In this meta-analysis, moderate interobserver agreement was found between expert thoracic radiologists interpreting high-resolution CT of interstitial lung disease, highlighting a need for greater standardization.

Objectives Early identification of lung cancer on chest radiographs improves patient outcomes. Artificial intelligence (AI) tools may increase diagnostic accuracy and streamline this pathway. This study evaluated the performance of commercially available AI-based software trained to identify cancerous lung nodules on chest radiographs. Design This retrospective study included primary care chest radiographs acquired in a UK centre. The software evaluated each radiograph independently and outputs were compared with two reference standards: (1) the radiologist report and (2) the diagnosis of cancer by multidisciplinary team decision. Failure analysis was performed by interrogating the software marker locations on radiographs. Participants 5722 consecutive chest radiographs were included from 5592 patients (median age 59 years, 53.8% women, 1.6% prevalence of cancer). Results Compared with radiologist reports for nodule detection, the software demonstrated sensitivity 54.5% (95% CI 44.2% to 64.4%), specificity 83.2% (82.2% to 84.1%), positive predictive value (PPV) 5.5% (4.6% to 6.6%) and negative predictive value (NPV) 99.0% (98.8% to 99.2%). Compared with cancer diagnosis, the software demonstrated sensitivity 60.9% (50.1% to 70.9%), specificity 83.3% (82.3% to 84.2%), PPV 5.6% (4.8% to 6.6%) and NPV 99.2% (99.0% to 99.4%). Normal or variant anatomy was misidentified as an abnormality in 69.9% of the 943 false positive cases. Conclusions The software demonstrated considerable underperformance in this real-world patient cohort. Failure analysis suggested a lack of generalisability in the training and testing datasets as a potential factor. The low PPV carries the risk of over-investigation and limits the translation of the software to clinical practice. Our findings highlight the importance of training and testing software in representative datasets, with broader implications for the implementation of AI tools in imaging.

Background and Objectives: Interest in artificial intelligence (AI) for outcome prediction has grown substantially in recent years. However, the prognostic role of AI using advanced cardiac magnetic resonance imaging (CMR) remains unclear. This systematic review assesses the existing literature on AI in CMR to predict outcomes in patients with cardiovascular disease. Materials and Methods: Medline and Embase were searched for studies published up to November 2021. Any study assessing outcome prediction using AI in CMR in patients with cardiovascular disease was eligible for inclusion. All studies were assessed for compliance with the Checklist for Artificial Intelligence in Medical Imaging (CLAIM). Results: A total of 5 studies were included, with a total of 3679 patients, with 225 deaths and 265 major adverse cardiovascular events. Three methods demonstrated high prognostic accuracy: (1) three-dimensional motion assessment model in pulmonary hypertension (hazard ratio (HR) 2.74, 95%CI 1.73–4.34, p < 0.001), (2) automated perfusion quantification in patients with coronary artery disease (HR 2.14, 95%CI 1.58–2.90, p < 0.001), and (3) automated volumetric, functional, and area assessment in patients with myocardial infarction (HR 0.94, 95%CI 0.92–0.96, p < 0.001). Conclusion: There is emerging evidence of the prognostic role of AI in predicting outcomes for three-dimensional motion assessment in pulmonary hypertension, ischaemia assessment by automated perfusion quantification, and automated functional assessment in myocardial infarction.

Quality of reporting of studies on artificial intelligence in radiology: what is the current state of the field? - Diagnostic and Interventional Radiology

Objectives: Right ventricular (RV) dysfunction carries elevated risk in acute pulmonary embolism (PE). An increased ratio between the size of the right and left ventricles (RV/LV ratio) is a biomarker of RV dysfunction. This study evaluated the reproducibility of RV/LV ratio measurement on CT pulmonary angiography (CTPA). Methods: 20 inpatient CTPA scans performed to assess for acute PE were retrospectively identified from a tertiary UK centre. Each scan was evaluated by 14 radiologists who provided a qualitative overall opinion on the presence of RV dysfunction and measured the RV/LV ratio. Using a threshold of 1.0, the RV/LV ratio measurements were classified as positive (≥1.0) or negative (<1.0) for RV dysfunction. Interobserver agreement was quantified using the Fleiss κ and intraclass correlation coefficient (ICC). Results: Qualitative opinion of RV dysfunction showed weak agreement (κ = 0.42, 95% CI 0.37–0.46). The mean RV/LV ratio measurement for all cases was 1.28 ± 0.68 with significant variation between reporters (p < 0.001). Although agreement for RV/LV measurement was good (ICC = 0.83, 95% CI 0.73–0.91), categorisation of RV dysfunction according to RV/LV ratio measurements showed weak agreement (κ = 0.46, 95% CI 0.41–0.50). Conclusion: Both qualitative opinion and quantitative manual RV/LV ratio measurement show poor agreement for identifying RV dysfunction on CTPA. Advances in knowledge: Caution should be exerted if using manual RV/LV ratio measurements to inform clinical risk stratification and management decisions.