From measuring progression to understanding the signals behind it.
New tools are creating opportunities to connect clinical measurements with real-world behaviour, environmental exposure and data-driven insights—supporting a more continuous view of myopia care.
Myopia care is moving into a technology-enabled era. Traditional clinical assessments remain essential, but emerging tools may add another layer of understanding by capturing information between appointments. Wearable sensors, smart spectacles, smartphone-based data and artificial intelligence could help researchers and clinicians explore how ocular measurements interact with everyday visual environments and behaviours.
The opportunity is not simply to collect more data. It is to translate reliable information into meaningful insight, support clinical judgement and improve continuity of care. The technologies discussed in this report range from working prototypes and validated research models to longer-term concepts that still require development and clinical evaluation.
Predicting Myopia Progression
One of the most significant opportunities for artificial intelligence (AI) in myopia care is the ability to analyse longitudinal clinical information and estimate how myopia may change over time. Age, refractive error, axial length, family history and environmental factors all contribute to an individual's risk profile. The International Myopia Institute identifies a range of genetic, demographic, educational and environmental factors relevant to myopia development and progression (Morgan et al., 2021).
A 2026 study in npj Digital Medicine described a Transformer-based Myopia Progression Predictive Model (MPPM). Its Natural Progression Module was trained using more than 1.1 million refractive records from over 304,000 children and adolescents, while a second module estimated outcomes under selected myopia-control interventions. The model reported promising prediction performance for spherical equivalent and axial length, including external validation (Liu et al., 2026).
Wearable Sensors: Measuring the Visual Environment
Outdoor light exposure is an important research area in myopia prevention. Yet estimating outdoor time from memory can be imprecise. Wearable devices equipped with light sensors offer a way to record illuminance over the day and create a more objective picture of a person's exposure patterns.
The FitSight project demonstrated a smartwatch-based tracker that recorded ambient light levels and synchronised outdoor-time information with a smartphone application. In a small feasibility study involving 23 children, the device captured daily light-exposure patterns and was designed to encourage outdoor activity (Verkicharla et al., 2017).
Such technologies could support research into duration, timing and patterns of outdoor exposure. Sensor readings should nevertheless be interpreted carefully: illuminance at a wearable device is not a direct measure of retinal light exposure, and device placement, clothing, weather and user compliance can affect readings.
Records changing illuminance levels across indoor and outdoor settings.
Builds a timeline of measured light exposure throughout the day.
Transfers readings to an app for review of daily and weekly patterns.
Smart Glasses: Understanding Visual Behaviour
Smart eyewear may extend monitoring beyond light exposure. A spectacle-mounted prototype described by Ramamurthy and colleagues incorporated sensors to measure near-working distance, ambient light intensity and spectral composition, alongside location tracking. Laboratory testing demonstrated the feasibility of measuring viewing distance and light-related parameters using a wearable frame-mounted device (Ramamurthy et al., 2023).
In future iterations, smart eyewear could help characterise aspects of everyday visual behaviour, including:
-
Distance
Working distance: how close a person holds reading material or a digital device.
-
Light
Light exposure: the intensity and spectral characteristics of ambient light.
-
Patterns
Patterns of use: when, for how long, and in what settings near-work behaviours occur.
These measurements could complement clinical information and self-reported behaviour. They do not independently establish the cause of myopia or determine an individual's treatment.
Smartphones: Turning Everyday Signals into Research Data
Smartphones are already embedded in daily life and can serve as platforms for questionnaires, activity logs and connected sensor data. With appropriate permissions, future research applications may explore device-use duration, posture or viewing angle, ambient conditions and broad activity patterns.
There is a growing evidence base examining digital device exposure and myopia. A 2021 systematic review and meta-analysis reported an association between smart-device screen time and myopia, while also highlighting limitations in exposure measurement and the need for better objective data (Foreman et al., 2021). A 2025 dose-response meta-analysis further examined associations between digital screen time and myopia, but observational associations should not be interpreted as proof that screen exposure alone causes myopia (Ha et al., 2025).
The Myopia Digital Twin: Modelling Possible Visual Futures
A digital twin is a virtual representation of a real-world entity or system, updated using relevant data and analytical models. In ophthalmology, digital twins have been discussed as an emerging approach with potential applications in modelling, simulation and personalised decision support (Xu et al., 2025).
Applied to myopia, a future digital-twin framework might integrate clinical measurements, treatment history and selected environmental or behavioural information to represent an individual's changing profile. It could allow researchers to explore hypothetical trajectories or compare possible scenarios. This is a developing concept: a clinically validated, individual-level digital twin for routine myopia management is not yet established.
Concept illustration only. A digital twin would require robust longitudinal data, transparent modelling, external validation, privacy safeguards and prospective evaluation before clinical use.
The Closed-Loop Myopia System
The value of these technologies may be greatest when they work together. A connected system could link clinical measurements with real-world monitoring and follow-up, creating a continuous cycle of observation and review.
- Monitor: Gather relevant clinical metrics alongside objective environmental and contextual information.
- Analyse: Identify longitudinal trends, rate of axial elongation, and behavioural changes.
- Decide: Interpret findings through rigorous professional judgement and evidence-based standards.
- Act: Implement and tailor an appropriate clinical and behavioural management plan.
- Improve: Review longitudinal outcomes regularly and adapt care pathways where necessary.
This approach places the clinician firmly at the centre of decision-making. Technology can organise, contextualise and interpret information, but treatment selection and adaptations should always remain grounded in thorough clinical assessment, patient needs and high-quality evidence.
The Future Myopia Clinic: Simple, Personalised and Preventive
A technology-enabled clinic may bring together advanced ocular measurements, connected monitoring and individualised care planning. Early assessment can identify subtle changes; longitudinal records can help track progression velocity; and digital tools may support seamless communication between visits.
| Capability | Potential Contribution | What is Needed |
|---|---|---|
| Predictive AI | Forecast possible refractive and axial-length trajectories across different control modalities. | External validation, transparent performance metrics and clinical oversight. |
| Wearable Sensors | Measure selected aspects of everyday ambient light exposure and outdoors duration. | Reliable sensor calibration, wear compliance and contextual interpretation. |
| Smart Eyewear | Capture continuous working distance and environmental near-work parameters. | Ergonomic comfort, measurement accuracy, battery life and real-world validation. |
| Digital Platforms | Organise follow-up data, streamline communication and support continuity of care. | Data interoperability, patient privacy, cloud security and informed consent. |
| Digital Twins | Explore personalised simulations, hypothetical scenarios and intervention responses. | Robust predictive models, prospective trials and demonstrated clinical utility. |
Technology should strengthen—not replace—the essential relationship between patients, families and eye care professionals. Equally important are global accessibility, affordability, ethical data governance and the inclusion of diverse populations in clinical trials. Tools that prove effective in controlled laboratory settings must be thoroughly evaluated in real-world clinical and community environments.
Better insights today. Better vision tomorrow.
The future of myopia care will be shaped not by a single device or algorithm, but by how effectively clinical science, responsible technology and human expertise are brought together. From predictive models to connected monitoring, the goal is a deeper understanding of each individual's visual journey—and more informed decisions at every stage.
References
- Morgan, I. G., et al. (2021). IMI Risk Factors for Myopia. Investigative Ophthalmology & Visual Science, 62(5), 3. https://doi.org/10.1167/iovs.62.5.3
- Verkicharla, P. K., et al. (2017). Development of the FitSight Fitness Tracker to Increase Time Outdoors to Prevent Myopia. Translational Vision Science & Technology, 6(3), 20. https://doi.org/10.1167/tvst.6.3.20
- Ramamurthy, D., et al. (2023). Development of smart spectacles to monitor and modify myopia-related health behaviour in children. Ophthalmic and Physiological Optics. https://doi.org/10.1111/opo.13119
- Foreman, J., et al. (2021). Association between digital smart device use and myopia: A systematic review and meta-analysis. The Lancet Digital Health, 3(12), e806–e818. https://doi.org/10.1016/S2589-7500(21)00135-7
- Ha, A., et al. (2025). Digital Screen Time and Myopia: A Systematic Review and Dose-Response Meta-Analysis. JAMA Network Open, 8(2), e2460026. https://doi.org/10.1001/jamanetworkopen.2024.60026
- Liu, S., et al. (2026). AI-guided personalized predictions on myopia progression and interventions. npj Digital Medicine, 9, 129. https://doi.org/10.1038/s41746-025-02308-4
- Xu, K., Chen, X., Liu, B., Jin, K., He, M., & Shi, D. (2025). Digital twins in ophthalmology: Concepts, applications, and challenges. Asia-Pacific Journal of Ophthalmology, 14(6), 100205. https://doi.org/10.1016/j.apjo.2025.100205
Evidence note: The report distinguishes published prototypes and research models from proposed future applications. Predictive accuracy reported in a study does not by itself establish clinical utility. Sensor-derived behavioural data are complementary to, not replacements for, validated eye examinations.
