Computational Ophthalmology – Page 11 – big data. machine learning. data science.

May 29, 2017September 27, 2020

The United Kingdom Diabetic Retinopathy Electronic Medical Record Users Group: Report 3: Baseline Retinopathy and Clinical Features Predict Progression of Diabetic Retinopathy

In this large study using data from more than 30,000 patients in the UK, the authors analyzed potential risk factors for developing proliferative diabetic retinopathy and vitreous hemorrhage in patients with diabetes mellitus. Diabetic retinopathy is a major cause of blindness in working-age adults, and early detection can substantially decrease the risk of progression to vision loss. Patients with diabetes should have regular screening for early signs of diabetic retinopathy, but the current severity classification systems may not be the most accurate method for predicting which patients are most at risk for vision-threatening disease, particularly as standards of care have been updated.

March 1, 2017September 27, 2020

Validation of the Total Visual Acuity Extraction Algorithm (TOVA) for Automated Extraction of Visual Acuity Data From Free Text, Unstructured Clinical Records

Pubmed

Journal

Citation

In this study, the authors created and tested an algorithm for extracting visual acuity testing information from clinical notes. The increasing use of electronic health records is allowing for large-scale data review in clinical research. The data accessed from electronic health records can be limited, however, because the manually transcribed data is often stored as free text. Automated conversion of free text into machine-readable data and extraction for research requires the application of computational linguistics and natural language processing.

December 12, 2016September 28, 2020

Evaluating Access to Eye Care in the Contiguous United States by Calculated Driving Time in the United States Medicare Population

Pubmed

Journal

Citation

In this important study, Dr. Cecilia Lee, Dr. Aaron Lee, and their co-authors used census and mapping data to quantify how far Medicare patients travel to access eye care in the contiguous United States. This type of information about medically underserved geographic areas is essential for improving access to care. The authors note that the issue of rural access to care has been cited as a reason for increasing the number of eye care providers in the United States. Some providers also use access to care as an argument for increasing optometrists' responsibilities and scope of practice.