Human–machine partnership with artificial intelligence for chest radiograph diagnosis

Recent notable applications of deep learning in medicine include automated detection of diabetic retinopathy, classification of skin cancers, and detection of metastatic lymphadenopathy in patients with breast cancer, all of which demonstrated expert level diagnostic accuracy.1,2,3 Recently, a deep-learning model was found to match or outperform human expert radiologists in diagnosing 10 or more pathologies on chest radiographs.4,5 The success of AI in diagnostic imaging has fueled a growing debate6,7,8,9 regarding the future role of radiologists in an era, where deep-learning models are capable of performing important diagnostic tasks autonomously and speculation surrounds whether the comprehensive diagnostic interpretive skillsets of radiologist can be replicated in algorithms. However, AI is also plagued with several disadvantages including biases due to limited training data, lack of cross-population generalizability, and inability of deep-learning models to contextualize.8,10,11,12 Human-in-the-loop (HITL) AI may offer advantages where both radiologists and machine-learning algorithms fall short.13,14