An Apriori Algorithm-Based Association Analysis of Analgesic Drugs in Chinese Medicine Prescriptions Recorded From Patients With Rheumatoid Arthritis Pain

Abstract

Chronic pain, a common symptom of people with rheumatoid arthritis, usually behaves as persistent polyarthralgia pain and causes serious damage to patients' physical and mental health. Opioid analgesics can lead to a series of side effects like drug tolerance and addiction. Thus, seeking an alternative therapy and screening out the corresponding analgesic drugs is the key to solving the current dilemma. Traditional Chinese Medicine (TCM) therapy has been recognized internationally for its unique guiding theory and definite curative effect. In this study, we used the Apriori Algorithm to screen out potential analgesics from 311 cases that were treated with compounded medication prescription and collected from "Second Affiliated Hospital of Zhejiang Chinese Medical University" in Hangzhou, China. Data on 18 kinds of clinical symptoms and 16 kinds of Chinese herbs were extracted based on this data mining. We also found 17 association rules and screened out four potential analgesic drugs-"Jinyinhua," "Wugong," "Yiyiren," and "Qingfengteng," which were promised to help in the clinical treatment. Besides, combined with System Cluster Analysis, we provided several different herbal combinations for clinical references.

Keywords: Apriori Algorithm; analgesic drugs; chronic pain; data mining; rheumatoid arthritis (RA).

Figure 1

Flow diagram of Apriori Algorithm-Based Association Analysis of analgesic drugs.

Figure 2

Proportions of different pain symptoms. The proportions of symptoms from 311 cases were classified into two kinds: “pain” and “other symptoms” (On the left). The pain symptoms mainly consisted of four kinds: “Joint pain of lower extremity,” “Upper limb joint pain,” “Polyarthralgia,” and “Lumbosacral pain” (On the right). Pink: Pain; Pastel yellow: Other symptoms; Purple: Joint pain of lower extremity; Green: Upper limb joint pain; Earthy yellow: Polyarthralgia; Blue: Lumbosacral pain.

Figure 3

Frequency of clinical symptoms of patients with chronic pain from rheumatoid arthritis. X-axis: Clinical symptoms; Y-axis: Total cases as well as the frequency that each symptom appeared in 311 cases (At the bottom and top of the column, respectively). Symptoms with their frequencies higher than 10% were enrolled in this study.

Figure 4

Screening of high frequency used herbs. X-axis: High frequency used herbs; Y-axis: Total times as well as its frequency that each herb appeared in 311 cases (At the bottom and top of the column, respectively). Herbs with their frequencies higher than 10% were enrolled in this study.

Figure 5

Different classifications of high frequency used herbs. Sixteen kinds of high frequency used herbs were classified into eight categories with their efficacy.

Figure 6

The network mapping of “Four properties,” “Five flavors,” and “Channel Tropism” of high-frequency herbs (bottle green: “Four properties”; pink: “Five flavors”; blue: “Meridians”; pale green: “Name of each herb”).

Figure 7

The bubble diagram of the grouping matrix for the 17 association rules based on the second-order association between different herbs. (X-axis: “LHS”; Y-axis: “RHS”; Size: “Support”; Color: “Lift.” Data were analyzed by using Apriori association rules and visualized by Python software).

Figure 8

(A–E) The bubble diagram of the third-order association between herbs and symptoms. (Title: “RHS”; X-axis: “Confidence”; Y-axis: “LHS”; Size: “Support”; Color: “Lift.” Data were analyzed by using Apriori association rule method and visualized by Python software).

Figure 9

Tree diagram of systematic clustering of high frequency used drugs.