RESUMO
INTRODUCTION: Early-stage lung cancer diagnosis through detection of nodules on computed tomography (CT) remains integral to patient survivorship, promoting national screening programmes and diagnostic tools using artificial intelligence (AI) convolutional neural networks (CNN); the software of AI-Rad Companion™ (AIRC), capable of self-optimising feature recognition. This study aims to demonstrate the practical value of AI-based lung nodule detection in a clinical setting; a limited body of research. METHODS: One hundred and eighty-three non-contrast CT chest studies from a single centre were assessed for AIRC software analysis. Prospectively collected data from AIRC detection and characterisation of lung nodules (size: ≥3 mm) were assessed against the reference standard; reported findings of a blinded consultant radiologist. RESULTS: One hundred and sixty-seven CT chest studies were included; 52% indicated for nodule or lung cancer surveillance. Of 289 lung nodules, 219 (75.8%) nodules (mean size: 10.1 mm) were detected by both modalities, 28 (9.7%) were detected by AIRC alone and 42 (14.5%) by radiologist alone. Solid nodules missed by AIRC were larger than those missed by radiologist (11.5 mm vs 4.7 mm, P < 0.001). AIRC software sensitivity was 87.3%, with significant false positive and negative rates demonstrating 12.5% specificity (PPV 0.6, NPV 0.4). CONCLUSION: In a population of high nodule prevalence, AIRC lung nodule detection software demonstrates sensitivity comparable to that of consultant radiologist. The clinical significance of larger sized nodules missed by AIRC software presents a barrier to current integration in practice. We consider this research highly relevant in providing focus for ongoing software development, potentiating the future success of AI-based tools within diagnostic radiology.
RESUMO
BACKGROUND: The risk of venous thromboembolism (VTE) is increased postpartum and contributes to important morbidity and mortality. While there have been advances in evaluating diagnostic algorithms for suspected VTE during pregnancy, there is limited data for postpartum individuals. OBJECTIVE: We conducted a scoping review to describe and evaluate diagnostic strategies used to investigate suspected VTE in postpartum individuals. METHODS: A comprehensive search strategy was conducted in Ovid MEDLINE, Embase and the Cochrane Central Register of Controlled Trials (January 1, 2000-September 30, 2022) to identify original articles that reported on diagnostic strategies in postpartum individuals with suspected VTE. We extracted demographics, clinical decision rules used, D-dimer and imaging completed, including test performance and VTE outcomes. RESULTS: A total of 13 studies conducted across 11 countries with separate postpartum data were included for 759 individuals with suspected PE (n = 634) or DVT (n = 125), including unpublished data (n = 251). Among those with suspected PE, computed tomography pulmonary angiography was conducted more commonly (n = 522) than ventilation-perfusion scans (n = 69), with PE positivity rates that ranged from 4 %-27.6 % and 0-50 % across studies, respectively. Among 131 postpartum individuals with suspected PE who had a D-dimer measured, only 4.6 % (6/131) had a negative D-dimer test. For postpartum individuals with suspected DVT, the most common diagnostic test was compression ultrasonography (positivity rate 12.2 %-18.6 %). There were limited retrospective data evaluating the clinical decision rules. CONCLUSIONS: There are heterogeneous approaches globally in the diagnosis of suspected postpartum VTE. Limited high-quality data available underscores the need for more robust evidence to inform clinical practice.