Data-driven study on why wrist pulse can assess health conditions.

Pulse diagnosis (PD) is a traditional diagnostic technique for health assessments, wherein experienced physicians palpate the wrist pulse at the radial artery to evaluate an individual's health status. However, the scientific validity of PD has been questioned due to the lack of quantitative and objective evidence. Specifically, variations in wrist pulse waves across different health conditions remain underexplored. A fundamental challenge lies in the quantitative characterization of pulse waveforms and their correlations with underlying physiological or pathological states. To fill these gaps, we design a data-driven analysis architecture consisting of a quantitative analysis method, medical knowledge, and association establishment. The quantitative analysis method systematically quantifies the pulse waves and presents the pulse characteristics, typical pulse wave, feature distributions, and recognition performance. Experiments on 900 samples demonstrate significant differences in pulse waveforms from various disease categories. Further, feature visualization and classification present distinct variations in pulse across different health conditions. By integrating the quantitative results with medical knowledge, we establish the correlations between wrist pulse and health status, interpreting how physiological changes influence pulse waveform morphology. This study is the first to quantitatively explore why pulse wave is able to evaluate health conditions, thereby addressing longstanding skepticism surrounding pulse diagnosis. The findings of this work significantly enhance PD's credibility.