Data Mining of Professor Chen Hongfeng' s Medication Rules for the Patients after Breast Cancer Surgery
YIN Yu-lian,FAN Yi-wei,WU Wei
LongHua Hospital of Shanghai University of Traditional Chinese Medicine,Shanghai 200032, China
Abstract:
Objective Through the method of real data acquisition and machine learning, to explore the medication characteristics of famous Shanghai TCM professor Chen Hongfeng after the operation of regulating breast malignant tumor. Methods The case data of breast cancer patients in Professor Chen' s outpatient department from August 2011 to June 2021 in the past 10 years were collected through the hospital information system of Shanghai University of Traditional Chinese Medicine. Then the data were processed using python 3.7.6 in terms of frequency, association rules and characteristics of traditional Chinese medicine theory. Finally,the results were analyzed based on clinical practice, so as to explore Professor Chen' s medication rules for breast cancer surgery. Results A total of 13 340 prescriptions were counted in this study. The majority of drugs were neutral, accounting for 33.55%. The most delicious was the sweet (137 683, 39.69%). The meridian of tropism mostly entered the spleen meridian (100 242, 18.45%). The top five drug frequencies from high to low were:Poria, Rhizoma Atractylodis Macrocephalae, Radix Adenophorae, raw Radix Astragali seu Hedysari and Radix Salviae Miltiorrhizae. The core drug pair was Rhizoma Atractylodis Macrocephalae–Poria (confidence 97.96%).In addition, a group of basic prescriptions for breast cancer surgery was found in this study, which was composed of Poria–Rhizoma Atractylodis Macrocephalae–Radix Salviae Miltiorrhizae–Radix Adenophorae–Radix Astragali seu Hedyotis–Rhizoma Curcumae. Conclusion Professor Chen Hongfeng pays attention to the regulation of middle-earth and mild attack of pathogenic factors and applies the method of warming and tonifying more after the operation of regulating breast cancer, which can provide new ideas for famous TCM clinical experience research through data mining.
