AI-facilitated health care requires education of clinicians

Abstract

Artificial intelligence (AI), particularly its subtype deep learning, has changed our lives. In our smartphones, laptops, and social media, deep learning provides image and speech recognition, language translation, and more. These advances have begun to percolate into medicine, with deep learning systems capable of diagnosing skin cancer and fully autonomous AI approved for diabetic retinopathy screening. Although AI-enabled health care has huge potential, we are still only in its early stages. As the field matures, a key concern is how should clinicians be educated in these advances and what roles they will assume in developing, validating, and implementing these technologies. Automated deep learning design for medical image classification by health-care professionals with no coding experience: a feasibility studyAll models, except the automated deep learning model trained on the multilabel classification task of the NIH CXR14 dataset, showed comparable discriminative performance and diagnostic properties to state-of-the-art performing deep learning algorithms. The performance in the external validation study was low. The quality of the open-access datasets (including insufficient information about patient flow and demographics) and the absence of measurement for precision, such as confidence intervals, constituted the major limitations of this study. Full-Text PDF Open AccessDigital medicine: empowering both patients and cliniciansWhen physicians and health-care professionals think of the term digital medicine a first reaction might be that this represents an oxymoron. Medicine involves human touch and anything digital has traditionally been conceived as its antithesis. This sentiment is unsurprising given reactions to the big foray of computers in medicine—electronic medical records—considered by some to have diminished the relationship between doctors and their patients. Full-Text PDF A global review of publicly available datasets for ophthalmological imaging: barriers to access, usability, and generalisabilityHealth data that are publicly available are valuable resources for digital health research. Several public datasets containing ophthalmological imaging have been frequently used in machine learning research; however, the total number of datasets containing ophthalmological health information and their respective content is unclear. This Review aimed to identify all publicly available ophthalmological imaging datasets, detail their accessibility, describe which diseases and populations are represented, and report on the completeness of the associated metadata. Full-Text PDF Open AccessWhat's lurking in your electrocardiogram?For decades one of my favourite tasks in medicine has been reading 12-lead electrocardiograms (ECGs). I've always thought the wealth of information provided was impressive—eg, conduction and heart rhythm abnormalities, lack of blood supply or damage to the heart, chamber enlargement or hypertrophy, and inflammation of the pericardium. In the 1980s, when I did emergency coronary angiograms for patients with acute myocardial infarction, I marvelled at how the ECG accurately predicted the infarct-related artery and whether the occlusion was proximal or distal. Full-Text PDF