Research Appraisals
Evidence-based critical appraisals of the latest medical research, systematically evaluated using Oxford CEBM methodology.
Showing 10 appraisals
Sleep medicine reviews
Artificial intelligence in sleep medicine I: Diagnosis, treatment, care, and research
Artificial intelligence (AI) is transforming sleep medicine (SM) through improved diagnostics, therapeutics, and research. AI enhances diagnostic accuracy, treatment personalization, workflow efficiency. However, implementation requires careful validation and oversight. This review explores AI applications across the sleep disorders spectrum. AI in diagnostic SM covers applications including polysomnography and home sleep testing. We examine how AI detects early neurodegenerative changes in REM sleep behavior disorder, identify novel biomarkers, and optimize chronotherapeutic timing. Wearables complement these advances by continuously monitoring sleep patterns, movement and physiological signals in natural settings, generating rich datasets ideal for AI analysis. In therapeutics, machine learning models enhance sleep apnea phenotyping, enabling precise treatment selection, and improve CPAP adherence prediction. AI helps identify biomarkers to optimize the timing of chronotherapeutic interventions. In medical care, natural language processing facilitates unstructured clinical chart data extraction. Implementation challenges include data standardization, algorithmic bias, and the "generalization gap." We provide a structured framework for clinical implementation, emphasizing validation requirements and ethical considerations. Large datasets using routine clinical care, cohort studies, and wearable derived data create vast amounts of data. In return, AI tools and methodologies enhance and expand development of phenotypes and endotypes with the final goal of personalized and precision SM.
2 Aug 2026
Read appraisal →Clinical infectious diseases : an official publication of the Infectious Diseases Society of America
Shorter Antitubercular Regimens Versus 9 Months of Isoniazid for Latent Tuberculosis in Children: A Systematic Review and Meta-Analysis
BACKGROUND: We conducted a systematic review and meta-analysis to compare effectiveness and safety of 9 months of isoniazid (9H) versus shorter rifamycin-containing regimens for treating latent tuberculosis infection (TBI) in children. METHODS: We systematically searched MEDLINE, Embase, and Cochrane Central Register of Controlled Trials to June 2025 for randomized, controlled trials (RCTs) and cohort studies that compared regimens that were shorter than 9 months of isoniazid in children aged 1-18 years. Outcomes were development of TB disease, treatment completion, and adverse events. Risk of bias was assessed using RoB 2.0 and the Risk Of Bias In Non-Randomized Studies - of Interventions (ROBINS-I) tool; certainty of evidence was graded using Grading of Recommendations Assessment, Development, and Evaluation (GRADE). RESULTS: Five RCTs and 7 nonrandomized studies that enrolled approximately 2950 children in trials and >25 000 in observational cohorts were included. In pooled analysis of 3 RCTs, shorter rifamycin-containing regimens resulted in little to no difference in development of TB disease compared with 9H (odds ratio [OR], 0.19; 95% confidence interval [CI], .03-1.12; moderate-certainty evidence). Treatment completion was probably higher with shorter regimens (OR, 0.51; 95% CI, .42-0.62; moderate-certainty evidence). Adverse events were similar between groups, but evidence is uncertain (low-certainty evidence). Observational data were consistent with these findings, showing higher completion rates and lower hepatotoxicity with shorter treatments. CONCLUSIONS: Shorter rifamycin-containing regimens for pediatric TBI probably increase treatment completion and have similar safety outcomes, with no important difference in development of TB disease compared with the standard regimen. These findings support current guideline recommendations that favor shorter regimens in children.
25 July 2026
Read appraisal →Pulmonology
Systematic review of prognostic scores and individual predictor variables for short-term mortality after acute pulmonary embolism.
BACKGROUND: For patients with acute pulmonary embolism (PE), assessment of prognosis helps with risk stratification, triage for level of care, management strategy, and communication among healthcare workers and patients. We sought to identify prognostic models and individual factors associated with short-term outcomes after acute symptomatic PE. METHODS: We performed a systematic review of prognostic factors for PE, searching MEDLINE, Embase, and Web of Science for records up to 1 June 2024. Studies of any design evaluating potential prognostic models or individual variables (not contained in the models) associated with short-term mortality after acute PE were included. RESULTS: We identified 314 studies that included 2,495,115 patients. Of these, 225 studies included 2,267,952 patients and evaluated 24 prognostic models for patients with acute PE. The most frequently used validated models were the simplified Pulmonary Embolism Severity Index (sPESI) (127 studies), the original PESI (79 studies), and the European Society of Cardiology risk schema (34 studies). Each model-development study had a c-index ≥ 0.7. Individual factors associated with prognosis included older age, presence of coexisting conditions, abnormal clinical signs and symptoms, clot burden, markers of right‑ventricle dilatation/dysfunction and myocardial injury, altered laboratory results indicating impaired haemodynamics, and tests that assess for systemic inflammation. Pooled odds ratios for variables not contained in any eligible prognostic model ranged from 1.43 (for D-dimer) to 2.65 (for right heart thrombi). CONCLUSIONS: This systematic review identified 24 prognostic models and 18 individual variables distinct from the prognostic models associated with short-term mortality after acute PE.
17 July 2026
Read appraisal →European respiratory review : an official journal of the European Respiratory Society
Risk prediction for lung cancer screening: a systematic review and meta-regression.
BACKGROUND: Lung cancer (LC) remains the deadliest cancer, often diagnosed at advanced stages. Screening reduces mortality in high-risk individuals. Eligibility criteria in European and US screening guidelines have recently expanded. Therefore, we conducted an updated systematic review of risk-based models for identifying candidates for low-dose computed tomography screening and post-screening nodule classification. METHODS: We systematically searched Embase and Medline (January 2020-January 2026), identifying studies proposing new risk models in the context of LC screening. We separated models by pre- and post-screening risk stratification. Data extraction included study design, population, model type, risk horizon and model performance metrics. We performed an exploratory meta-regression of areas under the curve (AUCs) to assess whether sample size, model type, validation type and inclusion of biomarkers were associated with performance. RESULTS: Of 2462 records, 91 were included. 56 models were for screening selection (30 included biomarkers) and 35 for post-screening nodule classification. Regression-based models predominated, though machine-learning approaches were increasingly common. Discrimination ranged from moderate (AUC∼0.70) to excellent (>0.90), with biomarker and imaging-enhanced models often outperforming models without. Calibration was inconsistently reported and fewer than half underwent external validation. CONCLUSION: We identified 91 risk prediction models for LC, developed after 2020. Although many demonstrated promising discrimination across both screening selection and post-screening management, most remain insufficiently mature for clinical adoption, as their performance and practical value outside the original study setting are uncertain. Future work should prioritise external validation, updating and comparative evaluation of existing models, and prospective implementation studies rather than continued development of additional models.
10 July 2026
Read appraisal →Current allergy and asthma reports
Harnessing Machine Learning and Electronic Health Record Data to Improve Asthma Management
PURPOSE OF REVIEW: The review examines the application of machine learning (ML) and large language models (LLMs) to asthma management. We sought to identify clinically relevant applications, and particularly those that harness electronic health record data. We review methodological challenges and future directions for translating these tools into meaningful improvements in asthma care. RECENT FINDINGS: ML applied to electronic health record data has been utilized across several domains of asthma management: predicting medication response to inhaled corticosteroids and biologics, improving inhaler adherence through digital inhaler systems, and predicting exacerbation risk with moderate-to-high accuracy. Tools for patient education include clinician-guided chatbots, as well as publicly available LLMs. Limitations include accuracy, hallucinations, and patient health literacy. ML and LLMs offer promising pathways towards personalized, data-driven asthma management. However, harnessing this potential will require rigorous external validation, transparent model design, equitable implementation, and adaptive clinician oversight. Collaboration among clinicians, data scientists, and policymakers will be essential to implement these tools for patient-centered asthma care.
30 June 2026
Read appraisal →Medicine
Machine learning models to predict ICU admission of patients with COPD and depression: A retrospective cohort study
This study aimed to develop and validate a machine learning (ML)-based predictive model to identify risk factors associated with intensive care unit (ICU) admission among patients with comorbid Chronic Obstructive Pulmonary Disease (COPD) and depression. Data of patients diagnosed with both COPD and depression were extracted from the MIMIC-IV version 3.1 database. A total of 1121 patients with first-time hospitalization and comorbid COPD and depression were included. Feature selection was performed using the Boruta algorithm. Five ML algorithms were employed to construct prediction models. Model performance was evaluated using the receiver operating characteristic curve, area under the curve, calibration curves, and decision curve analysis. Shapley additive explanations (SHAP) plots were used to interpret the contribution of each feature to the model's predictions. Sixteen variables identified by the Boruta algorithm were used to build the predictive models, including chloride, prothrombin time, phosphorus, bicarbonate, international normalized ratio, mean corpuscular hemoglobin (MCH) concentration (MCHC), mean corpuscular hemoglobin, hemoglobin, hematocrit (HCT), total calcium, paraplegia, cerebrovascular disease, smoker status, invasivevent, sepsis, and acute kidney injury (AKI). The Random Forest model performed the best: specificity (0.948), positive predictive value (0.924), precision (0.924), F1 score (0.887), balanced accuracy (0.901), sensitivity (0.853), negative predictive value (0.898), and recall (0.853). SHAP analysis indicated that AKI (0.212), sepsis (0.092), and invasivevent (0.073) were the most influential predictors, followed by anemia-related features such as hemoglobin (0.023), HCT (0.023), and MCHC (0.022). ML analysis revealed that AKI, sepsis, invasivevent, and anemia-related indicators are key risk factors for ICU admission among COPD patients with depression. However, it is important to note that the findings lack external validation, which warrants further investigation in diverse patient populations.
29 June 2026
Read appraisal →Pulmonology
Association between smoking and prognosis in idiopathic pulmonary fibrosis: A systematic review and meta-analysis
BACKGROUND: Although smoking is a well-established risk factor for idiopathic pulmonary fibrosis (IPF) development, its impact on clinical outcomes remains unclear. RESEARCH QUESTION: Is smoking associated with clinical outcomes of IPF? METHODS: A systematic search of PubMed, Embase, and the Cochrane Library was conducted to identify studies reporting associations between smoking status and IPF outcomes, including mortality, acute exacerbation (AE), lung cancer development, and baseline lung function. Summary estimates with 95% confidence intervals (CIs) were pooled using random-effects model. Subgroup analyses were conducted by study region. RESULTS: Forty-nine studies comprising 32 974 patients were included. Overall mortality did not differ by smoking status. However, significant regional differences were observed, with ever smokers demonstrating higher mortality in non - East Asian studies (Hazard ratio [HR] 1.17, 95% CI: 1.03-1.33) but lower mortality in East Asian studies (HR 0.75, 95% CI: 0.62-0.91, p-for-interaction < 0.001) compared with never smokers. Current smokers had a higher risk of developing lung cancer compared with non-current smokers (HR 1.88, 95% CI: 1.24-2.87). No significant associations were observed between smoking and the risk of AEs or baseline forced vital capacity. CONCLUSION: Smoking was not associated with overall mortality in IPF, although significant regional differences were observed.
26 June 2026
Read appraisal →European respiratory review : an official journal of the European Respiratory Society
Cough biomarkers for diagnosis and monitoring of respiratory disease: a systematic review
Cough is a common and physiologically informative component of respiratory morbidity, but its potential for diagnosing and monitoring disease is not thoroughly investigated. This systematic review synthesised the literature on algorithmic and statistical models analysing cough acoustics for diagnosing or monitoring respiratory conditions. Following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, five databases (PubMed, Embase, Scopus, Web of Science and CENTRAL) were systematically searched for studies published from January 2010 to June 2025. Eligible studies performed quantitative acoustic feature analysis of human coughs using statistical, machine learning or deep learning models and reported diagnostic or prognostic performance. 89 studies from 34 countries were assessed, covering cough detection (n=31), disease classification (n=55) and disease severity prediction (n=3), reflecting potential applications in disease monitoring. Deep learning approaches, especially convolutional and recurrent networks, were predominant (n=56) and tended to achieve the higher accuracies, although machine learning ensemble methods and logistic regression also demonstrated strong performance, particularly with well-engineered features. Across different diseases, sensitivities and specificities were often reported to be ≥90%, notably for tuberculosis, asthma and COVID-19. However, methodological weaknesses were common, with only 11.2% of studies introducing external validation, 71.1-87.6% demonstrating high risk of bias (according to PROBAST-AI) and most based on small, homogeneous or crowdsourced cohorts with limited generalisability. These limitations contribute to inflated internal performance and uncertainty about real-world applicability. Cough acoustic biomarkers hold promise as an adjunctive tool for screening and longitudinal monitoring in low-resource environments. Nevertheless, widespread implementation will require large, multicentre validation, standardised calibration, bias control and incorporation into privacy-preserving workflows.
25 June 2026
Read appraisal →Nicotine & tobacco research : official journal of the Society for Research on Nicotine and Tobacco
Efficacy of Yoga in Tobacco Cessation: A Systematic Review and Meta-Analysis
INTRODUCTION: Tobacco consumption is a global epidemic with a high relapse rate. A complementary method like yoga, recognized for addressing psychological and behavioral aspects of addiction, was evaluated in this systematic review and metaanlaysis. METHODS: The objective was to comprehensively summarize the current evidence and evaluate the efficacy of yoga in tobacco cessation. This review was registered with PROSPERO (CRD42025643806). A systematic search across four databases identified randomized controlled trials (RCTs) in English up to September 2024. Eligible studies included adults (≥18 years) using any form of tobacco excluding vaping, randomized to yoga as monotherapy or adjunct therapy. The primary outcome was 7-day point prevalence abstinence (7PPA), while the secondary outcomes included quality of life, depression, anxiety, and mood states. Two reviewers independently extracted data and assessed quality using the Cochrane Risk of Bias (RoB2) tool. A meta-analysis was conducted for outcomes assessed in at least two studies. RESULTS: Seven RCTs were included, with five suitable for meta-analysis. The pooled odds ratio for 7PPA at the end of treatment was 1.50 (95% confidence interval = 0.60 to 3.73), suggesting a positive but inconsistent effect. Considerable heterogeneity was observed (I2 = 65%, p = .07; τ2 = 0.7127), indicating substantial variability across studies. Heterogeneity (I2 = 65%) markedly reduced to 16% when high-risk trials were excluded in sensitivity analysis. Studies reported improvements in depression, anxiety, and quality of life. CONCLUSION: This review consolidates the best available evidence on the effects of yoga interventions for tobacco cessation, showcasing the promising potential of yoga in smoking cessation. IMPLICATIONS: Active yoga styles like hatha, vinyasa, and Iyengar improved 7PPA by reducing stress and depression, while pranayama reduced cravings and negative affect. Future research should explore yoga-based cessation programs in diverse settings, especially low- and middle-income countries, to address unique challenges. Standardizing methodologies across populations will enable a more comprehensive evaluation of yoga's role in tobacco cessation and its potential to enhance global public health outcomes.
25 June 2026
Read appraisal →PloS one
Inhaled nitric oxide in fibrotic and advanced interstitial lung disease: A systematic review and meta-analysis of randomized controlled trials.
PURPOSE: Interstitial lung disease (ILD) can lead to pulmonary hypertension (PH), contributing to reduced exercise capacity in patients with ILD. Inhaled nitric oxide (iNO) reduces pulmonary artery pressure and pulmonary vascular resistance and may improve exercise capacity in this population; however, the available evidence remains limited. Therefore, we conducted a systematic review and meta-analysis to compare the efficacy and safety of iNO versus placebo in patients with ILD. METHODS: We systematically searched PubMed, Embase, Cochrane databases, and ClinicalTrials.gov for randomized controlled trials (RCTs) comparing iNO with placebo in patients with ILD. The primary endpoint was 6-minute walk distance (6MWD). Secondary endpoint was moderate-to-vigorous physical activity (MVPA). Safety endpoint was any adverse events. Continuous endpoints were reported using mean differences (MDs) or standardized mean differences (SMDs), and binary endpoints were reported using risk ratios (RRs), all with 95% confidence intervals (CIs). RESULTS: Four RCTs, including one crossover trial, enrolling 274 patients were analyzed. Of these, 172 received iNO. The median follow-up period was 12 weeks. In the pooled analyses, iNO likely results in little to no difference in 6MWD compared with placebo (MD 1.83m; 95% CI -12.98 to 16.64; p = 0.81), and may result in little to no difference in any adverse events (RR 1.12; 95% CI 0.97 to 1.30; p = 0.12) and MVPA (SMD 0.32; 95% CI -0.93 to 1.56; p = 0.39). CONCLUSION: INO did not demonstrate improvements in 6MWD or MVPA. These findings do not support routine use of iNO in this population.
23 June 2026
Read appraisal →