Clinically applicable deep learning for diagnosis and referral in retinal disease

Abstract

The volume and complexity of diagnostic imaging is increasing at a pace faster than the availability of human expertise to interpret it. Artificial intelligence has shown great promise in classifying two-dimensional photographs of some common diseases and typically relies on databases of millions of annotated images. Until now, the challenge of reaching the performance of expert clinicians in a real-world clinical pathway with three-dimensional diagnostic scans has remained unsolved. Here, we apply a novel deep learning architecture to a clinically heterogeneous set of three-dimensional optical coherence tomography scans from patients referred to a major eye hospital. We demonstrate performance in making a referral recommendation that reaches or exceeds that of experts on a range of sight-threatening retinal diseases after training on only 14,884 scans. Moreover, we demonstrate that the tissue segmentations produced by our architecture act as a device-independent representation; referral accuracy is maintained when using tissue segmentations from a different type of device. Our work removes previous barriers to wider clinical use without prohibitive training data requirements across multiple pathologies in a real-world setting.

A roadmap for implementation of patient‐centered digital outcome measures in Parkinson's disease obtained using mobile health technologies

“…An exception was a recent study that addressed the long‐term compliance of patients to wear a smartwatch, a body‐worn sensor, and a smartphone; in this study, a helpdesk to support patients proved a critical strategy to improve adherence . Another pitfall is the aspirational development of mobile health technologies as fulfilling diagnostic needs . Although technologies can be harnessed for validating patient‐centered outcomes and for supporting a clinical diagnosis, they remain inadequate as stand‐alone measures for “diagnostic accuracy.” Aiming at fulfilling this goal perpetuates the concept that the many molecular subtypes subsumed within the clinical diagnosis of PD can be unified by an ideal set of behavioral features.…”

Clinical applications of machine learning algorithms: beyond the black box

“…Microsoft’s InnerEye offers a graphical user interface to algorithms that help radiologists diagnose cancerous tumours and plan precise surgical interventions 8. DeepMind Health recently partnered with Moorfields Eye Hospital to develop models for diagnosing common retinal pathologies based on optical coherence tomography scans 9. IBM’s Watson for Oncology seeks to provide personalised cancer care based on health records,10 although the project has run into numerous procurement problems, cost over-runs, and delays 11…”

Machine learning: Great opportunities, but will it replace nurses?

“…In medical imaging, for example, ML may revolutionize identification of clinical signs, using pattern recognition to predict likely diagnosis or referrals. Evaluation is showing performance accuracy equaling human experts but at much faster speeds (De Fauw et al, ; Rajpurkar et al, ). As well as automating stages of diagnosis, ML may expand our current definitions of diseases and their subtypes.…”