Performance of a Chest Radiograph AI Diagnostic Tool for COVID-19: A Prospective Observational Study

Abstract

Purpose To conduct a prospective observational study across 12 U.S. hospitals to evaluate real-time performance of an interpretable artificial intelligence (AI) model to detect COVID-19 on chest radiographs. Materials and Methods A total of 95 363 chest radiographs were included in model training, external validation, and real-time validation. The model was deployed as a clinical decision support system, and performance was prospectively evaluated. There were 5335 total real-time predictions and a COVID-19 prevalence of 4.8% (258 of 5335). Model performance was assessed with use of receiver operating characteristic analysis, precision-recall curves, and F1 score. Logistic regression was used to evaluate the association of race and sex with AI model diagnostic accuracy. To compare model accuracy with the performance of board-certified radiologists, a third dataset of 1638 images was read independently by two radiologists. Results Participants positive for COVID-19 had higher COVID-19 diagnostic scores than participants negative for COVID-19 (median, 0.1 [IQR, 0.0–0.8] vs 0.0 [IQR, 0.0–0.1], respectively; P < .001). Real-time model performance was unchanged over 19 weeks of implementation (area under the receiver operating characteristic curve, 0.70; 95% CI: 0.66, 0.73). Model sensitivity was higher in men than women ( P = .01), whereas model specificity was higher in women ( P = .001). Sensitivity was higher for Asian ( P = .002) and Black ( P = .046) participants compared with White participants. The COVID-19 AI diagnostic system had worse accuracy (63.5% correct) compared with radiologist predictions (radiologist 1 = 67.8% correct, radiologist 2 = 68.6% correct; McNemar P < .001 for both). Conclusion AI-based tools have not yet reached full diagnostic potential for COVID-19 and underperform compared with radiologist prediction. Keywords: Diagnosis, Classification, Application Domain, Infection, Lung Supplemental material is available for this article. . © RSNA, 2022

Can Artificial Intelligence Detect Monkeypox from Digital Skin Images?

“…Different artificial intelligence (AI) tools, especially deep learning approaches, have been widely used in different medical image analysis tasks (e.g., organ localization [8], [9], organ abnormality detection [9], [10], gene mutation detection [11], cancer grading [12], [13] and staging [14]) in the last decade. Notably, AI methods have recently played a significant role in COVID-19 diagnosis and severity ranking from multimodal medical images (e.g., computed tomography (CT), chest X-ray, and chest ultrasound) [15]–[17]. This success motivates the scientific community in utilizing AI approaches for Monkeypox diagnosis from the digital skin images of patients.…”

Diagnostik Klinis Infeksi SARS-CoV-2 dengan Metode Apusan

“…Sifat virus corona lebih mudah menginfeksi manusia dan menyebar secara mudah secara global. Akibatnya, terjadi pandemi COVID-19 di seluruh dunia (Burhan et al, 2022;Sun et al, 2022).…”

Usage of Particle Swarm Optimization in Digital Images Selection for Monkeypox Virus Prediction and Diagnosis

“…Several medical image analysis research projects have used a variety of arti cial intelligence (AI) techniques over the last ten years, most notably deep learning approaches (for example, organ positioning [8], [9], identi cation of organ abnormalities [9], [10], nding gene mutations [11], classifying cancer [12], [13], and staging [14]). Notably, AI algorithms have lately been crucial in the diagnosis and severity assessment of COVID-19 employing multimodal medical imaging (e.g., CT imaging, X-ray of the chest, and ultrasonography of the chest [9], [10]).…”