A real-world study on an AI-enabled tele-monitoring project shows significant impact on long-term outcomes.

A research team based at the National Eye Institute, National Institutes of Health, Bethesda, Maryland, has published long-term visual outcomes for patients participating with an AI-enabled monitoring program detecting the conversion from intermediate AMD (iAMD) to nAMD.  The patients that participated in the “ForeseeHome Monitoring Program” showed “excellent visual acuity at time of conversion to nAMD”, and these patients “were treated consistently and maintained good vision long-term, emphasizing the importance of early detection and treatment in this potentially visually devastating disease”.


The study, termed “ALOFT” (Analysis of the Long-term visual Outcomes of ForeseeHome  Remote Telemonitoring) is a monitoring strategy that incorporates home monitoring, symptoms realization that leads to request for a prompt visit and pre-scheduled office visits as part of standard care. The “FSH” device (ForeseeHome, Notal Vision Inc., Manassas VA, USA), which was cleared by the FDA in 2009, “is an AI-enabled visual field analyzer based on hyperacuity (or vernier acuity), a characteristic of the human visual system involving perception of even the most minute differences in the relative localization of 2 objects in space”.  The project was aimed to evaluate long-term visual acuity and performance with a self-operated artificial intelligence enabled home monitoring system in conjunction with standard care for early detection of neovascular age related macular degeneration (nAMD).


Results of the study had 3,334 eyes of 2,123 patients were reviewed with a mean (SD) age of 74(8) years, monitored for mean (SD) duration of 3.1(2.4) years, with a total of 1,706,433 tests in 10,474 eye-monitoring years. The mean (SD) weekly use per patient was 5.2(3.4) and it was persistent over the usage period. 285 eyes converted while monitored at an annual rate of 2.72%, and were treated with mean (SD) 17.3(16.5) injections over mean (SD) 2.7(2.0) years, with 6.4(3.1) injections per year for eyes treated for greater than one year. The median VA at baseline and final follow-up for eyes that did not convert were 20/27 and 20/34 with a median change of 0.0 letters. The median VA at baseline, conversion and final follow-up for eyes that converted during the monitoring period were 20/30, 20/39 and 20/32 with a median change from baseline to conversion, baseline to recent and conversion to recent of -4, -4 and 0 letters, respectively. 52% of conversions detected had a system alert prior to conversion. 48% of patients were detected by symptoms or routine visit. Patients experienced a non-nAMD alert on average every 4.6 years. At conversion and at final follow-up the proportion (95% CI) of eyes that maintained ≥20/40 was 84%(78%-88%) and 82%(76%-86%), respectively.  Commenting on the achievement, Richard Garfinkel, MD, study investigator from Retina Group of Washington stated, “we expected to see better outcomes with ForeseeHome given the extensive experience we have with the program in our practice, but we were truly amazed by the magnitude of long-term benefit for the patient population. Adopting a remote monitoring paradigm to augment the customary interval office visit is a game changer for AMD patients.”