Development and deployment of a smartphone application for diagnosing trachoma: Leveraging code-free deep learning and edge artificial intelligence

Daniel Milad; Fares Antaki; Marie-Claude Robert; Renaud Duval

doi:10.4103/sjopt.sjopt_106_22

Development and deployment of a smartphone application for diagnosing trachoma: Leveraging code-free deep learning and edge artificial intelligence

Saudi J Ophthalmol. 2023 Feb 16;37(3):200-206. doi: 10.4103/sjopt.sjopt_106_22. eCollection 2023 Jul-Sep.

Authors

Daniel Milad^{1

2

3}, Fares Antaki^{1

2

3}, Marie-Claude Robert^{1

3}, Renaud Duval^{1

2}

Affiliations

¹ Department of Ophthalmology, University of Montreal, Montreal, Quebec, Canada.
² Department of Ophthalmology, Maisonneuve-Rosemont Hospital, Montreal, Quebec, Canada.
³ Department of Ophthalmology, University of Montreal Hospital, Montreal, Quebec, Canada.

Abstract

Purpose: Automated machine learning (AutoML) allows clinicians without coding experience to build their own deep learning (DL) models. This study assesses the performance of AutoML in diagnosing trachoma from field-collected conjunctival images and compares it to expert-designed DL models.

Methods: Two ophthalmology trainees without coding experience carried out AutoML model design using a publicly available image data set of field-collected conjunctival images (1656 labeled images). We designed two binary models to differentiate trachomatous inflammation-follicular (TF) and trachomatous inflammation-intense (TI) from normal. We then integrated an Edge model into an Android application using Google Firebase to make offline diagnoses.

Results: The AutoML models showed high diagnostic properties in the classification tasks that were comparable or better than the bespoke DL models. The TF model had an area under the precision-recall curve (AuPRC) of 0.945, sensitivity of 87%, specificity of 88%, and accuracy of 88%. The TI model had an AuPRC of 0.975, sensitivity of 95%, specificity of 92%, and accuracy of 93%. Through the Android app and using an external dataset, the AutoML model had an AuPRC of 0.875, sensitivity of 83%, specificity of 81%, and accuracy of 83%.

Conclusion: AutoML models created by ophthalmologists without coding experience were comparable or better than bespoke models trained on the same dataset. Using AutoML to create models and edge computing to deploy them into smartphone-based apps, our approach brings the whole spectrum of DL model design into the hands of clinicians. This approach has the potential to democratize access to artificial intelligence.

Keywords: Artificial intelligence; deep learning; public health; screening; trachoma.