In the Journals

AI diagnostic system accuracy holds up to industry standards

Michael Abramoff, MD, PhD
Michael D. Abramoff

The artificial intelligence diagnostic system, IDx-DR, detects more than mild diabetic retinopathy and diabetic macular edema with significantly relevant sensitivity and specificity and has potential to help prevent vision loss in those with diabetes, according to researchers.

The trial enrolled 900 patients with diabetes who had no history of diabetic retinopathy by comparing the AI system to Wisconsin Fundus Photograph Reading Center (FPRC) widefield stereoscopic photography and macular OCT by FPRC-certified photographers. FPRC grading of Early Treatment Diabetic Retinopathy Study Severity Scale was used as the reference standard.

Participant median age was 59 years, with 47.5% male; 16.1% were Hispanic, 63.4% were white, 28.6% were African American, and 1.6% were Asian.

A total of 198 (23.8%) had more than mild diabetic retinopathy.

The AI system exceeded all pre-specified superiority endpoints at a sensitivity of 87.2%, specificity of 90.7% and imageability rate of 96.1%, according to researchers.

In the clinical study, IDx-DR achieved high diagnostic accuracy when compared to the most rigorous determination of the severity of diabetic retinopathy using advanced imaging techniques – wide-field stereo fundus imaging and OCT evaluated by the Wisconsin FPRC, according to a press release from IDx LLC.

“[It was] important for us to develop an exceptionally rigorous study that was reviewed by independent physician-scientists. Now that the results have been published in Nature Digital Medicine, scientists, physicians and patients can all evaluate the scientific evidence for the safety and effectiveness of an autonomous AI like IDx-DR,” Michael D. Abràmoff, PhD, MD, the study’s principal investigator and founder and president of IDx, said in the release.

Disclosures: Abramoff is shareholder, director and an employee of IDx LLC and has relevant patents and patent applications assigned to the University of Iowa. Please see the full study for all remaining authors’ financial disclosures.

Michael Abramoff, MD, PhD
Michael D. Abramoff

The artificial intelligence diagnostic system, IDx-DR, detects more than mild diabetic retinopathy and diabetic macular edema with significantly relevant sensitivity and specificity and has potential to help prevent vision loss in those with diabetes, according to researchers.

The trial enrolled 900 patients with diabetes who had no history of diabetic retinopathy by comparing the AI system to Wisconsin Fundus Photograph Reading Center (FPRC) widefield stereoscopic photography and macular OCT by FPRC-certified photographers. FPRC grading of Early Treatment Diabetic Retinopathy Study Severity Scale was used as the reference standard.

Participant median age was 59 years, with 47.5% male; 16.1% were Hispanic, 63.4% were white, 28.6% were African American, and 1.6% were Asian.

A total of 198 (23.8%) had more than mild diabetic retinopathy.

The AI system exceeded all pre-specified superiority endpoints at a sensitivity of 87.2%, specificity of 90.7% and imageability rate of 96.1%, according to researchers.

In the clinical study, IDx-DR achieved high diagnostic accuracy when compared to the most rigorous determination of the severity of diabetic retinopathy using advanced imaging techniques – wide-field stereo fundus imaging and OCT evaluated by the Wisconsin FPRC, according to a press release from IDx LLC.

“[It was] important for us to develop an exceptionally rigorous study that was reviewed by independent physician-scientists. Now that the results have been published in Nature Digital Medicine, scientists, physicians and patients can all evaluate the scientific evidence for the safety and effectiveness of an autonomous AI like IDx-DR,” Michael D. Abràmoff, PhD, MD, the study’s principal investigator and founder and president of IDx, said in the release.

Disclosures: Abramoff is shareholder, director and an employee of IDx LLC and has relevant patents and patent applications assigned to the University of Iowa. Please see the full study for all remaining authors’ financial disclosures.