Research Appraisals
Evidence-based critical appraisals of the latest medical research, systematically evaluated using Oxford CEBM methodology.
Showing 2 appraisals
JMIR cancer
Piloting a Clinical Decision Support System for Unintended Weight Loss in Primary Care: Mixed Methods Study on Early Cancer Detection
BACKGROUND: Delayed cancer diagnosis leads to poorer outcomes. Unintended weight loss (UWL) is a nonspecific symptom associated with cancer and other serious conditions, which can make it complex to identify the underlying cause. Clinical decision support systems (CDSSs) can provide evidence-based recommendations to facilitate timely investigation and diagnosis. OBJECTIVE: This study aimed to pilot the implementation of a CDSS for improving early cancer detection in primary care patients with UWL. METHODS: Five practices reviewed patients identified by the UWL CDSS. Staff were interviewed on the acceptability and feasibility of the CDSS. Interviews were analyzed thematically using 2 relevant frameworks: the acceptability of health care interventions and the sociotechnical model for evaluation of digital interventions framework. Clinical audits assessed the correct identification of UWL, follow-up rates, and patient characteristics. RESULTS: Of 60 patients identified by the CDSS as potentially having UWL, 36 (60%) had true UWL. Among the misclassified cases, most patients (16/55, 30%) were intentionally trying to lose weight; this intention was documented as free text in the clinical notes for 98% (58/60) of patients and in a structured field for only 20% of patients. Of the 36 patients, 5 (14%) were actively recalled by their practices for further follow-up; the others (31/36, 86%) were not recalled, as most were deemed already under appropriate follow-up. By 6 months, 94% (34/36) of the cohort had received follow-up care regardless of whether they had been formally recalled. One-third (12/36, 33%) of patients had no additional symptoms, while 36% (13/36) had recorded additional abdominal symptoms. Mental health conditions accounted for 19% of diagnoses linked to UWL consultation. Practice staff were generally receptive to the UWL CDSS concept. It was particularly appreciated by practices with strong quality improvement processes and prior CDSS experience. A high proportion of misclassified patients, poor workflow integration, and conflicting patients' agendas were cited as implementation barriers. CONCLUSIONS: Our study revealed challenges and potential benefits of implementing a CDSS for identifying patients with UWL at risk of cancer in primary care. While integration issues and misclassification of patients were noted, high rates of follow-up care were observed regardless of the CDSS. These high follow-up rates prompt consideration of whether they reflect Australian primary care and whether a CDSS with these characteristics is the most appropriate approach to support early cancer detection. Future research should focus on improving CDSS integration with existing workflows, enhancing correct identification through access to clinical notes and the use of more sophisticated digital methods (eg, AI). These findings highlight the potential of CDSS in improving patient care and the complexities involved in their successful implementation.
30 July 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 →