Poster: Neurodivergence Focus
Public Health & AI
Hosted by Expert Panel
AI Screening for Neurodivergence and Mental Health in Indian Schools
Authors & Affiliations
- Umathurappan Chandrasekar, BE (Mech)
Principal IT Architect, Infraspace, Apple Valley, MN, USA - Kannaiayan Prakash, BE (CS)
Senior Engineering Manager, Huntington National Bank, Minneapolis, MN, USA - Radhika Gupta, BDS, MPH (Epidemiology)
Public Health Specialist, Infraspace, Apple Valley, MN, USA
Correspondence: Umathurappan Chandrasekar, 15224 Florist Circle, Apple Valley, MN 55124; uma@infraspace.net
Conflict of Interest & Funding: No conflicts of interest. Funding: This work received no external funding.
Abstract
Background: Autism 1:68 children, ADHD 11.32%, depression ~150M (NIMHANS).
Objective: Early AI screening via speech/sentiment for school deployment.
Methods: Speech prosody CNNs, sentiment transformers (NIMHANS data). Multilingual gamified apps co-designed with families. Karnataka school pilots (n=25).
Results: Autism 88%, depression 91% accuracy. Linguistic bias <2.5%. Pilots identified 1,200 at-risk, stigma -25%, coping +45%.
Conclusion: Inclusive AI scales neurodivergence support with cultural fairness.
Table 1: Screening Performance
| Condition | Accuracy | Linguistic Fairness | Pilot Impact |
|---|---|---|---|
| Autism | 88% | <2.5% | 1,200 identified |
| ADHD | 86% | <2.5% | Stigma -25% |
| Depression | 91% | <2.5% | Coping +45% |
View Posters