Myopia control in the real world: treatments, target, timing, and terminus

ongoing

Background: Myopia, or near-sightedness, is increasing dramatically all over the world, mostly due to higher levels of education and changing lifestyles of young generations. The expectation is that half of the world’s citizens will be myopic by 2050. Myopia-related complications later in life are a serious threat to vision and will increase the rates of blindness. Prevention strategies and pharmacological and optical treatments to delay progression of myopia in childhood are emerging, but most eye care professionals still do not control myopia due to inadequate information and unpredictable outcomes. Aim: To radically improve patient management in myopia by providing an agile, AI-based clinical decision support system stooled on a solid scientific basis of integrated multidisciplinary data. Approach: 1. To construct population-based reference centiles for eye growth and progression of myopia for screening and surveillance of myopia in young generations in Europe 2. To capture high-quality, long-term, prospective data from the real world on myopia control, and specifically gain evidence on timing, effectiveness, side effects, and acceptability of current treatment modalities in daily practice 3. To investigate patient profiles for poor response and adherence to myopia control 4. To predict the final outcome of myopia based on a plethora of potential predictors using advanced machine learning techniques 5. To develop the CONTROL-MYOPIA platform with a user-centred and highly interactive design which provides an accurate prediction of myopia outcomes with and without myopia control, and which recommends the right prevention and treatment for the right patient at the right time Impact: CONTROL-MYOPIA’s outcomes will have widespread impact on clinical care, patient participation, public health, design of clinical trials, research innovation, and policy changes