Nadifit, data-driven diagnosis: a clinical study for evaluating the significance of traditional Chinese medicine organ patterns through pulse diagnosis (nadi pariksha) for accurate pathology predictions

Abstract

Background: Pulse diagnosis or nadipariksha, is a traditional diagnostic technique utilized in ayurveda and traditional Chinese medicine, analyzing various pulse characteristics such as force, patterns, rate, and rhythm to discern underlying health conditions. This method integrates TCM's five-element energy levels and Ayurveda's Tridosha levels to accurately identify the root cause of diseases, enabling practitioners to tailor treatments accordingly. In today's fast-paced world, the need for efficient health monitoring is imperative. However, finding expert practitioners proficient in pulse diagnosis is becoming increasingly challenging, necessitating the development of systems capable of providing personalized health insights based on accurate root-cause analysis. Methods: In this study, we compared predicted symptoms derived from objective TCM organ pattern analysis using the Nadifit pulse diagnosis system with subjective clinical assessments of patients' symptoms. TCM organ patterns were determined based on the combination of five elements and their Yin/Yang energy levels. Pulse signals were collected from 105 individuals and compared with clinical evaluations of patients' symptoms. Results: The analysis revealed a high level of agreement between the clinical assessment of symptoms and the predicted organ patterns, with a Kappa coefficient of 0.82. This suggests that objective pulse analysis effectively identifies root causes, aligning with subjective assessments. Conclusions: The findings of this study underscore the validity and reliability of objective pulse analysis in diagnosing health conditions. By demonstrating significant agreement with subjective clinical assessments, this method provides a promising avenue for enhancing diagnostic accuracy and facilitating personalized treatment strategies based on individual health profiles.