Field Evaluation of a Mobile App for Assisting Blind and Visually Impaired Travelers to Find Bus Stops.

Purpose: GPS location-based navigation apps are insufficient to aid blind and visually impaired (BVI) travelers for micro-navigation tasks, such as finding the exact location of bus stops. The resulting large gaps could lead to BVI travelers missing their bus. We evaluated the ability of a signage detection mobile app, All_Aboard, to guide BVI travelers precisely to the bus stops compared to Google Maps alone. Methods: The All_Aboard app detected bus stop signs in real-time via smartphone camera using a deep neural network model, and provided distance coded audio feedback to help localize the detected sign. BVI individuals used the All_Aboard and Google Maps app to localize 10 bus stops each in downtown and suburban Boston, Massachusetts. For each bus stop, the subjects used both apps to navigate as close as possible to the physical bus stop sign, starting from 30 to 50 meters away. The outcome measures were success rate and gap distance between the app-indicated location and the actual physical location of the bus stop. Results: The study involved 24 legally blind participants (mean age [SD] = 51 [14] years; 11 [46%] women). The success rate of the All_Aboard app (91%) was significantly higher than the Google Maps (52%, P < 0.001). The gap distance when using the All_Aboard app was significantly lower (mean = 1.8, 95% confidence interval [CI] = 1.2-2.3 meters) compared to the Google Maps alone (mean = 7, 95% CI = 6.5-7.5 meters, P < 0.001). Conclusions: All_Aboard micro-navigation app guided BVI travelers to bus stops more accurately and reliably than a location-based macro-navigation app alone. Translational Relevance: The All_Aboard app together with a macro-navigation app can potentially help BVI individuals independently access public transportation.

Evaluation of a mobile app for dark adaptation measurement in individuals with age-related macular degeneration.

We present clinical evaluation of a mobile app for dark adaptation (DA) measurement in age-related macular degeneration (AMD) patients and in older adults (age > 50 years) without AMD or other retinal disorders (NV). The outcome measures were the area under dark adaptation curve (AUDAC) and the time for visual sensitivity to recover by 3 log units (TR). Larger AUDAC and TR values indicated worse DA response. The association of AUDAC with AMD was analyzed using linear regression, while time-to-event analysis was used for TR. 32 AMD patients (mean ± SD; age:72 ± 6.3 years, VA:0.09 ± 0.08 logMAR) and 25 NV subjects (mean ± sd; age:65 ± 8.7 years, VA:0.049 ± 0.07 logMAR) were measured with the app. Controlling for age, VA, and cataract severity, the AMD presence was significantly associated with higher AUDAC (ß = 0.41, 95% CI 0.18-0.64, p = 0.001) and with slower sensitivity recovery (ß = 0.32, 95% CI 0.15-0.69, p = 0.004). DA measurements with the app were highly correlated with those obtained with AdaptDx-an established clinical device (n = 18, ρ = 0.87, p < 0.001). AMD classification accuracy using the app was 72%, which was comparable to the 71% accuracy of AdaptDx. Our findings indicate that the mobile app provided reliable and clinically meaningful DA measurements that were strongly correlated with the current standard of care in AMD.

Gaze Scanning at Street Crossings by Pedestrians With Homonymous Hemianopia With and Without Hemispatial Neglect.

Purpose: To investigate compensatory gaze-scanning behaviors during street crossings by pedestrians with homonymous hemianopia (HH) and hemispatial neglect (HSN). Methods: Pedestrians with right homonymous hemianopia (RHH) and left homonymous hemianopia without (LHH) and with left spatial-neglect (LHSN) walked on city streets wearing a gaze-tracking system that also captured scene videos. Street-crossing instances were manually annotated, and horizontal gaze scan of magnitude ≥20° and scanning rates were compared within-subject, between the side of the hemifield loss (BlindSide) and the other side (SeeingSide). Proportion of instances with scans to both the left and the right side at nonsignalized crossings (indicative of safe scanning behavior) were compared among the three subject groups. Results: Data from 19 participants (6 LHH, 7 RHH, and 6 with mild [4] or moderate [2] LHSN), consisting of 521 street-crossing instances of a total duration of 201 minutes and 5375 gaze scans, were analyzed. The overall gaze magnitude (mean [95% confidence interval (CI)]) was significantly larger toward the BlindSide (40.4° [39.1°-41.9°]) than the SeeingSide (36° [34.8°-37.3°]; P < 0.001). The scanning rate (mean [95% CI] scans/min) toward the BlindSide (14 [12.5-15.6]) was significantly higher than the SeeingSide (11.5 [10.3°-12.9°]; P < 0.001). The scanning rate in the LHSN group (10.7 [8.9-12.8]) was significantly lower than the LHH group (14 [11.6-17.0]; P = 0.045). The proportion of nonsignalized crossings with scans to both sides was significantly lower in LHSN (58%; P = 0.039) and RHH (51%; P = 0.003) than LHH (75%) participants. Conclusions: All groups demonstrated compensatory scanning, making more gaze scans with larger magnitudes to the blind side. Mild to moderate LHSN adversely impacted the scanning rate.

Impact of Apps as Assistive Devices for Visually Impaired Persons.

The pervasiveness of mobile devices and other associated technologies has affected all aspects of our daily lives. People with visual impairments are no exception, as they increasingly tend to rely on mobile apps for assistance with various visual tasks in daily life. Compared to dedicated visual aids, mobile apps offer advantages such as affordability, versatility, portability, and ubiquity. We have surveyed hundreds of mobile apps of potential interest to people with vision impairments, either released as special assistive apps claiming to help in tasks such as text or object recognition (n = 68), digital accessibility (n = 84), navigation (n = 44), and remote sighted service (n = 4), among others, or marketed as general camera magnification apps that can be used for visual assistance (n = 77). While assistive apps as a whole received positive feedback from visually impaired users, as reported in various studies, evaluations of the usability of every app were typically limited to user reviews, which are often not scientifically informative. Rigorous evaluation studies on the effect of vision assistance apps on daily task performance and quality of life are relatively rare. Moreover, evaluation criteria are difficult to establish, given the heterogeneity of the visual tasks and visual needs of the users. In addition to surveying literature on vision assistance apps, this review discusses the feasibility and necessity of conducting scientific research to understand visual needs and methods to evaluate real-world benefits.

Comparison of visual SLAM and IMU in tracking head movement outdoors.

Tracking head movement in outdoor activities is more challenging than in controlled indoor lab environments. Large-magnitude head scanning is common under natural conditions. Compensatory gaze (head and eye) scanning while walking may be critical for people with visual field loss. We compared the accuracy of two outdoor head tracking methods: differential inertial measurement units (IMU) and simultaneous localization and mapping (SLAM). At a fixed location experiment, a gaze aiming test showed that SLAM outperforms IMU in terms of error (IMU: 9.6°, SLAM: 4.47°). In an urban street walking experiment conducted with five patients with hemifield loss, the IMU drift, quantified by root-mean-square deviation, was as high as 68.1°, while the drift of SLAM was only 5.3°. However, the SLAM method suffered from data loss due to tracking failure (~10% overall, and ~ 18% when crossing streets). Our results show that the SLAM and IMU methods have complementary properties. Because of no data gaps, the differential IMU method may be desirable as compared to SLAM in settings where the signal drift can be removed in post-processing and small gaze estimation errors can be tolerated.

Dark Adaptation and Its Role in Age-Related Macular Degeneration.

Dark adaptation (DA) refers to the slow recovery of visual sensitivity in darkness following exposure to intense or prolonged illumination, which bleaches a significant amount of the rhodopsin. This natural process also offers an opportunity to understand cellular function in the outer retina and evaluate for presence of disease. How our eyes adapt to darkness can be a key indicator of retinal health, which can be altered in the presence of certain diseases, such as age-related macular degeneration (AMD). A specific focus on clinical aspects of DA measurement and its significance to furthering our understanding of AMD has revealed essential findings underlying the pathobiology of the disease. The process of dark adaptation involves phototransduction taking place mainly between the photoreceptor outer segments and the retinal pigment epithelial (RPE) layer. DA occurs over a large range of luminance and is modulated by both cone and rod photoreceptors. In the photopic ranges, rods are saturated and cone cells adapt to the high luminance levels. However, under scotopic ranges, cones are unable to respond to the dim luminance and rods modulate the responses to lower levels of light as they can respond to even a single photon. Since the cone visual cycle is also based on the Muller cells, measuring the impairment in rod-based dark adaptation is thought to be particularly relevant to diseases such as AMD, which involves both photoreceptors and RPE. Dark adaptation parameters are metrics derived from curve-fitting dark adaptation sensitivities over time and can represent specific cellular function. Parameters such as the cone-rod break (CRB) and rod intercept time (RIT) are particularly sensitive to changes in the outer retina. There is some structural and functional continuum between normal aging and the AMD pathology. Many studies have shown an increase of the rod intercept time (RIT), i.e., delays in rod-mediated DA in AMD patients with increasing disease severity determined by increased drusen grade, pigment changes and the presence of subretinal drusenoid deposits (SDD) and association with certain morphological features in the peripheral retina. Specifications of spatial testing location, repeatability of the testing, ease and availability of the testing device in clinical settings, and test duration in elderly population are also important. We provide a detailed overview in light of all these factors.

Area under the dark adaptation curve as a reliable alternate measure of dark adaptation response.

PURPOSE: Quantification of dark adaptation (DA) response using the conventional rod intercept time (RIT) requires very long testing time and may not be measurable in the presence of impairments due to diseases such as age-related macular degeneration (AMD). The goal of this study was to investigate the advantages of using area under the DA curve (AUDAC) as an alternative to the conventional parameters to quantify DA response. METHODS: Data on 136 eyes (AMD: 98, normal controls: 38) from an ongoing longitudinal study on AMD were used. DA was measured using the AdaptDx 20 min protocol. AUDAC was computed from the raw DA characteristic curve at different time points, including 6.5 min and 20 min (default). The presence of AMD in the given eye was predicted using a logistic regression model within the leave-one-out cross-validation framework, with DA response as the predictor while adjusting for age and gender. The DA response variable was either the AUDAC values computed at 6.5 min (AUDAC6.5) or at 20 min (AUDAC20) cut-off, or the conventional RIT. RESULTS: AUDAC6.5 was strongly correlated with AUDAC20 (ß=86, p<0.001, R2=0.87). The accuracy of predicting the presence of AMD using AUDAC20 was 76%, compared with 79% when using RIT, the current gold standard. In addition, when limiting AUDAC calculation to 6.5 min cut-off, the predictive accuracy of AUDAC6.5 was 80%. CONCLUSIONS: AUDAC can be a valuable measure to quantify the overall DA response and can potentially facilitate shorter testing duration while maintaining diagnostic accuracy.

Home-Use Evaluation of a Wearable Collision Warning Device for Individuals With Severe Vision Impairments: A Randomized Clinical Trial.

IMPORTANCE: There is scant rigorous evidence about the real-world mobility benefit of electronic mobility aids. OBJECTIVE: To evaluate the effect of a collision warning device on the number of contacts experienced by blind and visually impaired people in their daily mobility. DESIGN, SETTING, AND PARTICIPANTS: In this double-masked randomized clinical trial, participants used a collision warning device during their daily mobility over a period of 4 weeks. A volunteer sample of 31 independently mobile individuals with severe visual impairments, including total blindness and peripheral visual field restrictions, who used a long cane or guide dog as their habitual mobility aid completed the study. The study was conducted from January 2018 to December 2019. INTERVENTIONS: The device automatically detected collision hazards using a chest-mounted video camera. It randomly switched between 2 modes: active mode (intervention condition), where it provided alerts for detected collision threats via 2 vibrotactile wristbands, and silent mode (control condition), where the device still detected collisions but did not provide any warnings to the user. Scene videos along with the collision warning information were recorded by the device. Potential collisions detected by the device were reviewed and scored, including contacts with the hazards, by 2 independent reviewers. Participants and reviewers were masked to the device operation mode. MAIN OUTCOMES AND MEASURES: Rate of contacts per 100 hazards per hour, compared between the 2 device modes within each participant. Modified intention-to-treat analysis was used. RESULTS: Of the 31 included participants, 18 (58%) were male, and the median (range) age was 61 (25-73) years. A total of 19 participants (61%) had a visual acuity (VA) of light perception or worse, and 28 (90%) reported a long cane as their habitual mobility aid. The median (interquartile range) number of contacts was lower in the active mode compared with silent mode (9.3 [6.6-14.9] vs 13.8 [6.9-24.3]; difference, 4.5; 95% CI, 1.5-10.7; P < .001). Controlling for demographic characteristics, presence of VA better than light perception, and fall history, the rate of contacts significantly reduced in the active mode compared with the silent mode (ß = 0.63; 95% CI, 0.54-0.73; P < .001). CONCLUSIONS AND RELEVANCE: In this study involving 31 visually impaired participants, the collision warnings were associated with a reduced rate of contacts with obstacles in daily mobility, indicating the potential of the device to augment habitual mobility aids. TRIAL REGISTRATION: ClinicalTrials.gov Identifier: NCT03057496.

Influence of COVID-19 Lockdowns on the Usage of a Vision Assistance App Among Global Users With Visual Impairment: Big Data Analytics Study.

BACKGROUND: Millions of individuals with visual impairment use vision assistance apps to help with their daily activities. The most widely used vision assistance apps are magnifier apps. It is still largely unknown what the apps are used for. Lack of insight into the visual needs of individuals with visual impairment is a hurdle for the development of more effective assistive technologies. OBJECTIVE: This study aimed to investigate how needs for visual aids may vary with social activities, by observing the changes in the usage of a smartphone magnifier app when many users take breaks from work. METHODS: The number of launches of the SuperVision Magnifier app was determined retrospectively from 2018 to 2020 from among active users worldwide. The fluctuation in app usage was examined by comparing weekday vs weekend periods, Christmas and new year vs nonholiday seasons, and COVID-19 lockdowns vs the easing of restriction during the pandemic. RESULTS: On average, the app was used 262,466 times by 38,237 users each month in 2020 worldwide. There were two major trough points on the timeline of weekly app usage, one aligned with the COVID-19 lockdowns in April 2020 and another aligned with the Christmas and new year week in 2018 and 2019. The app launches declined by 6947 (11% decline; P<.001) during the lockdown and by 5212 (9% decline; P=.001) during the holiday weeks. There was no significant decline during March to May 2019. App usage compensated for seasonal changes was 8.6% less during weekends than during weekdays (P<.001). CONCLUSIONS: The need for vision assistance technology was slightly lower during breaks and lockdowns, probably because the activities at home were different and less visually demanding. Nevertheless, for the entire user population, the needs for visual aids are still substantial.

Delayed dark adaptation in central serous chorioretinopathy.

PURPOSE: To evaluate the effect of central serous chorioretinopathy (CSCR) on retinal function using dark adaptation in a human subject, and to follow it through resolution of the disease. PATIENTS: Single patient, 50 years old male patient, with acute CSCR in one eye and resolved old CSCR in the other eye. OBSERVATIONS: Observational study in patient with CSCR followed through resolution of the subretinal fluid (52 days). Dark adaptation was assessed using the AdaptDx® (Maculogix Inc.) measured by Rod Intercept time (RIT) in minutes. A normal retinal locus of the same eye on the opposite side of the fovea was used as control. Retinal separation (microns) was measured using Spectralis Optical Coherence Tomography (Spectralis®, HRA + OCT, Heidelberg engineering). Change in time to dark adapt, were correlated with retinal separation measured in microns, during the course of CSCR.The Rod Intercept time was delayed in the area of detached retina compared to the normal region (control) on presentation with retinal separation (RS) of 104 µm. The Rod Intercept time returned to normal as the retinal separation from retinal pigment epithelium decreased and eventually resolved. CONCLUSIONS: This case shows that delay in dark adaptation is proportional to the amount of separation of neurosensory retina from retinal pigment epithelium in CSCR, this may offer a potential of using DA to characterize visual function in CSCR. The association of dark adaptation response with the state of retinal pigment epithelial function and its ability to predict the recurrence of CSCR needs further evaluation.

A smartphone ocular alignment measurement app in school screening for strabismus.

BACKGROUND: Strabismus is the leading risk factor for amblyopia, which should be early detected for minimized visual impairment. However, traditional school screening for strabismus can be challenged due to several factors, most notably training, mobility and cost. The purpose of our study is to evaluate the feasibility of using a smartphone application in school vision screening for detection of strabismus. METHODS: The beta smartphone application, EyeTurn, can measure ocular misalignment by computerized Hirschberg test. The application was used by a school nurse in a routine vision screening for 133 elementary school children. All app measurements were reviewed by an ophthalmologist to assess the rate of successful measurement and were flagged for in-person verification with prism alternating cover test (PACT) using a 2.4Δ threshold (root mean squared error of the app). A receiver operating characteristic (ROC) curve was used to determine the best sensitivity and specificity for an 8Δ threshold (recommended by AAPOS) with the PACT measurement as ground truth. RESULTS: The nurse obtained at least one successful app measurement for 93% of children (125/133). 40 were flagged for PACT, of which 6 were confirmed to have strabismus, including 4 exotropia (10△, 10△, 14△ and 18△), 1 constant esotropia (25△) and 1 accommodative esotropia (14△). Based on the ROC curve, the optimum threshold for the app to detect strabismus was determined to be 3.0△, with the best sensitivity (83.0%), specificity (76.5%). With this threshold the app would have missed one child with accommodative esotriopia, whereas conventional screening missed 3 cases of intermittent extropia. CONCLUSIONS: Results support feasibility of use of the app by personnel without professional training in routine school screenings to improve detection of strabismus.

BASELINE PREDICTORS ASSOCIATED WITH 3-YEAR CHANGES IN DARK ADAPTATION IN AGE-RELATED MACULAR DEGENERATION.

PURPOSE: To assess the relationship between baseline age-related macular degeneration (AMD) and disease stage, as well as optical coherence tomography features seen in AMD, with 3-year changes in dark adaptation (DA). METHODS: Prospective longitudinal study including patients with AMD and a comparison group (n = 42 eyes, 27 patients). At baseline and 3 years, we obtained color fundus photographs, spectral-domain optical coherence tomography, and rod-mediated DA (20 minutes protocol). Multilevel mixed-effect models were used for analyses, with changes in rod intercept time at 3 years as the primary outcome. As some eyes (n = 11) reached the DA testing ceiling value at baseline, we used 3-year changes in area under the DA curve as an additional outcome. RESULTS: Baseline AMD, AMD stage, and hyperreflective foci on optical coherence tomography were associated with larger changes in rod intercept time at 3 years. When change in area under the DA curve was used as an outcome, in addition to these features, the presence of retinal atrophy and drusenoid pigment epithelial detachment had significant associations. New subretinal drusenoid deposits at 3 years were also associated with more pronounced changes in rod intercept time and area under the DA curve. CONCLUSION: Specific optical coherence tomography features are associated with DA impairments over time, which supports that structural changes predict functional loss over 3 years.

Inpatient Virtual Vision Clinic Improves Access to Vision Rehabilitation Before and During the COVID-19 Pandemic.

OBJECTIVE: To describe and evaluate a secure video call system combined with a suite of iPad vision testing apps to improve access to vision rehabilitation assessment for inpatients. DESIGN: Retrospective. SETTING: Two acute care inpatient rehabilitation hospitals and 1 long-term acute care (LTAC) hospital. PARTICIPANTS: Records of inpatients seen by the vision service. INTERVENTIONS: Records from a 1-year telemedicine pilot performed at acute rehabilitation (AR) hospital 1 and then expanded to AR hospital 2 and LTAC hospital during coronavirus disease 2019 (COVID-19) were reviewed. In the virtual visits, an occupational therapist measured the patients' vision with the iPad applications and forwarded results to the off-site Doctor of Optometry (OD) for review prior to a video visit. The OD provided diagnosis and education, press-on prism application supervision, strategies and modifications, and follow-up recommendations. Providers completed the telehealth usability questionnaire (10-point scale). MAIN OUTCOME MEASURES: Vision examinations per month at AR hospital 1 before and with telemedicine. RESULTS: With telemedicine at AR hospital 1, mean visits per month significantly increased from 10.7±5 to 14.9±5 (P=.002). Prism was trialed in 40% of cases of which 83% were successful, similar to previously reported in-person success rates. COVID-19 caused only a marginal decrease in visits per month (P=.08) at AR1, whereas the site without an established program (AR hospital 2) had a 3-4 week gap in care while the program was initiated. Cases at the LTAC hospital tended to be more complex and difficult to manage virtually. The telehealth usability questionnaire median category scores were 7 for Ease of Use, 8 for Interface Quality, 6 for Reliability, and 9 for Satisfaction and Future Use. CONCLUSIONS: The virtual vision clinic process improved inpatient access to eye and visual neurorehabilitation assessment before and during the COVID-19 quarantine and was well accepted by providers and patients.

Without low spatial frequencies, high resolution vision would be detrimental to motion perception.

A normally sighted person can see a grating of 30 cycles per degree or higher, but spatial frequencies needed for motion perception are much lower than that. It is unknown for natural images with a wide spectrum how all the visible spatial frequencies contribute to motion speed perception. In this work, we studied the effect of spatial frequency content on motion speed estimation for sequences of natural and stochastic pixel images by simulating different visual conditions, including normal vision, low vision (low-pass filtering), and complementary vision (high-pass filtering at the same cutoff frequencies of the corresponding low-vision conditions) conditions. Speed was computed using a biological motion energy-based computational model. In natural sequences, there was no difference in speed estimation error between normal vision and low vision conditions, but it was significantly higher for complementary vision conditions (containing only high-frequency components) at higher speeds. In stochastic sequences that had a flat frequency distribution, the error in normal vision condition was significantly larger compared with low vision conditions at high speeds. On the contrary, such a detrimental effect on speed estimation accuracy was not found for low spatial frequencies. The simulation results were consistent with the motion direction detection task performed by human observers viewing stochastic sequences. Together, these results (i) reiterate the importance of low frequencies in motion perception, and (ii) indicate that high frequencies may be detrimental for speed estimation when low frequency content is weak or not present.

Measuring Virtual Reality Headset Resolution and Field of View: Implications for Vision Care Applications.

SIGNIFICANCE: To judge the feasibility of virtual reality (VR) headsets for vision testing and treatment of binocular vision disorders and low vision, angular resolution (logMAR) and field of view must be known and may not be reliably provided. This is the first study to measure the limitations of VR systems for eye care applications. PURPOSE: This study aimed to measure, in a sample of VR headsets, eye-to-screen distance and other physical and optical characteristics needed to calculate minimum angular resolution in logMAR and field of view in determining feasibility for vision applications. METHODS: Eye-to-screen distance was measured, and logMAR, field of view, and maximum convergence demand were calculated for two standalone VR devices, Oculus Rift DK2 and HTC Vive, and, for four smartphone VR headsets, Zeiss VR1, Samsung Gear VR, VR Box, and SunnyPeak, each paired with four high-resolution smartphones, Samsung Galaxy S7/S8, iPhone X, and LG VR30. RESULTS: On average, the smallest letter that could be displayed in VR was 0.41 ± 0.09 (20/51), ranging from 0.59 (20/78) in the DK2 to 0.28 (20/39) in VR Box with S7. Mean field of view was 50.2 ± 4.8°, ranging from 39.6° in the VR Box with S7 to 55° in the HTC Vive. The mean field of view when used as a low vision aid was 23.0° and 12.7° for 2.2× and 4×, respectively. The mean maximum near convergence demand produced for a 60-mm interpupillary distance was 38.6 ± 10.1Δ. CONCLUSIONS: The minimum angular resolution in logMAR of current VR technology is insufficient for visual acuity testing and may be insufficient for standalone treatment of amblyopia. Field of view during movie watching or gaming is about half that reported by manufacturers but adequate for some types of visual field testing. Use for vergence testing and training is a concern for headsets with long eye-to-screen distance or interpupillary distances <60 mm.

Data Acquisition, Processing, and Reduction for Home-Use Trial of a Wearable Video Camera-Based Mobility Aid.

Purpose: Evaluating mobility aids in naturalistic conditions across many days is challenging owing to the sheer amount of data and hard-to-control environments. For a wearable video camera-based collision warning device, we present the methodology for acquisition, reduction, review, and coding of video data for quantitative analyses of mobility outcomes in blind and visually impaired participants. Methods: Scene videos along with collision detection information were obtained from a chest-mounted collision warning device during daily use of the device. The recorded data were analyzed after use. Collision risk events flagged by the device were manually reviewed and coded using a detailed annotation protocol by two independent masked reviewers. Data reduction was achieved by predicting agreements between reviewers based on a machine learning algorithm. Thus, only those events for which disagreements were predicted would be reviewed by the second reviewer. Finally, the ultimate disagreements were resolved via consensus, and mobility-related outcome measures such as percentage of body contacts were obtained. Results: There were 38 hours of device use from 10 participants that were reviewed by both reviewers, with an agreement level of 0.66 for body contacts. The machine learning algorithm trained on 2714 events correctly predicted 90.5% of disagreements. For another 1943 events, the trained model successfully predicted 82% of disagreements, resulting in 81% data reduction. Conclusions: The feasibility of mobility aid evaluation based on a large volume of naturalistic data is demonstrated. Machine learning-based disagreement prediction can lead to data reduction. Translational Relevance: These methods provide a template for determining the real-world benefit of a mobility aid.

Using an Automated Hirschberg Test App to Evaluate Ocular Alignment.

A smartphone app has been developed to perform the automated photographic Hirschberg test for objective measurement of ocular misalignment. By computing the difference in corneal reflection generated by the phone camera flash relative to the iris center based on high resolution images, the app can measure misalignment with a much higher precision than the naked eye performing the Hirschberg test. It has been validated in a previous clinical evaluation study by comparing to the clinical gold standard-prism and alternate cover test. The goal of this article is to describe the testing techniques regarding how to use the app to measure ocular alignment for different fixation distances, without or with cover to break fusion, as well as angle kappa, so that users can use the app to perform equivalent tests typically done in clinic using prisms.

A Mobile Application for Keyword Search in Real-World Scenes.

Keyword search in a cluttered environment is difficult in general, and even more challenging for people with low vision. While magnification can help in reading for low vision people, it does not facilitate efficient visual search due to the constriction of the field of view. The motivating observation for this study is that, in a large number of visual search tasks, people know what are they looking for (i.e., they know the keywords), they just do not know where to find them in the scene. We have developed a mobile application that allows the users to input keywords (by voice or by typing), uses an optical character recognition (OCR) engine to search for the provided keyword in the scene captured by the smartphone camera, and zooms in on the instances of the keyword detected in the captured images, to facilitate efficient information acquisition. In this paper we describe the development and evaluation of various aspects of the application, including comparing the various mainstream OCR engines that power the app, and an evaluation study comparing the app to the conventional optical magnifier vision aid. Normally sighted adults, while wearing blur glasses to lower their visual acuity, performed keyword searches for a series of items ranging from easy to difficult with the app and with a handheld magnifier. While there was no difference in the search times between the two methods for the easier tasks, the app was significantly faster than the magnifier for the difficult tasks.

Development and Preliminary Evaluation of a Smartphone App for Measuring Eye Alignment.

PURPOSE: We evaluate a smartphone application (app) performing an automated photographic Hirschberg test for measurement of eye deviations. METHODS: Three evaluation studies were conducted to measure eye deviations in the horizontal direction. First, gaze angles were measured with respect to the ground truth in nonstrabismic subjects (n = 25) as they fixated monocularly on targets of known eccentricity covering an angular range of approximately ±13°. Second, phoria measurements with the app at near fixation (distance = 40 cm) were compared with the modified Thorington (MT) test in normally-sighted subjects (n = 14). Third, eye deviations using the app were compared to a cover test with prism neutralization (CTPN; n = 66) and Synoptophore (n = 34) in strabismic subjects. Regression analyses were used to compare the app and clinical measurements of the magnitude and direction of eye deviations (prism diopters, Δ). RESULTS: The gaze angles measured by the app closely followed the ground truth (slope = 1.007, R 2 = 0.97, P < 0.001), with a root mean squared error (RMSE) of 2.4Δ. Phoria measurements with the app were consistent with MT (slope = 0.94, R 2 = 0.97, P < 0.001, RMSE = 1.7Δ). Overall, the strabismus measurements with the app were higher than with Synoptophore (slope = 1.15, R 2 = 0.91, P < 0.001), but consistent with CTPN (slope = 0.95, R 2 = 0.95, P < 0.001). After correction of CTPN values for near fixation, the consistency of the app measurements with CTPN was improved further (slope = 1.01). CONCLUSIONS: The app measurements of manifest and latent eye deviations were consistent with the comparator clinical methods. TRANSLATIONAL RELEVANCE: A smartphone app for measurement of eye alignment can be a convenient clinical tool and has potential to be beneficial in telemedicine.