Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “medical image analysis”

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.

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

1,736 records · Page 15Linked to original sources
PubMed2026

Process evaluation of a nurse-led transitional care model (Cardiolotse) within a randomized controlled trial aiming to improve care coordination for patients with cardiovascular diseases in Germany.

BACKGROUND: Patients with higher age suffering from cardiovascular disease discharged from hospital are at greater risk of readmission within 30 days. We evaluated an innovative care program providing post-discharge support and helping patients to navigate through the healthcare system. This paper reports the findings of the process evaluation of the randomized controlled trial Cardiolotse, a nurse-led transitional care model improving care coordination for patients with cardiovascular diseases in Germany. METHODS: A process evaluation, following the guidelines of the Medical Research Council (MRC) Framework, was performed. Semi-structured interviews with all relevant target groups were conducted to gain more insight about implementation processes. Questionnaires and medical records were used to explore mechanisms of impact and understand how change was produced in the intervention. Qualitative data were analysed using content analysis with deductive and inductive categories. Descriptive statistics and subgroup analyses were utilized to explore quantitative data. RESULTS: Overall, the designed training programme was perceived positively by the study nurses, so called Cardiolotsen (CLs). Patients receiving support by the CLs reported positive satisfaction ratings. Interactions between CLs and patients were reported as trustworthy and reliable. A total of approximately 12,500 contacts were made over the course of the intervention. However, changes in satisfaction scores between intervention and control groups in terms of medical treatment or the interaction between medical health providers involved in the treatment could not be determined. Furthermore, data suggested reach issues with respect to office-based physicians, as regular CL contact could not be achieved with 90% of the participating general practitioners and cardiologists. CONCLUSIONS: The CLs served as an important source of support for the participating patients throughout the intervention. At regular intervals, they checked a patient's health status and their adherence to therapies after discharge. However, the process evaluation identified cross-sectoral communication and information exchange between CLs and office-based physicians as an implementation challenge. TRIAL REGISTRATION: The study was retrospectively registered at German Clinical Trial Register, http://www.drks.de/DRKS00020424 (Trial Registration Number DRKS00020424) on 18 June 2020.

Humans↗
PubMed2026

Diagnostic Performance of Machine Learning for Systemic Lupus Erythematosus: Systematic Review and Meta-Analysis.

BACKGROUND: Early and accurate diagnosis of systemic lupus erythematosus (SLE) and its organ involvement is essential. Previous reviews of machine learning (ML) in SLE combined heterogeneous tasks and validation strategies and may have overinterpreted model performance. OBJECTIVE: This study evaluated the diagnostic performance of ML and deep learning (DL) models for 3 clinically distinct SLE-related tasks: SLE classification or diagnosis, lupus nephritis (LN) diagnosis, and neuropsychiatric systemic lupus erythematosus (NPSLE) discrimination. We also assessed methodological quality and certainty of evidence. METHODS: PubMed, Embase, Cochrane Library, Web of Science, and IEEE Xplore were searched from January 2014 to April 2026. Eligible peer-reviewed diagnostic accuracy studies developed or validated ML or DL models for 1 of the 3 prespecified tasks, used an accepted reference standard, and provided data for a 2×2 contingency table. Bivariate random-effects meta-analyses with the Hartung-Knapp-Sidik-Jonkman adjustment were used to pool sensitivity and specificity. We reported 95% prediction intervals (PIs), assessed risk of bias using the Quality Assessment of Diagnostic Accuracy Studies for Artificial Intelligence tool (QUADAS-AI; Viknesh Sounderajah [Imperial College London]), and evaluated certainty of evidence using the Grading of Recommendations Assessment, Development, and Evaluation framework for diagnostic test accuracy. RESULTS: Twenty-nine studies were included: 17 for SLE classification, 5 for LN diagnosis, and 7 for NPSLE discrimination. In the primary task-stratified analysis, pooled sensitivity was 0.91 (95% CI 0.86-0.94; 95% PI 0.56-0.99), and pooled specificity was 0.94 (95% CI 0.91-0.96; 95% PI 0.69-0.99), with low heterogeneity (I²=23.9% and 22.9%, respectively). DL models showed a sensitivity of 0.93 and specificity of 0.95, compared with 0.88 and 0.94 for traditional ML models. Certainty of evidence was high for most analyses but low for LN diagnosis because of inconsistency and imprecision. All studies were retrospective, and only 9 of 29 (31%) performed independent external validation. Overall risk of bias was high or unclear in 22 of 29 (75.9%) studies. No study reported model calibration, decision-curve analysis, or net clinical benefit. CONCLUSIONS: ML models showed promising diagnostic accuracy across 3 distinct SLE-related tasks, but wide PIs, limited external validation, and pervasive risk of bias restrict conclusions about real-world generalizability. Prospective multicenter studies with standardized tasks and reference standards, independent external validation, and formal assessment of calibration and clinical utility are required before clinical implementation.

Humans↗
PubMed2026

The Impact of Chatbot Type and Normative Messaging on Chatbot Usage Intention Based on the Health Technology Acceptance Model: Randomized Controlled Trial.

BACKGROUND: Digital health tools, such as health chatbots, may improve access to scalable health support, but adoption remains inconsistent. Existing models do not fully integrate technology acceptance factors with health motivation factors relevant to digital health use. OBJECTIVE: This study proposed and tested the health technology acceptance model and examined whether normative message framing and chatbot type were associated with health motivation, technology acceptance, and intention to use a health chatbot. METHODS: In October 2025, we conducted a 4 &#xd7; 2 between-participants online experiment with 1000 US adults recruited from a nationally representative YouGov panel. Participants were randomized to 1 of 8 conditions varying norm message type (self-oriented, peer-oriented, expert-oriented, or family-oriented) and chatbot type (AI-powered or rule-based) in a cancer prevention and genetic risk information scenario. Outcomes included descriptive norms, injunctive norms, perceived susceptibility, perceived severity, perceived benefits, self-efficacy, perceived ease of use, trust, privacy concerns, and usage intention. Data were analyzed using a multivariate ANOVA with Bonferroni-adjusted post hoc tests and multiple linear regression. RESULTS: Peer-oriented and family-oriented messages produced higher usage intention than expert-oriented messages, and peer-oriented messages also increased descriptive norms, injunctive norms, self-efficacy, and trust. AI-powered chatbots were associated with higher usage intention (P=.02) and greater trust (P=.008) than rule-based chatbots. In regression analyses, the model explained 50.8% of the variance in usage intention. Usage intention was positively associated with descriptive norms (&#x3b2;=0.087; P=.003), injunctive norms (&#x3b2;=0.078; P=.009), perceived susceptibility (&#x3b2;=0.051; P=.03), perceived benefits (&#x3b2;=0.253; P<.001), and trust (&#x3b2;=0.33; P<.001), and negatively associated with perceived severity (&#x3b2;=-0.047; P=.049) and privacy concerns (&#x3b2;=-0.11; P<.001). Perceived ease of use and self-efficacy were not significant predictors. CONCLUSIONS: The health technology acceptance model was a useful framework for explaining the intention to use a health chatbot by combining technology acceptance and health motivation constructs. Both social design features and chatbot design features shaped adoption-related beliefs, with peer-oriented and family-oriented framing and AI-powered chatbots showing particular promise. Trust and privacy concerns remained central determinants of intended use.

Humans↗
PubMed2026

Automated CEAP Classification of Venous Duplex Reports Using Multimodal Artificial Intelligence.

OBJECTIVE: To develop and internally validate a prototype multimodal artificial intelligence system for automated CEAP (Clinical, Etiological, Anatomical and Pathophysiological) classification of venous duplex ultrasound (VDUS) reports, integrating natural language processing of free-text components with computer vision analysis of hand-drawn anatomical diagrams. METHODS: Single centre retrospective observational study using routinely collected clinical data. One thousand consecutive venous duplex ultrasound reports from Cambridge University Hospitals NHS Foundation Trust, UK (July 2024 - May 2025) were labelled according to the CEAP classification, excluding the Etiological component, which could not be reliably determined from duplex reports alone. Transfer learning was applied using ClinicalBERT for text and MobileNetV3 for diagrammatic data. Clinical classes were predicted from request line text. Text- and image-based pathophysiological models were developed for four anatomical territories (Great Saphenous Vein, Small Saphenous Vein, Deep system, Perforators), combined using late fusion with probability averaging. RESULTS: The clinical CEAP model achieved accuracy of 0.91, macro-F1 of 0.82, and macro-AUC of 0.98. Pathophysiological prediction varied, with text models broadly outperforming image models. Fusion yielded heterogeneous benefits, improving SSV performance but reducing Deep system accuracy. The performance of the final pathophysiological CEAP fusion models varied across anatomical territories: accuracy ranged from 0.70-0.92 and macro-AUC from 0.80-0.92. CONCLUSION: This study demonstrates the feasibility of automated CEAP classification from VDUS reports. Despite class imbalance affecting minority class predictions, the strong discriminatory performance validates this multimodal ML model for extracting clinically meaningful information from real-world data. This approach offers potential, pending external validation, to streamline vascular services through automated triage and guideline-compliant decision making.

Artificial intelligence↗
PubMed2026

Applications of artificial intelligence in robot-assisted surgery: a systematic review.

To characterize applications of artificial intelligence (AI) in robot-assisted surgery, summarize technical and clinical performance, and assess the quality of the available evidence. PubMed, Web of Science Core Collection, and Scopus were searched for English-language journal articles published from 1 January 2020 through 31 October 2025. Randomized, observational, model-development, validation, and feasibility studies evaluating AI in robot-assisted surgery or closely related image-guided minimally invasive workflows were eligible. Two reviewers independently performed study selection, data extraction, and risk-of-bias assessment. Owing to heterogeneity in surgical procedures, AI tasks, analytical units, validation strategies, and outcomes, findings were synthesized descriptively without statistical pooling. The review was registered in the International Prospective Register of Systematic Reviews (CRD420251175699). Seventeen studies were included: seven clinical prediction or decision-support studies, eight intraoperative recognition, segmentation, or image-guided studies, and two training or workflow studies. Five prediction studies reported area-under-the-curve values of 0.74-0.95. Technical studies reported F1 or Dice scores of 0.525-0.995 and task-specific accuracies of 0.840-0.998. Two randomized studies suggested benefits for personalized suturing feedback and automated camera control, but neither established improved patient outcomes. Only one study had low overall risk of bias; the remaining studies were at high or unclear risk or raised some concerns. AI applications in robot-assisted surgery show promise for prediction, intraoperative perception, training, and workflow support. Evidence primarily demonstrates technical feasibility rather than established clinical effectiveness. Independent multicenter validation and prospective evaluation of patient, educational, and workflow outcomes are required before widespread implementation.

Robotic Surgical Procedures↗
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

Comparative Evaluation of Virtual Reality versus Standard Nursing Care in Managing Pain and Fear during Lumbar Puncture Procedures: A Randomised Controlled Trial.

BACKGROUND: Meningitis is a serious infectious disease that can cause significant morbidity and long-term neurological problems. Although a lumbar puncture is a necessary diagnostic procedure, it is often accompanied by discomfort, anxiety, and fear, which can severely impact the patient's experience. Although there is few data on its application prior to lumbar puncture in adult patients with meningitis, immersive virtual reality (VR) has become a promising non-pharmacological technique for lowering procedural distress. Thus, among individuals undergoing lumbar punctures, this randomized controlled research assessed how well pre-procedural VR reduced pain, anxiety, and fear while enhancing patient satisfaction. OBJECTIVE: This study aims to evaluate the effectiveness of virtual reality (VR) in reducing pain and fear among adults undergoing lumbar puncture (LP) compared with standard care protocol. METHODS: A randomised clinical trial was conducted from May to October 2025, using a single-blind, true experimental design. A total of 85 patients were randomly assigned to either the VR intervention group ( n = 41) or the control group receiving standard care ( n = 44). Pain levels were assessed using a visual analogue scale. Fear was assessed using the Multidimensional Fear-of-Injection Scale. Data were analysed using SPSS version 26. RESULTS: According to the study, the findings revealed a significant reduction in pain levels among the study group following the VR intervention, with mean pain scores dropping from 7.54 &#xb1; 1.925 to 2.49 &#xb1; 0.675. In contrast, the control group showed increased pain intensity, with mean scores rising from 6.84 &#xb1; 1.842 to 8.36 &#xb1; 1.348. The VR group showed a significant reduction in fear scores across all domains, whereas no significant changes were observed in the control group. Direct fear decreased from 20.12 &#xb1; 1.71 to 9.44 &#xb1; 2.00, indirect fear from 17.24 &#xb1; 1.46 to 8.66 &#xb1; 2.24, physiological response improved from 0.34 &#xb1; 0.66 to 3.00 &#xb1; 1.00 and avoidance behaviour decreased from 16.71 &#xb1; 1.49 to 7.80 &#xb1; 1.85. CONCLUSIONS: The research shows that the use of VR prior to LP significantly reduces level of pain and fear compared to standard care. These results support VR as a non-pharmacological intervention for fear and pain to improve patient experience during invasive procedures. In contrast, the control group experienced no improvement.Trial Registration: The IRCT code for the trial was IRCT ID 20250803066743N1.

Humans↗
PubMed2026

Compliance With Ecological Momentary Assessment Among Patients With Cancer: Systematic Review and Meta-Analysis.

BACKGROUND: Patients with cancer often experience substantial fluctuations in psychological states during disease management. Traditional research tools are limited in capturing these dynamic changes in real time, constraining clinicians' understanding of patients' true conditions. Ecological momentary assessment (EMA) enables high-frequency, real-time data collection, providing patient-reported data with greater ecological validity. However, the effectiveness of EMA studies critically depends on patient compliance, and reported compliance rates vary widely, with a lack of systematic quantitative synthesis. OBJECTIVE: This study aims to systematically review and quantitatively analyze compliance with EMA among patients with cancer, and to examine whether EMA design characteristics were associated with compliance. METHODS: Web of Science, PubMed, Embase, Cochrane Library, CINAHL, PsycINFO, CNKI, and Wanfang databases were searched for literature published up to April 30, 2026. Compliance was defined as completed prompts divided by delivered prompts. Single-group proportions were pooled using logit transformation and random-effects models with the Hartung-Knapp-Sidik-Jonkman adjustment. Prediction intervals were calculated to describe the expected distribution of compliance in future comparable settings. Subgroup analyses, univariable meta-regressions, leave-one-out sensitivity analyses, and tests for small-study effects were performed. Risk of bias was assessed using the Joanna Briggs Institute Critical Appraisal Checklist for Studies Reporting Prevalence Data, methodological reporting quality was assessed using a modified Checklist for Reporting EMA Studies, and certainty of evidence was evaluated using the Grading of Recommendations Assessment, Development, and Evaluation approach. RESULTS: Twenty-three studies involving 13,565 participants were included. The pooled compliance rate was 78.55% (95% CI 73.48%-82.87%), with a prediction interval of 48.59%-93.41%. Subgroup analyses identified no robust differences across study characteristics. Although study length showed a statistically significant subgroup test, the result was not stable after excluding singleton categories. Meta-regression analyses similarly found no significant linear associations for study length, prompts per day, items per prompt, or assessment window. Leave-one-out analyses showed that no single study drove the pooled estimate. Regarding the risk of bias, 2 studies were judged as low, while 21 were judged as moderate risk. Quality scores ranged from 6.5 to 9.0, and the certainty of evidence for the pooled compliance rate was rated as very low according to the Grading of Recommendations Assessment, Development, and Evaluation approach. CONCLUSIONS: Overall compliance with EMA among patients with cancer was moderate to high, suggesting that repeated real-world assessment may be feasible in oncology research settings. Nevertheless, the very high heterogeneity, wide prediction interval, and very low certainty of evidence indicate that compliance is context-dependent. The pooled estimate should therefore be interpreted as an approximate benchmark rather than a universal expected rate. Future oncology EMA studies should use standardized compliance denominators, report missing prompts transparently, and prospectively evaluate patient-centered design strategies that reduce burden while preserving data quality.

Humans↗
PubMed2026

Digital Mindfulness Intervention for Pregnant Women With Affective Disorders and Acute Stress Reactions: Prespecified Secondary Analysis of a Randomized Controlled Trial.

BACKGROUND: Pregnant women with ICD-10 (International Statistical Classification of Diseases, Tenth Revision) affective or stress-related disorders face an elevated risk of perinatal depression and anxiety, yet evidence on digital nonpharmacologic interventions for this population remains limited. OBJECTIVE: This study evaluated the effectiveness of an 8-week digital mindfulness-based intervention (eMBI) compared with treatment as usual (TAU) among pregnant women with ICD-10 affective or stress-related disorders participating in a randomized controlled trial (RCT). METHODS: This prespecified secondary analysis was conducted within a multicenter RCT in Baden-W&#xfc;rttemberg, Germany. Pregnant women aged 18 years and older with elevated depressive symptoms (Edinburgh Postnatal Depression Scale [EPDS]>9) and ICD-10-diagnosed affective or stress-related disorders were randomized 1:1 to eMBI or TAU. The intervention consisted of 8 weekly app-based mindfulness sessions (45 min each) delivered during gestational weeks 29-36, with no direct therapist contact. The primary outcome was continuous depressive symptom severity measured with the EPDS at 4-6 weeks post partum. Secondary outcomes included the EPDS at 6 months post partum, generalized anxiety (State-Trait Anxiety Inventory-State [STAI-S], State-Trait Anxiety Inventory-Trait [STAI-T]), and Pregnancy-Related Anxiety Questionnaire-Revised (PRAQ-R). Analyses followed the intention-to-treat (ITT) principle, using mixed models for repeated measures and multiple imputation. RESULTS: Of the 5299 screened women, 147 met the inclusion criteria for this subgroup analysis (intervention group [IG] had n=73 women and control group had n=74 women). Groups were comparable at baseline. The IG showed significantly greater reductions in EPDS scores at gestational week 34 (&#x394;=-2.21, P=.01), week 36 (&#x394;=-3.25, P=.01), and 4-6 weeks post partum (&#x394;=-4.81, P=.007). Treatment effects remained robust under conservative missing-data assumptions. At 4-6 weeks post partum, a higher proportion of participants in the IG achieved clinically meaningful improvement (31/73, 42.5% vs 21/74, 28.4%; adjusted odds ratio 1.56, 95% CI 1.19-2.05; P=.001). Anxiety outcomes followed a similar pattern, whereas pregnancy-related anxiety did not differ between groups. CONCLUSIONS: In this prespecified subgroup of pregnant women with ICD-10 affective or stress-related disorders, the eMBI was associated with clinically meaningful reductions in depressive symptoms from late pregnancy to 4-6 weeks post partum. Effects at 6 months post partum were attenuated and less stable across missing-data assumptions. These findings support eMBIs as a scalable, nonpharmacological adjunct to perinatal mental health care for women with affective or stress-related disorders, while confirmation in adequately powered trials with strategies to reduce postpartum attrition is warranted.

Humans↗
PubMed2026

Effectiveness of a Web-Based Educational eHealth Platform on Women's Health Literacy About Phthalate Exposure: Randomized Controlled Trial.

BACKGROUND: Phthalates are environmental endocrine-disrupting chemicals widely used in plastics, cosmetics, food packaging, and personal care products. Women may experience frequent exposure through everyday consumer and household products. Improving phthalate-related health literacy may support informed exposure-reduction decisions; however, conventional health education provides limited opportunities for repeated, interactive, and individually tailored learning. OBJECTIVE: This randomized controlled trial evaluated the effectiveness of an eHealth educational intervention (Phthalates Free) in improving women's overall and domain-specific phthalate-related health literacy and examined the association between platform engagement and health literacy outcomes. METHODS: A double-blind randomized controlled trial was conducted in the outpatient department of a regional teaching hospital in Taipei, Taiwan. A total of 114 women were randomly assigned to an intervention group (n=58) receiving a 6-month eHealth platform-based education program and a control group (n=56) receiving conventional paper-based education. Assessments were conducted at baseline (T0), 3 months (T1), and 6 months (T2). The Phthalate Health Literacy Scale (10 items; &#x3b1;=.90, content validity index=0.93) measured overall and domain-specific literacy (health care, disease prevention, and health promotion). Longitudinal outcomes were analyzed using generalized estimating equations based on all available observations according to participants' original randomized assignments, with adjustment for waist circumference and pregnancy history. Analysis of covariance (ANCOVA) was used to compare 6-month outcomes after adjustment for baseline scores. Platform engagement and perceived usability were assessed using back-end analytics and the System Usability Scale (SUS). RESULTS: At 6 months, the intervention group showed a significantly greater increase in total health literacy than the control group (+9.93 points, Wald &#x3c7;&#xb2;1=17.74; P<.001). Domain analyses revealed significant improvements in health care (+1.52; P=.001), disease prevention (+1.32; P=.001), and health promotion (+1.12; P=.001) domains. ANCOVA confirmed the between-group difference at T2 after adjusting for baseline scores (F1,109=11.43; P=.001; adjusted mean difference=7.15, 95% CI 2.96-11.34). Engagement analysis showed that high-engagement users (n=10) scored significantly higher in overall health literacy (t55=-3.00; P=.004) and all domains than general users. The SUS results (mean 84.7, SD 5.2; n=46, 79.3%) indicated high perceived usability. CONCLUSIONS: The Phthalates Free eHealth educational intervention significantly improved women's overall and domain-specific health literacy over 6 months. Higher platform engagement was associated with better health literacy outcomes. The intervention may serve as a practical adjunct to nurse-led education in outpatient and community settings by providing accessible, continuous, and evidence-based guidance on reducing phthalate exposure.

Humans↗
PubMed2026

Artificial Intelligence for Diagnosing Meibomian Gland Dysfunction: A Systematic Review and Meta-Analysis of Diagnostic Test Accuracy Studies.

PURPOSE: To identify, appraise, and synthesize the performance of artificial intelligence-based meibography reading as compared with human graders in diagnosing meibomian gland dysfunction. METHODS: We followed Cochrane methodology and reporting guidelines for diagnostic test accuracy reviews. To assess potential risk of bias and applicability, we used a modified Quality Assessment of Diagnostic Accuracy Studies-2 checklist. We applied bivariate logistic models to estimate summary sensitivity and specificity when appropriate and used the GRADE framework to rate the certainty of the evidence. RESULTS: We identified 14 eligible studies involving 5511 predominantly middle-aged participants (average age: 27-55 years) who were primarily female (&#x2265;54.5%). A total of 18,926 meibography images were obtained through noncontact infrared (11 studies) or in vivo confocal microscopy (three studies). Two studies reported external validation of deep learning models, 12 reported internally validated models, and one reported both. All but one study had high risk of bias in at least one domain; 12 studies raised high or intermediate concern about applicability. Based on three external evaluations, the summary sensitivity and specificity for diagnosing meibomian gland dysfunction from normal glands were 97.5% (95% confidence interval: 77.5%-99.8%) and 85.5% (95% confidence interval: 47.3%-97.5%). Sources of heterogeneity in internally validated models included study population, case mix, and others. The overall evidence was very low to low certainty because of imprecision, high risk of bias, and concerns about applicability. CONCLUSIONS: Artificial intelligence-based meibography grading appears less accurate than human graders. Future studies should adopt rigorous designs, including a more diverse participant pool (or image set), and external validation.

Humans↗
PubMed2026

Comparative Efficacy of Different AI Systems for Polyp Detection by Size During Colonoscopy: Systematic Review and Network Meta-Analysis.

BACKGROUND: Colorectal cancer remains a leading cause of death despite being largely preventable through polypectomy. AI systems designed to enhance polyp detection during colonoscopy have shown promise, but the extent to which they improve detection of different-sized polyps remains unclear. OBJECTIVE: This study compared the size-stratified efficacy of AI-assisted colonoscopy vs standard colonoscopy using the Hartung-Knapp-Sidik-Jonkman (HKSJ) method, and generated exploratory rankings while acknowledging all cross-platform comparisons are indirect. METHODS: This systematic review and network meta-analysis (NMA) searched PubMed, Embase, Cochrane CENTRAL, and Web of Science from inception to July 25, 2026, supplemented by citation searching. We included randomized controlled trials (RCTs) comparing AI-assisted vs standard colonoscopy in adults (&#x2265;18 years of age), reporting mean polyp detection counts stratified by size (&#x2264;5 mm, 6-9 mm, and &#x2265;10 mm). Two reviewers screened studies, extracted data, and assessed risk of bias using the Cochrane Risk of Bias 2.0. We conducted frequentist NMA using the HKSJ method with restricted maximum likelihood estimation, calculated 95% prediction intervals (PIs), and assessed heterogeneity using I2 and &#x3c4;2. Certainty of evidence was rated using the GRADE (Grading of Recommendations Assessment, Development, and Evaluation) framework. RESULTS: A total of 13 RCTs (4156 participants) compared 8 AI systems to standard colonoscopy, forming a network without direct AI comparisons. For diminutive polyps (&#x2264;5 mm), AI showed a modest advantage (standardized mean difference [SMD] 0.21, 95% CI 0.07 to 0.35, 95% PI -1.12 to 1.54), but substantial heterogeneity (I2=86.6%) and wide PI crossing the null indicated high uncertainty. EndoScreener showed the most consistent evidence (SMD 0.36, 95% CI 0.18-0.54). For small and large polyps, effects were minimal (SMD 0.02, 95% CI -0.02 to 0.06, 95% PI -0.03 to 0.07; SMD 0.01, 95% CI 0.00-0.02, 95% PI -0.01 to 0.03). GRADE certainty was very low for diminutive polyps and low for small and large polyps. Sensitivity analysis excluding Tianjin YuJin did not materially change findings. CONCLUSIONS: AI may modestly enhance diminutive polyp detection, but effects on small and large polyps are minimal, with no platform superiority. Given very low to low certainty, findings are hypothesis-generating. This exploratory NMA provides size-stratified comparisons that can inform future head-to-head trial design. Unlike prior reviews aggregating all polyp sizes, we show the overall AI benefit is driven by diminutive polyp detection, providing a framework for targeted deployment-prioritizing AI for diminutive polyp screening, with limited value for larger lesions. Head-to-head trials are urgently needed. TRIAL REGISTRATION: PROSPERO International Prospective Register of Systematic Reviews CRD420251266932; https://www.crd.york.ac.uk/PROSPERO/view/CRD420251266932.

Colonoscopy↗
PubMed2026

Impact of Contact Lens Use on Clinical Profile and Outcomes of Fungal Keratitis: An 8-Year Retrospective Study.

PURPOSE: To compare clinical characteristics, microbiological profiles, treatment strategies, and outcomes between contact lens-associated (CL) and noncontact lens-associated (non-CL) fungal keratitis. DESIGN: Retrospective, comparative clinical cohort study. METHODS: A review of culture-proven fungal keratitis treated at a tertiary referral center between 2018 and 2025 was conducted. Cases were categorized as CL or non-CL-associated. Demographic, clinical, microbiological, treatment, and outcome data were analyzed and compared between groups. RESULTS: Thirty-seven eyes were included, comprising 16 CL and 21 non-CL cases. CL users presented earlier than non-CL patients (median 7 vs 14 days, P = .007) and had fewer associated ocular risk factors (31% vs 81%, P = .001). Baseline visual acuity and infiltrate size did not differ significantly between groups. Candida species were isolated in 21% cases, Fusarium in 16% and Aspergillus in 8%. Fusarium (19% vs 13%) and Candida (24% vs 19%) infections were slightly more frequent in non-CL cases. Overall, filamentous fungi were the predominant organism group. Topical voriconazole was the most frequently used antifungal agent (78%). All CL-associated cases resolved with medical therapy alone, with a median time to resolution of 38 days (IQR 22-58). In contrast, 76% of non-CL cases resolved medically (median 42 days, IQR 32-76), while 23% required therapeutic keratoplasty (P = .04). Final visual acuity was comparable between groups (logMAR 0.2 vs 0.5, P = .56). CONCLUSION: Contact lens-associated fungal keratitis is characterized by earlier presentation and fewer underlying ocular comorbidities, with favorable outcomes achieved through medical therapy alone. Despite similar microbiological profiles and treatment approaches, noncontact lens-associated fungal keratitis more frequently follows a complicated course requiring surgical intervention.

Humans↗
PubMed2026

Cost-Effectiveness of Electronic Patient-Reported Outcome Measure Interventions in Cancer: Systematic Review and Parameter Extraction for Economic Modeling.

BACKGROUND: Complex digital interventions that integrate electronic patient-reported outcome measures (ePROM) into clinical practice in cancer have the potential to improve quality of life, increase survival, and reduce health resource use and costs. Such systems can help patients with cancer self-manage chemotherapy symptoms, reduce clinicians' workloads through automated decision support, and resolve problems earlier. However, more research on the cost-effectiveness of ePROM monitoring is needed. OBJECTIVE: This paper comprises two complementary components: (1) a systematic literature review summarizing and evaluating the quantitative and qualitative evidence related to the cost-effectiveness of ePROM monitoring and (2) a health economic model parameter extraction. We also conducted supplementary targeted searches and scoping to provide context to our findings. METHODS: We searched Ovid (including MEDLINE and Embase), Scopus, and the International Health Technology Assessment Database for original English-language papers published on or before March 2025 using search strings that combined terms related to ePROMs, health economics, and cancer/oncology. We included papers reporting health economic-related outcomes for ePROM interventions designed for adult cancer populations and excluded screening tools and conference abstracts. RESULTS: We included 34 publications from 27 unique studies and identified and analyzed 26 ePROM-integrated interventions within these. Most (23/26) of the included interventions explicitly described some form of alert handling and automated decision support based on remote ePROM monitoring. Of the 34 publications, 5 presented full cost-effectiveness analysis results, of which 3 were highly uncertain and lacked clear differences in costs and health outcomes between ePROMs and standard care; conversely, 2 presented strong evidence of cost-effectiveness due to quality-of-life improvements, reduced hospitalizations, and potentially more autonomy in health-related travel (eg, ePROM-monitored patients can drive or walk to the hospital instead of using taxis or ambulances). A further 5 publications reported partial health economic results (eg, cost-consequence and budget impact), of which 1 detected no difference in strategies; in contrast, 4 reported lower health resource use and costs of ePROMs, mainly due to hospitalization reductions. Overall, 12 of the 27 studies included a qualitative component but mostly focused on user experience and design-related themes; only 2 of these addressed economic-specific themes (eg, changes in workflow and resource use due to ePROM implementation and integration), indicating some potential for time saving due to ePROM monitoring. CONCLUSIONS: Some ePROM-integrated interventions demonstrated cost-effectiveness in cancer care, but the evidence base remains limited. Where evidence does exist, cost-effectiveness appears driven by reduced hospitalization and improved quality of life. Qualitative research within the included studies rarely addressed economic questions. We provide a detailed parameter extraction for use in future economic modeling and recommend research priorities, including quantitative mapping of ePROM symptom data onto health resource use patterns, and qualitative work exploring how ePROM implementation affects clinical workloads and patient-perspective costs.

Humans↗
PubMed2026

The Impact of Baseline Negative Emotions on Postoperative Quality of Life in Adolescent Idiopathic Scoliosis Patients: A 2-Year Follow-Up Study.

OBJECTIVE: Adolescent idiopathic scoliosis (AIS) is a three-dimensional spinal deformity that develops during puberty without a clear etiology. Beyond physical manifestations, AIS severely impacts adolescents' psychological and social well-being, leading to anxiety, depression, and low self-esteem. While advancements in surgical techniques have enhanced objective outcomes, existing studies on AIS have primarily focused on objective indices, with limited attention to the long-term impact of preoperative negative emotions on patient-reported subjective quality of life. METHODS: This was a retrospective cohort study. A total of 112 eligible AIS patients who underwent posterior spinal correction surgery between April and August 2023 were enrolled. Inclusion criteria included confirmed AIS, completion of 2-year follow-up, and informed consent; exclusion criteria included missing imaging/questionnaire data, comorbid psychiatric/neurological diseases, or prior spinal surgery. Patients were grouped using the Hospital Anxiety and Depression Scale (HADS) administered on admission. Quality of life was assessed preoperatively and 2&#x2009;years postoperatively using the Scoliosis Research Society-22 (SRS-22, evaluating self-image, mental health, pain, function, treatment satisfaction) and Short Form 36 Health Survey (SF-36, assessing 8 physical and mental health dimensions). Statistical analysis was performed via SPSS, using independent t-tests, paired t-tests, Mann-Whitney U test, and chi-square test. p&#x2009;<&#x2009;0.05 was considered significant. RESULTS: There were no significant differences in baseline characteristics (age, gender, BMI, surgical parameters, scoliosis type, preoperative/postoperative Cobb angles) between the two groups (all p&#x2009;>&#x2009;0.05). Preoperatively, SRS-22 and SF-36 scores showed no inter-group differences (all p&#x2009;>&#x2009;0.05). Postoperatively, the Negative Emotion Group had significantly lower scores in SRS-22 mental health (3.9&#x2009;&#xb1;&#x2009;0.3 vs. 4.5&#x2009;&#xb1;&#x2009;0.2) and treatment satisfaction (4.0&#x2009;&#xb1;&#x2009;0.3 vs. 4.6&#x2009;&#xb1;&#x2009;0.7), as well as SF-36 general health (68.6&#x2009;&#xb1;&#x2009;6.4 vs. 79.7&#x2009;&#xb1;&#x2009;13.3), role-emotional (61.3&#x2009;&#xb1;&#x2009;9.3 vs. 70.8&#x2009;&#xb1;&#x2009;9.7), and mental health (61.8&#x2009;&#xb1;&#x2009;14.3 vs. 68.9&#x2009;&#xb1;&#x2009;10.7) (all p&#x2009;<&#x2009;0.05); no inter-group differences were observed in physical function-related dimensions. Both groups showed significant improvements in physical function-related dimensions postoperatively. The Non-Negative Emotion Group also exhibited significant improvements in SRS-22 self-image/pain and SF-36 bodily pain (all p&#x2009;<&#x2009;0.05), while the Negative Emotion Group showed no significant improvements in these dimensions. CONCLUSIONS: Preoperative anxiety and depression do not affect the recovery of physical function in AIS patients after spinal correction surgery but significantly impede improvements in subjective quality of life dimensions, including mental health and treatment satisfaction. These findings highlight the need to integrate psychological assessment and targeted interventions into the perioperative management of AIS. Such a patient-centered approach will help optimize both physical and psychological outcomes, ultimately achieving comprehensive rehabilitation for AIS adolescents.

Humans↗
PubMed2026

Health Literacy and Capecitabine Adherence in a Remote Monitoring Pilot Trial for Breast Cancer: Post Hoc Exploratory Analysis.

BACKGROUND: Oral anticancer therapy enables convenient, home-based cancer care but can introduce adherence challenges, particularly with complex dosing schedules. Capecitabine is commonly used in breast cancer, often as adjuvant therapy or in advanced disease, and typically requires twice-daily dosing on cyclical schedules, increasing the risk of missed or incorrect doses. Low health literacy may exacerbate these difficulties, and emerging remote monitoring tools may help close this gap. OBJECTIVE: In this post hoc exploratory analysis, we evaluated whether health literacy (1) was associated with capecitabine adherence and (2) modified a remote monitoring intervention's effectiveness. METHODS: We conducted post hoc analyses of a 2-arm pilot trial that randomized women with breast cancer treated with capecitabine to enhanced usual care (EUC) or remote patient monitoring (RPM). Adherence was captured with a smart pill bottle, Nomi by SMRxT, that recorded dose timing and quantity. Participants in the RPM group received messages for missed or incorrect doses and weekly symptom assessments. Incorrect or missed doses and severe symptoms triggered alerts to the oncologist. Health literacy was assessed at enrollment. To evaluate moderation, we used linear regression with an interaction term (health literacy &#xd7; intervention arm) predicting adherence (proportion of days). Marginal effects quantified differences in adherence by study arm and health literacy. RESULTS: Among 28 participants (EUC, n=15 and RPM, n=13), 9 (32.1%) had lower health literacy, 16 (57.1%) identified as Black, 10 (35.7%) identified as White, and 15 (53.6%) had income below 200% of the federal poverty level. In the regression model, the health literacy &#xd7; randomized group interaction did not reach statistical significance (-16.3 percentage points, 95% CI -35.5 to 2.9; P=.09). Predicted adherence among lower health literacy participants was 87.5% in the RPM group and 65.5% in the EUC group (difference: +22.1 percentage points, 95% CI 6.2-37.9; P=.008). Among participants with higher health literacy, adherence was 89.9% in the RPM group and 84.1% in the EUC group (difference: +5.7 percentage points, 95% CI -5.2 to 16.7; P=.29). Within the EUC group, predicted adherence was 18.6 percentage points lower among those with lower versus higher health literacy (95% CI -32.4 to -4.9; P=.01); within the RPM group, this difference was 2.3 percentage points lower among those with lower versus higher health literacy (95% CI -15.8 to 11.1; P=.73). CONCLUSIONS: In this post hoc exploratory analysis, the estimated difference in capecitabine adherence between the RPM and EUC groups was larger among participants with lower health literacy. Although the formal interaction test was not statistically significant, the magnitude and direction of the observed difference support further investigation of RPM as a potential approach to improve adherence among patients facing health literacy-related adherence barriers. Larger, prospectively powered studies are needed to confirm these findings and evaluate downstream clinical outcomes.

Humans↗
PubMed2026

Perspectives of participating neurologists and study nurses - Mixed-methods process evaluation of a web-based program for relapse management in multiple sclerosis (POWER@M2).

BACKGROUND: Relapsing-remitting multiple sclerosis is a chronic inflammatory disease of the central nervous system and the leading cause of disability in young adults. In Germany, 90% of relapses are treated with high-dose intravenous glucocorticoids, despite limited evidence for long-term benefit and international preference for oral administration. Time constraints often hinder informed decision-making. The multicentre Randomized Controlled Trial (RCT) POWER@MS2 (N&#x202f;=&#x202f;160, 2020-2023), conducted at 18 German MS-centres, aimed to promote self-determined relapse management through a complex intervention (dialogue-based decision aid, nurse-led webinar, online-chat). OBJECTIVE: While RCTs demonstrate effectiveness, process evaluations are essential to understand implementation, mechanisms of impact and contextual factors. This study explored healthcare professionals' experiences and attitudes toward implementing relapse self-management and self-medication in clinical practice. METHODS: A mixed-methods process evaluation followed the UK Medical Research Council- framework. Quantitative data were collected via validated questionnaires at up to three time points and analysed descriptively. Interview guides were developed based on these results. Qualitative data from neurologist and study nurse interviews were thematically analysed. Results were triangulated using a joint display. RESULTS: Data were collected from 55 neurologists and 17 study nurses (quantitative) and from 7 neurologists and 4 nurses (qualitative) (2020-2024). Most neurologists opposed routine steroid use, reserving it for severe relapses. Some voiced concerns about self-management, but informed patients were generally viewed as capable of safe self-medication. Study nurses gave mixed feedback on the intervention, citing overload and improved guidance. CONCLUSION: Clinicians showed openness toward implementing the intervention. Enhancing accessibility and addressing specific concerns may support broader adoption.

Humans↗
PubMed2026

Cerebrovascular involvement in Erdheim-Chester disease: a case report and systematic literature review.

BACKGROUND: Intracranial perivascular/vascular infiltrations and stenoses related to Erdheim-Chester disease (ECD), often associated with ischemic events, are rarely documented. This study aims to characterize intracranial perivascular/vascular infiltrations and stenoses. METHODS: We first report a new case of strokes revealing ECD with intracranial arterial involvement. We then searched all English- and French-language publications from database inception to November 2025 across 12 different search interfaces, including grey literature sources. Vascular involvement was defined by the presence of intracranial perivascular/vascular infiltrations and stenosis on imaging and/or histopathological evidence of small-vessel involvement. Cases with intracranial nodules or masses abutting vessels but without clear longitudinal perivascular infiltration were excluded. RESULTS: We present a case of recurrent strokes with intracranial vertebral and basilar artery wall stenosis, and aortitis. Initially diagnosed as giant cell arteritis, the patient was treated with corticosteroids, cyclophosphamide followed by methotrexate, but relapsed. The identification of tibial osteosclerosis led to the diagnosis of ECD, with a favorable response to anakinra. Twelve relevant articles were retrieved, in addition to our own case. Most patients exhibited focal cerebrovascular signs (11/13) and associated parenchymal involvement (11/13). Intracranial perivascular/vascular infiltrations and stenoses involved the carotid arteries (7/13), the vertebrobasilar arteries (1/13), or both territories (4/13). Aorta was involved in 8/12 cases. Among the nine patients with available follow-up data, five had poor overall or neurovascular outcomes. CONCLUSIONS: Intracranial perivascular/vascular infiltrations and stenoses, which leads to recurrent focal ischemic events, represents a likely underdiagnosed CNS pattern in ECD, referred to as "cerebrovascular ECD", which worsens overall prognosis. Vascular imaging should be included in brain MRI protocols for patients with ECD, given the overlap with parenchymal involvement.

Humans↗