Work

Integrated Trauma Detection and Tele-Referral System using Hybrid AI

Year: 2026

Type: conference-paper

Abstract: Mental health issues are increasing globally, but there is a shortage of professionals to help everyone immediately. While many AI chatbots exist today, they often fail because they either trigger false alarms too easily or lack real empathy. This paper presents the Integrated Trauma Detection and Tele-Referral System, which solves these problems by moving from just chatting to active medical help. A hybrid approach was employed to build this: the Gemini API handles the conversation to make it feel human and supportive in multiple languages, while a Naive Bayes algorithm runs in the background to objectively calculate a safety score. To prevent the system from panicking over one bad sentence, a Cumulative Trauma Score was implemented, which only flags a crisis if the user shows distress three times in a row. Furthermore, a voice feature was integrated using Pydub and Google Speech so users can speak naturally instead of typing. Our proposed method achieved an accuracy score of 96%.

Source: International Conference on Electronics, Computing, Communication and Control Technology (ICECCC)

DOI: 10.1109/iceccc70334.2026.11633033

Authors: Pranamita Nanda, Sagarika Behera, Ranjana V A, Narmadha L, Ramya P

Institution: CMR University

Language: English

Topic: Mental Health via Writing

Subfield: Social Psychology

Field: Psychology

Domain: Social Sciences

SDG: Good health and well-being

Open Access status: hybrid

OpenAlex ID: W7202363567

FWCI:

Cites: 13

Cited by:

Related to: 10