In the era of artificial inelegance(AI), a shift from tertiary to secondary and primary care when caring for a patient with diabetic retinopathy is highly recommended.
Due to low operation, AI could be used in the early detection and screening of diabetic retinopathy by application of the service across a mass population and resource-limited areas with a scarcity of eye care services.
AI-based eye care in terms of screening for diabetic retinopathy will make the screening process more effective and cheap and could be delegated to technicians, practitioners, and/or even home-based self-screening.
Recognizing the high prevalence of type 2 diabetes mellitus (T2DM) among adults, the use of a nonmydriatic fundus camera with AI is effective in eye exams as it improves adult adherence to eye screening.
The primary aim of the trial will be to assess the effectiveness of the application of AI devices in terms of fundus cameras in the early detection of diabetic retinopathy and macular oedema among diabetic patients attending primary care centres.
Research Questions:
To what extent does the application of artificial intelligence-based eye care at primary care centre is effective in achieving a high detection rate of macular oedema? To what extent does the application of artificial intelligence-based eye care at primary care clinic is effective in achieving a high detection rate of retinopathy?
General objective:
To estimate the effectiveness of applying AI-based eye care at primary care centres in achieving a high detection rate of macular oedema and retinopathy among diabetics.
Specific Objectives:
Aim 1: To compare the proportion of detected cases of macular oedema in the intervention versus the control group (routine eye care) attending the primary care centre.
Aim 2: To compare the proportion of detected cases of retinopathy in the intervention versus the control group (routine eye care) attending the primary care centre
Literature Review:
Although recent models had been suggested for implementing digital health solutions like stream fishing, inflow funnel, pyramid, and shuffling cards that represent options for clinical services with progressively increasing capacity and willingness to operationalize digital health.
However, various challenges are facing the deployment of AI, telehealth, and the internet of things (IoT) worldwide. Barriers to adopting these digital health solutions are many and could be inferred to infrastructure, the quality of the device, common willingness, and legal aspects.
Evidence revealed that using Macustat retina function scan AI in remote monitoring of a patient with age-related macular oedema or diabetic retinopathy has a great impact on patient health.
Research Design and Methods:
This is a six months clustered randomized trial that will recruit patients with type II diabetes who are attending primary eye care clinics at primary care centres in Hail city.
Participants (P):
The participants will be type II diabetic patients of both genders attending the selected primary care centres irrespective of their duration of disease and the types of medication currently received. The participants are expected to be adults aged 18 years and above. Children and young adults with juvenile diabetes mellitus will be excluded. In addition, severely ill patients, and patients with mental disorders will be excluded. The participants will be assessed at the start to collect the baseline data about diabetic retinopathy and macular oedema using AI devices to report detected cases. At the end of the trial, a similar report of detected cases will be obtained three and six months after the beginning of the trial.
