Unsupervised Partition Method for Traditional Chinese Medicine Data
Author Information
Author(s): Chen Jing, Xi Guangcheng
Primary Institution: Key Laboratory of Complex Systems and Intelligence Science, Institute of Automation, Chinese Academy of Sciences, Beijing, PR China
Hypothesis
Can a revised mutual information method effectively identify syndromes in Traditional Chinese Medicine data?
Conclusion
The algorithm provides an excellent solution for identifying syndromes in both patient and rat data within the context of Traditional Chinese Medicine.
Supporting Evidence
- The algorithm achieved a sensitivity of 96.48% in identifying syndromes.
- Six hundred and one patients were surveyed to validate the algorithm.
- The study successfully discovered 16 clinically effective patterns.
Takeaway
This study created a smart way to find patterns in health data, helping doctors understand different sicknesses better.
Methodology
The study used a revised mutual information approach to discover patterns in patient and rat data, validating the algorithm through sensitivity analysis.
Potential Biases
Potential biases may arise from the selection of symptoms and the subjective nature of syndrome diagnosis.
Limitations
The study may be limited by the quality and consistency of the data collected from patients and rats.
Participant Demographics
Patients aged 18-65 with chronic renal failure, recruited from six clinical centers in China.
Statistical Information
P-Value
0.0001
Confidence Interval
not provided
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website