SEARCH · Search PubMed

Results for “External genitalia score”

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.

348 recordsLinked to original sources

PubMed2026

The role of the external genitalia score (EGS) in evaluation of disorders of sex development.

OBJECTIVE: To investigate the utility of the External Genitalia Score (EGS) in the diagnosis of disorders of sex development (DSD) and decision-making regarding gender assignment in affected patients. METHODS: A retrospective cohort study was conducted, enrolling 114 DSD patients aged <2 years (88 reared as males, 26 reared as females) treated at our hospital between April 2005 and June 2023, alongside 40 hypospadias patients aged <2 years who underwent surgery at our institution from January to July 2023. Demographic data (age) and EGS assessments of external genitalia were collected for all participants. Statistical analyses included independent samples t-tests, Mann-Whitney U tests and Receiver Operating Characteristic (ROC) curve analysis. Specifically, EGS scores were compared between the hypospadias group and the male-reared subgroup of the DSD cohort; additionally, EGS scores were contrasted between male-reared and female-reared DSD subgroups. RESULTS: The mean age was 20.3 months in the hypospadias group, 17.9 months in the male-reared DSD group, and 18.8 months in the female-reared DSD group. EGS ranged from 5.5 to 11.5 (median 10.5) in the hypospadias group and from 1 to 12 (median 4.75) in the DSD group. ROC curve analysis was performed to compare EGS scores between the hypospadias group and the male-reared DSD subgroup. The optimal diagnostic threshold was determined by maximizing the Youden index (sensitivity + specificity - 1), which balances sensitivity and specificity. A cut-off value of ≤8.50 was identified as indicative of DSD; clinically, patients with an EGS score <9 should be prioritized for DSD screening. Further comparison between male-reared and female-reared DSD subgroups yielded a threshold of 4.00. Clinically, an EGS score ≤4 may suggest a preference for female gender assignment. DISCUSSION: The EGS scale is a reliable, valid, and clinically feasible tool for characterizing external genitalia in DSD patients. An EGS score of 9 can serve as an indicator for initiating detailed sex development evaluation in hypospadias patients. While gender assignment in DSD is a complex, multifactorial process, EGS scores showed a significant association with the sex of rearing in our cohort. In settings where major determinants are balanced, EGS may serve as an adjunctive descriptive parameter rather than a standalone decision-making tool.

Humans↗

PubMed2026

Quality of life and gender identity in females with congenital adrenal hyperplasia after genital restoration surgery: A single-center experience.

BACKGROUND: Legislation restricting surgical interventions in children with differences of sex development (DSD) has intensified debate about female genital restoration surgery (FGRS) in patients with congenital adrenal hyperplasia (CAH). Long-term patient-reported outcomes are needed regarding the optimal timing of surgery. OBJECTIVE: We aimed to assess health-related quality of life (HRQoL), gender identity, and family satisfaction regarding surgical timing and outcome in females with CAH following genital restoration surgery. STUDY DESIGN: Cross-sectional survey of CAH patients who underwent surgery between January 2007 to December 2016 at our institution. Validated instruments (KINDL questionnaire for HRQoL, Utrecht Gender Dysphoria Scale, UGDS) and structured telephone interviews were employed. RESULTS: Data on HRQoL was available for 25 patients (self- and/or parent-reported) out of 56 eligible patients (45% response rate). Median age at first surgery was 6 months (range: 3-137 months). Patients' age at time of participation ranged from 2 to 28 years. All had 21-hydroxylase deficiency (92% salt-wasting form) with Prader grades ranging from II-V. Wound dehiscence requiring secondary suturing occurred in 15% of patients with primary surgery at our center, while only one (4%) patient developed vaginal stenosis after early primary vaginoplasty. Two additional patients (8%) with prior outside surgery required vaginal revision after FGRS at age 12. HRQoL scores were comparable to healthy reference populations across most age groups. Children aged 3-6 and adolescents and young adults showed no significant difference from reference values, while children aged 7-13 showed a slight elevation. None of five patients ≥14 years demonstrated gender dysphoria (all UGDS scores <40, threshold ≥40). 14 patients and families were also interviewed by telephone. All preferred early surgical timing. No family expressed regret about the decision or preferred delayed surgery. DISCUSSION: This study provides validated intermediate-term patient- and parent-reported outcomes after FGRS in CAH. Key limitations include the small sample size, single-center design, and young age of most patients. Selection bias may exist, though participating families included those who underwent revision surgery. The absence of a non-operated comparison group reflects current clinical reality, as nearly all CAH patients with urogenital sinus underwent surgical correction. CONCLUSIONS: Females with CAH reported normal HRQoL and a comfortable female gender identity after early FGRS. The patients and their families expressed a preference for early surgery. However, there is need for longer-term follow-up to assess sexual function and reproductive outcomes as well comparison of outcomes with a non-operated group.

Humans↗

PubMed2026

Paediatric penile length: a systematic review and meta-analysis.

OBJECTIVE: To assess geographical variation in stretched penile length among prepubertal boys and evaluate temporal trends over the past two decades, as defining reference values for genital organ size remains crucial for early identification of development disorders. METHODS: The PubMed, Cochrane and Scopus databases (no deadlines for publishing were imposed) were searched according to the Preferred Reporting Items for Systematic Review and Meta-analyses statement. Five authors independently extracted individual participant data and assessed the risk of bias. Studies with quantitative penile lengths were included; those involving congenital malformations were excluded. The review protocol was prospectively registered in the International Prospective Register of Systematic Reviews (registration number CRD42022335643). RESULTS: A total of 55 studies from 2000 to 2024 were evaluated, including data from 31 915 boys. Pooled mean stretched penile length estimates were 3.07 cm (95% confidence interval [CI] 2.88-3.26 cm) for the 1-week-old boys, 3.73 cm (95% CI 3.53-3.93 cm) for the 1-year-old boys, 4.69 cm (95% CI 4.49-4.88 cm) for the 2-5 year-old boys, and 5.43 cm (95% CI 5.20-5.66 cm) for the 5-10 year- old boys. When comparing data from the 2000s to the 2020s, stretched penile length decreased by 16.2% (from 3.46 to 2.90 cm), 16.3% (from 4.17 to 3.49 cm), 21.5% (from 5.31 to 4.17) and 26.2% (from 6.46 to 4.77 cm) in the 1-week-old, 1-year-old, 2-5-year-old and 5-10-year-old boys, respectively. Subgroup analysis for those aged >2 years showed significant variations by geographical region (P < 0.001). CONCLUSIONS: The present study observed large variations in penile length across geographical regions and among prepubescent boys of different ages, while also suggesting a possible decline over the past two decades.

Humans↗

PubMed2026

Combined Effects of Nicorandil and Enhanced External Counterpulsation on Coronary Microcirculation and Exercise Capacity in Patients With Coronary Slow Flow Phenomenon: A Randomized, Controlled, 3-Arm Trial.

PURPOSE: To evaluate the combined efficacy and safety of combined nicorandil and enhanced external counterpulsation (EECP) therapy compared with respective monotherapies in patients with coronary slow flow phenomenon (CSFP). METHODS: In this prospective, randomized, 3-arm clinical trial, 309 patients with angiographically defined CSFP based on corrected TIMI frame count were assigned (1:1:1) to the Nicorandil group (N group, n = 103), the EECP group (E group, n = 103), or the Combined therapy group (N+E group, n = 103). The trial was prospectively registered at ClinicalTrials.gov (NCT07534410). IMR and CFR were measured to characterize coronary microvascular physiological status and treatment response. The primary endpoint was corrected TFC at 6 months. Key secondary endpoints included invasive physiological indices (IMR and CFR), Seattle Angina Questionnaire scores, 6-minute walk test (6MWT) distance, peak oxygen uptake via cardiopulmonary exercise testing, and the 12-month rate of re-hospitalization due to recurrent angina. FINDINGS: At 6 months, the N+E group demonstrated superior improvement in coronary hemodynamics compared to the N and E monotherapy groups, with significantly lower TFC (30.4 ± 3.5 vs 38.2 ± 3.8 and 37.5 ± 4.0, respectively; P < 0.001) and IMR (21.2 ± 2.8 vs 28.4 ± 3.2 and 27.6 ± 3.5, respectively; P < 0.001). Clinical symptoms and functional capacity showed the most substantial gains in the N+E group, with significantly higher Seattle Angina Questionnaire angina frequency scores (87.5 ± 8.8) and 6MWT distances (506.8 ± 41.8 m) compared to monotherapy groups (all P < 0.001). Furthermore, peak oxygen uptake in the N+E group increased to 23.5 ± 2.6 mL/kg/min, significantly outperforming the N and E groups (P < 0.001). During the 12-month follow-up, the observed rate of re-hospitalization due to recurrent angina was lower in the N+E group (5.8%) than in the N group (17.5%, P = 0.017), although this clinical outcome should be interpreted cautiously because the trial was powered primarily for physiological endpoints. No significant differences were observed in the incidence of adverse reactions among the 3 groups (P = 0.954). IMPLICATIONS: For patients with CSFP, the combination of Nicorandil and EECP improved coronary microvascular function, anginal symptoms, and objective exercise tolerance more effectively than either active monotherapy. The lower observed rate of angina-related re-hospitalization suggests a potential clinical benefit, but this finding should be considered exploratory and requires confirmation in trials adequately powered for clinical outcomes.

Humans↗

PubMed2026

Machine learning vs. traditional methods for predicting postoperative cardiac complications after non-cardiac surgery: a systematic review and Bayesian network meta-analysis.

INTRODUCTION: Accurate prediction of peri-operative cardiac complications is critical to optimise pre-operative decision-making. Traditional risk prediction scores, such as the Revised Cardiac Risk Index, show only modest discrimination. Machine learning can model complex, non-linear relationships but their predictive performance compared with traditional scores remains unclear. METHODS: We performed a systematic review and Bayesian network meta-analysis. The primary outcome was postoperative adverse cardiac events following non-cardiac surgery. Prediction models were assessed relative to the Revised Cardiac Risk Index. As many studies evaluated multiple versions of each model type, the highest performing ('best version') and lowest performing ('worst version') results were analysed. Models were ranked using the surface under the cumulative ranking curve (SUCRA). RESULTS: Thirteen studies evaluating 54 models and 927,113 patients were included. Machine learning approaches generally outperformed traditional risk scores. Automated machine learning ranked highest (SUCRA 96.6) showed the greatest improvement in the best version analysis (mean difference (MD) 0.28 (95%CrI 0.16-0.40)) and remained superior in the sensitivity analysis (MD 0.30 (95%CrI 0.14-0.45)). Gradient boosting models showed superior performance over the Revised Cardiac Risk Index across analysis (best version: MD 0.20 (95%CrI 0.14-0.26), worst version: MD 0.18 (95%CrI 0.12-0.25), SUCRA 82.4). The Gupta Perioperative Risk for Myocardial Infarction or Cardiac Arrest score outperformed the Revised Cardiac Risk Index in the best version analysis (MD 0.16 (95%CrI 0.01-0.32)). Between-study heterogeneity was low. None of the included studies externally validated their machine learning models and only six were judged to be at low risk of bias. DISCUSSION: Most machine learning models showed better discrimination than traditional risk scores, with automated machine learning and gradient boosting models ranking highest. However, study quality, calibration reporting and absence of external validation limit immediate clinical adoption. Prospective, multicentre evaluation is required before integration of these models into peri-operative practice.

Humans↗

PubMed2026

External ventricular drain safety campaign and opportunities for global neuroanesthesiology quality and safety.

PURPOSE OF REVIEW: This review describes the conceptualization and implementation of the External Ventricular Drain (EVD) Safety Campaign, a global patient safety initiative by the Society for Neuroscience in Anesthesiology and Critical Care. It summarizes recent literature on EVD insertion and maintenance, highlights opportunities to advance quality and safety in neuroanesthesiology, and outlines priorities and a framework for future work. RECENT FINDINGS: The Society for Neuroscience in Anesthesiology and Critical Care launched a global initiative to improve EVD management. EVD insertion and maintenance remain key areas of ongoing research and quality improvement, particularly in reducing complications. SUMMARY: The EVD Safety Campaign provides a structured framework to improve care delivery and patient outcomes worldwide. Continued focus on standardization, education, and complication reduction, especially infection prevention, will be essential to advancing the field.

Humans↗

PubMed2026

External load metrics and monitoring in women's football match play: A systematic review.

This systematic review aimed to identify the most commonly used variables for monitoring external load during elite women's football matches and to compare reporting practices internationally and in Brazil. Searches were conducted in Web of Science, PubMed, and SciELO using the PICOS framework between February and March 2026, resulting in the inclusion of 35 studies. The main outcomes analysed were total distance covered (TD), distance covered across speed zones (HSR, VHSR, sprint), number of accelerations and decelerations, and maximum speed. TD and distance covered across speed zones were the most frequently reported indicators (94.3%), followed by HSR (82.8%) and sprint distance (68.5%). Considerable variability was observed in the classification of speed zones and thresholds used to define accelerations and decelerations, limiting comparisons between studies. External load values varied according to playing position and competition level, with international matches generally imposing greater demands than national competitions. Brazilian research remains limited and demonstrates notable methodological variability. This review proposes standardised speed and acceleration/deceleration thresholds based on the most recurrent ranges reported in the literature, supporting improved consistency in monitoring practices across elite women's football contexts.

Humans↗

PubMed2026

Externally validated risk prediction models for gestational diabetes mellitus: A systematic review and meta-analysis.

INTRODUCTION: Risk prediction models for gestational diabetes mellitus (GDM) offer potential for early identification and targeted prevention. External validation is crucial to assess model performance across diverse populations. Despite the availability of numerous GDM prediction models, limited evidence exists on their external validation frequency, methodological quality, and clinical applicability. This systematic review evaluated externally validated GDM prediction models, focusing on methodological rigor, reporting standards, and clinical relevance to inform future research and implementation. MATERIAL AND METHODS: Databases including Ovid MEDLINE, Embase, Scopus, Emcare, and CINAHL were searched up to May 1, 2025. Studies reporting external validation of GDM risk prediction models were included. Two reviewers independently screened studies. Data were extracted using the CHARMS framework, and risk of bias and applicability were assessed using PROBAST+AI. The study protocol was registered in the International Prospective Register of Systematic Reviews (PROSPERO; CRD420251125758). RESULTS: Twenty-six studies validated 33 models, with validation sample sizes ranging from 50 to 75 161. Over half used the IADPSG criteria to define GDM. Discrimination metrics were commonly reported, but calibration, overall performance, and clinical utility were often lacking. Meta-analysis was feasible for only four models: Teede et al., Nanda et al., Naylor et al., and Van Leeuwen et al., each showing fair discrimination. The Teede et al. model was the most widely validated, with 11 external validations across six continents and a pooled AUC of 0.72 (95% CI: 0.67-0.76). Despite fewer validations, the Nanda et al. model achieved the highest pooled discrimination (5 validations; pooled AUC 0.77, 95% CI: 0.74-0.80). The Naylor et al. and van Leeuwen et al. models also underwent meta-analysis, as sufficient external validation studies were available to support comparative performance assessment. Notably, 69.23% of studies had a high risk of bias. CONCLUSIONS: While many models showed acceptable predictive performance, most validations were methodologically weak. Future studies should follow best-practice guidelines and promote scalable validation strategies, such as algorithm sharing, to enhance clinical utility.

Humans↗

PubMed2026

A clinical study on the efficacy of rectal administration of Tongfu Qinghua decoction combined with external application of Ruyi Jinhuang powder in treating acute pancreatitis.

BACKGROUND: Acute pancreatitis (AP) is a common acute abdominal disease with high mortality in moderate and severe cases. Integrated Chinese and Western medicine therapy has promising clinical application prospects. OBJECTIVES: This study investigated the efficacy and safety of Tongfu Qinghua decoction enema combined with Ruyi Jinhuang powder external application for AP and its therapeutic effects across different age groups. METHODS: A total of 100 AP patients from October 2023 to August 2025 were randomly divided into observation and control groups (50 cases each). The control group received conventional Western medicine and the observation group received additional combined Chinese medicine therapy. Outcomes including hospital stay, symptom relief, inflammatory and pancreatic injury markers, clinical efficacy and adverse reactions were compared, with subgroup analysis of patients aged 18-40, 41-60 and 61-75 years. RESULTS: The observation group had significantly shorter hospital stay, faster symptom relief and gastrointestinal recovery (P<0.05). Post-treatment inflammatory and pancreatic markers improved significantly and the total effective rate was higher (P<0.05), with no significant difference in adverse reactions (P>0.05). Benefits were consistent across all age subgroups, with younger patients recovering faster and elderly patients still achieving significant improvement. CONCLUSION: This combined therapy is effective and safe for AP patients aged 18-75 years, significantly improving clinical outcomes and worthy of clinical promotion.

Humans↗

PubMed2026

Role of External Vibratory Lithoclast (Lithecbole) in Improving Lower Pole Stone Clearance After Extracorporeal Shock Wave Lithotripsy (ESWL).

Background and Objective: Extracorporeal shock wave lithotripsy (ESWL) is a widely used non-invasive treatment for renal stones. However, its effectiveness in clearing stones located in the lower pole of the kidney is often limited due to the anatomical challenges that impede the spontaneous passage of fragmented stones. This study evaluate the efficacy and safety of External Physical Vibration Lithecbole (EPVL) when used as an adjunctive therapy following ESWL in patients with lower pole renal stones, with a focus on improving stone clearance rates. Materials and Methods: This prospective interventional study was conducted at Al Yarmouk Teaching Hospital over two years and included 100 patients with 10-15 mm lower pole renal stones. Patients were randomized into two groups: The ESWL alone and ESWL plus EPVL. All patients received two ESWL sessions (3000 shocks/session). The treatment group additionally received EPVL therapy using a flank-applied vibration device. Follow-up was performed using ultrasound and KUB radiography. Statistical analysis was conducted using appropriate tests with significance set at p<0.05. Results: Baseline characteristics, including age, gender, weight, stone size and location, were statistically comparable between groups. The mean stone size was 12.4±1.7 mm. A significantly higher stone-free rate was observed in the ESWL+EPVL group compared to the ESWL-only group (66% vs. 48%, p = 0.027). Although the residual stone size showed a numerical difference favoring EPVL, it was not statistically significant (p = 0.11). Complication rates were low, mild and similar in both groups (p = 0.3). Logistic regression analysis revealed that smaller stone size (p<0.001) and lower patient weight (p = 0.030) were significantly associated with successful stone clearance. Subgroup analysis further confirmed that patients with stones <11 mm or a weight <70 kg had the highest stone-free rates. Conclusion: In this initial evaluation, EPVL demonstrated a safe and effective adjunct to ESWL in enhancing stone clearance for lower-pole renal stones. Its application was associated with improved treatment outcomes without increasing complication rates. Further studies with extended EPVL sessions and longer follow-up are warranted.

Humans↗

PubMed2026

The effect of hip abductor or external rotator strength on dynamic knee valgus in healthy subjects-a systematic review with partial meta-analysis.

BACKGROUND: Weak hip abductors and external rotators (ER) have long been suggested to cause increased dynamic knee valgus. Patients are often prescribed strengthening of these muscles with the expectation that it will reduce their risk of pain and injury. The validity of this claim remains unclear. METHOD: We conducted a systematic review and partial meta-analysis assessing the association between hip strength and knee valgus in healthy subjects. An online search was conducted in May 2026. Databases included Medline, EMBASE, CINAHL and Google Scholar. INCLUSION CRITERIA: English language, asymptomatic subjects, dynamometric hip strength, single or multi-camera kinematic analysis, and statistical tests of difference or correlations between hip abductor or ER strength and dynamic valgus. Data were extracted concerning study design, subject characteristics, relevant outcome measures and statistics. RESULTS: 22 papers qualified for inclusion. Hip abductor correlations: 12 papers found no significant correlation, 2 supported the hypothesis and 2 found evidence contrary. Hip ER correlations: 8 papers found no significant correlation, 2 supported the hypothesis and 2 were contrary. Group differences for hip abduction strength: 3 papers found no difference, 2 found significant differences in support of the hypothesis, 1 found significant difference to contrary. Group differences for ER strength: 1 paper found no significant difference. None of the partial meta-analyses achieved statistical significance. CONCLUSION: Weakness in hip abductors or external rotators may not result in increased dynamic knee valgus in healthy subjects. While continued research may further illuminate our understanding, we discuss alternative explanations.

Humans↗

PubMed2026

Advanced/Novel Stenting for Pediatric Dynamic Airway Collapse.

Pediatric dynamic airway collapse is a complex condition that can impact all levels of the pediatric airway. These conditions can pose life threatening risk to pediatric patients and carry lasting impacts. While traditionally, tracheostomy has been used to address all levels of dynamic collapse, recent advances have allowed for more individualized, anatomy-specific stenting and splinting strategies for treatment. This article covers pathophysiology and the latest evidence on strategies to address nasopharyngeal, oropharyngeal, proximal trachea, and tracheobronchial dynamic collapse.

Humans↗

PubMed2026

ALID score for treatment-effect heterogeneity of adjunctive low-voltage area ablation in persistent atrial fibrillation: A post hoc analysis of SUPPRESS-AF.

BACKGROUND: In persistent atrial fibrillation (AF), the incremental benefit of adjunctive low-voltage area (LVA) ablation beyond pulmonary vein isolation (PVI) remains inconsistent. OBJECTIVE: To examine whether a simple clinical score characterizes treatment-effect heterogeneity of adjunctive LVA ablation among patients with mapped LVA > 5 cm2 and to perform an exploratory supportive analysis in an independent randomized cohort. METHODS: In this post-hoc analysis of SUPPRESS-AF, which included patients with persistent AF and mapped LVA > 5 cm2 after PVI, four variables-age ≥ 75 years, left atrial diameter > 44 mm, estimated glomerular filtration rate < 60 mL/min/1.73 m2, and absence of diabetes-were combined into the ALID score (0-4). Patients were stratified into low (0-1), intermediate (2), and high (3-4) score groups. Because EARNEST-PVI did not use LVA-guided ablation or select patients based on mapped LVA, it was analyzed as an exploratory supportive cohort rather than as an external validation cohort. RESULTS: In SUPPRESS-AF (n = 336), a significant treatment-by-score interaction was observed (P < 0.001). Adjunctive LVA ablation was associated with increased recurrence in the low-score stratum (HR 3.92; 95% CI 1.50-10.20) and reduced recurrence in the high-score stratum (HR 0.48; 95% CI 0.26-0.86). In EARNEST-PVI (n = 494), a qualitatively similar interaction pattern was observed for additional ablation beyond PVI (interaction P = 0.029), although the ablation strategy differed from LVA-guided ablation. CONCLUSIONS: Among patients with persistent AF and mapped LVA >5 cm2, the ALID score identified heterogeneity in response to adjunctive LVA ablation. These hypothesis-generating findings require prospective validation before clinical implementation.

Humans↗

PubMed2026

Meniscal preservation in the age of biologics: toward a quantitative decision algorithm for personalized repair.

BACKGROUND: Despite advances in arthroscopic repair and biologic augmentation, surgical indication for meniscal tears remains heterogeneous. No standardized framework currently integrates biomechanical, clinical, and biological determinants to guide repair versus resection. PURPOSE: To develop a quantitative decision model-the Meniscal Preservation Score (MPS)-that unifies biomechanical and biological evidence to stratify reparability potential and standardize treatment selection in meniscal surgery. METHODS: A systematic evidence synthesis conducted in accordance with PRISMA 2020 reporting standards of studies published from 2000 to 2025 in PubMed, Embase, and Scopus identified key determinants of meniscal healing. Five consistent predictors-patient age, vascularity, tear morphology, associated pathology, and activity profile-were weighted through a two-round modified Delphi consensus among ten experienced knee surgeons. The resulting 0-9-point MPS was incorporated into a stepwise decision tree linking lesion morphology, biological context, and surgical strategy. Conceptual validation used 50 simulated cases and a retrospective cohort of 45 patients to test agreement between algorithm recommendations and expert surgical decisions. RESULTS: The MPS achieved 86% concordance with expert judgment in simulation and 84% agreement in clinical validation. In this retrospective exploratory cohort, cases in which surgical management was concordant with MPS recommendations demonstrated higher mean IKDC scores at 24 months and lower observed reoperation rates. These findings should be interpreted as associative rather than causal, as treatment allocation was not controlled and discordant cases may have represented inherently more complex pathology. CONCLUSION: The MPS represents an evidence-informed decision-support framework designed to systematize reparability assessment. While exploratory analyses suggest structural coherence with expert reasoning, prospective implementation and external validation are required before clinical adoption as a predictive tool. LEVEL OF EVIDENCE: conceptual model with exploratory validation.

Humans↗

PubMed2026

Data-centric, robust, and explainable multimodal deep learning for clinical decision support: A systematic review.

PURPOSE: Multimodal deep learning is increasingly proposed for clinical decision support (CDS) under a "data-centric" framing that prioritizes label quality, missing-modality robustness, distribution shift, calibration, and explainability. Prior reviews have examined multimodal medical AI, CDS, and data-centric methods separately, but none address their intersection. We mapped the modalities, fusion strategies, and data-centric and explainability techniques used in this recent literature, quantified how often each is implemented rather than merely mentioned, assessed deployment-relevant evidence (external validation, clinical-outcome measurement, equity), and formally appraised study-level risk of bias. METHODS: Following the PRISMA 2020 statement (PROSPERO CRD420261427815; registered retrospectively), we screened 150 records and included primary, clinical, multimodal studies that applied machine or deep learning to a decision-support task and reported at least one quantitative result. Two reviewers screened and extracted data with consensus adjudication. Each study was coded against pre-specified operational definitions, separating implemented or empirically evaluated techniques from those only mentioned. Study-level risk of bias was assessed with PROBAST + AI. Synthesis was narrative. RESULTS: Thirty-one studies met inclusion; 30 (97%) were published between 2024 and 2026, with a median of three modalities (range 2-6), most commonly structured EHR (71%) and imaging (39%). Data-centric techniques were frequently reported (74-84% across label-noise, distribution-shift, calibration, missing-modality and class-imbalance handling; equity 61%). However, external validation was reported in only 4/31 studies (13%), a clinical or provider outcome in 3/31 (10%), and no study reported routine deployment. Overall risk of bias was high in 27/31 studies (87%), driven by the analysis domain. CONCLUSION: Within this recent, self-selected slice of the field, technical robustness and explainability techniques are widely reported but rarely validated out-of-distribution or against clinical outcomes, and the underlying evidence is at high risk of bias. Progress requires external multi-site validation, clinical-outcome measurement, formal bias appraisal, and adherence to AI reporting standards (e.g., TRIPOD + AI) before deployment can be justified.

Deep Learning↗

PubMed2026

Diagnostic performance of machine learning models for malignant and non-malignant pleural effusion: Systematic review and meta-analysis.

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.

Humans↗

PubMed2026

The Effect of Game-Based Virtual Reality Rehabilitation and Its Impact on Upper Extremity Function After Arthroscopic Rotator Cuff Repair: A Randomized Controlled Trial.

BACKGROUND: Arthroscopic rotator cuff repair (ARCR) often results in prolonged recovery and limited shoulder function. Conventional physical therapy rehabilitation programs require sustained patient engagement; however, adherence is frequently low. Game-based virtual reality (VR) offers an interactive and engaging environment that may enhance rehabilitation outcomes. OBJECTIVE: To evaluate the effect of a game-based VR program on the function of the upper limb in patients following ARCR. METHODS: A randomized controlled trial was conducted with patients who underwent ARCR. Participants were randomized into two groups: game-based VR or conventional rehabilitation. Outcomes were evaluated using the Disabilities of the Arm, Shoulder and Hand score, pain severity by the Numerical Pain Rating Scale, range of motion measures, and muscle strength testing. Assessments were performed at baseline and at 6 weeks and 12 weeks post surgery. RESULTS: Results have shown significant within-group improvements in pain, function, range of motion, and isometric muscle strength across all time points (P < 0.05). Between-group analysis revealed greater improvements in pain, function, flexion range, and abduction and external rotation strength in the experimental group at both time points (P < 0.05). Abduction range improved significantly only at 12 weeks (P = 0.02), whereas external rotation range showed no significant difference between groups at either time point (P > 0.05). CONCLUSION: The findings indicate that integrating game-based VR rehabilitation provides additional benefits over conventional therapy in improving pain and upper extremity function following ARCR. These findings support the use of VR as an effective alternative to the conventional rehabilitation for postoperative rehabilitation.

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↗