Applications of Artificial Intelligence to Electronic Health Record Data in Ophthalmology

Abstract

Widespread adoption of electronic health records (EHRs) has resulted in the collection of massive amounts of clinical data. In ophthalmology in particular, the volume range of data captured in EHR systems has been growing rapidly. Yet making effective secondary use of this EHR data for improving patient care and facilitating clinical decision-making has remained challenging due to the complexity and heterogeneity of these data. Artificial intelligence (AI) techniques present a promising way to analyze these multimodal data sets. While AI techniques have been extensively applied to imaging data, there are a limited number of studies employing AI techniques with clinical data from the EHR. The objective of this review is to provide an overview of different AI methods applied to EHR data in the field of ophthalmology. This literature review highlights that the secondary use of EHR data has focused on glaucoma, diabetic retinopathy, age-related macular degeneration, and cataracts with the use of AI techniques. These techniques have been used to improve ocular disease diagnosis, risk assessment, and progression prediction. Techniques such as supervised machine learning, deep learning, and natural language processing were most commonly used in the articles reviewed.

A qualitative investigation into the impact of hemophagocytic lymphohistiocytosis on children and their caregivers

“…Using pHLH as an example, the implementation of a referral awareness campaign within secondary care hospitals aimed at those patients presenting with febrile illness that does not subside and is not associated with typical etiologies may reduce the time to diagnosis for such patients. In ophthalmology, artificial intelligence techniques have been applied to patient data within electronic health records to improve disease diagnosis, risk assessments and prognosis predictions [ 19 ]; however, the application of similar techniques to rare diseases requires further study. Our study suggests that HCPs’ understanding of the whole impact of pHLH (outside of the immediate medical needs) and how to approach and discuss the condition with patients and caregivers needs improvement.…”

Predictive modeling of proliferative vitreoretinopathy using automated machine learning by ophthalmologists without coding experience

“…Recent widespread adoption of EHRs has allowed the collection of large quantities of clinical data, especially in ophthalmology 15 . Data analysis from EHRs and the development of predictive models had been reserved for scientists with considerable mathematical and coding knowledge.…”

Machine learning in clinical decision making

“…Precision-medicine approaches and improved available measurement devices, along with the rise of electronic health records, have provided a solid ground for the introduction of AI to the field of EWSs. [131][132][133] Examples of clinically utilized EWSs include predictors of acute illness at the intensive care setting, 134,135 predictors of kidney failure, 136,137 sepsis, 138,139 glaucoma, age-related macular degeneration, diabetic retinopathy, 140 detection and monitoring of Parkinson's disease, 141,142 fall risk estimation, 143 and heart monitoring. 144 We want to highlight the potential power of natural language processing, a deep-learning approach particularly suitable to process large amounts of textual structured and unstructured data.…”