Down Syndrome Detection Through Graphical Analysis of Facial Dysmorphic Features in Newborn Children With Ethnicity/Racial Slicing: An AI/ML-Based Approach. Issue 3 (September 2022)

• Record Type: Journal Article
• Authors: Mehra, Saanvi; Shah, Binoy; Sethi, Ankur; Puri, Ratna; Nimbalkar, Somashekhar
• Is Part Of: Journal of neonatology. Volume 36:Issue 3(2022)
• Page Start: 199
• Page End: 205
• Publication Date: 2022-09
• Subjects: Down syndrome -- postnatal screening -- Google Vision AutoML -- classification and facial recognition -- ethnicity slicing -- race slicing; Neonatology -- Periodicals; Neonatology -- India -- Periodicals; 618.9201
• DOI: 10.1177/09732179221113677
• Languages: English
• ISSNs: 0973-2179

Abstract

Background: Down syndrome (DS) is associated with high mortality in India, due to nondiagnosis/late-diagnosis caused by unavailability of qualified doctors and/or lack of access to expensive medical/diagnostic facilities, especially in rural India. Using artificial intelligence/machine learning graphical pattern recognition tools, relevant facial points can be extracted from children's photographs, facial anomalies can be identified, and probability of DS affliction can be predicted. Methods: Trained Google's Cloud Vision AutoML Image Classification model was employed with ~2, 000 photographs of DS positive children and ~3, 000 photographs of DS negative children. A subset of 300 images, 100 each of Asian, Caucasian, and Other-Race children, was used to train and test 3 race-specific models. These results were compared against a unified model trained and tested with same 300 images. Results: The CloudML model trained with ~5, 000 images initially achieved: Sensitivity—94.6%, specificity—96.9%, and accuracy—96.0%. Upon optimizing confidence threshold to 0.1, model maximized sensitivity at 99.6%, specificity dropped to 93.8%, and accuracy maintained at 96.0%. Each of the race-specific models trained with 100 images each, after optimization, yielded perfect scores on sensitivity, specificity, and accuracy of 100% each. Against this, the unified model with 300 images yielded overall accuracy of 98% (100% sensitivity, 83% specificity for Caucasian children, and 100% sensitivity, 100% specificity for Asian/Other children). Conclusions: Post optimization, this model can be used as an effective postnatal screening tool for DS detection. Preliminary results indicate that race-specific models can achieve even higher accuracy, sensitivity, and specificity.