Education & Certifications


  • Bachelor of Arts, Princeton University (2019)

All Publications


  • Predicting Systemic Health Features from Retinal Fundus Images Using Transfer-Learning-Based Artificial Intelligence Models. Diagnostics (Basel, Switzerland) Khan, N. C., Perera, C., Dow, E. R., Chen, K. M., Mahajan, V. B., Mruthyunjaya, P., Do, D. V., Leng, T., Myung, D. 2022; 12 (7)

    Abstract

    While color fundus photos are used in routine clinical practice to diagnose ophthalmic conditions, evidence suggests that ocular imaging contains valuable information regarding the systemic health features of patients. These features can be identified through computer vision techniques including deep learning (DL) artificial intelligence (AI) models. We aim to construct a DL model that can predict systemic features from fundus images and to determine the optimal method of model construction for this task. Data were collected from a cohort of patients undergoing diabetic retinopathy screening between March 2020 and March 2021. Two models were created for each of 12 systemic health features based on the DenseNet201 architecture: one utilizing transfer learning with images from ImageNet and another from 35,126 fundus images. Here, 1277 fundus images were used to train the AI models. Area under the receiver operating characteristics curve (AUROC) scores were used to compare the model performance. Models utilizing the ImageNet transfer learning data were superior to those using retinal images for transfer learning (mean AUROC 0.78 vs. 0.65, p-value < 0.001). Models using ImageNet pretraining were able to predict systemic features including ethnicity (AUROC 0.93), age > 70 (AUROC 0.90), gender (AUROC 0.85), ACE inhibitor (AUROC 0.82), and ARB medication use (AUROC 0.78). We conclude that fundus images contain valuable information about the systemic characteristics of a patient. To optimize DL model performance, we recommend that even domain specific models consider using transfer learning from more generalized image sets to improve accuracy.

    View details for DOI 10.3390/diagnostics12071714

    View details for PubMedID 35885619

  • Integration of Artificial Intelligence into a Telemedicine-Based Diabetic Retinopathy Screening Program Chen, K., Dow, E. R., Khan, N. C., Levine, M., Perera, C., Phadke, A., Dang, J., Weng, K., Do, D. V., Mahajan, V. B., Mruthyunjaya, P., Mishra, K., Leng, T., Myung, D. ASSOC RESEARCH VISION OPHTHALMOLOGY INC. 2022
  • Predicting systemic health features from retinal fundus images using transfer-learning based AI models Khan, N. C., Perera, C., Dow, E. R., Leng, T., Mahajan, V. B., Mruthyunjaya, P., Do, D. V., Myung, D. ASSOC RESEARCH VISION OPHTHALMOLOGY INC. 2022
  • Real-life Wrist Movement Patterns Capture Motor Impairment in Individuals with Ataxia-Telangiectasia. Cerebellum (London, England) Gupta, A. S., Luddy, A. C., Khan, N. C., Reiling, S., Thornton, J. K. 2022

    Abstract

    Sensitive motor outcome measures are needed to efficiently evaluate novel therapies for neurodegenerative diseases. Devices that can passively collect movement data in the home setting can provide continuous and ecologically valid measures of motor function. We tested the hypothesis that movement patterns extracted from continuous wrist accelerometer data capture motor impairment and disease progression in ataxia-telangiectasia. One week of continuous wrist accelerometer data were collected from 31 individuals with ataxia-telangiectasia and 27 controls aged 2-20 years old. Longitudinal wrist sensor data were collected in 14 ataxia-telangiectasia participants and 13 controls. A novel algorithm was developed to extract wrist submovements from the velocity time series. Wrist sensor features were compared with caregiver-reported motor function on the Caregiver Priorities and Child Health Index of Life with Disabilities survey and ataxia severity on the neurologist-performed Brief Ataxia Rating Scale. Submovements became smaller, slower, and less variable in ataxia-telangiectasia compared to controls. High-frequency oscillations in submovements were increased, and more variable and low-frequency oscillations were decreased and less variable in ataxia-telangiectasia. Wrist movement features correlated strongly with ataxia severity and caregiver-reported function, demonstrated high reliability, and showed significant progression over a 1-year interval. These results show that passive wrist sensor data produces interpretable and reliable measures that are sensitive to disease change, supporting their potential as ecologically valid motor biomarkers. The ability to obtain these measures from a low-cost sensor that is ubiquitous in smartwatches could help facilitate neurological care and participation in research regardless of geography and socioeconomic status.

    View details for DOI 10.1007/s12311-022-01385-5

    View details for PubMedID 35294727

  • Free-Living Motor Activity Monitoring in Ataxia-Telangiectasia. Cerebellum (London, England) Khan, N. C., Pandey, V., Gajos, K. Z., Gupta, A. S. 2021

    Abstract

    With disease-modifying approaches under evaluation in ataxia-telangiectasia and other ataxias, there is a need for objective and reliable biomarkers of free-living motor function. In this study, we test the hypothesis that metrics derived from a single wrist sensor worn at home provide accurate, reliable, and interpretable information about neurological disease severity in children with A-T.A total of 15 children with A-T and 15 age- and sex-matched controls wore a sensor with a triaxial accelerometer on their dominant wrist for 1week at home. Activity intensity measures, derived from the sensor data, were compared with in-person neurological evaluation on the Brief Ataxia Rating Scale (BARS) and performance on a validated computer mouse task.Children with A-T were inactive the same proportion of each day as controls but produced more low intensity movements (p<0.01; Cohen's d=1.48) and fewer high intensity movements (p<0.001; Cohen's d=1.71). The range of activity intensities was markedly reduced in A-T compared to controls (p<0.0001; Cohen's d=2.72). The activity metrics correlated strongly with arm, gait, and total clinical severity (r: 0.71-0.87; p<0.0001), correlated with specific computer task motor features (r: 0.67-0.92; p<0.01), demonstrated high reliability (r: 0.86-0.93; p<0.00001), and were not significantly influenced by age in the healthy control group.Motor activity metrics from a single, inexpensive wrist sensor during free-living behavior provide accurate and reliable information about diagnosis, neurological disease severity, and motor performance. These low-burden measurements are applicable independent of ambulatory status and are potential digital behavioral biomarkers in A-T.

    View details for DOI 10.1007/s12311-021-01306-y

    View details for PubMedID 34302287