Constructing a Syndrome Differentiation Model by Combining Latent Structure Analysis of Association Rules： An Example of Kidney Yang Deficiency Syndrome in Primary Osteoporosis
10.13288/j.11-2166/r.2023.24.008
- VernacularTitle:结合关联规则的隐结构分析构建证候状态辨识模型
- Author:
Beibei LI
1
;
Jing WANG
2
;
Xinghua XIANG
1
;
Wenyuan XU
1
;
Weiguo BAI
1
;
Mengyu LIU
1
;
Yukun LI
1
;
Xiaokun WU
3
;
Yongjun WANG
2
;
Wei YANG
1
Author Information
1. Institute of Basic Research in Clinical Medicine， China Academy of Chinese Medical Sciences， Beijing， 100700
2. Institute of Spine Disease， Shanghai University of Traditional Chinese Medicine
3. Department of Mathematics and Science， North China Electric Power University
- Publication Type:Journal Article
- Keywords:
primary osteoporosis;
association rules;
latent structure （latent tree）;
kidney yang deficiency syndrome;
syndrome differentiation model
- From:Journal of Traditional Chinese Medicine
2023;64(24):2522-2531
- CountryChina
- Language:Chinese
-
Abstract:
ObjectiveTo construct a quantitative differentiation model of traditional Chinese medicine （TCM） syndromes by taking primary osteoporosis （POP） with kidney yang deficiency syndrome as an example， and to provide methodological reference for the standardization of syndrome differentiation. MethodsHigh-frequency clinical features of POP were screened by descriptive statistical analysis， and strong association features of POP were obtained by association rule algorithm. On this basis， a latent structure （latent tree） model was established through latent structure analysis， and the implicit and explicit variables （features） related to POP with kidney yang deficiency syndrome were comprehensively clustered， and the clustering results were interpreted by the indexes of mutual information and cumulative information coverage， to explore the primary and secondary symptoms， and to deduce the categories of POP with kidney yang deficiency syndrome based on the probability of the features appearing in the various latent categories. Based on the categories， the clinical feature scores and identification thresholds were calculated， and the syndrome differentiation model of POP with kidney yang deficiency was initially constructed by combining the comprehensive judgment rules. Finally， the results of TCM professionals' judgment were used as the gold standard to further evaluate the effectiveness of the model in assisting the syndrome differentiation. ResultsThe 32 features strongly associated with POP were obtained， and the Bayes information critedon score of the further constructed latent tree model was -15291.93. Based on the mutual information and the cumulative information coverage， the main symptoms of POP with kidney yang deficiency syndrome were bone weakness， fatigue， pale tongue， clear urine， frequent nocturnal urination， cold limbs， thin pulse， white coating， and secondary symptoms were weakness， loss of libido， loose stool， frequent urination， lumbar and knee weakness， and fear of cold. From the probability of the occurrence of each clinical feature in different latent categories of POP with kidney yang deficiency syndrome， the state was introduced as S0 category （none/mild kidney yang syndrome）/ S1 category （moderate kidney yang syndrome）/ S2 category （severe kidney yang syndrome）. Optimizing the preliminary rules of state identification and refining the state of S1 category， the results showed that among 970 patients with POP， there were 520 patients having no/mild kidney yang deficiency syndrome， 224 patients with moderate to mild kidney yang deficiency syndrome， 81 patients with moderate to severe kidney yang deficiency syndrome， and 145 patients with severe kidney yang deficiency syndrome. During the evaluation and validation process， the correct rate of the model assessment index was 0.8835， while the sensitivity was 0.7181， and the specificity was 0.9437. ConclusionCombined with the latent structure analysis of the association rule， the syndrome differentiation model for POP with kidney yang deficiency could be constructed， and the model shows a good quantitative identification effect， which can provide methodological supports for clinicians to improve the efficiency and accuracy of TCM diagnosis.
