SJSaravanan Jebarani

Saravanan Jebarani

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Saravanan Jebarani has a total of 40 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Development and Validation of DIANA (Diabetes Novel Subgroup Assessment tool): A web-based precision medicine tool to determine type 2 diabetes endotype membership and predict individuals at risk of microvascular disease

    by Viswanathan Baskar, Mani Arun Vignesh, Sumanth C. Raman, Arun Jijo, Bhavadharini Balaji, Nico Steckhan, Lena Maria Klara Roth, Moneeza K. Siddiqui, Saravanan Jebarani, Ranjit Unnikrishnan, et al.

    Background: Previous research has identified four distinct endotypes of type 2 diabetes in Asian Indians, which include Severe Insulin Deficient Diabetes (SIDD), Combined Insulin Resistant and Deficient Diabetes (CIRDD), Insulin Resistance and Obese Diabetes (IROD), and Mild Age-related Diabetes (MARD). DIANA (Diabetes Novel Subgroup Assessment) is an online precision medicine tool that can predict endotype membership of type 2 diabetes and individual risk for retinopathy and nephropathy. Methodology: The DIANA tool determines subgroup membership using a machine learning model (support vector machine) on T2D subgroups in the Asian Indian population. We used a support vector machine (SVM) model to classify type 2 diabetes patient endotypes, and the model is trained based on k-fold cross-validation. Its performance was compared with an algorithm determined based on conditional pre-determined cut-offs and weights for each clinical feature [age at diagnosis, BMI, waist, HbA1c, Serum Triglycerides, HDL-Cholesterol, (C-peptide fasting, C-peptide stimulated) – optional. This study employed local interpretable model-agnostic explanations (LIME) and SHapley Additive exPlanations (SHAP) to demystify the endotype prediction model. A random forest model was built to assess an individual’s risk for nephropathy and retinopathy based on individual risk algorithms. Findings: The SVM model has relatively high accuracy, specificity, sensitivity, and precision values compared to conditional pre-determined cut-offs 98% vs 63.6%, 99.8% vs 88%, 98.5% vs 65.1%, and 98.7% vs 63.4%. Clinician face value validation of the prediction by the SVM model reported an accuracy, specificity, sensitivity and precision compared to conditional pre-determined cut-offs 97% vs 85%, 95.3% vs 63%, 95.8% vs 73%, and 98.9% vs 66.9%. Additionally, our study demonstrated the impact of features on ML models through LIME and SHAP analyses. The accuracy of the random forest risk prediction model for nephropathy and retinopathy was 89.6% (p < 0.05) and 78.4% (p < 0.05), respectively. Conclusion: We conclude that, DIANA is an accurate, clinically explainable AI tool that clinicians can use to make informed decisions on risk assessment and provide precision management to individuals with new-onset type 2 diabetes.


  • Lean diabetes is one end of the spectrum of type 2 diabetes and not a separate entity

    by Viswanathan Mohan, Thyparambil Aravindakshan Pramodkumar, Mohan Deepa, Rajendra Pradeepa, Ranjit Unnikrishnan, Phillips Routray, Sridhar Tharunika, Natarajan Lakshmi, Dhanasekaran Killivalavan, Sadhasivam Ganesan, et al.


  • Open Access

    Sex-Based Differences in Clinical Profile and Complications among Individuals with Type 2 Diabetes Seen at a Private Tertiary Diabetes Care Centre in India

    by Rajendra Pradeepa, Lal Shreya, Ranjit Mohan Anjana, Saravanan Jebarani, Ulagamathesan Venkatesan, Nithyanantham Kamal Raj, Onkar C. Swami, Viswanathan Mohan

    This study aimed to compare the clinical and biochemical profiles as well as the complications in males and females with type 2 diabetes (T2DM) presenting to a private tertiary diabetes care centre in India. This is a retrospective study, conducted between 1 January 2017 and 31 December 2019, and included 72,980 individuals with T2DM, aged ≥ 18 years (age and sex-matched—males—36,490; females—36,490). Anthropometric measurements, blood pressure, fasting plasma glucose (FPG), post-prandial plasma glucose (PPPG), glycated haemoglobin (HbA1c), lipids, urea, and creatinine were measured. Retinopathy was screened using retinal photography, neuropathy using biothesiometry, nephropathy measuring urinary albumin excretion, peripheral vascular disease (PVD) using Doppler, and coronary artery disease (CAD) based on the history of myocardial infarction and/or drug treatment for CAD and/or electrocardiographic changes. Obesity (73.6% vs. 59.0%) rates were significantly higher in females compared to males. FPG, PPPG, and HbA1c were higher among younger age groups among both sexes, with males having higher values compared to females. However, after the age of 44 years, control of diabetes was worse among females. In addition, only 18.8% of the females achieved glycemic control (HbA1c < 7%) compared to 19.9% in males (p < 0.001). Males had higher prevalence of neuropathy (42.9% vs. 36.9%), retinopathy (36.0% vs. 26.3%), and nephropathy (25.0% vs. 23.3%) compared to females. Males had 1.8- and 1.6-times higher risk of developing CAD and retinopathy compared to females. Hypothyroidism (12.5% vs. 3.5%) and cancers (1.3% vs. 0.6%) were significantly higher in females compared to males. In this large sample of T2DM seen at a chain of private tertiary diabetes centres, females had higher prevalence of metabolic risk factors and poorer diabetes control compared to males, emphasizing the need for better control of diabetes in females. However, males had higher prevalence of neuropathy, retinopathy, nephropathy, and CAD compared to females.


  • Profiles of Intraday Glucose in Type 2 Diabetes and Their Association with Complications: An Analysis of Continuous Glucose Monitoring Data

    by Jithin Sam Varghese, Joyce C. Ho, Ranjit Mohan Anjana, Rajendra Pradeepa, Shivani A. Patel, Saravanan Jebarani, Viswanathan Baskar, K.M. Venkat Narayan, Viswanathan Mohan

    Aims: To identify profiles of type 2 diabetes from continuous glucose monitoring (CGM) data using ambulatory glucose profile (AGP) indicators and examine the association with prevalent complications. Methods: Two weeks of CGM data, collected between 2015 and 2019, from 5901 adult type 2 diabetes patients were retrieved from a clinical database in Chennai, India. Non-negative matrix factorization was used to identify profiles as per AGP indicators. The association of profiles with existing complications was examined using multinomial and logistic regressions adjusted for glycated hemoglobin (HbA1c; %), sex, age at onset, and duration of diabetes. Results: Three profiles of glycemic variability (GV) were identified based on CGM data—Profile 1 [“TIR Profile”] ( n = 2271), Profile 2 [“Hypo”] ( n = 1471), and Profile 3 [“Hyper”] ( n = 2159). Compared with time in range (TIR) profile, those belonging to Hyper had higher mean fasting plasma glucose (202.9 vs. 167.1, mg/dL), 2-h postprandial plasma glucose (302.1 vs. 255.6, mg/dL), and HbA1c (9.7 vs. 8.6; %). Both “Hypo profile” and “Hyper profile” had higher odds of nonproliferative diabetic retinopathy (“Hypo”: 1.44, 1.20–1.73; “Hyper”: 1.33, 1.11–1.58), macroalbuminuria (“Hypo”: 1.58, 1.25–1.98; “Hyper”: 1.37, 1.10–1.71), and diabetic kidney disease (DKD; “Hypo”: 1.65, 1.18–2.31; “Hyper”: 1.88, 1.37–2.58), compared with “TIR profile.” Those in “Hypo profile” (vs. “TIR profile”) had higher odds of proliferative diabetic retinopathy (PDR; 2.84, 1.65–2.88). Conclusions: We have identified three profiles of GV from CGM data. While both “Hypo profile” and “Hyper profile” had higher odds of prevalent DKD compared with “TIR profile,” “Hypo profile” had higher odds of PDR. Our study emphasizes the clinical importance of recognizing and treating hypoglycemia (which is often unrecognized without CGM) in patients with type 2 Diabetes Mellitus.


  • Acceptability and Utilization of Newer Technologies and Effects on Glycemic Control in Type 2 Diabetes: Lessons Learned from Lockdown

    by Ranjit Mohan Anjana, Rajendra Pradeepa, Mohan Deepa, Saravanan Jebarani, Ulagamathesan Venkatesan, Somasundaram Jaya Parvathi, Muthuswamy Balasubramanyam, Venkatesan Radha, Subramani Poongothai, Vasudevan Sudha, et al.

    Aim: To evaluate the effects of a prolonged lockdown due to Coronavirus (COVID-19) on the adoption of newer technologies and changes in glycemic control on patients with type 2 diabetes (T2D) in India. Methods: The study population included a random list of 3000 individuals with T2D derived from 30,748 individuals who had visited a large tertiary diabetes center during the past year. The survey was carried out through a telephonic interview. A structured questionnaire was used to collect information on changes in lifestyle, access and challenges to diabetes care and use of technologies such as telemedicine facilities and use of self-monitoring of blood glucose (SMBG), etc. Results: Of the 2510 individuals successfully interviewed (83.7% response rate), 382 (15.2%) reported having attempted to consult their health care providers during the lockdown, of whom only 30.6% utilized the telemedicine facility. However, 96 (82%) of those who utilized the telemedicine facility ( n = 117) were happy with their experience and 68 (58.1%) were willing to continue to use the facility in the future. Only 11.4% of participants utilized online support for management of diabetes. Use of SMBG increased significantly from 15.5% to 51.3% during the lockdown. There was an improvement in glycemic control during the lockdown (HbA1c:before vs. during lockdown: 8.2% ± 1.9% vs. 7.7% ± 1.7%, P < 0.001) in a nonrandomly selected subset of subjects ( n = 205). Conclusions: Acceptance of telemedicine facilities remains suboptimal in this Asian Indian population, in spite of high levels of satisfaction among those who utilized it. The COVID-19 pandemic and the subsequent lockdown have not adversely affected metabolic control in our patients, and indeed there appears to be an improvement in HbA1c levels. Greater accessibility and acceptance of technology could help individuals with diabetes to maintain better contact with their physicians and ensure better metabolic control in the future.