An unsupervised partition method based on association delineated revised mutual information
2009

Unsupervised Partition Method for Traditional Chinese Medicine Data

Sample size: 601 publication 10 minutes Evidence: high

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)

10.1186/1471-2105-10-S1-S63

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication