A Development of Inflammatory Bowel Disease Pattern Identification Algorithm Using Case Series Data

NCT04296500 | Completed

• 1 other identifier: KyungheeU
• Study Type: observational
• Target: 67
• Locations: 1 country
• Sites: 1

Brief Summary

This study aimed to identify inflammatory bowel disease (IBD) patterns based on presenting symptoms and to suggest algorithms for determining pattern and herbal prescriptions for corresponding patterns. The investigators collected symptom data of 67 IBD patients who achieved and maintained clinical remissions after they had taken herbal medicine prescriptions. Prescriptions were categorised into 5 patterns, which were named after main features and symptoms of included patients. Associations between presenting symptoms and patterns were visualised using a term frequency inverse document frequency (TF-IDF) method. Determining IBD patterns from symptoms of patients was analysed and charted by decision tree modeling.

Conditions

Inflammatory Bowel Diseases

Keywords

Herbal prescription; Herbal medicine; Pattern identification; Algorithm; Decision tree; TF-IDF

Outcome Measures

Primary Outcomes (1)

• Accuracy of pattern identification algorithm

  Pattern identification algorithm was suggested using a decision tree method. Decision tree method was employed to explore the process of decision making on types of pattern based on clinical features of patients.

  Oct 2015

Study Arms (1)

Decision tree algorithm training/testing

The investigators divided data of 67 patients into 5 groups to do 5 fold cross validation. Four groups were used to train decision tree algorithm and one group was used to test it.

Other: Decision tree modeling

Interventions

Decision tree modeling OTHER

A decision tree analysis was employed to explore the process of decision-making on types of pattern based on the existence or nonexistence of a symptom. At the end of tree presented is the proportion of patients who are categorised into each pattern. In this study, the classification was performed by applying the classification and regression tree (CART) algorithm using Scikit-learn package of Python, which performs a division using the Gini coefficient or the decrement of dispersion. The Gini coefficient is one of the tools for measuring entropy or diversity in each node and it measures the decrement by comparing the information entropy before and after separation. To avoid overfitting, the maximum number of leaf nodes was limited to four and the pruning method which complied with the principle of minimum description length was applied.

Decision tree algorithm training/testing

Eligibility Criteria

• Age: 15 Years - 65 Years
• Sex: all
• Healthy Volunteers: No
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

Patients who had been diagnosed with IBD by gastroenterologist and achieved clinical remission after treatment with herbal medicine prescriptions

You may qualify if:

• Diagnosis of IBD by gastroenterologist
• Patients have achieved and maintained clinical remission of IBD symptoms after they took herbal prescriptions
• Patients have provided written informed consent

You may not qualify if:

• Details regarding any of 25 symptoms were omitted

Sponsors & Collaborators

• Hyangsook Lee, KMD, PhD: lead

Study Sites (1)

Acupuncture & Meridian Science Research Centre

Seoul, 02447, South Korea

Location

Related Publications (6)

• Bernstein CN, Fried M, Krabshuis JH, Cohen H, Eliakim R, Fedail S, Gearry R, Goh KL, Hamid S, Khan AG, LeMair AW, Malfertheiner, Ouyang Q, Rey JF, Sood A, Steinwurz F, Thomsen OO, Thomson A, Watermeyer G. World Gastroenterology Organization Practice Guidelines for the diagnosis and management of IBD in 2010. Inflamm Bowel Dis. 2010 Jan;16(1):112-24. doi: 10.1002/ibd.21048.

  PMID: 19653289 BACKGROUND

• Panaccione R, Rutgeerts P, Sandborn WJ, Feagan B, Schreiber S, Ghosh S. Review article: treatment algorithms to maximize remission and minimize corticosteroid dependence in patients with inflammatory bowel disease. Aliment Pharmacol Ther. 2008 Sep 15;28(6):674-88. doi: 10.1111/j.1365-2036.2008.03753.x.

  PMID: 18532990 BACKGROUND

• Abitbol V, Lahmek P, Buisson A, Olympie A, Poupardin C, Chaussade S, Lesgourgues B, Nahon S. Impact of complementary and alternative medicine on the quality of life in inflammatory bowel disease: results from a French national survey. Eur J Gastroenterol Hepatol. 2014 Mar;26(3):288-94. doi: 10.1097/MEG.0000000000000040.

  PMID: 24407360 BACKGROUND

• Lee MS, Lee JA, Alraek T, Bian ZX, Birch S, Goto H, Jung J, Kao ST, Moon SK, Park B, Park KM, You S, Yun KJ, Zaslawski C. Current research and future directions in pattern identification: Results of an international symposium. Chin J Integr Med. 2016 Dec;22(12):947-955. doi: 10.1007/s11655-014-1833-3. Epub 2014 Jun 18.

  PMID: 24938445 BACKGROUND

• Yu F, Takahashi T, Moriya J, Kawaura K, Yamakawa J, Kusaka K, Itoh T, Morimoto S, Yamaguchi N, Kanda T. Traditional Chinese medicine and Kampo: a review from the distant past for the future. J Int Med Res. 2006 May-Jun;34(3):231-9. doi: 10.1177/147323000603400301.

  PMID: 16866016 BACKGROUND

• Liu B, Zhou X, Wang Y, Hu J, He L, Zhang R, Chen S, Guo Y. Data processing and analysis in real-world traditional Chinese medicine clinical data: challenges and approaches. Stat Med. 2012 Mar 30;31(7):653-60. doi: 10.1002/sim.4417. Epub 2011 Dec 9.

  PMID: 22161304 BACKGROUND

MeSH Terms

Conditions

Inflammatory Bowel Diseases

Condition Hierarchy (Ancestors)

Gastroenteritis; Gastrointestinal Diseases; Digestive System Diseases; Intestinal Diseases

Study Officials

• Hyangsook Lee, Doctor

  Kyunghee University

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: observational
• Observational Model: CASE ONLY
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: SPONSOR INVESTIGATOR
• PI Title: Professor

Study Record Dates

• First Submitted: March 3, 2020
• First Posted: March 5, 2020
• Study Start: November 1, 2007
• Primary Completion: February 28, 2015
• Study Completion: October 28, 2015
• Last Updated: March 6, 2020

Record last verified: 2020-03

Locations

KR (1)