report finalization, superiority testing for diagnostic accuracy, and reporting consistency. CONCLUSION: AI ECHO INSIGHT is a prospective randomized blinded clinical trial evaluating the clinical impact of AI-assisted TTE interpretation on diagnostic accuracy, cardiologist efficiency, and reporting consistency in real-world echocardiography workflows. TRIAL REGISTRATION: ClinicalTrials.gov registration number NCT07229300.

Humans↗

PubMed2026

The future of pediatric vesicoureteral reflux management.

BACKGROUND AND OBJECTIVE: Vesicoureteral reflux (VUR) is a common condition in pediatric urology, yet important uncertainties persist regarding risk stratification, imaging strategies, and prevention of long-term renal damage. Emerging technologies may help address these challenges. This review provides a forward-looking overview of recent advances in artificial intelligence (AI) and immunomodulation that may influence future management of pediatric VUR. METHODS: A forward-looking literature review was performed using the PubMed database (January 2000-March 2025), focusing on studies addressing AI, immunomodulation, or vaccination in the context of VUR and urinary tract infections. Criteria of inclusion were the relevance to pediatric VUR, the novelty of the proposed concept, the potential clinical implications and, for the AI literature, the existence of a clinical evaluation of the algorithm on a dataset from patients. KEY FINDINGS AND LIMITATIONS: AI-based models show promising performance in supporting clinical decision-making, including prediction of the need for voiding cystourethrography, automated grading of VUR, estimation of recurrent urinary tract infection risk and prediction of chemoprophylaxis. These tools may facilitate more individualized diagnostic and therapeutic strategies, although current evidence is largely retrospective and requires prospective validation. Immunization and immunomodulatory approaches aim to reduce infection burden and modulate inflammatory pathways associated with renal scarring. While early experimental and adult clinical data are encouraging, pediatric-specific evidence remains limited, and clinical applicability in children with VUR is not yet established. CONCLUSION: Artificial intelligence and immunologically targeted strategies represent complementary, emerging approaches that may contribute to more personalized management of pediatric VUR. At present, both should be regarded as exploratory tools whose clinical impact will depend on further validation and appropriately designed pediatric studies.

Humans↗

PubMed2026

Artificial intelligence (AI) uses in stereotactic radiosurgery (SRS): diagnosis with brain metastasis (BM) - A systematic review.

BACKGROUND: Brain metastases (BM) are the most common intracranial tumors in adults, and stereotactic radiosurgery (SRS) has become a mainstay of management. However, several diagnostic challenges persist in the SRS pathway, particularly the differentiation of radiation necrosis (RN) from true tumor progression, which conventional MRI and even advanced imaging techniques often cannot reliably resolve. Recent advances in artificial intelligence (AI) offer the potential to address these diagnostic limitations. This systematic review synthesizes current literature on AI applications for MRI-based diagnostic decision support in BM patients undergoing SRS, with a focus on radiomics and deep learning tools for distinguishing RN from progression, classifying molecular and histologic subtypes, and predicting treatment response. METHODS: A systematic review was performed in accordance with PRISMA guidelines. PubMed, Web of Science, and Scopus were searched using a targeted query combining terms related to AI, brain metastasis, diagnosis or imaging, and SRS. After screening 483 records and applying strict inclusion and exclusion criteria, 18 studies published between 2015 and 2025 were included. Data were extracted on study design, cohort characteristics, imaging modality, AI methodology, validation strategy, and reported diagnostic performance. RESULTS: Among the 18 included studies, AI models demonstrated strong performance across diagnostic tasks in the BM-SRS pathway. The differentiation of RN from true tumor progression was the most extensively studied application, addressed by 14 of 18 studies, with reported AUCs ranging from 0.71 to 0.94. Support vector machines, random-forest ensembles, convolutional neural networks, and transformer-based multimodal architectures were widely used. The literature evolved from single-sequence radiomic classifiers in 2018 to multimodal deep learning frameworks fusing imaging with clinical and genomic data in 2025. Contrast-enhanced T1-weighted MRI was the dominant imaging input, and texture-based radiomic features (GLCM, GLSZM, GLDM, and wavelet-derived features) were the most consistently predictive. The highest-performing models reached AUCs of 0.85-0.91 through multimodal integration of imaging with clinical and genomic features, and consistently outperformed expert neuroradiologist read on matched cases. Remaining studies addressed longitudinal segmentation-based detection of local failure and adverse radiation effects, BRAF mutation status in melanoma BM, early Gamma Knife treatment response, and primary tumor histology classification, with more variable performance. CONCLUSION: AI models, particularly those integrating MRI-derived radiomic features with clinical and genomic data, show high accuracy in supporting diagnostic decisions for BM patients treated with SRS. The post-SRS differentiation of radiation necrosis from true tumor progression has reached the greatest level of maturity and is closest to clinical translation, with potential to reduce unnecessary biopsies, personalize surveillance intervals, and rationalize treatment-pathway decisions. Other diagnostic applications, including molecular subtyping and primary tumor histology classification, remain exploratory and require further multicenter validation. Integration of AI tools into multidisciplinary tumor-board workflows, combined with prospective validation and standardized reporting, will be essential to realize the full clinical benefits of AI in SRS for brain metastases.

Humans↗

PubMed2026

Comparison of summative assessments between simulated electronic health records versus traditional paper-based patient cases: A non-inferiority randomized controlled trial.

INTRODUCTION: Electronic health records are fundamental to contemporary pharmacy practice, yet evidence supporting their use in pharmacy education is lacking. This single-center, non-inferiority randomized controlled trial with blinded outcome assessment evaluated whether delivering patient cases via a simulated academic EHR (aEHR) was non-inferior to a traditional paper-based format in student exam performance. METHODS: 53 third-year PharmD students at the University of British Columbia were randomized 1:1 to complete a mock summative examination using either the aEHR or paper-based case delivery, stratified by self-reported EHR comfort level. The primary outcome was mean written exam score (%). Non-inferiority was pre-specified at a margin of 14%. Adjusted linear regression was used for the primary analysis, with a multiple imputation sensitivity analysis. Student perceptions were explored through post-exam focus groups analyzed using inductive thematic analysis. RESULTS: 42 students (21 per group) completed the exam and were included in the primary analysis. Mean scores were 66% (SD 11) in the aEHR group and 68% (SD 10) in the paper group. The adjusted mean difference (paper minus aEHR) was -2.2% (95% CI -9.2% to +4.8%), satisfying non-inferiority but not superiority. Sensitivity analysis (n = 53) yielded consistent results (-2.3%; 95% CI -7.1% to +4.1%). Focus groups revealed initial student anxiety with the aEHR but recognized its alignment with clinical practice. DISCUSSION: These findings support the feasibility of integrating simulated EHRs into summative pharmacy assessments without compromising performance. CONCLUSION: Simulated EHRs are a non-inferior assessment medium compared with paper-based formats and represent a viable step toward technology-driven pharmacy practice environments.

Humans↗

PubMed2026

The potential of clustering methods for pre-test triage in sleep medicine: A systematic review.

Sleep disorders exhibit substantial heterogeneity, and traditional classifications may not fully capture clinically relevant subtypes. Clustering techniques can identify patient subgroups that improve phenotypic characterization and may support personalized management. This systematic review evaluated the application of clustering in sleep medicine, with particular focus on its potential use as a pre-test triage tool prior to formal sleep testing. PubMed/MEDLINE, Embase, Web of Science, and Scopus were searched to February 2025. Eligible studies applied clustering to classify sleep disorders in adults. Two reviewers independently conducted screening, data extraction, and risk-of-bias assessment using QUADAS-2. The protocol was registered on PROSPERO. Fifty-one studies (1983-2025) were included, predominantly focused on obstructive sleep apnea (OSA) (n = 38, 74%). Hierarchical clustering (n = 20) and K-means clustering (n = 14) were the most frequently used techniques. Internal validation was reported in only 18% of studies, and external validation was reported in only 1 study. Seven studies relied exclusively on baseline clinical, demographic, or questionnaire data, representing pre-test scenarios, whereas most incorporated polysomnography-derived variables, limiting their applicability to early clinical stratification. Hierarchical clustering was the most commonly applied method; however, the overall lack of validation limits confidence in the robustness and clinical applicability of identified phenotypes. The potential role of clustering as a pre-test triage strategy remains largely unexplored, as most studies focused on post-diagnostic phenotyping and were affected by incorporation bias. Future research should prioritize pre-test clinical variables, rigorously validate internally and externally, and adopt standardized methodological and reporting practices to facilitate clinical translation.

Humans↗

PubMed2026

A systematic approach to standardizing the visual appearance of endometriotic lesions for artificial intelligence recognition.

INTRODUCTION: Numerous studies have shown that the diagnostic performance and reproducibility of visual recognition of endometriosis during laparoscopy are poor. The use of artificial intelligence (AI) seems relevant for exhaustive lesion recognition. Standardization of the visual classification of lesions, in the form of an ontology, is an essential prerequisite to enable medical experts to annotate surgical data consistently and subsequently allow engineers to train and build an artificial intelligence tool for endometriosis recognition. MATERIAL AND METHODS: A systematic search was conducted in the MEDLINE (via PubMed), EMBASE, and the Cochrane Library databases up to May 2022, aiming to identify studies describing the laparoscopic visual appearance of superficial endometriosis, endometriomas, and deep infiltrating endometriosis. The accumulated data in the literature concerning the visual appearance of the different forms of endometriosis were used to create an ontology that could be used for artificial intelligence applications. RESULTS: Out of 932 articles screened, 35 studies were selected based on the inclusion criteria of human subjects with histologically confirmed endometriosis lesions visualized via laparoscopy. The selected studies were reviewed to develop a visual ontology of endometriosis lesions observed via laparoscopy. The lesions were categorized into 4 classes and further subdivided into 11 subclasses: superficial (black, red, white, or subtle), adhesions (dense or filmy), deep (obliteration, retraction, or deformation), and ovarian (endometrioma or chocolate fluid). The positive predictive value (PPV) varied across lesion types: black lesions (PPV 47%-97%), red lesions (PPV 33%-100%), white lesions (PPV 20%-81%), and ovarian endometriosis (PPV 42%-98%). Nonspecific lesions such as adhesions (PPV 16%-50%) and subtle superficial lesions (PPV 0%-67%) presented lower PPVs. Deep endometriosis lesions, often buried within organs, required indirect signs (obliteration, retraction, deformation) for identification. CONCLUSIONS: The visual ontology proposed in this systematic search could facilitate the detection and classification of endometriosis lesions using artificial intelligence. This study highlights the challenges of reaching a consensus on lesion recognition and classification in AI projects due to the diverse visual presentations of endometriosis.

Humans↗