SEARCH · Search PubMed
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.
Explore the source record for details and available documents.
BACKGROUND: Most European population mammography screening programs rely on double reading with arbitration, a model that delivers mortality benefit but is increasingly challenged by radiologist workload, variable specificity, and interval cancers. Artificial intelligence (AI) is being evaluated to support or optimize these established European screening pathways. PURPOSE: To synthesize prospective or program-embedded evaluations of AI conducted within European-style population screening programs and to estimate exploratory program-level absolute risk differences (RDs) per 1000 examinations for cancer detection rate (CDR) and recall. MATERIALS AND METHODS: We performed a prespecified, focused evidence synthesis of three large studies embedded within routine population screening programs operating under European-relevant workflows: MASAI (randomized AI-supported risk triage within a national program), ScreenTrustCAD (prospective paired-reader evaluation with AI as an independent reader in a double-reading framework), and PRAIM (nationwide decision-referral implementation). Outcomes were harmonized as AI-control RDs per 1000 examinations. Random-effects pooling used Hartung-Knapp-Sidik-Jonkman models. For the paired-reader design, sensitivity analyses applied a Kish effective sample-size approach across plausible within-examination correlations (ρ = 0.3-0.8). Positive predictive value (PPV) and workflow/time outcomes were summarized descriptively. RESULTS: Across 597,419 examinations, the pooled CDR RD was +0.9 per 1000 (95% CI -0.0 to +1.8; I2 ≈ 12%), consistent with a modest directional increase with borderline statistical uncertainty. The pooled recall RD was -0.6 per 1000 (95% CI -3.1 to +2.1; I2 ≈ 41-43%), indicating no consistent recall increase across screening programs. Where reported, PPV was higher with AI-supported screening. Efficiency signals included 44.3% fewer total readings in MASAI and shorter reading times for AI-normal examinations in PRAIM; in PRAIM, a program-level safety-net mechanism recovered 204 cancers that would otherwise have been missed. CONCLUSION: In European population screening programs characterized by double reading and arbitration, prospective program-embedded evidence suggests that AI integration may yield a small absolute increase in cancer detection (≈1/1000) without a consistent increase in recall, alongside improved PPV and efficiency signals. These findings suggestAI primarily as a complementary reader within European screening workflows, with implementation requiring explicit quality assurance and monitoring of interval cancers and stage distribution.
INTRODUCTION AND OBJECTIVE: Suction-enhanced flexible ureteroscopy (URS) aims to improve stone clearance and reduce complications. We performed a Bayesian network meta-analysis to compare the efficacy and safety of flexible aspiration navigable sheaths (FANS) and direct in-scope suction (DISS) for renal calculi ≤ 2 cm. METHODS: A systematic search of PubMed, MEDLINE, Scopus, Web of Science, and Google Scholar was conducted through June 2026. Comparative studies of FANS, DISS, or conventional access sheaths for renal stones ≤ 2 cm were included. The primary outcome was 30-day stone-free rate (SFR). Secondary outcomes included operative time, fever, sepsis, and complications. A Bayesian random-effects network meta-analysis synthesized direct and indirect evidence. RESULTS: Seventeen studies including 3,657 patients (1,677 FANS, 56 DISS, 1,924 control) were included. FANS showed higher SFR (OR 2.5, 95% CrI 2.0-3.1), while grouped DISS had a similar but less precise effect (OR 3.1, 95% CrI 1.0-8.8). Calyxo V2 had the highest SFR (OR 5.4, 95% CrI 1.0-29.0), whereas PUSEN showed no significant difference (OR 1.6, 95% CrI 0.41-6.3). FANS reduced postoperative fever and complications. FANS also showed lower odds of postoperative sepsis (OR 0.40, 95% CrI 0.12-0.97). CONCLUSIONS: Suction-assisted ureteroscopy improves SFR for renal calculi ≤ 2 cm. FANS was associated with shorter operative time, fever, and complications. DISS systems show promising but limited results, with performance differing by technology configuration. Larger prospective trials are needed.
OBJECTIVES: To synthesize the roles and core functions of AI in nursing simulation education for nursing students via systematic review, quantitatively evaluate its effects on students' knowledge and skill outcomes through meta-analysis, and map the research landscape and development trends of this field through bibliometric visualization analysis. DESIGN: Systematic review, meta-analysis and bibliometric visualization analysis. DATA SOURCES: Eight electronic databases: PubMed, Web of Science, MEDLINE, ERIC, Academic Search Complete, China National Knowledge Infrastructure (CNKI), Wanfang Database, VIP Chinese Science and Technology Journal Database (VIP) were employed to search studies from the time of construction to 16 December 2025. REVIEW METHODS: Studies meeting the inclusion criteria were screened. The revised Cochrane Risk of Bias tool (ROB 2) and Joanna Briggs Institute (JBI) critical appraisal checklists were used for quality assessment. Meta-analysis was performed with Review Manager 5.4, and bibliometric visualization analysis was conducted using VOSviewer 1.6.20 and Bibliometrix (based on R4.4.3). RESULTS: A total of 61 studies were included. AI primarily played two roles in nursing simulation education: peer-type new subject (n = 24) and direct mediator (n = 22). Meta-analysis showed that AI interventions significantly improved nursing students' knowledge (SMD = 1.49, 95% CI [0.55,2.43], p = 0.002) and skills (SMD = 0.66, 95% CI [0.02,1.31], p = 0.04). Bibliometric analysis identified that the United States of America and China were the two main contributing countries in this field, and the key motor themes included generative artificial intelligence, virtual patients, and geriatric care. CONCLUSIONS: AI exerts positive effects on nursing students' knowledge acquisition and skill enhancement in simulation education, with peer-type new subject and direct mediator as the dominant roles. Future research should focus on expanding AI applications in multi-specialty simulation scenarios, activating the data-driven value of machine learning, and strengthening international collaboration and standardization construction, so as to promote the sustainable development of AI-integrated nursing simulation education.
Virtual surgical planning (VSP)-assisted reconstruction is increasingly used as an alternative to conventional free-hand (FH) techniques in mandibular and maxillary free-flap reconstruction. This systematic review and meta-analysis compared clinical outcomes and proposed a Reconstruction Complexity-Completeness classification. PubMed/MEDLINE, Scopus, Web of Science, Google Scholar, and reference lists were searched from inception to 20 June 2026. Comparative studies were eligible. Risk of bias was assessed using RoB 2 or the Newcastle-Ottawa Scale. Random-effects meta-analyses used restricted maximum likelihood estimation and Hartung-Knapp adjustment. Forty-two studies included 2763 patients (1204 VSP; 1559 FH). VSP significantly reduced operative time (33 studies; MD -64.75 min, 95% CI -83.51 to -46.00), ischemia time (15 studies; MD -37.40 min, 95% CI -48.97 to -25.82), and hospital stay (16 studies; MD -1.75 days, 95% CI -3.43 to -0.08). VSP was associated with significantly lower odds of bony non-union (OR 0.31, 95% CI 0.16-0.59) and malocclusion (OR 0.14, 95% CI 0.03-0.64), whereas flap loss, surgical site infection, and plate exposure did not differ significantly. VSP-assisted reconstruction was associated with improved operative efficiency, shorter hospitalization, and lower odds of bony non-union and malocclusion, while no statistically significant differences were detected in flap loss, surgical site infection, or plate exposure. The proposed classification may support complexity-adjusted reporting and comparison.
BACKGROUND: Accurately distinguishing malignant pleural effusion (MPE) from non-malignant pleural effusion is clinically important, but the generalisability and methodological quality of machine-learning (ML) models remain uncertain. METHODS: We searched eight databases to 23 April 2026. Diagnostic performance was pooled using random-effects and Reitsma bivariate models, and study quality was assessed using PROBAST+AI. RESULTS: Forty-two studies were included; 17 contributed to the AUC meta-analysis and 14 to the bivariate analysis. The pooled AUC was 0.90 (95 % CI 0.85-0.94; 95 % prediction interval 0.62-0.98), with sensitivity of 0.80 (95 % CI 0.77-0.83) and specificity of 0.87 (95 % CI 0.79-0.92). Only nine studies reported external, temporal or independent validation. Externally validated studies had a lower pooled AUC than studies without external validation (0.83 vs 0.92), with lower specificity observed in the two externally validated studies contributing sensitivity and specificity data. All 42 development assessments had high overall quality concerns, and all 42 model evaluations were judged at high risk of bias. CONCLUSIONS: ML models showed good apparent accuracy for distinguishing MPE from non-MPE, but the evidence was limited by substantial heterogeneity, high risk of bias and scarce external validation. The pooled estimates reflect the average performance of different selected models rather than the expected accuracy of a single clinical test. ML models should be regarded as adjuncts to existing diagnostic pathways until they are confirmed by rigorous multicentre prospective external validation and clinical-impact studies.
BACKGROUND: The necessity of routine parenchymal renorrhaphy during off-clamp robot-assisted partial nephrectomy (RAPN) remains uncertain. This study aimed to compare perioperative, functional, safety, and oncological outcomes between sutureless and conventional renorrhaphy. METHODS: We conducted a systematic review and meta-analysis following PRISMA 2020 guidelines. Comparative studies evaluating sutureless versus conventional renorrhaphy during purely off-clamp RAPN were included. Trifecta achievement was the primary outcome. Random-effects models were used for pooled analyses, with subgroup analysis according to study design. RESULTS: Four studies involving 787 patients, including one randomized controlled trial (RCT) and three propensity score-matched (PSM) studies, were included. The overall pooled estimate showed no statistically significant difference in Trifecta achievement (RR 1.17, 95% CI 0.97-1.41), with substantial heterogeneity (I² = 86.5%). The PSM studies favored the sutureless approach (RR 1.26, 95% CI 1.05-1.52), whereas the RCT yielded an RR of 0.97 (95% CI 0.92-1.04) and met the prespecified noninferiority criterion without demonstrating superiority. The sutureless approach was associated with a smaller perioperative eGFR decline (MD - 3.89, 95% CI - 6.16 to - 1.62), while no significant difference was observed in eGFR at 3 months. No statistically significant differences were identified in major complications, blood transfusion, or positive surgical margins; urinary and vascular complications were sparsely reported. CONCLUSIONS: In selected patients undergoing purely off-clamp RAPN, randomized evidence supports the noninferiority of a strategy that omits routine parenchymal renorrhaphy while permitting clinically necessary selective repair, but does not demonstrate superiority. Favorable estimates from PSM studies remain vulnerable to intraoperative treatment-selection bias. Current evidence is insufficient to determine whether omission of renorrhaphy affects urinary complications, long-term renal function, or oncological outcomes. REGISTRATION: This systematic review was registered prospectively in PROSPERO (CRD420261435995).
BACKGROUND: Left ventricular assist devices (LVADs) prolong survival in end-stage heart failure, and warfarin thromboprophylaxis is recommended to prevent device thrombosis and thromboembolic complications. When bleeding occurs or emergency surgery is required, rapid anticoagulation reversal is critical. Prothrombin complex concentrate (PCC) provides rapid reversal; however, its risk-benefit profile in LVAD recipients remains unclear. We conducted a systematic review and meta-analysis comparing PCC with non-PCC strategies for warfarin reversal in LVAD recipients. METHODS: MEDLINE, Embase, and Scopus were searched through June 2025 for studies of PCC versus non-PCC strategies for warfarin reversal in LVAD recipients. Two reviewers independently extracted data. Random-effects models were used to pool arm-level estimates and to pool head-to-head comparisons using mean differences or risk ratios (RRs). RESULTS: Eighteen studies involving 779 patients were included. Arm-level pooled estimates for PCC versus non-PCC comparators were 24.0% versus 15.8% for mortality, 16.5% versus 12.1% for thrombotic events, and 3.1 versus 5.7 for FFP units. Arm-level time to INR correction was longer with PCC overall (16.5 versus 13.6 h), driven by one elective cohort, but faster within the ICH subgroup (6.0 versus 13.7 h). In head-to-head comparisons, PCC achieved faster INR correction than non-PCC comparators (mean difference - 7.6 h; p = 0.001) and required fewer FFP units (-2.6 units; p = 0.019), with no significant difference in all-cause mortality (RR 1.14; p = 0.490) or thrombotic events (RR 1.43; p = 0.176). CONCLUSIONS: In head-to-head studies, PCC was associated with faster INR correction and lower FFP requirements than non-PCC strategies, whereas mortality and thrombotic events did not differ significantly. Given the observational evidence, wide confidence intervals, and heterogeneity, equivalent safety cannot be established, and prospective studies are needed to define the relative safety and effectiveness of the two approaches. IMPLICATIONS FOR CLINICAL PRACTICE: PCC-based strategies may be considered for urgent warfarin reversal in LVAD recipients, particularly when rapid INR reduction or avoidance of large-volume plasma transfusion is clinically important. Treatment decisions should account for the indication, bleeding severity, and underlying thrombotic risk. TRIAL REGISTRATION: CRD42024573925.
BACKGROUND: Critical thinking and clinical reasoning underpin healthcare professionals' ability to navigate uncertainties and deliver safe and effective care. With artificial intelligence (AI) advancement and growing adoption, AI-based educational tools are increasingly used to support these cognitive competencies' development. OBJECTIVE: To synthesize randomised and controlled clinical trials on AI-based educational tools in health professions education and examine their effects on critical thinking and clinical reasoning among health professions students. METHODS: Six electronic databases were searched from January 1, 2014 to July 28, 2025 was reviewed: PubMed, Cochrane Central Register of Controlled Trials, CINAHL, Scopus, Embase and Web of Science. Two independent reviewers performed data extraction and quality assessment using standardized JBI checklists. The GRADE approach was used to assess the certainty of evidence. Studies were pooled via random-effects meta-analyses or narrative syntheses. RESULTS: Fourteen randomised controlled trials and seven controlled clinical trials were included (n = 21). Meta-analyses revealed small to medium effect sizes for the surrogate clinical reasoning outcomes of performance-based assessment scores (SMD 0.68; 95% CI [0.38, 0.98], p-value = 0.00; I2 = 38%) and knowledge test scores (SMD 0.39; 95% CI [0.09, 0.69], p-value = 0.01; I2 = 79%). Critical thinking and clinical reasoning skills and dispositions were narratively synthesized, with majority of included studies favouring AI-based interventions but the evidence had low to very low certainty. CONCLUSION: AI-based educational interventions may improve critical thinking and clinical reasoning among health profession students, but the evidence is very uncertain. This review offers preliminary insights but does not allow identification of optimal interventions or discipline-specific recommendations due to small sample sizes and substantial intervention heterogeneity. Further research is required to draw definitive conclusions. PROTOCOL REGISTRATION: CRD42025634074.
This review examined whether robotic assistance alters postoperative leg-length discrepancy (LLD), acetabular cup orientation, or early hip-specific outcomes relative to conventional total hip arthroplasty (THA). We searched PubMed and Web of Science through May 2026 for comparative English-language reports. Study eligibility, data extraction, and methodological appraisal were undertaken independently by two reviewers. Mean differences (MDs) and 95% confidence intervals (CIs) were calculated in Review Manager 5.4. Model selection was based on the target estimand and anticipated clinical and methodological diversity; leave-one-out and alternative-model sensitivity analyses were undertaken for heterogeneous outcomes. The protocol is registered with PROSPERO (CRD420261454043). The review included seven studies and 968 participants. Compared with conventional THA, robot-assisted THA yielded a smaller postoperative LLD (MD = -2.02, 95% CI -3.46 to -0.58; P = 0.006) and a higher Harris Hip Score (MD = 2.96, 95% CI 1.12 to 4.80; P = 0.002). Mean cup anteversion was lower in the robotic group (MD = -1.52, 95% CI -2.29 to -0.76; P < 0.0001), whereas cup inclination did not differ (MD = -0.71, 95% CI -3.26 to 1.83; P = 0.58). The robotic group also had higher Forgotten Joint Score (MD = 14.68, 95% CI 5.02 to 24.33; P = 0.003) and Oxford Hip Score values (MD = 2.61, 95% CI 0.71 to 4.51; P = 0.007). Robotic assistance was linked to a modest improvement in leg-length restoration and to higher scores on several early functional measures. The limited number of studies, predominance of nonrandomized designs, and marked heterogeneity in some analyses temper the certainty of these findings.
Background Chest CT is a primary method for identifying pulmonary nodules, yet interpreting scans remains time-intensive and demanding. Currently, artificial intelligence (AI) is expected to reduce reading times, but the effect of AI on reporting times in this setting is unknown. Purpose To evaluate the impact of a commercial AI software on radiologists' reading time for pulmonary nodule assessment on chest CT scans within a real-world clinical setting. Materials and Methods This retrospective study included patients who underwent chest CT examinations at a tertiary medical center between September 2021 and May 2024. The study period was divided into pre- and post-AI phases. The primary outcome was radiology reporting time. The association between AI implementation and reporting time was evaluated using a multivariable parametric Weibull shared frailty survival model adjusted for reader function, examination type, patient location, and requesting specialty, with clustering at the radiologist level. Interaction analyses assessed heterogeneity across prespecified subgroups. An exploratory extrapolation estimated projected workforce and financial impact. Results This study included 19 433 patients (mean age, 62 years ± 14.2 [SD]; 21 814 men; 39 323 chest CT examinations, 19 190 pre-AI, and 20 133 post-AI). AI implementation was associated with faster report completion (adjusted hazard ratio, 1.17; 95% CI: 1.14, 1.21; P < .001). The adjusted median reporting time decreased from 21.3 minutes pre-AI to 18.2 minutes post-AI (14.6% reduction; P < .001). Heterogeneity was observed across reader function (P < .001), examination type (P = .048), and requesting specialty (P = .03). The largest relative reductions were observed for CT thorax electrocardiogram-gated examinations (-41.1%; P < .001) and thoracic radiologists (-25.0%; P < .001), whereas emergency department examinations showed increased median reporting time (7.1%; P < .001). At institutional scan volumes (approximately 20 000-22 000 chest CT examinations annually), exploratory modeling suggested an approximate reduction of 0.5 full-time equivalent radiologist workload. Conclusion Implementation of commercial AI-assisted pulmonary nodule assessment on chest CT scans reduced radiologist reporting time in a real-world clinical setting. © The Author(s) 2026. Published by the Radiological Society of North America under a CC BY 4.0 license. Supplemental material is available for this article. See also the editorial by Iwasawa in this issue.
Robot-assisted percutaneous vascular intervention (R-PVI) has expanded beyond coronary procedures, but previous reviews were largely coronary-focused and observational. Recent randomized controlled trials (RCTs) warrant broader reassessment of R-PVI versus manual percutaneous vascular intervention (M-PVI) across vascular territories. PubMed, Embase, Web of Science, and the Cochrane Central Register of Controlled Trials were searched from database inception to January 31, 2026, following PRISMA guidelines. RCTs and observational studies including ≥10 adult patients in total were eligible. Comparative studies informed primary analyses, while single-arm studies provided supportive evidence. Primary outcomes were clinical success rate and major adverse cardiovascular/cerebrovascular events (MACE) rate. Secondary outcomes included mortality rate, technical success rate, procedural time metrics, contrast volume, and radiation exposure. Random-effects models were used. Forty studies were included: 3 RCTs, 10 comparative observational studies, and 27 single-arm observational studies, comprising 3,870 patients undergoing R-PVI and 1,142 undergoing M-PVI. Comparative analyses showed similar clinical success rates (RR 1.00, P = 0.46), MACE rates (RR 0.72, P = 0.43), and mortality. Single-arm pooled estimates for clinical and technical success were 98.76% and 96.09%, respectively. R-PVI prolonged total procedure time overall (MD 15.92 min, P = 0.01), with consistent increases in the neurovascular, RCT, and non-RCT subgroups. Fluoroscopy time was also longer (MD 1.91 min, P = 0.04), mainly in the RCT subgroup (MD 2.83 min, P = 0.001). In contrast, intravascular intervention time was unchanged overall and in RCTs, but was prolonged in non-RCTs (MD 8.72 min, P = 0.006). Operator radiation exposure was markedly reduced (MD -33.97 μSv, P < 0.001), whereas patient radiation exposure and contrast volume were similar. R-PVI appears feasible and safe across selected vascular procedures. Its clearest benefit is reduced operator radiation exposure, whereas lower whole-procedure efficiency remains its main limitation.
PURPOSE: To synthesizes evidence on artificial intelligence (AI) performance in neuroblastoma (NB) diagnosis, risk stratification, prognosis, and genomic characterization. MATERIALS AND METHODS: A systematic review and meta-analysis was conducted following PRISMA 2020 guidelines (PROSPERO: CRD42024539475) across five databases. Meta-analyses used random-effects models with logit-transformed Area Under the Curve (AUCs) and cluster-robust standard errors. AI models were classified as Machine Learning Models (MLM) or Hybrid Nomograms (HN) based on their construction methodology. RESULTS: Of 3,742 articles identified, 53 were included. MLMs demonstrated higher point estimates than radiologists in differential diagnosis (AUC: 0.87 vs. 0.83), though this difference was not statistically significant and carried substantial uncertainty. HNs achieved stronger performance in risk stratification (AUC: 0.87). AI-derived nomograms (AUC: 0.9) and gene signatures (AUC: 0.8) outperformed conventional prognostic markers descriptively. Chemotherapy response prediction remained below clinical utility thresholds across all model types. Only 33.9% of models reported calibration and 24.5% underwent external validation. CONCLUSIONS: AI demonstrates proof-of-concept across multiple NB clinical domains. However, clinical adoption remains premature given persistent gaps in external validation, calibration, dataset size, and pediatric-specific model development. Future studies should test these models prospectively in multicenter pediatric cohorts, ideally through COG or SIOPEN, using shared definitions for diagnosis, risk group, treatment response, and survival outcomes.
Robotic-assisted bronchoscopy (RAB) and computed tomography-guided transthoracic biopsy (CTTB) are competing strategies for sampling peripheral pulmonary lesions (PPLs). Whether they differ in yield or safety is uncertain. To our knowledge, this is the first systematic review restricted to direct comparisons. We searched MEDLINE, Europe PMC, Scopus, Web of Science and ClinicalTrials.gov from inception to 7 July 2026 for studies directly comparing RAB with CTTB in adults with PPLs. The primary outcome was strict 2024 American Thoracic Society/American College of Chest Physicians diagnostic yield. Risk of bias was assessed with ROBINS-I and certainty with GRADE. A cohort-genealogy step identified, per outcome, the largest set of cohorts sharing no patients; only that set was pooled, with Hartung-Knapp and Mantel-Haenszel sensitivity analyses. Five retrospective studies from one US health system were eligible. Four share patients; at most three cohorts are mutually independent. Across those three, diagnostic yield was comparable (risk ratio [RR] 0.99, 95% confidence interval [CI] 0.93-1.06; I²=24%; Hartung-Knapp 0.87-1.13), with an identical relative effect under strict and intermediate definitions although absolute yields fell from 88% to 74-84% under strict criteria. Pneumothorax requiring a chest tube and/or admission was about three-quarters less frequent with RAB across all three cohorts (RR 0.25, 95% CI 0.14-0.46; I²=0%; Hartung-Knapp 0.07-0.96). Strict yield (RR 0.99) and any pneumothorax (RR 0.06) were reported by two cohorts each and neither survives the few-studies correction. RAB took about 50 min longer than CTTB where same-session staging endobronchial ultrasound was counted in the robotic time, but only about 8 min longer than CTTB where it was not. Only one cohort reported yield by lesion size category and none reported yield by bronchus sign or lung zone, so lesion-level subgroups could not be pooled. Certainty was low for pleural complications and very low elsewhere. Low-certainty evidence indicates that RAB is associated with fewer pleural complications, with no statistically detectable difference in diagnostic yield; equivalence was not formally established. Because all evidence is retrospective, confined to one health system, and almost never stratified by lesion size or accessibility, these findings are hypothesis-generating and require a multicenter randomized trial.
ObjectiveTo evaluate the prevalence, access to care, and health outcomes of orofacial clefts (OFCs) among American Indian and Alaska Native (AI/AN) populations through a systematic review and meta-analysis.DesignSystematic review and meta-analysis performed in accordance with PRISMA 2020 guidelines and registered with PROSPERO (CRD420251035364).SettingUS-based population registries, hospital databases, and institutional or community-level retrospective studies involving AI/AN populations.Patients and ParticipantsAI/AN individuals with OFCs compared with non-Hispanic White patients.InterventionsPrimary cleft lip and palate repair, secondary cleft-related procedures, and multidisciplinary cleft care.Main Outcome Measure(s)Prevalence of OFCs, timing of cleft surgery, discharge disposition, access to specialists, and qualitative determinants of disparities.ResultsEighteen studies including more than 1985 AI/AN patients were identified. Meta-analysis of 5 studies estimated a pooled OFC prevalence of 15 per 10 000 live births (95% confidence interval: 5-49), with substantial heterogeneity (I2 = 99.8%). Individual studies reported significantly higher OFC prevalence in AI/AN populations compared to non-Hispanic Whites (odds ratio range: 1.44-2.68). Geographic maldistribution of craniofacial-trained surgeons, increased odds of nonhome discharge, and delayed cleft palate repair were consistently observed barriers. Qualitative analyses highlighted structural inequities, perceived racism, and lack of culturally responsive care as major contributors to disparities.ConclusionsAI/AN populations face a disproportionately high burden of OFCs alongside structural barriers to timely, culturally competent care. Addressing these disparities requires community-engaged, multidisciplinary interventions that improve geographic access and integrate culturally responsive approaches to care.
Robot-assisted guidance may improve the technical precision of percutaneous cannulated-screw fixation for femoral neck fractures. Whether these procedural advantages translate into better clinical outcomes remains uncertain. We compared robot-assisted and conventional freehand fixation in adults with femoral neck fractures. MEDLINE, Embase and CINAHL were searched from inception to 15 July 2026 without language restrictions. Google Scholar was used only as a supplementary search source, together with forward and backward citation searching. Comparative studies of robot-assisted versus freehand fluoroscopy-guided cannulated-screw fixation were included. Risk of bias was assessed using RoB 2 and ROBINS-I, with the Newcastle-Ottawa Scale used as a complementary appraisal of non-randomised studies. Random-effects meta-analyses included prediction intervals and prespecified sensitivity analyses. The protocol was registered prospectively (PROSPERO CRD420261465038). Sixteen comparative studies involving 1,293 participants were included. Of these, 597 underwent robot-assisted fixation and 696 underwent freehand fixation. Two studies reporting random allocation and 14 non-randomised studies were included in the study. Robot-assisted fixation was associated with fewer guide-wire manipulations, greater screw-placement accuracy and 13.9 fewer fluoroscopic acquisitions per procedure (95% confidence interval [CI] -20.3 to -7.5). Earlier radiographic healing and modestly higher final Harris Hip Scores were also observed. Pooled estimates suggested lower risks of union failure, avascular necrosis and composite complications. Fluoroscopy duration, overall operative time and reoperation did not differ significantly. Heterogeneity was substantial for several continuous outcomes, with prediction intervals crossing the null for several estimates, indicating that the magnitude of benefit varied considerably between studies. Some clinical associations were also sensitive to eligibility-restricted analyses. Robot-assisted cannulated-screw fixation improves technical execution compared with freehand fixation. Patient-important clinical superiority and economic value have not been established, and evidence concerning learning curves, operator acceptability and system reliability remains insufficient. Current evidence does not support routine widespread adoption; adequately powered multicentre randomised trials incorporating economic and implementation evaluation are required.
In skeletal Class III patients, treatment options range from orthodontics to orthognathic surgery. Choosing the optimal approach requires a comprehensive clinical evaluation, which may be supported by AI tools. The aim of this study was to assess the performance of AI models in predicting the need for orthognathic surgery and in identifying predictors influencing treatment decisions. A PRISMA-guided electronic database search (PubMed, Web of Science; 2009-2024; English/French) was performed to identify studies using machine learning (ML) or deep learning (DL) on cephalometric and clinical data. After screening and assessment for eligibility, 15 studies were critically appraised. Model performance was summarized using accuracy, sensitivity, specificity, and the area under the curve (AUC). ML algorithms (particularly Random Forest and XGBoost) and DL models (ResNet-based convolutional neural networks (CNNs)) achieved high accuracy for predicting surgical need. Frequently selected predictors included Wits appraisal, ANB angle, the maxillomandibular ratio (Mx/Md), overjet, and the divergence of the lower gonial angle. AI methods show promise for assisting treatment decisions in Class III malocclusion, with Random Forest and XGBoost performing well on tabular cephalometric data and CNNs on imaging. Larger, multicentre datasets and external validation are needed to improve reliability, address bias, and support clinical implementation.
BACKGROUND: Skin cancer is one of the most prevalent malignancies worldwide, particularly within Caucasian populations. This systematic review and meta-analysis aimed to quantitatively review the current literature on non-invasive diagnosis of skin cancer and evaluate the current evidence to support the use of tools in addition to, or in replacement of clinician face-to-face assessment. METHODS: A literature search was conducted for publications in PubMed, Medline and Embase databases. Articles describing accuracy, sensitivity, specificity and outcomes of their mode of assessment were included. A total of 208 articles met the inclusion criteria. RESULTS AND CONCLUSION: This systematic review and meta-analysis showed that the diagnostic performance of artificial intelligence (AI) in the interpretation of dermatoscopic images was high for melanoma diagnosis, basal cell carcinoma or malignancy, in comparison to dermatoscopic assessment alone by clinicians and experts. Although AI interpretation of images demonstrated higher sensitivity for melanoma diagnosis in comparison to clinical assessment combined with dermatoscopic assessment, it is unclear if this is also the case for basal cell carcinoma and squamous cell carcinoma diagnosis. Reflectance confocal microscopy, a non-invasive high resolution imaging technique, is known to have a high sensitivity for diagnosing cutaneous malignancy, and this may have applications within secondary care. Therefore, AI could help reduce resource burden and aid in clinical assessment, particularly within primary care settings.