Integrated Risk Assessment for Madhumeha (Diabetes)

PURPOSE

Further validation of a predictive model developed for the risk assessment of Diabetes based on the modern and Ayurveda principles using machine learning techniques by CCRAS-CARI Bengaluru in association with CIIRC - Centre For Incubation, Innovation, Research and Consultancy, Bengaluru.

BACKGROUND

Adequate care for people with chronic illnesses such as diabetes mellitus has become an increasing challenge for healthcare systems globally. There are several risk assessment scores available worldwide, most of which include questions regarding Age, Gender, Family history, Hypertension, Physical activity, and BMI. Some questionnaires include certain additional parameters such as smoking (Australian risk score), ethnicity (American and Australian risk score), Corticosteroid use (Cambridge score for the UK), and fruit and vegetable intake (Finish risk score).

The present questionnaire is envisaged to include Ayurvedic aetiological parameters in addition to the above and develop a comprehensive Risk Assessment Diabetes predictive model. The machine learning and artificial intelligence expertise was employed for devising scoring and calculation of the percentage of risk.

INVESTIGATORS

Dr. Harshvardhan Tiwari, Associate Professor, CIIRC - Centre For Incubation, Innovation, Research, and Consultancy, Bengaluru, and Dr. Sulochana Bhat, Assistant Director Incharge, Central Ayurveda Research Institute, Bengaluru (under Central Council for Research in Ayurvedic Sciences, Ministry of AYUSH, Govt. of India).

METHODS

A cross-sectional study was carried out using a Risk Assessment Questionnaire with a sample size of 1000 participants, including adults with or without being known cases of Diabetes. The questionnaire was designed to assess the risk of developing Diabetes Mellitus among the general public based on factors influencing the development of the disease in an individual as per Ayurveda literature and other contemporary questionnaires used worldwide. The responses of the participants were clubbed into a dataset that was fed into machine learning algorithms, and risk evaluation was done based on Artificial Intelligence.

RESULTS

Risk of development of Diabetes Mellitus in the general public was evaluated, and a Diabetes predictive model for early detection of Diabetes Mellitus, based on machine learning techniques, was developed.

ACKNOWLEDGEMENT

• Dr. Kavya N., Sr. Consultant (Ayu)
• Miss. Anagha Jenu, SRF(Bio-Statistics)

REFERENCES

• Hausler B, Fischer GC, Meyer S, Sturm D. Risk assessment in diabetes management: how do general practitioners estimate risks due to diabetes? Qual Saf Health Care. 2007;16(3):208-212.
• Lei Chen et.al. AUSDRISK: an Australian Type 2 Diabetes Risk Assessment Tool based on demographic, lifestyle, and simple anthropometric measures. The Medical Journal of Australia. 2010; 192(4):197-202.
• Lindström J, Tuomilehto, J. The diabetes risk score: a practical tool to predict type 2 diabetes risk. Diabetes Care. 2003; 26(3): 725-731.
• Griffin SJ, Little PS, Hales CN, Kinmonth AL, Wareham NJ. Diabetes risk score: towards earlier detection of type 2 diabetes in general practice. Diabetes Metab Res Rev. 2000 May-Jun;16(3):164-71.
• Cameron AJ, Magliano DJ, Zimmet PZ, Welborn TA, Colagiuri S, Tonkin AM, Shaw JE. The metabolic syndrome as a tool for predicting future diabetes: the AusDiab study. J Intern Med. 2008 Aug;264(2):177-86.
• Mohan et.al. A simplified Indian Diabetes risk score for screening for Undiagnosed Diabetic subjects. Journal of Association of Physicians of India. 2005;53:759-763.
• Bang H, Edwards AM, Bombach AS, et al. Development and validation of a patient self-assessment score for diabetes risk. Ann Intern Med 2009;151:775–783.