SEARCH · Search PubMed

Results for “assisted image interpretation”

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.

568 records · Page 13Linked to original sources

PubMed2026

Effectiveness of a blended care intervention in physiotherapy with exercise and education for patients with hip or knee osteoarthritis (SmArt-E): A multicentre pragmatic randomized controlled trial.

OBJECTIVE: To evaluate the effectiveness of a twelve-month smartphone-assisted physiotherapy (SmArt-E) intervention versus usual care in hip and/or knee osteoarthritis (OA), and to assess usability and patient satisfaction with the digital support. METHOD: We conducted a multicentre, pragmatic, parallel-group randomized controlled trial in 27 physiotherapy practices in Germany. Patients with physician-diagnosed hip and/or knee OA aged ≥50 (hip) or ≥38 years (knee) were randomly allocated to SmArt-E (IG; n=166) or usual care (CG; n=164). The twelve-month intervention combined supervised and smartphone-assisted training and education (blended care). Primary outcomes were pain (NRS, 0-10) and physical function (HOOS/KOOS-ADL, 0-100) at twelve months. Secondary outcomes followed OARSI domains; usability and patient satisfaction were also assessed. RESULTS: Among 330 participants (mean age 64±8 years), baseline NRS was 3.2±2.3 in the CG and 3.5±2.4 in the IG; HOOS/KOOS-ADL was 71.6±17.7 and 69.4±17.5, respectively. No significant between-group differences were found for pain (-0.36; 95% CI: -0.84 to 0.12; p=0.14) or physical function (2.66; 95% CI: -0.46 to 5.77; p=0.09). Among 13 secondary outcomes, significant differences favouring the IG emerged at three and twelve months for several domains; however, effect sizes were small and unlikely to be clinically meaningful. CONCLUSION: SmArt-E did not demonstrate superior effectiveness over usual care in mild hip and/or knee OA. Both groups improved over time, with slightly more favourable but clinically inconclusive outcomes in the IG. Findings highlight the need to refine the intervention, better identify eligible patients, and optimize digital and in-person components.

Humans↗

PubMed2026

Beyond predictive performance: A systematic review and critical methodological appraisal of AI/ML and conventional modelling strategies in breast, colorectal, and pancreatic Cancer.

BACKGROUND: Predictive modelling for cancer risk, treatment-related complications, and survival is central to precision oncology. Conventional logistic regression (LR) and Cox proportional hazards (CoxPH) regression remain widely used but are limited when modelling nonlinear interactions, high-dimensional imaging features, and multimodal clinical-metabolic predictors. Artificial intelligence (AI) and machine learning (ML) methods offer expanded capability through automated feature extraction, ensemble learning, and flexible survival modelling, but the evidence on when AI/ML adds value over conventional models across cancer sites and predictive tasks remains fragmented. OBJECTIVE: To systematically evaluate the methodological performance, validation strategies, and translational limitations of AI/ML models compared with conventional statistical models in published predictive-modelling studies for breast, colorectal, or pancreatic cancer. METHODS: PubMed, Scopus, and Web of Science were searched for studies published between January 2019 and March 2025. Two reviewers independently conducted title-and-abstract screening, full-text eligibility assessment, and PROBAST risk-of-bias assessment. Sixty-five studies (n = 907,567 participants) were narratively synthesised by cancer site, predictive task, model family, comparator, validation strategy, predictor modality, and calibration or explainability reporting. RESULTS: The 65 studies comprised breast cancer (n = 35), colorectal cancer (n = 21), and pancreatic cancer (n = 9). AI/ML superiority over LR and CoxPH was task- and data-dependent. CNN- and U-Net-based models predominated in imaging and body-composition tasks, tree-based ensembles consistently outperformed LR for tabular perioperative complication prediction, and CoxPH remained competitive, and in the largest pancreatic risk study, superior to XGBoost (C-index 0.802 vs 0.723) in well-structured datasets. PROBAST analysis-domain risk was moderate in 54 of 65 studies (83%), driven by limited external validation, sparse calibration reporting (11/65), and few decision-curve analyses (7/65). CONCLUSION: AI/ML adds the most methodological value in imaging-derived feature extraction and nonlinear perioperative prediction, while conventional regression remains preferable in large, structured datasets with linear predictors. Clinical translation requires standardised body-composition definitions, external validation, calibration assessment, decision-curve analysis, and explainability, in line with TRIPOD+AI and CLAIM standards.

Humans↗

PubMed2026

Vestibular schwannoma associated normal pressure hydrocephalus: clinical features and shunt responsiveness compared with idiopathic NPH.

BACKGROUND: Vestibular schwannoma (VS) is commonly associated with obstructive hydrocephalus due to mass effect; however, a rarer communicating form resembling normal pressure hydrocephalus (NPH) has also been described, possibly related to impaired CSF absorption from elevated CSF protein. We aimed to characterize the clinical and imaging features of VS-associated NPH (VS-NPH) and compare them with those of an idiopathic NPH (iNPH) cohort. METHODS: We retrospectively analyzed 18 patients with VS-NPH identified between 2008 and 2024. For comparison, 41 iNPH patients were drawn from a prospective longitudinal study at our center. Variables included demographics, tumor size, VS treatment modality, CSF parameters, Radscale imaging features, and shunt responsiveness. RESULTS: VS-NPH patients had markedly higher CSF protein levels than patients with iNPH (median 100 vs. 51 mg/dL, p < 0.001). Radiological features largely overlapped; however, parasagittal sulcal narrowing was more frequent in VS-NPH (61 % vs.13 %, p = 0.002). These differences remained significant in the sensitivity analysis excluding the two patients without gait impairment. VS-NPH patients were younger in the primary analysis (66.8 vs. 72.0 years, p = 0.03), while exploratory associations between larger tumor size and both earlier NPH symptom onset (r = -0.48, p = 0.049) and smaller callosal angle (r = -0.49, p = 0.048) attenuated to non-significant trends in the sensitivity analysis. Tumor size was < 30 mm in 89 % of patients. Ventriculoperitoneal shunt (VPS) resulted in clinical improvement in both groups, although response rates were numerically lower in VS-NPH than in iNPH (63 % vs.75 %). CTT was positive in 9 of 11 VS-NPH patients who underwent testing, although improvement after shunting also occurred in patients with negative CTT results or without prior CTT. CONCLUSIONS: VS-NPH may represent a secondary subtype of NPH with distinct biochemical and subtle imaging features. Elevated CSF protein may contribute to altered CSF dynamics. These findings are exploratory and require confirmation in larger prospective studies.

Humans↗

PubMed2025

The wider erection angle in hypospadias: A neglected feature affecting surgical outcomes.

INTRODUCTION: Penile curvature often accompanies hypospadias, and numerous techniques have been described for its correction; however, in some cases, an abnormal erection angle may also be present, further exacerbating the perception of curvature. OBJECTIVE: This study investigates the significance of the erection angle in hypospadias cases and its correlation with the severity of the anomaly. STUDY DESIGN: A retrospective analysis of intraoperative photographs of hypospadias cases operated between 2019 and 2023 was performed. Erection angle was measured with a digital goniometer during a full artificial erection. Erection angles in proximal and distal hypospadias cases were analyzed and compared to data from Kinsey's subgroups representing healthy male erection angles. RESULTS: This study involved images of 68 patients, with 31 having proximal and 37 distal hypospadias. The median age of the whole group was 11 months (6-156, IQR 9). Median erection angle was 91 (63-119, IQR 11) for distal cases, whereas it was 96 (75-138, IQR 21) for proximal cases. The difference was statistically significant (p = 0.009). The erection angle distribution in our cohort, including both proximal and distal hypospadias cases, skewed toward wider angles, highlighting a distinct pattern compared to data constituted by Kinsey and Sparling. DISCUSSION: Our findings indicate that the erection angle in hypospadias is significantly wider in proximal cases, suggesting a correlation between erection angle and severity of the hypospadias. While we acknowledge the limitation of comparing our prepubertal cohort with Kinsey's adult data, the absence of evidence suggesting significant post-pubertal changes in erection angle justifies this approach. Additionally, the use of digital images for angle assessment is not a standardized technique in hypospadias evaluation; these images were initially captured for curvature assessment. Despite these limitations, our study provides novel insights into seldom mentioned association with hypospadias - a wide erection angle, emphasizing the need for further research on its implications for surgical planning and long-term outcomes. CONCLUSION: This study introduces a wider erection angle as an additional characteristic of hypospadias particularly pronounced in proximal cases. To our knowledge, this is the first focused investigation on addressing this aspect of the condition. It emphasizes the need for further research on adults with wide post-repair erection angles to explore its long-term impact on sexual function and aesthetics.

Humans↗

PubMed2026

How I do it: 3-Suture robotic pyeloplasty: Step-by-step technique.

Robot-assisted pyeloplasty is now a gold standard in the treatment of pediatric ureteropelvic junction obstruction. We describe a standardized "3-suture" technique designed to facilitate the pyelo-ureteral anastomosis. We used this technique in 65 paediatric patients aged 3-17 years. Early major complications (Clavien-Dindo grade III) occurred in 3 patients (4.6%). The median operative time was 150 min. Surgical success was achieved in 96% of cases at a median follow-up of 9.5 months. This 3-suture approach offers a highly reproducible method for robotic pyeloplasty, facilitating accurate anatomical reconstruction with excellent surgical outcomes.

Humans↗

PubMed2026

Beyond Photometric Consistency: Addressing Loss Insensitivity to Depth Noise in Endoscopic Estimation via Error Calibration.

Self-supervised monocular depth estimation in endoscopy is fundamentally constrained by the ill-posed nature of photometric supervision. In this work, we identify a critical yet overlooked cause of this ambiguity: the inherent insensitivity of photometric loss to depth noise. To overcome this intrinsic limitation, we propose Depth Error Calibration Learning (DECL), a two-stage framework that suppresses prediction variance and mitigates residual errors in self-supervised depth estimation. In Stage I (Variance Reduction), a cyclic depth generation strategy produces multiple depth hypotheses for the input image. The per-pixel empirical variance is quantified and integrated into a dedicated variance loss term, which penalizes inconsistent predictions and encourages the network to generate more stable and reliable depth estimates. In Stage II (Bias Calibration), an image-conditioned diffusion model refines the Stage-I depth prior and mitigates structured residuals through iterative denoising, thereby improving geometric accuracy and global consistency. Extensive experiments on three public endoscopic datasets demonstrate that DECL achieves consistent improvements over representative self-supervised monocular depth estimation methods under the evaluated protocols. Moreover, ablation studies on two representative backbones indicate that DECL is not restricted to a single network implementation, while broader validation on additional backbone families remains necessary. The source code is publicly available at https://github.com/DavidLuBit/EndoDenoising.

Journal Article↗

PubMed2026

Topical Carboxytherapy as an Adjunct to Skin Recovery Post-CO2 Laser Fractional Resurfacing.

BACKGROUND: Topical carboxytherapy, a transcutaneous carbon dioxide (CO2) delivery system, may support skin repair and regeneration, yet its role as an adjunct to fractional laser treatment remains underexplored. OBJECTIVE: To investigate the effectiveness and safety of topical CO2 mask (CO2Lift® Carboxy Gel, Lumisque Skincare) in supporting skin recovery and improving clinical outcomes following fractional CO2 laser resurfacing. METHOD: This 12-week randomized, placebo-controlled trial evaluated mild-to-moderate photoaging (n=6 females only). Participants received either topical carboxytherapy (n=4) or standard care (n=2). Assessments included VISIA-CR imaging, biophysical measurements, investigator ratings, and paired (baseline and 4-week) skin biopsies. RESULTS: Topical carboxytherapy accelerated recovery and was well-tolerated, with no major adverse events. VISIA-CR imaging showed accelerated erythema resolution, transepidermal water loss normalized more rapidly, and pH remained stable. Skin histology at week 4 revealed epidermal thickening and rete ridge formation with topical carboxytherapy vs placebo. Investigator ratings demonstrated significantly improved healing, global assessment, and global aesthetic improvement scale scores, with trends toward improvement in photodamage, rhytides, and pigmentation. CONCLUSION: Adjunctive topical carboxytherapy after fractional CO2 resurfacing accelerated healing, improved barrier recovery, and overall aesthetic outcomes. Larger studies are needed to confirm these findings.

Humans↗

PubMed2026

Extending the Treatment Window for Intravenous Thrombolysis in Acute Ischemic Stroke: An Updated Systematic Review and Meta-Analysis.

BACKGROUND AND OBJECTIVES: Intravenous thrombolysis (IVT) is the standard treatment for acute ischemic stroke within 4.5 hours of onset. However, imaging-based selection may extend the treatment window. This systematic review and meta-analysis evaluated the efficacy and safety of IVT administered beyond 4.5 hours after stroke onset or last known well (LKW) in patients selected based on imaging findings. METHODS: A comprehensive search of PubMed, Scopus, and Cochrane Library was performed to identify randomized controlled trials comparing IVT with alteplase or tenecteplase (TNK) administered >4.5 hours after stroke onset/LKW vs standard care. Primary outcomes were 3-month excellent (modified Rankin Scale [mRS] 0-1) functional outcome and symptomatic intracranial hemorrhage (sICH). Secondary outcomes included good (mRS 0-2) functional outcome, recanalization, and 3-month mortality. Pooled odds ratios (ORs) with 95% confidence intervals (CIs) were calculated using random-effects models. Subgroup analysis assessed differences between alteplase and TNK. RESULTS: Fourteen studies involving 4,944 patients were included. The mean age was 69.8 years, 58.2% were male, the median National Institutes of Health Stroke Scale score was 9, and 12.3% received preplanned endovascular thrombectomy (EVT). A total of 2,492 patients received IVT in an extended time window (4.5-24 hours). Compared with standard care, extended IVT was associated with higher odds of achieving an excellent functional outcome (OR: 1.43 [95% CI 1.25-1.63]), a good functional outcome (OR: 1.25 [95% CI 1.11-1.40]), and recanalization (OR: 3.28 [95% CI 2.09-5.16]). There was no difference in 3-month mortality (OR: 1.21 [95% CI 0.95-1.53]). However, IVT increased the risk of sICH (OR: 2.51 [95% CI 1.47-4.28]). Sensitivity analysis excluding patients who received EVT showed no impact on the outcomes. TNK exhibited similar efficacy to alteplase but showed potentially lower odds of sICH (OR: 1.96, 95% CI 1.06-3.64) compared with alteplase (OR: 5.29, 95% CI 1.80-15.57); however, the subgroup difference was not significant (p = 0.11). DISCUSSION: Among patients selected based on imaging, 4.5-24 hours after stroke onset/LKW, IVT improves outcomes despite an increased risk of sICH. TNK showed similar efficacy to alteplase, with a possible lower risk of sICH; however, direct comparisons in future trials are needed.

Humans↗

PubMed2026

Prognostic Value of Circulating Tumor DNA-Based Minimal Residual Disease for Recurrence-Free Survival in Resectable Gastric Cancer: A Systematic Review and Meta-Analysis with Serial Monitoring Analysis.

BACKGROUND: Circulating tumor DNA (ctDNA)-based minimal residual disease (MRD) is an emerging biomarker, but its utility in resectable gastric cancer remains incompletely characterized. METHODS: We conducted a systematic review and meta-analysis of eight studies (520 patients) to evaluate the prognostic value of ctDNA-based MRD for recurrence-free survival (RFS) and overall survival (OS) in resectable gastric cancer. RESULTS: In localized resectable gastric cancer (Stage I-III), the setting in which postoperative ctDNA most coherently represents true molecular residual disease after curative-intent surgery, postoperative ctDNA positivity was associated with diminished recurrence-free survival (RFS: HR 12.26, 95% CI 3.30-45.52) and overall survival (OS: HR 8.57, 95% CI 3.06-23.98). The test for subgroup differences between localized and mixed-stage cohorts was not statistically significant (P = 0.57), and the numerically higher HR in the localized subgroup should therefore not be interpreted as evidence of a quantitatively stronger prognostic effect. Postoperative ctDNA detection demonstrated substantially stronger prognostic value (overall RFS: HR 10.00, 95% CI 4.53-22.10) compared to preoperative assessment (HR 2.17, 95% CI 1.10-4.28). Both tumor-informed and tumor-agnostic strategies effectively stratified high-risk patients. However, these effect sizes should be interpreted cautiously given the small number of studies and substantial heterogeneity (I2 = 65-72%). Results from mixed-stage cohorts including Stage IV disease are supportive but should not be considered equivalent to localized-disease findings, as ctDNA in metastatic disease reflects persistent systemic burden rather than minimal residual disease in the postoperative sense. CONCLUSIONS: Postoperative ctDNA-based MRD shows a consistent adverse prognostic association in resectable gastric cancer, with localized disease (Stage I-III) representing the most biologically and clinically coherent setting for interpretation. However, the large pooled hazard ratios (HR 10.00-12.26) should be interpreted as a directionally consistent signal rather than precise quantitative estimates, given the small number of studies, wide confidence intervals, and substantial heterogeneity (I2 = 65-73%). This heterogeneity is largely driven by substantial variation in postoperative sampling timing (4 days to 16 weeks) and ctDNA assay characteristics (platform, sensitivity, coverage, variant filtering, and positivity thresholds), which require standardization in future studies. While ctDNA is prognostically valuable, its clinical utility remains unestablished. Prospective randomized trials are needed to determine whether ctDNA-guided strategies improve patient outcomes before routine clinical implementation can be recommended.

Humans↗

PubMed2026

Isometric Exercises for Tendinopathies: A Systematic Literature Review.

PURPOSE: Musculoskeletal disorders are among the most common reasons for medical consultation, with tendinopathies accounting for up to 30% of such presentations. Although exercise remains the cornerstone of management, the most effective modality continues to be debated. Eccentric exercise has long been the mainstay, but the role of isometric exercise in pain modulation and functional recovery remains unclear. This systematic review aims to evaluate the current evidence on the efficacy of isometric exercises in the management of tendinopathies across various anatomic sites. METHODS: A systematic search was conducted in PubMed, MEDLINE, Embase, and the Cochrane Library from inception to August 1, 2025. Eligible studies included randomized controlled trials and prospective or retrospective cohort studies assessing isometric exercise interventions for tendinopathy, with or without comparator groups. Case series and case reports were excluded. Data extracted included participant demographic characteristics, site of tendinopathy, symptom duration, treatment duration, adherence, and outcome measures such as Victorian Institute of Sports Assessment (A, P, or G), visual analog scale, Patient-Specific Functional Scale, 36 item short form health survey (SF-36), and EuroQol 5-Dimension questionnaires. Imaging outcomes (ultrasound or magnetic resonance imaging) were recorded where available. Methodological quality and risk of bias were assessed using the Cochrane Risk of Bias tool in accordance with Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines. FINDINGS: The search identified 304 articles, of which 13 randomized controlled trials met the inclusion criteria, encompassing 336 participants (40% female). Tendinopathy sites included the patellar (n = 4), Achilles (n = 3), lateral elbow (n = 2), rotator cuff (n = 2), wrist extensor (n = 1), and gluteal (n = 1) tendons. Median symptom duration was 23 months (interquartile range, 3-51 months). Intervention periods ranged from a single 45-minute session to 4-month exercise programs. Treatment adherence was high initially (nearly 100%) but declined over time, with 70% of participants in the isometric and 58% in the control (isotonic) groups completing ≥80% of sessions. Pain reduction and functional improvement were statistically significant in only 3 studies. Imaging-based outcomes were inconsistently reported, and study heterogeneity precluded meta-analysis. Overall methodological quality was rated as good in 3 studies and poor in 10. IMPLICATIONS: Current evidence provides limited support for the superiority of isometric exercise in tendinopathy management. Although isometric regimens appear tolerable and may confer short-term analgesic benefits, their long-term efficacy relative to eccentric or isotonic protocols remains uncertain. Future research should prioritize standardized outcome measures, longer follow-up, and uniform diagnostic criteria to strengthen the evidence base for exercise prescription in tendinopathies.

Humans↗

PubMed2026

Manual, digital, and AI tumour-infiltrating lymphocyte scoring: a secondary analysis of the APHINITY randomised trial.

BACKGROUND: Stromal tumour-infiltrating lymphocytes (sTILs) are prognostic in early-stage HER2-positive breast cancer, but their role in the context of dual HER2 blockade remains undefined. We evaluated manual, digital, and artificial intelligence (AI)-based sTIL quantification, together with AI-derived spatial metrics, for prognostic and treatment-benefit stratification using tumour samples from the phase 3 APHINITY trial. METHODS: In the APHINITY trial, 4805 patients were randomly assigned to receive chemotherapy plus trastuzumab with pertuzumab or chemotherapy plus trastuzumab with placebo. Median follow-up was 74·1 months (IQR 68·3-75·4). We analysed 4262 haematoxylin and eosin-stained images using manual assessment, an automated digital approach, AI-based lymphocyte quantification (AI percentage lymphocytes), and two AI-derived spatial features (AI-TIL and immune hotspot). Interobserver reproducibility was assessed in 262 randomly chosen tumour samples scored independently by five pathologists. Multivariable Cox models were used to assess associations between TIL levels and invasive disease-free survival (primary outcome in APHINITY), distant recurrence-free interval, and overall survival. The heterogeneity of pertuzumab benefit was evaluated using subgroup analyses, subpopulation treatment effect pattern plot analyses, and nested Cox models with treatment-by-biomarker interaction terms. FINDINGS: Manual scoring showed high interobserver reproducibility (intraclass correlation coefficient 0·84 [95% CI 0·79-0·88]). Concordance between manual and automated methods was modest. AI-based scoring (AI percentage lymphocytes) reclassified 120 (11·6%) of 1035 node-positive tumours from immune-low (by manual scoring) to immune-high; this subgroup of patients showed greater separation of 5-year invasive disease-free survival curves between pertuzumab and placebo groups compared with patients whose tumours were concordantly classified as immune-low by both manual and AI-based approaches. Higher levels of TILs were associated with improved invasive disease-free survival for all sTIL measurement approaches and spatial measurements (hazard ratios [HRs] 0·41-0·93). Pertuzumab was associated with improved invasive disease-free survival at higher sTIL levels across all measurement approaches (HRs 0·36-0·48), but was not associated with higher values of spatial measures. The largest 6-year absolute improvements with pertuzumab were observed in patients with node-positive disease whose tumours scored in the highest level of immune infiltration of manual sTIL scoring (≥70·0%; mean absolute improvement 12·1 percentage points [SD 2·8]). In nested prognostic and predictive models, AI-based immune hotspot scores provided the most consistent additional information when combined with any sTIL measurement (all p<0·010). INTERPRETATION: Standardised manual sTIL scoring was reproducible, and digital and AI-based methods showed consistent prognostic stratification and potential for treatment-benefit stratification despite only modest correlation between platforms. AI spatial metrics provided complementary information beyond sTIL density and could support more scalable immune assessment. Future studies are needed to validate these approaches in independent cohorts and to clarify their clinical utility for stratifying contemporary HER2-directed therapies. FUNDING: None.

Humans↗

PubMed2026

Quo vadis, BGA? A collaborative EDNAP exercise on the challenges and progress in forensic biogeographical ancestry inference.

There is a broad consensus that forensic tests for the prediction of externally visible characteristics (EVC) and analysis of biogeographic ancestry (BGA) of an individual are technically reliable. However, interpretation of the results and population-specific genotype distribution patterns remains challenging. EVC and BGA analyses provide valuable information for population genetics studies and as investigative leads for criminal cases, as well as for historical and contemporary identification tests. However, inaccurate or incorrect predictions, for example, from subjective bias in the interpretations made, have the potential to misdirect police investigations. The legal situation regarding EVC and BGA testing varies by country: ranging from countries where it is explicitly prohibited, to those without specific regulations on biogeographic ancestry prediction, and others that have already enacted laws governing its use. The reluctance to utilize these analyses is not only due to legal restrictions and data protection concerns, but also to initial limited sets of sufficiently comprehensive forensic DNA assays. Forensic BGA marker panels typically contain up to ∼300 SNPs. This relatively small number of genetic markers, along with limited reference population data, complicates the interpretation of results from donors of unknown origin. This paper presents the results of a collaborative EDNAP study, which, for the first time, evaluated the approach to reporting EVC and BGA data between international laboratories. For the study, DNA from nine individuals with self-reported ancestry was collected and analysed using various forensic panels differing in the number and composition of ancestry-informative markers genotyped, comprising: the Precision ID mtDNA Whole Genome Panel, the VISAGE Basic Tool and the VISAGE Enhanced Tool for Appearance and Ancestry Prediction, and the Ion AmpliSeq™ PhenoTrivium Panel. To ensure full data protection, all SNP genotypes and uniparental marker haplotypes obtained were not shared with third parties. Instead, the genetic data were analysed using a range of commonly used population analysis software packages. These analysis outcomes were then distributed to twelve European forensic laboratories (both academic and law enforcement institutions), who were asked to prepare reports based on their interpretation of the phenotypes and ancestry they inferred from the analysis data. A questionnaire sent alongside the genetic information, aimed to evaluate which difficulties were encountered by the participants in processing the BGA analysis data they were given.

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 (≥18 years of age), reporting mean polyp detection counts stratified by size (≤5 mm, 6-9 mm, and ≥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 τ2. 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 (≤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

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

AI-enabled viral genomics: from virus discovery to host prediction and emerging variant forecasting.

The rapid expansion of metagenomic sequencing has generated vast repositories of viral sequence data that far outpace our capacity to interpret them using conventional approaches. Highly divergent sequences, sparse functional annotation, and taxonomically uneven sampling present fundamental challenges for reference-dependent methods, which lose sensitivity precisely for novel and understudied viruses with high public health relevance. Artificial intelligence (AI) provides a new avenue to address these challenges by enabling predictive inference from viral genomes and proteins while reducing dependence on sequence similarity. In this Review, we discuss representative advances in AI for virus discovery, taxonomic classification and functional annotation, prediction of host range and zoonotic potential, and efforts toward forecasting emerging variants. These advances are transforming viral genomics from a largely descriptive discipline into one with increasing predictive capability. We also critically assess the major challenges that constrain current approaches, including the availability of high-quality and representative datasets, rigorous model evaluation, biological interpretability and responsible governance for increasingly capable AI models.

Artificial Intelligence↗

PubMed2026

Diagnostic utility of high-risk HPV polymerase chain reaction-based testing in head and neck FNA specimens with indeterminate cytomorphology.

BACKGROUND: Fine-needle aspiration (FNA) is critical in the initial diagnosis of many high-risk human papillomavirus (HR-HPV)-associated, metastatic oropharyngeal squamous cell carcinomas. Updated guidelines recommend HR-HPV-specific polymerase chain reaction (PCR) analysis over p16 immunohistochemistry on FNA specimens because p16 performs poorly on cytology material. PCR-based assays on liquid cytology material have demonstrated excellent analytic performance; however, the diagnostic utility of a positive HR-HPV PCR result in specimens with indeterminate cytomorphology remains uncharacterized. METHODS: The authors retrospectively identified 279 head and neck FNA specimens that had paired HR-HPV PCR testing on residual liquid cytology material over a 5-year period. The positive predictive value for histopathologically confirmed squamous cell carcinoma on surgical follow-up was calculated within each cytologic interpretive category. RESULTS: The HR-HPV PCR results were positive in 50.2% of specimens, negative in 40.9%, and indeterminate in 9.0%. The HR-HPV positivity rate ranged from 0% in specimens categorized as negative for malignancy to 57.3% in cytologically positive specimens, with 19.0%, 41.2%, and 50.0% positivity in the atypical, suspicious, and nondiagnostic categories, respectively. Among cytologically indeterminate specimens with positive HR-HPV PCR results (n = 14), the positive predictive value was 100% (95% confidence interval, 78.5%-100.0%). Blinded slide review additionally identified 15 cytologically positive specimens in which the definitive malignant interpretation depended substantially on HR-HPV positivity; all 15 were confirmed as squamous cell carcinoma. CONCLUSIONS: A positive HR-HPV PCR result on liquid cytology material carries a positive predictive value of 100% for malignancy in cytologically indeterminate head and neck FNA specimens. These findings support integrating HR-HPV PCR analysis into routine cytologic interpretation with the potential to upgrade some indeterminate specimens to malignant when HR-HPV is detected, expediting definitive treatment and sparing patients additional, invasive sampling.

Humans↗

PubMed2026

Recent advances in supramolecular macrocycle-based artificial light-harvesting systems.

Artificial light-harvesting systems (ALHSs) inspired by the antenna function of natural photosynthesis provide molecular platforms for collecting excitation energy and directing it to emissive or reactive acceptors. In many supramolecular ALHSs, however, practical performance is limited by poorly defined donor-acceptor orientation, aggregation-caused quenching (ACQ), interfacial defects, and limited stability in aqueous or complex media. Supramolecular macrocycles-particularly pillar[n]arenes (PAs), cucurbit[n]urils (CBs), calixarenes (CAs), cyclodextrins (CDs), and supramolecular coordination complexes (SCCs)-offer a useful design space because their cavities, pre-organized scaffolds, and reversible non-covalent interactions can confine chromophores, tune local donor/acceptor ratios, and modulate Förster resonance energy transfer (FRET). This Review systematically examines the unique structural advantages and assembly mechanisms of the five macrocyclic families, with an emphasis on their use in constructing ALHSs-from single-step to cascaded FRET-and in advancing aqueous photocatalysis, near-infrared bioimaging, panchromatic fluorescence modulation, and singlet oxygen generation. The resulting structure-property-application framework is intended to guide the rational design of macrocycle-assisted photofunctional materials while avoiding overextension of the photosynthesis analogy.

Journal Article↗

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↗