Artificial Intelligence-Assisted Prescription Determination for Orthokeratology Lens Fitting: From Algorithm to Clinical Practice.

OBJECTIVES: To explore the potential of artificial intelligence (AI) to assist prescription determination for orthokeratology (OK) lenses. METHODS: Artificial intelligence algorithm development followed by a real-world trial. A total of 11,502 OK lenses fitting records collected from seven clinical environments covering major brands. Records were randomly divided in a three-way data split. Cross-validation was used to identify the most accurate algorithm, followed by an evaluation using an independent test data set. An online AI-assisted system was implemented and assessed in a real-world trial involving four junior and three senior clinicians. RESULTS: The primary outcome measure was the algorithm's accuracy (ACC). The ACC of the best performance of algorithms to predict the targeted reduction amplitude, lens diameter, and alignment curve of the prescription was 0.80, 0.82, and 0.83, respectively. With the assistance of the AI system, the number of trials required to determine the final prescription significantly decreased for six of the seven participating clinicians (all P <0.01). This reduction was more significant among junior clinicians compared with consultants (0.76±0.60 vs. 0.32±0.60, P <0.001). Junior clinicians achieved clinical outcomes comparable to their seniors, as 93.96% (140/149) and 94.44% (119/126), respectively, of the eyes fitted achieved unaided visual acuity no worse than 0.8 ( P =0.864). CONCLUSIONS: AI can improve prescription efficiency and reduce discrepancies in clinical outcomes among clinicians with differing levels of experience. Embedment of AI in practice should ultimately help lessen the medical burden and improve service quality for myopia boom emerging worldwide.

Effect of mount location on the quantification of light intensity in myopia study.

PURPOSE: To investigate how the mounting location of wearable devices affects the measurement of light intensity. METHODS: Two commercially available wearable devices, HOBO and Clouclip, were used to compare the effects of different mount locations on light intensity measurement. We assessed the consistency of the measurements of the two devices by placing a HOBO and a Clouclip simultaneously in 26 different light environments and measuring the light intensity. To simulate the real-life usage scenarios of the two devices, we had 29 participants wear two HOBOs-one on the wrist and the other on the chest-along with a Clouclip on their spectacles for 1 day; meanwhile, the light intensity was measured and analysed. RESULTS: When under the same light environments, the light intensity measured by the Clouclip was 1.09 times higher than that by the HOBO, with an additional 82.62 units (r2=1.00, p<0.001). When simulating the real-life scenarios, the mean light intensity at the eye-level position was significantly lower than that at the chest position (189.13±665.78 lux vs 490.75±1684.29 lux, p<0.001) and the wrist position (189.13±665.78 lux vs 483.87±1605.50 lux, p<0.001). However, there was no significant difference in light intensity between the wrist and chest positions (483.87±1605.50 lux vs 490.75±1684.29 lux, p=1.00). Using a threshold of 1000 lux for outdoor exposure, the estimated light exposure at the eye-level position was significantly lower than that at the chest position (3.9% vs 7.8%, χ2=266.14, p<0.001) and the wrist position (3.9% vs 7.7%, χ2=254.25, p<0.001). CONCLUSIONS: Our findings revealed significant variations in light exposure among the wrist, chest and eye position. Therefore, caution must be exercised when comparing results obtained from different wearable devices.

Two-Dimensional Peripheral Refraction and Higher-Order Wavefront Aberrations Induced by Orthokeratology Lenses Decentration.

Purpose: The purpose of this study was to explore two-dimensional peripheral refraction and higher-order aberrations (HOAs) induced by orthokeratology lens decentration. Methods: Two-dimensional peripheral refraction and HOAs in a rectangular field (horizontally 60 degrees and vertically 36 degrees) were obtained using an open-view Hartmann-Shack wavefront sensor. The peripheral field was divided into 8 regions according to a combination of superior (UZ) or inferior (LZ) and a value, 1 (T25 to T30), 2 (T20 to T25), 3 (N20 to N25), or 4 (N25 to N30). The decentration of the lens was evaluated based on the change of power in the front of the tangential corneal map. All measurements were taken at the baseline and 1 month after lens fitting. Results: In total, 134 myopic children (age = 12.47 ± 1.70 years, SER = -2.44 ± 1.10 diopters [D]) were recruited. In general, horizontally asymmetrical change was observed in relative peripheral refraction (RPR), spherical aberration (SA), and horizontal coma. The root-mean square of higher order aberration (RMSHOA) and vertical coma demonstrated radial symmetrical change and vertically asymmetric change, respectively. Relative peripheral myopia was significantly increased after the treatment, with more myopic refraction in the temporal side. RPR changes in UZ2, UZ3, UZ4, LZ1, and LZ2 were related to the amount of lens decentration (r ≈ 0.4, P < 0.05). All HOAs increased after lens fitting (around 0.03 um, 0.02 um, 0.04 um, and 0.41 um for SA, horizontal COMA, vertical COMA, and RMSHOA in the periphery region). Conclusions: RPR and HOAs are related to lens decentration, which might contribute to the efficacy of orthokeratology. Translational Relevance: The study found a decentration-related optical feature after 1 month of lens wear, which is a suggested protective factor in myopia treatment. The findings might provide new insights for customized contact lens myopia treatment based on optics.

Characteristics of the Ocular Surface in Myopic Child Candidates of Orthokeratology Lens Wear.

INTRODUCTION: The purpose of this study was to investigate the characteristics of objective ocular surface parameters using non-invasive objective instruments in children with myopia who are candidates for orthokeratology lens wear. METHODS: Children with myopia who are candidates for orthokeratology lens wear were retrospectively investigated. The subjects were divided into three age groups. The Keratograph 5M and LipiView interferometry were used to assess non-invasive tear meniscus height (TMH), non-invasive tear film break-up time (NIBUT), conjunctival hyperemia redness score (RS), meibomian gland loss (MGL) score, lipid layer thickness (LLT), and blink pattern analysis, including the number of partial blinks (PB) and total blinks (TB), as well as the partial blink rate (PBR). RESULTS: A total of 1119 children with myopia (2070 eyes) aged 7-18 years were selected. The mean TMH, NIBUT, and LLT of the subjects was 0.21 mm, 12.45 s, and 65.28 nm, respectively. The mean RS and upper and lower MGL scores were 0.64, 1.00, and 1.06, respectively. The mean PB, TB, and PBR was 5.13, 6.46, and 0.81, respectively. Age was significantly correlated to all ocular surface parameters (p = 0.00), except for PB. NIBUT and LLT did not differ between male participants and female participants (all p > 0.05). TMH, RS, and upper and lower MGL were significantly higher in male participants than in female participants (all p < 0.01). In addition, NIBUT was positively associated with TMH (r = 0.13, p = 0.00) and LLT (r = 0.28, p = 0.00). Both upper and lower MGL were positively correlated with TMH, PB, and TB (all p = 0.00), whereas upper MGL was negatively correlated with NIBUT and LLT (all p < 0.05). TB was negatively correlated with NIBUT and LLT (all p = 0.00). PB had no relation with TMH, NIBUT, and LLT (all p > 0.05). In addition, PBR was positively correlated with NIBUT and LLT (all p = 0.00) but not with TMH, RS, or MGL (all p > 0.05). Overall, 57.00% had a TMH ≤ 0.2 mm, 43.20% had a NIBUT ≤ 10 s, 48.10% had an LLT ≤ 60 nm, and 88.10% had a PBR > 0.4. CONCLUSIONS: Child orthokeratology candidates have enhanced tear secretion and increased meibomian gland deficiency with aging. In addition, the adult dry eye diagnostic criteria may apply to orthokeratology candidates aged 12-18 years but should be lower for younger candidates. Given the proportion of abnormal risk, it is necessary to assess tear film status and blink pattern by reliable and feasible objective examination before fitting orthokeratology.

Outdoor Scene Classrooms to Arrest Myopia: Design and Baseline Characteristics.

PURPOSE: This study aimed to investigate the impact on childhood myopia of classrooms with spatial properties of classrooms resembling those of outdoor environments. This article describes the design, baseline characteristics, and the acceptability of this strategy. METHODS: Classrooms had custom-made wallpaper installed with forest and sky scenes that had spatial frequency spectra comparable with outdoor environments (i.e., outdoor scene classrooms). Acceptability of this strategy was evaluated by questionnaires. Outcomes to access the efficacy include cumulative proportion of myopia, change of cycloplegic spherical equivalent refractive error, and axial length. RESULTS: Ten classes, comprising 520 students, were randomly assigned into outdoor scene or tradition classrooms. There was no difference in refractive status between two groups (myopia/emmetropia/hyperopia, 16.3% vs. 49.4% vs. 34.2% in outdoor scene classrooms, 18.3% vs. 49.0% vs. 32.7% in traditional classrooms; P = .83). Compared with the traditional classrooms, 88.9% of teachers and 87.5% of students felt the outdoor scene classrooms enjoyable, 22.2% of teachers and 75.3% of students reported higher concentration, and 77.8% of teachers and 15.2% of students reported no change. In addition, 44.4% of teachers and 76.0% of students reported higher learning efficiency in the outdoor scene classrooms, and 55.6% of teachers and 18.3% of students reported no change. CONCLUSIONS: Outdoor scene classrooms are appealing to teachers and students. Outcomes of the study will inform the efficacy of this strategy in Chinese children.

Relative Myopic Defocus in the Superior Retina as an Indicator of Myopia Development in Children.

Purpose: To investigate the role of peripheral refraction in children's myopization. Methods: This 2-year study included 214 children (8-15 years old). Refraction across the retina (field of view: 60° × 36°) was measured with a custom-made aberrometer every year. Three datasets were established: dataset 1, 214 subjects from baseline to the first-year visit; dataset 2, 152 subjects from baseline to the second-year visit; and dataset 3, 59 initial emmetropes from baseline to the second-year visit. The baseline refraction of different retina regions was correlated with the central myopic shift, and was compared among groups with different levels of myopic shift. Results: In datasets 1 and 2, the refraction distribution across the retina was significantly different among the subjects who were initially emmetropes but not among those who were initially hyperopic or myopic. Refraction in the central vertical retina, especially in the superior retina (r = -0.5, P < 0.001), was significantly correlated with the myopic shift for emmetropes in that subjects with more relative myopia in the superior retina manifested greater central myopic shifts. In dataset 3, 21 subjects remained emmetropic after 2 years, 15 subjects became myopic at the 1-year visit, and 23 subjects became myopic at the 2-year visit. No difference was found for the relative peripheral refraction in all of the peripheral regions between the stage prior to and after the onset of myopia. Conclusions: Relative myopic defocus in the superior retina could be a predictor of central myopia shift. Changes in relative peripheral refraction are more likely a consequence of myopia progression rather than a cause.

The Reliability and Acceptability of RDx-Based Tele-Controlled Subjective Refraction Compared with Traditional Subjective Refraction.

Purpose: The purpose of this study was to compare the reliability and acceptability of tele-controlled subjective refraction supported by RDx, a new technique that involves optical software designed for controlling phoropters remotely, to traditional subjective refraction. Methods: Sixty-five participants underwent tele-controlled subjective refraction and traditional subjective refraction randomly and nine of them underwent the second tele-controlled subjective refraction measurement on the same day. After their examinations, we distributed a validated satisfaction questionnaire to each participant. The elapsed time taken for refraction, sphere (S), cylinder (C), spherical equivalent (SE), vertical and oblique cylindrical vectors (J0 and J45), and best corrected visual acuity (BCVA) were compared. Age and refractive error type were included as covariates. Bland-Altman analysis was used to assess the agreement between both methods of refraction. Results: The mean age was 20.5 ± 5.9 years for all participants (aged 9 to 40 years); 57% were female participants. The repeatability analysis of tele-controlled method showed no significant differences for all parameters (P > 0.05). We found no statistical differences (P > 0.05) between tele-controlled subjective refraction and traditional subjective refraction for all parameters in either group. The mean difference and 95% limits of agreement for SE, J0, and J45 were -0.03 ± 0.36 diopters (D), -0.00 ± 0.57 D, and -0.01 ± 0.79 D, respectively. The tele-controlled method took more time to perform than the traditional one (P < 0.05). Completed questionnaires were returned by 55 participants (85%), and they showed high satisfaction and acceptance of the tele-controlled method (98%). Conclusions: Tele-controlled subjective refraction results agreed with traditional subjective refraction for all refraction components except for cylinder vectors. In addition, the broad acceptability of tele-controlled subjective refraction means practicability in clinical practice. Translation Relevance: The RDx-based tele-controlled method can provide an alternative to subjective refraction, especially in areas that lack experienced optometrists.

A Deep Learning-Based Framework for Accurate Evaluation of Corneal Treatment Zone After Orthokeratology.

Purpose: Given the robust effectiveness of inhibiting myopia progression, orthokeratology has gained increasing popularity worldwide. However, identifying the boundary and the center of reshaped corneal area (i.e., treatment zone) is the main challenging task in evaluating the performance of orthokeratology. Here we present automated deep learning algorithms to solve the challenges. Methods: A total of 6328 corneal topographical maps, including 2996 axial subtractive maps and 3332 tangential subtractive maps, were collected from 2044 myopic patients who received orthokeratology. The boundary and the center of the treatment zones were annotated by experts as ground truths using axial subtractive maps and tangential subtractive maps, respectively. The algorithms based on neural network structures of fully convolutional networks (FCNs) and convolutional neural networks (CNNs) were developed to automatically identify the boundary and the center of the treatment zone, respectively. Results: The algorithm of FCNs identified the treatment zone boundaries with an accuracy intersection over union (IoU) of 0.90 ± 0.06 (mean ± SD; range, 0.60-0.97). The algorithm of CNNs also identified the treatment zone centers with an average deviation of 0.22 ± 0.22 mm (range, 0.01-1.66 mm). Conclusions: These results show that a deep learning-based solution is able to provide an automatic and accurate tool to accomplish the two main challenges of orthokeratology. Translational Relevance: Deep learning in orthokeratology can shorten the time while maintaining accurate results in clinical practice, which enables clinicians to help more patients daily.

The Clouclip, a wearable device for measuring near-work and outdoor time: validation and comparison of objective measures with questionnaire estimates.

PURPOSE: To validate a novel wearable device that can measure both viewing distance and light exposure, Clouclip, and compare questionnaire estimates regarding near-work and outdoor time with the objective measures obtained using Clouclip. METHODS: Fifteen Clouclips were selected to measure different distances and levels of illuminance. With each Clouclip, five measurements at different distances and light intensities were measured and recorded. Eighty participants wore Clouclips for a week and completed an activity questionnaire afterwards. RESULTS: The intra- and inter-Clouclip coefficients were 1.00 and 0.99 for measuring distance and 1.00 and 1.00 for illuminance, respectively. Within the measurement limit, the maximum relative error was 2.07% for distance and 2.23% for illuminance. Assuming that <30 cm was the typical distance for near-work activities and >1000 Lux was the typical cut-off for outdoor environments, the questionnaire showed a trend of overestimation for both. The greatest overestimation of near-work occurred during the school period [Questionnaire: 4.73 hr (4.73, 5.07) versus Clouclip: 2.16 hr (1.74, 2.78); p < 0.01]. The greatest overestimation of outdoor activity also occurred during the school period [Questionnaire: 1.60 hr (1.33, 1.85) versus Clouclip: 1.21 hr (0.96, 1.50); p < 0.01]. Based on Clouclip, the total time spent outdoors was estimated to be 1.55 hr on school days, of which 0.34 hr occurred after school. For weekend days, however, the duration was only 0.17 hr. CONCLUSIONS: Clouclip had excellent precision and accuracy. Although the agreement between the questionnaire and Clouclip was relatively poor, they were able to complement each other to provide a more logical and feasible assessment of exposure to near-work and outdoor activity. Indoor-oriented lifestyles were found to predominate in Chinese children.

A Novel Approach to Quantify Environmental Risk Factors of Myopia: Combination of Wearable Devices and Big Data Science.

Purpose: To develop a practical approach to quantify the exposure to environmental risk factors of myopia. Methods: In total, 179 children (age, mean ± standard deviation [SD] 9.17 ± 0.52 years) were requested to wear Clouclip, designed to measure working distance (WD) and light intensity (LI), for a whole week. The spherical equivalent refraction (SER) was determined by cycloplegic autorefraction. The raw data of WD and LI were preprocessed through several steps, including data denoising, constructing a two-dimensional WD-LI space, and data sparseness disposing. Weighted linear regression was used to explore the relationship between WD/LI and SER. A novel parameter visual behaviour index (VBI) was developed to summarize the overall impact of WD/LI on SER. Results: The mean ± SD SER of 179 participants was 0.22 ± 1.18 D. WD and LI were positively associated with SER. However, their magnitude of effect on SER varied with the relative level between them. When WD and LI were split up, the detrimental threshold was approximately 40 cm for WD and 6300 lux for LI. VBI was significantly positively associated with SER (ß = 0.0623, R2 = 0.031, P < 0.05). Conclusions: The current study provides a novel approach to quantify environmental risk factors of myopia. Despite the complexity of the interaction between these risk factors and their impact on SER, this information can be summarized as one single-parameter VBI, which provides a useful tool to investigate the effect of environmental factors on myopia development and progression. Translational Relevance: We developed a novel approach to quantify environmental risk factors of myopia.

Objectively measured near work, outdoor exposure and myopia in children.

AIM: To reassess the association between near work, outdoor exposure and myopia in children through an objective approach. METHODS: Eighty-six children (10.13±0.48 years) were asked to wear Clouclip, a newly developed wearable device that is able to measure working distance and eye-level illuminance, for a complete week to obtain information on near work and outdoor exposure. The mean daily Clouclip wearing time was 11.72±1.14 hour. The spherical equivalent refraction was determined by cycloplegic autorefraction. RESULTS: The myopic children were found to be exposed to light intensities >3000 lux (0.68±0.50 hour vs 1.02±0.53 hour, p=0.012) and >5000 lux (0.42±0.35 hour vs 0.63±0.31 hour, p=0.004) for shorter durations on average each day than the non-myopic children. Additionally, the myopic children spent more time on average each day on activities at a distance of <20 cm than non-myopic children (1.89±0.61 hour vs 1.52±0.77 hour, p=0.019). In the multivariate logistic analysis, the time spent with a higher light intensity (>3000 lux (OR=0.27, 95% CI: 0.10 to 0.72, p=0.009); >5000 lux (OR=0.11, 95% CI: 0.02 to 0.56, p=0.008)) and a working distance of <20 cm (in a circumstance of >3000 lux (OR=1.17, 95% CI: 1.09 to 1.86, p=0.038) or in that of >5000 lux (OR=1.12, 95% CI: 1.03 to 1.77, p=0.046)) were the independent protective factors and risk factors, respectively. CONCLUSION: The current study provides novel evidence, based on objective data, to support the association between the intensity of near work, light intensity and myopia. However, the causality and the dose-effect relationship need to be investigated further.

An effectiveness study of a wearable device (Clouclip) intervention in unhealthy visual behaviors among school-age children: A pilot study.

INTRODUCTION: The study aimed to determine the effectiveness of an intervention for unhealthy visual behaviors of school-age children using a wearable device (Clouclip). METHOD: The design was a self-controlled prospective study. Clouclip, with the vibration alert disabled, was first applied to measure baseline near-work behaviors in the first week. The vibration alert was then enabled to signal unhealthy visual behaviors (near-work distance < 30 cm and >5 seconds, or near-work distance <60 cm for >45 minutes) for 3 weeks. Near-work behaviors were measured again at the first week and the first month after intervention, respectively. The changes in behaviors between the baseline and the first week and the first month after intervention were analyzed. RESULTS: Sixty-seven subjects were eligible for this experiment (the mean age 10.45 ±â€Š0.50 years, 34 boys). Children who logged sufficient wearing time (12.30 ±â€Š0.18 hours on weekdays and 12.16 ±â€Š0.23 hours on weekends) were included for analysis. The average daily near-work distance was significantly increased after the vibration intervention. The time ratio of near-work activity <30 cm to the total <60 cm and the frequency of continuous near-work (distance <60 cm and continuous time >30 minutes) were significantly decreased after the intervention. Although some of the effects were reversed with time following the intervention, some were observed to be maintained until the end of the observation period, and the improvement of the behaviors was more prominent in children who had a shorter near-work distance (<30 cm) at baseline. CONCLUSIONS: In conclusion, Clouclip can significantly modify near-work behaviors in school-age children and it can last a certain period of time. If these behaviors are causes of myopia development and progression, Clouclip might provide a strategy for managing myopia.

The Adaptation and Acceptance of Defocus Incorporated Multiple Segment Lens for Chinese Children.

PURPOSE: We investigated the adaptability and acceptance of a novel spectacle lens design that was recently reported to achieve a significant antimyopia effect. DESIGN: A prospective, cross-over study. METHODS: Twenty children were recruited to wear both Defocus Incorporated Multiple Segments (DIMS) and single vision (SV) lens, with a random assignment of which type of lens was experienced first. For each type of lens, high and low contrast central distant visual acuity (VA) and high contrast mid-peripheral near VA were measured at both 500 lux and 50 lux ambient illuminance after 30 minutes' and a week's wearing of the lens. A self-developed questionnaire was applied to evaluate the visual discomfort at the 1-week visit. All quantitative data were analyzed by paired t test, while qualitative data were analyzed with the χ2 or Wilcoxon signed-rank tests. RESULTS: Central VA was not affected by DIMS lens compared with SV lens in all circumstances (all P > .05). However, the mid-peripheral near VA was found to reduce by approximately 0.06 logarithm of minimal angle of resolution unit in 2 of 4 quadrants (500 lux; P < .05) and in 3 quadrants (50 lux; P < .05) for DIMS lenses. No improvement was detected in the 1-week visit. Mid-peripheral blurred vision was the main visual complaint, which was noticed only once or twice a day. Being aware of the average antimyopic efficacy, 90% of children subjects preferred DIMS lenses. CONCLUSION: Mid-peripheral vision through DIMS lenses was slightly affected compared with SV lenses. Otherwise, DIMS lenses received good tolerance and acceptance by Chinese children.

An Objective Comparison of Light Intensity and Near-Visual Tasks Between Rural and Urban School Children in China by a Wearable Device Clouclip.

PURPOSE: To compare light intensity and near-visual tasks objectively between rural and urban children. METHODS: Clouclip, a wearable device, was applied to assess metrics of these two factors in 78 fifth-grade students from an urban and from a rural school. RESULTS: The light intensity experienced by urban students was found significantly lower both in the school period (614.05 ± 178.77 vs. 918.41 ± 257.81 lux, P < 0.001) and on the weekend (444.53 ± 216.65 vs. 882.21 ± 536.67 lux, P < 0.001). The duration of exposure to bright light (>1000 lux) was also substantially shorter for urban students. Although no significant difference was found in near work-related behaviors during the school period and the weekend, for the after-school period the urban students had a shorter average viewing distance (30.94 ± 4.14 vs. 34.81 ± 3.93 cm, P < 0.001), a longer accumulated duration of near work (2.25 ± 0.53 vs. 1.95 ± 0.46 hours, P = 0.010), a greater time ratio of near work (56% ± 14% vs. 49% ± 14%, P = 0.045), and a greater time ratio of excessively close near work (49% ± 13% vs. 40% ± 12%, P = 0.001). CONCLUSIONS: Our data indicate there were substantial differences in light exposure and near-work metrics between the two regions. The correlation between these differences and the discrepancy in regional myopia prevalence needs further investigation. TRANSLATIONAL RELEVANCE: The objective quantification of these metrics might help explain the varied myopia prevalence among regions.