SEARCH · Search PubMed

Results for “external ventricular drain”

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.

73 records · Page 2Linked to original sources

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

Meta-analysis of prostacyclin therapy for persistent pulmonary hypertension with congenital diaphragmatic hernia.

OBJECTIVE: To evaluate the efficacy and safety of prostacyclin in the treatment of persistent pulmonary hypertension in congenital diaphragmatic hernia. METHODS: A systematic literature search was conducted in four main databases (PubMed, Web of Science, EMBASE, and the Cochrane Central Register of Controlled Trials (CENTRAL). The protocol was registered in advance in the International Prospective of Systematic Reviews (CRD420261325458). RESULTS: A total of nine studies were included involving a total of 7009 infants in this systematic review and meta-analysis. GRADE assessment revealed substantial heterogeneity in the quality of evidence across outcomes, with most outcomes rated very low quality and only one rated moderate quality. Studies were performed meta-analysis, which showed the use of prostacylin resulted a statistically significant decrease in the OI compared to the control group (Mean Difference (MD), 9.34; I2 0%; p < 0.00001), no statistically significant in mortality (OR, 0.83; I2 84%; p = 0.70), ECMO (OR = 4.9; I2 98%; p = 0.27), BNP (std MD, 6.98; I2 98%; p = 0.31), FiO2 (SMD = 8.0;, I2 64%; p = 0.11), Systolic orientation of IVS curvature (SMD = 0.69; I2 97%; p = 0.32), Diastolic orientation of IVS differences (MD = 0.62; I2 93% p = 0.26). After applying the Hartung-Knapp adjustment, with the exception of BNP, the pooled effects of the other outcomes were not statistically significant, and there was high heterogeneity in measures such as ECMO and ventricular septal curvature. CONCLUSION: In conclusion, this meta-analysis has confirmed that prostacyclin may temporarily improve oxygenation. However, after applying the Hartung-Knapp adjustment, with the exception of BNP, the pooled effects of the other outcomes were not statistically significant, and there was high heterogeneity in measures such as ECMO and ventricular septal curvature. Further validation through high-quality studies are still needed. TRIAL REGISTRATION: PROSPERO: CRD420261325458.

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

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

Nurse-Led Home-Based Mobile Health Cardiac Rehabilitation Program for Patients With Chronic Heart Failure: A Randomized Controlled Trial.

This 12-week randomized controlled trial evaluated a nurse-led mHealth intervention for patients with chronic heart failure, conceptually informed by Riegel's middle-range theory of self-care of chronic illness. The program integrated wearable activity tracking with weekly nurse-led behavioral coaching, reflecting the core self-care processes of monitoring, maintenance, and management. Compared with usual care, the intervention significantly improved daily step count, 6-minute walk distance, metabolic equivalents, and left ventricular ejection fraction. Findings highlight the effectiveness of theory-informed, nurse-delivered mHealth strategies in enhancing physical activity and cardiopulmonary function, while underscoring the critical role of advanced practice nurses in home-based chronic disease management.

Aged↗

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

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

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

Humans↗

PubMed2026

Not just when, but how: An exploratory dual-control approach to video feedback in motor learning.

The present study provides exploratory evidence for a novel dual-control paradigm. It examines whether combining temporal over video feedback timing with learner-controlled interactive playback functions (pause, slow-motion, rewind) would enhance motor skill acquisition beyond temporal autonomy alone. Sixty-four novice adults were randomly assigned to one of four conditions: Full Control (self-controlled timing + interactive replay), Partial Control (self-controlled timing + non-interactive replay), Yoked Full Control (externally controlled timing + interactive replay), or Yoked Partial Control (externally controlled timing + non-interactive replay). Motor accuracy (Radial Error), movement consistency (Bivariate Variable Error), technical execution, and self-efficacy were assessed at pre-test, 24-h retention, and 72-h retention following two acquisition sessions on a dart-throwing task (120 trials total). The Full Control group demonstrated the greatest and most durable learning gains across all outcomes. The Group × Time interaction was significant across all dependent variables (η2ₚ ranging from 0.140 to 0.234), with Full Control demonstrating superior retention at both 24 and 72 h relative to other groups (though differences relative to Partial Control were more pronounced at 72-h retention). Critically, the Yoked Full Control group showed comparatively weaker outcomes despite access to the same interactive playback functions. These findings suggest that interactive video tools may be most useful when learners can regulate both when feedback is accessed and how it is inspected. Theoretical and practical implications for the design of learner-centered video feedback systems are discussed.

Humans↗

PubMed2026

Non-parametric differential methylation analysis characterizes histotype-specific promoter regions in epithelial ovarian cancer.

Epithelial ovarian cancer (EOC) is a heterogenous disease with frequent late-stage diagnosis and high mortality rates, for which no reliable screening tests exist. In recent years, epigenetic biomarkers in the form of DNA methylation in CpG-rich regions have gained increased attention in the scientific community due to their robust nature and accessibility, allowing for diagnosis without the need for invasive surgery. In this study, we investigated the aberrant methylation of promoter regions in early stage EOC through non-parametric methods, with the purpose of characterizing candidate epigenetic biomarkers. The approach was used on a cohort of early stage EOC samples, and results were compared to existing programs for differential methylation. Significant regions were then used to construct a CpG panel for stratifying EOC histotypes through predictive classification in external data. Identified promoter regions were highly reproducible across cohorts, and the constructed CpG model stratified histotypes in external cohorts through predictive classification. Comparisons against other DMP and DMR callers showed a degree of homogeneity between results but also revealed promoter regions that were overlooked despite clear signs of aberrant methylation. Finally, EOC histotypes were found to differ in their methylation distribution types, and results indicate that methods sensitive to non-normally distributed data may be poorly suited to compare groups with different distribution types. The non-parametric approach identified aberrantly methylated promoter regions that were highly reproducible across cohorts. Results from predictive classification indicate that these regions may be useful for the purpose of EOC histotype stratification.

Humans↗

PubMed2026

New Evidence in Heart Failure: 2026 Update.

Heart failure (HF) remains a major cause of morbidity, mortality, impaired quality of life and healthcare expenditure worldwide. The global burden of HF continues to increase due to population aging, improved survival, and the growing prevalence of cardiovascular, renal, and metabolic comorbidities. Simultaneously, the pace of scientific progress in HF has accelerated considerably. Recent advances have refined our understanding of HF epidemiology, prognosis, and disease trajectories, including emerging concepts of HF improvement, remission, and recovery. The Second Universal Definition of HF has also updated the classification framework, moving beyond the traditional ejection fraction-based categories. HF is now broadly classified into two major phenotypes: heart failure with reduced ejection fraction (HFrEF) and heart failure with preserved ejection fraction (HFpEF). Novel mechanistic insights highlight the role of inflammation, immune activation, metabolic dysfunction, mitochondrial biology, and multisystem interactions in HF progression. There has also been significant progress in the characterization and management of major comorbidities, including chronic kidney disease (CKD), diabetes, obesity, atrial fibrillation (AF), pulmonary hypertension, frailty, malnutrition, and cancer. Diagnostic innovations include novel biomarkers, multi-omics technologies, artificial intelligence-based approaches, advanced imaging techniques, congestion assessment tools, and emerging digital health solutions. Important advances have occurred in specific HF aetiologies, including cardiomyopathies, cardiac amyloidosis (CA), myocarditis, arrhythmia-induced cardiomyopathy (AiCM), and Chagas cardiomyopathy. Therapeutic developments continue to reshape HF management across the spectrum of left ventricular ejection fraction. Recent evidence has focused on optimization of guideline-directed medical therapy in HFrEF, expansion of evidence-based therapies in HFpEF, and growing roles for sodium-glucose cotransporter-2 inhibitors, finerenone, incretin-based therapies, and transcatheter valve interventions. Collectively, these advances support the transition from a predominantly phenotype-based approach towards a more personalized and biologically informed model of HF care, with the potential to further improve outcomes across the entire HF spectrum.

Journal Article↗

PubMed2026

Identification Matters: How Data Sharing Affects Pupil Honesty and Engagement in Universal School Well-Being Assessments.

PURPOSE: Universal well-being assessments in schools may support early identification of pupils needing mental health support. However, little is known about how privacy and confidentiality concerns influence pupils' acceptability of assessments and willingness to engage authentically. This study examined how hypothetical identification, where responses are linked to pupils and shared with key stakeholders, affects pupils' anticipated honesty and engagement, and whether known help-seeking barriers predict negative responses. METHODS: Cross-sectional data were collected from 12,377 primary (ages 8-10) and secondary pupils (ages 11-17) across 55 schools in England. Pupils reported whether their responses would change if identifiable and shared with school staff, parents/guardians, or external professionals. Responses indicating reduced honesty or likelihood of disengagement were coded as negative. Predictors were examined using mixed-effects logistic regression models, including demographics, school connectedness, and mental well-being. RESULTS: Identification and data sharing influenced pupils' anticipated engagement, particularly in secondary schools. Identification by school staff elicited the highest proportion of negative responses in both phases, whereas external professionals elicited the fewest. Most primary pupils reported they would respond authentically, while a larger proportion of secondary pupils indicated they would respond less honestly or disengage when responses were identifiable and shared. Across primary and secondary samples, low well-being, low school connectedness, and being female were associated with greater likelihood of negative response. DISCUSSION: Pupils' anticipated engagement with well-being assessments is shaped by who accesses their data, with marked developmental differences. Strengthening trust, privacy, and connectedness, and supporting pupils' autonomy, may improve the acceptability and response accuracy.

Humans↗

PubMed2026

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

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

Humans↗

PubMed2026

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

Incidence of silent cerebral lesions during pulsed field ablation for paroxysmal atrial fibrillation.

BACKGROUND: Radiofrequency catheter ablation (RFCA) is a first-line treatment for paroxysmal atrial fibrillation (PAF). Complications such as silent cerebral lesion (SCL) may occur during ablation. Pulsed field ablation (PFA) is a non-thermal method thatablates cardiac tissue via irreversible electroporation. Limited studies have reported the incidence of SCL during PFA, with highly variable results. However, randomized controlled trials (RCTs) remain scarce. The objective of this study was to compare perioperative SCL incidence between PFA and RFCA, and to identify risk factors for SCL during PFA. METHODS: In this prospective pilot RCT (ChiCTR2400088774), 62 patients with PAF were randomized 1:1 to undergo PFA or RFCA. Cerebral MRI (3.0 T) was performed preoperatively and 24-48h postoperatively. SCL was defined as a new acute brain lesion on MRI without neurological deficits. Baseline and surgical data of the patients were collected. RESULTS: SCL was detected post-procedure in 6.45% (2/31) in the RFCA group, 12.90% (4/31) in the PFA group. No statistically significant difference in the incidence of postoperative SCL was detected between the two groups (p = 0.67). Left atrium dimension (LAD), left atrial operation time (LAOT), left ventricular end-diastolic dimension (LVEDD), and total operation time (TOT) were significantly higher in SCL group than those in no-SCL group (p < 0.05) through univariate analyses. CONCLUSIONS: SCL incidence was 12.90% in the PFA group versus 6.45% in the RFCA group. While no statistically significant difference was detected between two groups, the numerically higher rate in the PFA group warrants larger studies to evaluate cerebral safety associated with PFA.

Humans↗

PubMed2026

Empagliflozin and functional aerobic capacity in individuals with increased risk of heart failure: The Empire Prevent Cardiac trial.

BACKGROUND: Higher maximal oxygen consumption (VO₂ max) is associated with lower risk of developing heart failure (HF). Empagliflozin improves VO2 max in HF with reduced ejection fraction, but the effect on VO2 max in individuals at risk of HF remain unknown. OBJECTIVE: This study aimed to evaluate the effect of 180 days treatment with empagliflozin compared to placebo on VO2 max, daily physical activity level, and quality of life (QoL) in individuals with overweight or obesity and risk of HF. METHOD: This investigator-initiated, double-blinded, randomized, placebo-controlled, multicenter trial included elderly individuals with body mass index >28 kg/m2 and at least one additional risk factor for HF, including hypertension, ischemic heart disease, stroke, or chronic kidney disease. Individuals with HF or type 2 diabetes mellitus were excluded. The primary endpoint was the mean difference in change of VO2 max. The secondary outcome was objectively measured physical activity level. QoL was an explorative outcome. RESULTS: Among 191 randomized individuals (94 empagliflozin, 97 placebo), 89% had hypertension and 66% ischemic heart disease. At baseline, 69% were male, median age was 68 years, median body mass index 31.9 kg/m², mean left ventricular ejection fraction 65 ± 9%, and mean VO₂ max 18.1 ± 4.3 mL/min/kg. Empagliflozin did not change VO2 max with an estimated treatment difference of -0.2 mL/min/kg (97.5% confidence interval -1.2 to 0.8), adjusted P = 1.00. No significant treatment differences were observed for neither daily physical activity nor QoL. CONCLUSIONS: Empagliflozin did not affect VO2 max, physical activity level, or QoL in elderly individuals with overweight or obesity and risk of HF.

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

Predicting ACL injury risk in athletes: A systematic review of machine learning-based models.

BACKGROUND: Early ACL injury risk identification in athletes is essential. This systematic review examines machine learning (ML) models for predicting ACL injuries, evaluating their methodological quality, performance, and reliability. METHOD: A comprehensive electronic search was conducted across PubMed, Scopus, Web of Science, and IEEE Xplore databases, supplemented by Google Scholar for grey literature, covering articles published between January 1, 2015, and August 30, 2025. Eligible studies were appraised using the Prediction Model Study Risk of Bias Assessment Tool (PROBAST) for methodological quality and risk of bias, and the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) guidelines for quality of evidence. RESULTS: Ten studies were included. PROBAST showed eight studies had moderate risk of bias and two low risk. TRIPOD found only two studies met quality criteria. ML models included logistic regression (n = 5), support vector machines (n = 4), k-nearest neighbor (n = 3), decision trees (n = 3), random forests (n = 5), neural networks (n = 2), linear discriminant analysis (n = 1), and pre-trained CNNs (n = 1). AUC ranged from 0.63 to 0.98. Accuracy (reported in six studies) ranged from 26% to 95%; however, these values should be interpreted with caution due to the absence of confidence intervals, lack of class imbalance handling, and limited external validation across studies. Tree-based ensemble methods such as random forest achieved competitive accuracy (74-86%), while SVM, a non-ensemble classifier, reported accuracy ranging from 71% to 95%; however, the highest values were obtained in studies with notably small sample sizes (n = 12 to n = 39), raising concerns about overfitting and generalizability. CONCLUSION: Current ML algorithms show promise for identifying athletes at high ACL injury risk and detecting relevant risk factors. Although study quality was generally satisfactory, future research should prioritize external validation and model interpretability to support clinical translation.

Humans↗