Clinical validation of artificial intelligence-based cataract screening solution with smartphone images (Logy AI cataract screening module)

Mano Aarthi V. M.; Nivedita Tiwari; Vinay Khobragade; Mitali Pareek; Anand Panchbhai; Priyanjit Ghosh; Jayachandhran Saravanan

doi:10.18203/2349-3933.ijam20240007

Authors

Mano Aarthi V. M. Aster Specialty Hospital and Dr. Moopen’s Medical College, Wayanad, Kerala, India
Nivedita Tiwari Logy AI, Hyderabad, Telangana, India
Vinay Khobragade Logy AI, Hyderabad, Telangana, India
Mitali Pareek Logy AI, Hyderabad, Telangana, India
Anand Panchbhai Logy AI, Hyderabad, Telangana, India
Priyanjit Ghosh Logy AI, Hyderabad, Telangana, India
Jayachandhran Saravanan Logy AI, Hyderabad, Telangana, India

DOI:

https://doi.org/10.18203/2349-3933.ijam20240007

Keywords:

Cataract, Artificial intelligence, Smartphone, Deep learning

Abstract

Background: Purpose of the study was to clinically assess the accuracy of Logy AI cataract screening solution, an artificial intelligence-based module, which works through WhatsApp and also as a separate smart phone application, that can detect cataracts using images taken by a smartphone camera, by comparing with slit lamp based diagnoses made by ophthalmologists.

Methods: A prospective clinical study was conducted in an eye clinic of a tertiary care hospital in the southern part of India with 437 patients. Smartphone images taken were sent to the Logy AI cataract screening solution which predicted if the patient had cataract or not. It graded cataracts as immature and mature. Patients were examined by ophthalmologists with slit-lamp and diagnosis was documented. Both were compared.

Results: 794 eye images were included in the study. The overall accuracy of the AI screening solution for cataract detection was computed to be 90.08%. Further, the accuracy was 88.02% for immature cataract, 97.16% for mature cataract, and 90.08% normal category. The sensitivity was 90.38%, the specificity was 89.87%, and the F1 score was 87.98%. The positive predictive value was 85.71% and the negative predictive value was 93.29%. Logy AI cataract prediction module’s AUC (0.8946) falls under the good category.

Conclusions: Logy AI cataract screening module could work as an effective cataract screening tool at the community level in remote areas where there is no expensive equipment and ophthalmic health care workers considering the accuracy and efficiency to work in low resource settings. It can also be a good home screening tool suitable for the post-COVID era.

Metrics

Metrics Loading ...

References

Brian G, Taylor H. Cataract blindness: challenges for the 21st century. Bull World Health Org. 2001;79:249-56.

Allen D, Vasavada A. Cataract and surgery for cataract. BMJ. 2006;333(7559):128-32.

Naghavi M, Wang H, Lozano R, Davis A, Liang X, Zhou M. Global burden of disease collaborative network. global, regional, and national age–sex specific all-cause and cause specific mortality for 240 causes of death, 1990–2013: a systematic analysis for the global burden of disease study 2013. Lancet. 2015;385(9963):117-71.

Pascolini D, Mariotti SP. Global estimates of visual impairment: 2010. Br J Ophthalmol. 2012;96(5):614-8.

Wang L, Zhang K, Liu X, Long E, Jiang J, An Y, et al. Comparative analysis of image classification methods for automatic diagnosis of ophthalmic images. Scientific Rep. 2017;7(1):41545.

Goh JHL, Lim ZW, Fang X, Anees A, Nusinovici S, Rim TH, Cheng CY, Tham YC. Artificial Intelligence for Cataract Detection and Management. Asia Pac J Ophthalmol (Phila). 2020;9(2):88-95.

Gunasekeran DV, Wong TY. Artificial Intelligence in Ophthalmology in 2020: A Technology on the Cusp for Translation and Implementation. Asia Pac J Ophthalmol (Phila). 2020;9(2):61-6.

Raju M, Pagidimarri V, Barreto R, Kadam A, Kasivajjala V, Aswath A. Development of a Deep Learning Algorithm for Automatic Diagnosis of Diabetic Retinopathy. Stud Health Technol Inform. 2017;245:559-63.

P Burlina PM, Joshi N, Pekala M, Pacheco KD, Freund DE, Bressler NM. Automated Grading of Age-Related Macular Degeneration From Color Fundus Images Using Deep Convolutional Neural Networks. JAMA Ophthalmol. 2017;135(11):1170-6.

Ting DSW, Cheung CY, Lim G, Tan GSW, Quang ND, Gan A, et al. Development and Validation of a Deep Learning System for Diabetic Retinopathy and Related Eye Diseases Using Retinal Images From Multiethnic Populations With Diabetes. JAMA. 2017;318(22):2211-23.

Poplin R, Varadarajan AV, Blumer K, Liu Y, McConnell MV, Corrado GS, et al. Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning. Nat Biomed Eng. 2018;2(3):158-64.

Kermany DS, Goldbaum M, Cai W, Valentim CCS, Liang H, Baxter SL, et al. Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning. Cell. 2018;172(5):1122-31.

Askarian B, Ho P, Chong JW. Detecting Cataract Using Smartphones. IEEE J Transl Eng Health Med. 2021;9:3800110.

Yamashita R, Nishio M, Do RKG, Togashi K. Convolutional neural networks: an overview and application in radiology. Insights Imaging. 2018;9(4):611-29.

Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, et al. PyTorch: An Imperative Style, High-Performance Deep Learning Library. Advances in Neural Information Processing Systems 32. Wallach H, Larochelle H, Beygelzimer A, d’Alch´e Buc F, Fox E, Garnett R, editors. Curran Associates, Inc. 2019;8024-35.

Falcon W. The PyTorch Lightning team. PyTorch Lightning. 2019.

Nirmalan PK, Robin AL, Katz J, Tielsch JM, Thulasiraj RD, Krishnadas R, Ramakrishnan R. Risk factors for age related cataract in a rural population of southern India: the Aravind Comprehensive Eye Study. Br J Ophthalmol. 2004;88(8):989-94.

Chen YI, Yang KH. Consort 2010. The Lancet. 2010;376(9737):230.

Lin H, Li R, Liu Z, Chen J, Yang Y, Chen H, et al. Diagnostic efficacy and therapeutic decision-making capacity of an artificial intelligence platform for childhood cataracts in eye clinics: a multicentre randomized controlled trial. EClinicalMedicine. 2019;9:52-9.

Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, et al. Scikit-learn: Machine learning in Python. J Machine Learning Res. 2011;12:2825-30.

Virtanen P, Gommers R, Oliphant TE, Haberland M, Reddy T, Cournapeau D, et al. SciPy 1.0 Contributors. SciPy 1.0: Fundamental Algorithms for Scientific Computing in Python. Nature Methods. 2020;17:261-72.

Harris CR, Millman KJ, van der Walt SJ, Gommers R, Virtanen P, Cournapeau D, et al. Array programming with NumPy. Nature. 2020;585:357-62.

Waskom ML. Seaborn: statistical data visualization. J Open Source Software. 2021;6(60):3021.

Hunter JD. Matplotlib: A 2d graphics environment. Computing in Science Engineering. 2007;9(3):90-5.

Nahm FS. Receiver operating characteristic curve: overview and practical use for clinicians. Korean J Anesthesiol. 2022;75(1):25-36.

Pareek M, Kaushik B. Artificial intelligence in prosthodontics: a scoping review on current applications and future possibilities. Int J Adv Med. 2022;9:367.

Lam D, Rao SK, Ratra V, Liu Y, Mitchell P, King J, et al. Cataract (primer). Nat Rev Dis Primers. 2015;1:1.

Resnikoff S, Lansingh VC, Washburn L, Felch W, Gauthier TM, Taylor HR, et al. Estimated number of ophthalmologists worldwide (International Council of Ophthalmology update): will we meet the needs? Br J Ophthalmol. 2020;104(4):588-92.

Vasan CS, Gupta S, Shekhar M, Nagu K, Balakrishnan L, Ravindran RD, et al. Accuracy of an artificial intelligence-based mobile application for detecting cataracts: Results from a field study. Indian J Ophthalmol. 2023;71(8):2984-9.