Title:A Multi-dimensional Data Mining-based Study on the Prescriptions
Developed by Professor Xu Zhiyin in Treating Thyroid Nodules
Volume: 24
Issue: 9
Author(s): Hai-Jian Sun, Xiao-Man Wei, Ming Lu, Hong Zhu*Yao Zhu*
Affiliation:
- Department of General Surgery, Affiliated Hospital of Nanjing University of Chinese Medicine, Nanjing 210029, China
- Nanjing University of Chinese Medicine, Nanjing 210023, China
Keywords:
Academic inheritance and innovation, data mining, medical case review and research, thyroid nodules, Curcuma longa, radix codonopsis.
Abstract:
Objectives: In this study, we employed a multi-dimensional data mining approach to
examine the clinical instances where Professor Xu Zhiyin treated thyroid nodules. Our aim is to
understand the patterns of symptoms, underlying causes, and treatment approaches used for thyroid
nodules. By doing so, the intention is to distill the essential aspects, compile Professor Xu
Zhiyin's clinical insights, and investigate his scholarly perspectives.
Methods: Professor Xu Zhiyin's clinical diagnoses and treatments spanning from 2009 to 2019
were entered into Microsoft Excel. Subsequently, the collected data was imported into the Medcase
V5.2 system to facilitate data mining. Various techniques, such as frequency-based method,
association rule analysis, and clustering, including a decentralized system clustering approach,
were employed on a set of 346 cases involving patients with thyroid nodules that conformed
to the specified criteria. The primary focus was on extracting insights regarding symptoms
and the underlying causes from the medical records. By integrating these findings with
Professor Xu Zhiyin's clinical expertise, we examined and summarized the outcomes of the data
mining process.
Results: The fundamental prescriptions were successfully extracted using the techniques for
mining across multiple dimensions. Utilizing the scattered grouping of these prescriptions and
with reference to the cluster analysis of the frequency-linked system, the fundamental prescriptions
proposed by Professor Xu Zhiyin for addressing thyroid nodules encompass the following
ingredients: Glycyrrhiza uralensis Fisch, Cortex Moutan, Paeoniae radix rubra, Curcuma longa
L., Radix Curcumae, persica seed, Citri Reticulatae Viride Pericarpium, Pinellia ternata, Spica
Prunellae, Ostreae concha, Gleditsia sinensis spine, Tuckahoe and Radix Codonopsis.
Conclusion: The fundamental prescriptions were acquired using the frequency approach, association
rule technique, k-means clustering approach, and systematic clustering approach. The
research findings corroborate one another, demonstrating that Professor Xu Zhiyin's approach to
distinguishing and treating thyroid nodules is embodied in distinct prescriptions tailored to specific
diseases.
