Diabetes Screening and Monitoring Using Tongue Images and Self-reported Symptoms: a Machine Learning Approach

NCT05819151 | Unknown

• 1 other identifier: HMRF19200811
• Study Type: observational
• Target: 4,000
• Locations: 1 country
• Sites: 2

Brief Summary

Study Background: Diabetes mellitus (DM) is a major non-communicable disease. Diagnosis and self-management of DM is important. Currently, detection of diabetes requires blood tests, which is costly and inconvenient, especially for elderlies.Tongue diagnosis has been used in Chinese medicine as a routine diagnostic method, and it has recently been studied for detection of DM and diabetic retinopathy (DR). We have developed a method for taking tongue images using smartphone, which can reveal more detailed features than conventional clinical tongue inspection. There are many limitations of the preliminary study. Therefore, it is our plan in this study to address these specific limitations with the following objectives. The results of this study will enable us to develop a practical App for diabetes screening and monitoring. Study Objective The aim of the study is to develop an algorithm for diabetes screening, with the following objectives:

1. 1.. To determine the sensitivity and specificity of tongue images taken with smartphone in predicting abnormal HbA1c (≥6.5%);
2. 2.To determine tongue image features responsible for the classification of normal and abnormal levels of HbA1c (≥6.5%);
3. 3.To determine the sensitivity and specificity of tongues image in predicting four different levels of HbA1c: \<6% (normal), 6-6.4% (prediabetes), 6.5-8.9% (diabetes) and ≥ 9% (diabetes with high HbA1c);
4. 4.To determine the sensitivity and specificity of combining image analysis results with the results from a TCM symptom questionnaire in predicting the four levels of HbA1c.
5. 5.Tongue segmentation The images containing the tongue and its surrounding area will be processed for segmentation of the tongue area. This segmentation is carried out by a computer algorithm developed in-house by machine learning.
6. 6.Machine learning Two approaches will be used in machine learning. In the first approach, we will first perform image classification of either normal or abnormal HbA1c and generate the probabilities for the classification using convolutional neural networks (CNNs) (Anwar et al., 2016; Ødegaard et al., 2016). Then we will try to classify the images into four different classes according to their HbA1c level: \<6% (normal), 6-6.4% (prediabetes), 6.5-8.9% (diabetes) and ≥ 9% (diabetes with high HbA1c).

Conditions

Diabetes Mellitus

Outcome Measures

Primary Outcomes (1)

• Tongue image features

  We will extract tongue image features and perform image classification of either normal or abnormal HbA1c and generate the probabilities for the classification using convolutional neural networks (CNNs). Then we will try to classify the images into four different classes according to their HbA1c level: \<6% (normal), 6-6.4% (prediabetes), 6.5-8.9% (diabetes) and ≥ 9% (diabetes with high HbA1c). Then find out whether there is any difference among touge images in different groups.

  Through study completion, an average of 1year

Secondary Outcomes (1)

• Symptom patterns

  Through study completion, an average of 1year

Study Arms (4)

HbA1c<6% (normal)

Subjects with HbA1c\<6%, i.e, non-diabetes population

Diagnostic Test: HbA1c Test

HbA1c 6-6.4% (prediabetes)

Subjects with HbA1c 6-6.4%, i.e, prediabetes population

Diagnostic Test: HbA1c Test

HbA1c 6.5-8.9% (diabetes)

Subjects with HbA1c HbA1c 6.5-8.9%, i.e. diabetes population

Diagnostic Test: HbA1c Test

HbA1c≥ 9% (diabetes with high HbA1c)

Subjects with HbA1c≥ 9%, i.e. diabetes population with high HbA1c

Diagnostic Test: HbA1c Test

Interventions

HbA1c Test DIAGNOSTIC_TEST

HbA1c Test is required. No other interventions. The researchers will only take photos of the subjects' tongues, and ask them to fulfil a questionnaire.

HbA1c 6-6.4% (prediabetes); HbA1c 6.5-8.9% (diabetes); HbA1c<6% (normal); HbA1c≥ 9% (diabetes with high HbA1c)

Eligibility Criteria

• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

Adult subjects with HbA1c test results from a laboratory that meets the ISO 15189 standard, such as those laboratories used by the Hospital Authority of Hong Kong.

You may qualify if:

• Adult subjects With HbA1c test results from a laboratory meeting the ISO 15189 standard within two weeks before or after the tongue images and questionnaire collection.

You may not qualify if:

• Unable to give consent Unable to answer the questionnaire or to cooperate in tongue image collection Unable to understand written Chinese or English.

Sponsors & Collaborators

• Hong Kong Baptist University: lead
• Health and Medical Research Fund: collaborator
• The Queen Elizabeth Hospital: collaborator
• Guangdong Provincial Hospital of Traditional Chinese Medicine: collaborator

Study Sites (2)

School of Chinese Medicine Building

Kowloon Tong, Kowloon, 0000, Hong Kong

NOT YET RECRUITING

Queen Elizabeth Hospital

Kowloon, Hong Kong

RECRUITING

MeSH Terms

Conditions

Diabetes Mellitus

Condition Hierarchy (Ancestors)

Glucose Metabolism Disorders; Metabolic Diseases; Nutritional and Metabolic Diseases; Endocrine System Diseases

Study Officials

• Shi Ping Zhang, PhD

  Hong Kong Baptist University

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Jingting Tian, Bachelor

CONTACT

85254846560; ayatian@hkbu.edu.hk

Shi Ping Zhang, PhD

CONTACT

85234112466; spzhang@hkbu.edu.hk

Study Design

• Study Type: observational
• Observational Model: OTHER
• Time Perspective: CROSS SECTIONAL
• Target Duration: 1 Day
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: March 20, 2023
• First Posted: April 19, 2023
• Study Start: October 12, 2022
• Primary Completion: March 31, 2024
• Study Completion: June 30, 2024
• Last Updated: April 19, 2023

Record last verified: 2022-10

Locations

HK (2)