RESUMO
BACKGROUND: Blood-borne tumour markers in the form of circulating tumour cells (CTCs) are of intense research interest in the diagnostic and prognostic work-up of hepatocellular carcinoma (HCC). METHODS: This is a meta-analysis. Using a PICO strategy, adults with HCC was the population, with the individual CTCs as the intervention and comparators. The primary outcome was the sensitivity and specificity of HCC detection with tumour specific single gene methylation alteration. Secondary outcomes were the comparison using specific assay methods and the effect of early vs. late stages on CTC positivity. We included patients with HCC who had samples taken from peripheral blood and had sufficient data to assess the outcome data. ASSIA, Cochrane library, EMbase, Medline, PubMed and the knowledge network Scotland were systematically searched with appropriate Mesh terms employed. The quality assessment of diagnostic accuracy studies (QUADAS) was used to ensure quality of data. Statistical analysis was performed using the 'Rev Man' meta-analysis soft ward for Windows. RESULTS: The review included 36 studies, with a total of 5,853 patients. Here, we found that AFP has the highest overall diagnostic performance. The average Youden index amongst all CTC was 0.46 with a mode and median of 0.5 with highest of 0.87 and lowest of 0.01. CONCLUSIONS: The available literature provides weak evidence that there is potential in the use of CTC, however the lack of a standardised procedure in the study of CTC contribute to the lack of consensus of use. Future research should include large scaled, standardized studies for the diagnostic accuracy of CTCs.
RESUMO
Chest X-rays (CXRs) are the first-line investigation in patients presenting to emergency departments (EDs) with dyspnoea and are a valuable adjunct to clinical management of COVID-19 associated lung disease. Artificial intelligence (AI) has the potential to facilitate rapid triage of CXRs for further patient testing and/or isolation. In this work we develop an AI algorithm, CovIx, to differentiate normal, abnormal, non-COVID-19 pneumonia, and COVID-19 CXRs using a multicentre cohort of 293,143 CXRs. The algorithm is prospectively validated in 3289 CXRs acquired from patients presenting to ED with symptoms of COVID-19 across four sites in NHS Greater Glasgow and Clyde. CovIx achieves area under receiver operating characteristic curve for COVID-19 of 0.86, with sensitivity and F1-score up to 0.83 and 0.71 respectively, and performs on-par with four board-certified radiologists. AI-based algorithms can identify CXRs with COVID-19 associated pneumonia, as well as distinguish non-COVID pneumonias in symptomatic patients presenting to ED. Pre-trained models and inference scripts are freely available at https://github.com/beringresearch/bravecx-covid .
