.png){kind=icon}
.png){kind=icon}
Return
Artificial Intelligence Based Clustering Algorithm for Pulse Diagnosis
.png){kind=icon}
OA
AI
DOI：10.2147/JMDH.S551150.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Junsuk Kim,1 Won-Joon Koh,2 Heeyoung Moon,3 Su Hyun Lim,4 Minsoo Kim,4 HeeJung Kang,5 Hyeongsuk Ryu,1,6 In-Seon Lee4 1School of Information Convergence, Kwangwoon University, Seoul, Republic of Korea; 2Department of Korean Medicine, Graduate School, Kyung Hee University, Seoul, Republic of Korea; 3Department of Meridian and Acupoints, College of Korean Medicine, Semyung University, Jecheon, Republic of Korea; 4Department of Meridian and Acupoints, College of Korean Medicine, Kyung Hee University, Seoul, Republic of Korea; 5DAEYOMEDI Co. Ltd., Ansan, Republic of Korea; 6Department of Neurology, Seoul National University Bundang Hospital, Seongnam, Republic of Korea Correspondence: In-Seon Lee, Department of Meridian and Acupoints, College of Korean Medicine, Kyung Hee University, Dongdaemun-Gu, Seoul, 02447, Republic of Korea, Tel +82-2-961-2204, Email inseon.lee@khu.ac.kr Background: In traditional medicine, pulse palpation is a unique diagnostic technique focusing on identifying patterns of symptoms through subjective assessment of bio-signals. However, its reliability and objectivity have been questioned. We developed an artificial intelligence-based algorithm for clustering doctors’ diagnostic results using unsupervised clustering techniques on pulse waveform signals. Methods: Raw pulse signals were recorded from both wrists of healthy individuals and were then analyzed, with diagnoses provided by a Korean Medicine doctor. To measure pairwise pulse similarity, Dynamic Time Warping (DTW) was used, and Multidimensional Scaling (MDS) was applied for dimensionality reduction, enabling the clustering and validation of data-driven diagnostic patterns. Results: Our findings revealed discrepancies between traditional pulse diagnosis and automated diagnoses, yet the clustering algorithm showed high alignment between data-driven groupings and expert diagnoses. Notably, pulse signals from the left wrist had better alignment in several categories than those from the right wrist (cosine similarity: left hand 0.56 ± 0.13; right hand 0.54 ± 0.15). The “Floating-Sinking” pattern was particularly identifiable, achieving the highest Cosine similarity (0.83). Conclusion: The results suggest significant alignment between data-driven pattern identification and expert diagnoses, especially for the “Floating-Sinking” pattern. Further refinement with diverse populations is necessary, but data-driven diagnostic tools hold potential for standardizing and quantifying traditional pulse diagnosis, moving it toward a scientifically robust practice. Trial Registration: Clinical Research Information Service KCT0007655 (registered on 2024-02-29). Keywords: pulse diagnosis, pulse waveforms, traditional medicine, artificial intelligence, pattern identification
Keywords:
pulse diagnosis
pulse waveforms
traditional medicine
artificial intelligence
pattern identification
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
2.4
Papers:
630
Citations:
5.2K
View more organizations