Artificial Intelligence in Medicine: Today and Tomorrow

The use of artificial intelligence, and the deep-learning subtype in particular, has been enabled by the use of labeled big data, along with markedly enhanced computing power and cloud storage, across all sectors. In medicine, this is beginning to have an impact at three levels: for clinicians, predominantly via rapid, accurate image interpretation; for health systems, by improving workflow and the potential for reducing medical errors; and for patients, by enabling them to process their own data to promote health. The current limitations, including bias, privacy and security, and lack of transparency, along with the future directions of these applications will be discussed in this article. Over time, marked improvements in accuracy, productivity, and workflow will likely be actualized, but whether that will be used to improve the patient-doctor relationship or facilitate its erosion remains to be seen.

Physician burnout, a work-related syndrome involving emotional exhaustion, depersonalization and a sense of reduced personal accomplishment, is prevalent internationally. Rates of burnout symptoms that have been associated with adverse effects on patients, the healthcare workforce, costs and physician health exceed 50% in studies of both physicians-in-training and practicing physicians. This problem represents a public health crisis with negative impacts on individual physicians, patients and healthcare organizations and systems. Drivers of this epidemic are largely rooted within healthcare organizations and systems and include excessive workloads, inefficient work processes, clerical burdens, work-home conflicts, lack of input or control for physicians with respect to issues affecting their work lives, organizational support structures and leadership culture. Individual physician-level factors also play a role, with higher rates of burnout commonly reported in female and younger physicians. Effective solutions align with these drivers. For example, organizational efforts such as locally developed practice modifications and increased support for clinical work have demonstrated benefits in reducing burnout. Individually focused solutions such as mindfulness-based stress reduction and small-group programmes to promote community, connectedness and meaning have also been shown to be effective. Regardless of the specific approach taken, the problem of physician burnout is best addressed when viewed as a shared responsibility of both healthcare systems and individual physicians. Although our understanding of physician burnout has advanced considerably in recent years, many gaps in our knowledge remain. Longitudinal studies of burnout's effects and the impact of interventions on both burnout and its effects are needed, as are studies of effective solutions implemented in combination. For medicine to fulfil its mission for patients and for public health, all stakeholders in healthcare delivery must work together to develop and implement effective remedies for physician burnout.

The development of decision support systems for pathology and their deployment in clinical practice have been hindered by the need for large manually annotated datasets. To overcome this problem, we present a multiple instance learning-based deep learning system that uses only the reported diagnoses as labels for training, thereby avoiding expensive and time-consuming pixel-wise manual annotations. We evaluated this framework at scale on a dataset of 44,732 whole slide images from 15,187 patients without any form of data curation. Tests on prostate cancer, basal cell carcinoma and breast cancer metastases to axillary lymph nodes resulted in areas under the curve above 0.98 for all cancer types. Its clinical application would allow pathologists to exclude 65–75% of slides while retaining 100% sensitivity. Our results show that this system has the ability to train accurate classification models at unprecedented scale, laying the foundation for the deployment of computational decision support systems in clinical practice.