FULL DETAILS (Read-only)  -> Click Here to Create PDF for Current Dataset of Trial
CTRI Number  CTRI/2024/12/078673 [Registered on: 27/12/2024] Trial Registered Prospectively
Last Modified On: 09/12/2024
Post Graduate Thesis  Yes 
Type of Trial  Interventional 
Type of Study   Medical Device
Process of Care Changes
Behavioral 
Study Design  Randomized, Parallel Group, Active Controlled Trial 
Public Title of Study   Machine Learning Algorithm to predict insulin dosage for insulin-dependent Diabetics 
Scientific Title of Study   Assessment of the Safety and Efficacy of a Novel Machine-learning Algorithm in the Management of Glycaemic Control in Insulin-Dependent Diabetics: A Randomised Controlled Clinical Trial 
Trial Acronym  NIL 
Secondary IDs if Any  
Secondary ID  Identifier 
NIL  NIL 
 
Details of Principal Investigator or overall Trial Coordinator (multi-center study)  
Name  Dr. Noel Sam Thomas 
Designation  Postgraduate Resident 
Affiliation  Saveetha Medical College and Hospital 
Address  Room 350, Department of General Medicine, Saveetha Medical College and Hospital, Saveetha Institue of Medical and Technical Sciences (SIMATS)

Kancheepuram
TAMIL NADU
602105
India 
Phone  9803769655  
Fax    
Email  noelsam14@gmail.com  
 
Details of Contact Person
Scientific Query
 
Name  Dr. Venkateswaran 
Designation  Professor 
Affiliation  Saveetha Medical College and Hospital 
Address  Room 250, Department of Medical Gastroenterology, Saveetha Medical College and Hospital, Saveetha Institue of Medical and Technical Sciences (SIMATS)

Kancheepuram
TAMIL NADU
602105
India 
Phone  9361249611  
Fax    
Email  venkateswaran086@gmail.com  
 
Details of Contact Person
Public Query
 
Name  Dr. Noel Sam Thomas 
Designation  Postgraduate Resident 
Affiliation  Saveetha Medical College and Hospital 
Address  Room 350, Department of General Medicine, Saveetha Medical College and Hospital, Saveetha Institue of Medical and Technical Sciences (SIMATS)

Kancheepuram
TAMIL NADU
602105
India 
Phone  9803769655  
Fax    
Email  noelsam14@gmail.com  
 
Source of Monetary or Material Support  
Department of General Medicine, Saveetha Medical College and Hospital, Saveetha Institue of Medical and Technical Sciences (SIMATS), Kancheepuram, Tamil Nadu, India - 602105 
 
Primary Sponsor  
Name  Dr Noel Sam Thomas 
Address  Room 350, Department of General Medicine, Saveetha Medical College and Hospital, Saveetha Institue of Medical and Technical Sciences (SIMATS), Kancheepuram, Tamil Nadu 602105 
Type of Sponsor  Private medical college 
 
Details of Secondary Sponsor  
Name  Address 
NIL  NIL 
 
Countries of Recruitment     India  
Sites of Study  
No of Sites = 1  
Name of Principal Investigator  Name of Site  Site Address  Phone/Fax/Email 
Dr Noel Sam  Saveetha Medical College and Hospital  Room 350, Department of General Medicine, Saveetha Medical College and Hospital, Saveetha Institue of Medical and Technical Sciences (SIMATS)
Kancheepuram
TAMIL NADU 
9803769655

noelsam14@gmail.com 
 
Details of Ethics Committee  
No of Ethics Committees= 1  
Name of Committee  Approval Status 
IEC-Saveetha Medical College Hospital  Approved 
 
Regulatory Clearance Status from DCGI  
Status 
Not Applicable 
 
Health Condition / Problems Studied  
Health Type  Condition 
Patients  (1) ICD-10 Condition: E119||Type 2 diabetes mellitus without complications,  
 
Intervention / Comparator Agent  
Type  Name  Details 
Comparator Agent  An actively doctor-managed insuin regimen fixed every week during OPD visit after reviewing CBG charting of previous week maintained by the patient at home.  The patients will be fixed on an appropriate insulin regigmen as determined by the treating doctor during OPD visits. Patient will also be asked to regularly measure capillary blood glucose pre or post prandially on a chart and produce the same after 1 week during next OPD visit. 
Intervention  Machine learning algorithm to predict insulin dosages for diabetic patients dependent on insulin for glycemic control  The ML algorithm runs on an app that auto-predicts the required insulin dosage to be taken each time the patient enters their latest capillary blood glucose reading. 
 
Inclusion Criteria  
Age From  18.00 Year(s)
Age To  70.00 Year(s)
Gender  Both 
Details  Patients aged 18 years and above, but below 70 years of age and
Clinically diagnosed T2DM and
Patients already on insulin therapy as part of their DM therapy
 
 
ExclusionCriteria 
Details  Known hypersensitivity to insulin and
Pregnant or lactating women and
Patients above 70 years of age, or below 18 years of age and
Comorbidities – Chronic Kidney Disease and
T1DM patients on insulin therapy 
 
Method of Generating Random Sequence   Computer generated randomization 
Method of Concealment   On-site computer system 
Blinding/Masking   Investigator Blinded 
Primary Outcome  
Outcome  TimePoints 
Reduction in Hba1c level  6 months 
 
Secondary Outcome  
Outcome  TimePoints 
Other demographic factors that determine reduction in Hba1c between the two arms of the study.  6 months 
 
Target Sample Size   Total Sample Size="60"
Sample Size from India="60" 
Final Enrollment numbers achieved (Total)= "Applicable only for Completed/Terminated trials"
Final Enrollment numbers achieved (India)="Applicable only for Completed/Terminated trials" 
Phase of Trial   Phase 2/ Phase 3 
Date of First Enrollment (India)   01/01/2025 
Date of Study Completion (India) Applicable only for Completed/Terminated trials 
Date of First Enrollment (Global)  Date Missing 
Date of Study Completion (Global) Applicable only for Completed/Terminated trials 
Estimated Duration of Trial   Years="0"
Months="6"
Days="0" 
Recruitment Status of Trial (Global)   Not Yet Recruiting 
Recruitment Status of Trial (India)  Not Yet Recruiting 
Publication Details   N/A 
Individual Participant Data (IPD) Sharing Statement

Will individual participant data (IPD) be shared publicly (including data dictionaries)?  

Response - NO
Brief Summary  

<p><strong>23.1 Title of the research project</strong></p>

<p>Assessment of the Safety and Efficacy of a Novel Machine-learning Algorithm in the Management of Glycaemic Control in Insulin-Dependent Diabetics: A Randomised Controlled Clinical Trial</p>

<p><strong>23.2&nbsp;Aim and objectives of the research project</strong></p>

<p>AIM: To evaluate the safety and efficacy of a novel machine learning model for insulin dosage estimation in patients that use insulin as the main drug for diabetes management.</p>

<p>Objectives:&nbsp;</p>

<ul>

<li>To assess the safety profile of the novel machine-learning algorithm</li>

<li>To evaluate the glycaemic control achieved while using the algorithm</li>

<li>To compare the reduction in HbA1c reduction attained&nbsp;</li>

<li>To measure patient satisfaction on using the application</li>

</ul>

<p><strong>23.3&nbsp;Introduction and need for the research</strong></p>

<p>The burden of diabetes, both globally, and particularly in India, is huge &ndash; is an understatement. Diabetes, once considered a disease of affluence, has now become a significant public health challenge in India. With its burgeoning population, diverse cultural practices, and rapid urbanization, India finds itself grappling with an alarming increase in diabetes cases. This silent epidemic is not only a threat to individual health but also poses substantial economic burdens and strains on the healthcare system.</p>

<p>This innovative invention aims to mitigate some of these challenges. Using machine learning models, we have developed a system whereby individuals can simply use an app-based interface which, when fed data related to their pre-prandial capillary blood glucose readings, can estimate the required insulin dosage to be administered by the individual, such that the dosage is:-&nbsp;</p>

<ul>

<li>adequate to prevent blood glucose spikes post-meal, thereby preventing complications associated with hyperglycaemia</li>

<li>safe to prevent any hypoglycaemic symptoms (provided the recommended calorie intake is ensured);&nbsp;</li>

<li>personalised to each individual by relying on their own glucose and insulin levels as feed-data for machine learning. This obsoletes the need to follow standard reference insulin charts, which is the current norm.</li>

</ul>

<p><strong>23.4&nbsp;Methodology and research design</strong></p>

<p>This will be a randomized investigator-blind controlled clinical trial. Patients meeting the inclusion criteria will be recruited and randomized into a trial group and a control group. The participants in the trial group will have their insulin dosages estimated by the machine learning algorithm, while the control group participants will have their insulin dosages predefined by the treating physicians, following contemporary clinical practices. Safety profile will be estimated on a real-time basis using a mobile application and efficacy will be evaluated based on Hba1c reduction in both groups.</p>

<p><strong>23.5&nbsp;Inclusion criteria</strong></p>

<ul>

<li>Patients aged 18 years and above, but below 70 years of age</li>

<li>Clinically diagnosed T2DM</li>

<li>Patients already on insulin therapy as part of their DM therapy&nbsp;</li>

</ul>

<p><strong>23.6&nbsp;Exclusion criteria</strong></p>

<ul>

<li>Known hypersensitivity to insulin</li>

<li>Pregnant or lactating women</li>

<li>Patients above 70 years of age, or below 18 years of age.</li>

<li>Comorbidities &ndash; Chronic Kidney Disease</li>

<li>T1DM patients on insulin therapy</li>

</ul>

<p><strong>23.7&nbsp;Sample size, sampling technique and statistical analyses</strong></p>

<p>Sample Size: 60, divided into two equal arms.</p>

<p>Sampling Technique: Non-probability convenience sampling</p>

<p>Statistical Analysis: Descriptive and Correlation Statistics</p>

<p>Software for Statistical Analysis: IBM SPSS</p>

<p><strong>23.8&nbsp;Potential risks and benefits</strong></p>

<p>Potential Risks: Hypoglycaemia, Hyperglycaemia, Diabetic Ketoacidosis</p>

<p>Potential Benefits: Reduced hospital visits with better overall diabetic control within the comforts of one&rsquo;s home.</p>

<p><strong>23.9&nbsp;Expected outcome&nbsp;</strong></p>

<p>The primary outcome will be the correlation of the Hba1c (glycosylated haemoglobin) levels of patients in the arm of the study that used the mobile application with the control group that does not use the app.</p>

<p>The secondary outcomes will be determine other demographic factors that correlate with the reduction in the Hba1c levels in the two arms of the study.</p>

<p>We expect that the mobile application will demonstrate superior performance and achieve a greater and stricter control of blood sugar in the population that uses it and will be evidenced by the greater reduction in the Hba1c level in that group. Thus, this study, if successful, would establish the safety, efficacy, and public utility of the mobile application for general use among the public diagnosed with insulin-dependent type-2 diabetes.</p>

<p><strong>23.10&nbsp;Limitations of the study</strong></p>

<ol>

<li>Small sample size may suffer from selection bias due to non-probability convenience sampling methodology used</li>

<li>Participant usage of the mobile application may not be regular resulting in sampling loss and thereby, affecting the overall performance of the app</li>

<li>Generalisability of the findings may be limited to healthy diabetics without added comorbidities such as nephropathy or neuropathy.</li>

</ol>

<p><strong>23.13&nbsp;References</strong></p>

<ol>

<li>Inzucchi SE, Bergenstal RM, Buse JB. Management of hyperglycemia in type 2 diabetes, 2015: a patient-centered approach: update to a position statement of the American Diabetes Association and the &hellip;. Diabetes [Internet] 2015;Available from: https://diabetesjournals.org/care/article-abstract/38/1/140/37869</li>

<li>Owens DR, Monnier L, Barnett AH. Future challenges and therapeutic opportunities in type 2 diabetes: Changing the paradigm of current therapy. Diabetes Obes Metab 2017;19(10):1339&ndash;52.</li>

<li>Ritzel R, Roussel R, Giaccari A, Vora J, Brulle-Wohlhueter C, Yki-J&auml;rvinen H. Better glycaemic control and less hypoglycaemia with insulin glargine 300 U/mL vs glargine 100 U/mL: 1-year patient-level meta-analysis of the EDITION clinical studies in people with type 2 diabetes. Diabetes Obes Metab 2018;20(3):541&ndash;8.</li>

</ol>

 
Close