AI-Based Screening May Be Cost-Effective in Retinopathy of Prematurity Care


AI-based screening for ROP may be more cost-effective than traditional screening modalities, but depends significantly on the added cost of AI.

AI-Based Screening May Be Cost-Effective in Retinopathy of Prematurity Care

J. Peter Campbell, MD, MPH

New data suggest artificial-intelligence (AI) based screening for retinopathy of prematurity (ROP) may be more cost-effective compared to traditional screening modalities, including telemedicine and ophthalmoscopy.

However, the cost-effectiveness of AI-based screening may depend significantly on what cost is assigned to AI and the relative performance versus human examiners detecting severe ROP

“Importantly, AI-based ROP screening also introduces objectivity into the screening, diagnosis, and monitoring of ROP,” wrote study author J. Peter Campbell, MD, MPH, Department of Ophthalmology, Casey Eye Institute, Oregon Health & Science University. “Growing evidence suggests AI-based screening may identify infants’ progression to [treatment-requiring]-ROP before diagnosis, improving sensitivity of disease detection and facilitating early identification and treatment and reduction of adverse outcomes.”

Although telemedicine has improved access to care in numerous regions, its widespread use is limited by low reimbursement and inefficiency in screening, as nearly 80% of screening results indicate no or mild disease.

As such, the current study modeled the cost-effectiveness of assistive or autonomous AI-based ROP screening in comparison to telemedicine and ophthalmoscopy in a simulated population. A theoretical cohort of 52,000 neonates approximated the number of infants born in the United States annually needing screening.

Investigators created decision trees to model costs, outcomes, and cost-effectiveness associated with 4 possible screening strategies for ROP:

  • Ophthalmoscopy per standard guidelines
  • Weekly telemedicine screening
  • Weekly assistive AI with telemedicine review
  • Weekly autonomous AI with positive screen results reviewed by clinicians

A total of 4 outcomes were modeled based on clinical outcomes, consisting of correctly untreated, timely treatment, treated but not requiring treatment, and late treatment. The study compared mean outcomes, costs, effectiveness, and incremental cost-effectiveness ratios, using a commonly accepted willingness-to-pay (WTP) threshold of $100,000 per QALY.

Investigators observed autonomous AI outperformed all other modalities in incremental cost-effectiveness and was at least as effective, but less costly compared to each of the other 3 options. Autonomous AI had lower mean costs compared with telemedicine and ophthalmoscopy, while assistant AI had higher mean costs than telemedicine.

In the primary analysis, data show AI-based ROP screening was cost-effective up to $7 for assistive and $34 for autonomous screening compared with telemedicine and $64 and $91 compared with ophthalmoscopy.

Among a second cohort with a higher AI sensitivity of 99%, the number of late treatments for ROP decreased from 265 when ROP screening was performed with ophthalmoscopy to 40 using autonomous AI.

They noted that both forms of AI resulted in an increased number of neonates receiving timely treatment and decreased numbers with late treatment, when compared to either telemedicine or ophthalmoscopy.

Then, in the probabilistic sensitivity analyses, investigators found autonomous AI screening to be more than 60% likely to be cost-effective at all willingness-to-pay levels, compared to other modalities.

“It may be both less costly and more effective, depending on the sensitivity and specificity of AI compared with the standard of care, which remains to be seen as there are no AI models currently in clinical practice for ROP,” Campbell concluded.

The study, “Cost-effectiveness of Artificial Intelligence–Based Retinopathy of Prematurity Screening,” was published in JAMA Ophthalmology.

Related Videos
Cindy X. Cai, MD: Impact of Race, Neighborhood on Diabetic Retinopathy Care | Image Credit: Johns Hopkins University
Dimitra Skondra, MD, PhD: Protective Effect of Metformin in Geographic Atrophy| Image Credit: University of Chicago
Deepak Sambhara, MD | Image Credit: American Society of Retina Specialists
Sean Adrean, MD: Impact of Baseline VA on Aflibercept 8 mg Outcomes in DME | Image Credit: Linkedin
Mark Barakat, MD: Stable IOP Outcomes After Aflibercept 8 mg in DME | Image Credit: Retina Macula Institute of Arizona
Roger Goldberg, MD: Impact of Dual Inhibition on Hard Exudates in DME | Image Credit: Bay Area Retina Associates
Deepayan Kar, PhD, MS: A Virtual Reality Approach to Contrast Sensitivity in AMD | Image Credit: LinkedIn
Dolly Chang, MD, PhD | Image Credit: LinkedIn
Daniel Su, MD: | Image Credit: Retina Vitreous-Associates Medical Group
Daniela Ferrara, MD, PhD: Machine Learning Predicts Functional Outcomes in DME | Image Credit: Ophthalmology Innovation Summit
© 2024 MJH Life Sciences

All rights reserved.