C-GAN Augmented Framework for Digital Nadi Tantra and Cardiovascular Risk Estimation

DOI

10.2991/978-94-6239-789-7_34How to use a DOI?

Keywords

Nadi Tantra; PPG; CVD Risk; C-GAN Data Augmentation; Ayurvedic Informatics

Abstract

Traditional Nadi Tantra is a pulse diagnosis technique rooted in Ayurveda. It provides a non-invasive way to assess a person’s health by feeling three specific points on the radial artery: Vata, Pitta, and Kapha. Even though this is a comprehensive system, it often struggles in modern clinical settings because the results depend on a practitioner’s subjective interpretation and there aren't enough large digital datasets available. This research introduces a new diagnostic framework by building a wearable module using an ESP32 microcontroller and three-point Photoplethysmography (PPG) sensors to capture these pulses. Since clinical data is scarce, an Enhanced Conditional Generative Adversarial Network (C-GAN) has been used to grow the original 45-person pilot group into a much stronger dataset of 1,000 samples. Several machine learning models have been tested to see which could best estimate Cardiovascular Disease (CVD) risk. Logistic Regression ended up being the most effective tool, reaching an F1-score of 0.7027 and an accuracy of 61.5%. When analyzed which features mattered the most, the data actually supported Pitta amplitude and the consistency of the Vata and Pitta pulses were the main digital markers for CVD risk. These results show that combining multi-node PPG sensing with generative AI offers a real, scalable way to bring Nadi interpretation into modern healthcare.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Aditya Tandon
AU  - Vivek Kumar
AU  - Tanupriya Choudhury
PY  - 2026
DA  - 2026/10/08
TI  - C-GAN Augmented Framework for Digital Nadi Tantra and Cardiovascular Risk Estimation
BT  - Proceedings of theInternational Conference on Innovation and Practices in Artificial Intelligence (ICIPAI 2026)
PB  - Atlantis Press
SP  - 495
EP  - 506
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-789-7_34
DO  - 10.2991/978-94-6239-789-7_34
ID  - Tandon2026
ER  -