Better Risk Perception Via Patient Similarity to Control Hyperglycemia and Sustained by Telemonitoring (BRILLIANT)

May 7, 2026 updated by: Tan Ngiap Chuan, SingHealth Polyclinics

Background: Diabetes significantly raises the likelihood of complications, thereby increasing the risk of diabetes-related mortality, particularly due to vascular complications. It is vital to address this rising trend of mortality, by enhancing awareness of diabetes complications to improve risk perception and ultimately reduce mortality rates. Managing diabetes effectively requires interventions addressing both risk communication and monitoring, helping patients better understand and make informed decisions about their health.

Objectives: The primary aim is to evaluate and compare the effectiveness of combined risk communication session using an AI module (PERDICT.AI) and home-based diabetes monitoring (PTEC-DM) versus a standalone risk communication session in improving health outcomes (risk perception, medication adherence, self-care activities and glycaemic control) among poorly controlled diabetes patients. Secondary aims are to explore participants' views and experiences of risk communication session using PERDICT.AI, PTEC-DM and usual care and clinician' views on utility of the new approach to improve risk perception.

Methods: A mixed-method study design will be employed to conduct a multi-arm randomized controlled trial across four of the SingHealth Polyclinics cluster (Pasir Ris, Eunos, Sengkang, Tampines North). Patient participants will be randomly allocated in a 1:1:1 ratio to one of the three arms. Arm 1 will receive risk communication session using PERDICT.AI and home-based diabetes monitoring using PTEC-DM alongside usual care. Arm 2 participants will undergo a standalone risk communication session using PERDICT.AI with usual care while arm 3 will serve as the control group with usual care. A total of 360 (120 in each group) participants will be enrolled by simple randomization. Eligible patient must be of age between 36 and 65 years with HbA1c >8.0% within the last 6 months.

Significance of the study: Findings from the study may add evidence to the scientific knowledge of using these approaches to improve risk perception and recommend development of similar interventions.

Study Overview

Status

Active, not recruiting

Conditions

Intervention / Treatment

Detailed Description

Diabetes has emerged as a significant public health concern globally, and Singapore is no exception. As of 2022, 8.5% of the adults in Singapore is affected by diabetes and the number is expected to reach 1 million by 2050, making it imperative to address the associated challenges. The economic implications of diabetes extend beyond healthcare costs, impacting productivity and quality of life. The total cost among the working-age population with diabetes - direct and indirect costs included - is expected to rise from USD 787 million (USD 5,646 per person) in 2010 to USD 1,867 million in 2050 (USD 7,791 per person).

In addition, diabetes poses a substantial risk of complications that can adversely impact various organ systems. Complications such as cardiovascular diseases, neuropathy, and retinopathy pose severe threats to the health of individuals with poorly managed diabetes. A study on global trend of diabetes mortality revealed a concerning global increase in diabetes-related mortality, particularly due to vascular complications, posing a significant challenge to diabetes management. To address the rising trends of mortality, it is crucial to enhance awareness of diabetes complications to improve risk perception and ultimately reduce mortality rates.

Perceived risk of diabetes complications can impact patient behavior, influencing adherence to treatment plans and lifestyle changes. Individuals with a higher risk perception may be more likely to engage in proactive management, leading to better health outcomes and potentially reducing mortality rates associated with diabetes complications. On the other hand, individuals with poorer risk perception may neglect necessary precautions, leading to suboptimal disease management and an increased likelihood of complications, potentially impacting mortality rates.

A systematic review on risk perceptions of diabetes complications highlights a concerning lack of awareness regarding the risk of diabetes related complications among individuals with type 2 diabetes mellitus (T2DM). Similarly, research studies on diabetes complications risk awareness, particularly in Singapore, revealed knowledge gaps among adults. Despite the significant impact on quality of life, later-stage T2DM and its complications were perceived as slowly progressing and not immediately life-threatening. Hence, for poorly controlled diabetes patients, effective communication regarding the risks of complications is paramount.

Weaver et al defined risk communication as "the effective and accurate exchange of information about health risks and hazards" so as to "advance risk awareness and understanding and promote health-protective behaviors". Enhancing risk communication not only promotes informed decision-making but also advances early intervention and preventive measures. Furthermore, Hashim J et al emphasized the importance of considering social and cultural factors in the development of effective interventions among adults with elevated risk perception yet do not engage in preventive actions. The study also suggested that diverse perspectives concerning the benefits and weaknesses related to preventive measures can impact the long-term sustainability of these behaviors.

Risk communication interventions have been developed for patients with T2DM to improve their risk perceptions and health actions. These interventional studies explore different methods to communicate diabetes complication risks to those with T2DM. interventions include range of innovative risk communication methods like visual aids, general nudges, digital tool for personalized risk information and family support through WeChat. While such interventions contribute to valuable insights, there are some limitations with these tools like limited long-term impact, technology adoption challenges. Addressing these drawbacks with an integrated approach could enhance the robustness and applicability of the findings in diverse healthcare settings.

PERDICT.AI based counselling

An AI-enabled similarity-based model, named PERDICT.AI (Personalised Diabetes Counselling Tool using Artificial Intelligence) was developed by a team of primary care physicians and computer scientists in Singapore to help physicians communicate risks to patients with diabetes mellitus. The tool ranks a patients' HbA1c levels with similar patients (or peers) from a de-identified database, showing how prevalent diabetes complications are based on HbA1c severity. This is referred to as "peer-comparison" and the tool underwent revisions following feedback from primary care physicians to enhance its usefulness in risk communication.

Based on Health Belief Model (HBM), a risk communication intervention, was developed for Primary care Physicians (PCPs) to counsel patients with T2DM on their glycemic control and the complications that could arise, and to recommend ways to improve glycemic control and prevent complications (or further complications). This will be supported by information from PERDICT.AI.

Risk communication using PERDICT.AI dynamically communicates an individual's glycaemic control, offering a comparative ranking among peers to enhance motivation and awareness. Furthermore, it assesses the risk of potential complications comparing with peer data with exemplary cases to underscore the consequences of suboptimal management. In addition, it will generate personalized recommendations including medication adjustment and personalized health plans.

Diabetes management often requires consistent encouragement and guidance, which a static risk communication tool may not deliver. In addition, passive receipt of information might not motivate patients to actively take part in diabetes management. Such lack of engagement could lead to reduced adherence to recommended strategies, limiting the tool's overall impact. This is evident from the @RISK study, where the improved risk perception observed initially at 2 weeks dissipated by the 12th week, highlighting a temporal limitation in sustaining positive outcomes. Although participants in the intervention arm reported higher satisfaction with risk communication, this did not translate into sustained improvements. This underscores the need for an integrated approach to sustain positive outcomes beyond short-term.

Integration with telemonitoring system

Sustaining improved risk perception over an extended period can be achieved through telemonitoring. By utilizing telemonitoring technology, healthcare providers can maintain a consistent connection with patients, offering real-time insights into their health status. Additionally, telemonitoring facilitates continuous education and support, thereby contributing to the long-term sustainability of improved risk perception and can significantly enhance diabetes management and prevent complications.

The Primary Tech-Enhanced Care (PTEC) programme focuses on encouraging patients to manage chronic conditions at home through user-friendly kits. The Home Diabetes Monitoring programme (PTEC-DM) enables home-based glucose and blood pressure monitoring once a week using a Bluetooth enabled device. These reading will be securely transmitted to the study team via the app and managed appropriately through teleconsultation. Additionally, participants will receive health nudges, encouragements, and reminders through in-app messages to support their well-being.

The integration of PTEC-DM with the risk communication using PERDICT.AI capitalizes on the strengths of human interaction and adaptability, contributing to a more holistic and patient-centred diabetes management approach. Such combined approach addresses both monitoring and guidance, contributing to enhanced patient understanding and informed decision-making. Hence this study is designed with the following objectives, adopting a multi-site, multi-arm randomized controlled trial design.

Objectives

Primary objective:

i. To assess the effectiveness of the risk communication using an AI enabled tool (PERDICT.AI) in improving risk perception score, quality of life and health outcomes (medication adherence and selfcare activities and glycemic control) among poorly controlled diabetes patients ii. To determine the effectiveness of a combination of risk communication session using PERDICT.AI and telemonitoring (PTEC-DM) in improving risk perception, quality of life and health outcomes

Secondary objectives:

iii. To compare the impact of the two approaches in improving risk perception, quality of life and health outcomes among poorly controlled diabetes patients iv. To assess the cost-effectiveness of the advanced care by comparing the incremental costs and health outcomes v. To explore participants' views and experiences of risk communication session using PERDICT.AI, PTEC-DM and usual care vi. To explore clinician' views on utility of the new approach to improve risk perception

Hypothesis:

• There will be improvement in patients' risk perception score and health outcomes (glycemic control and self-care activities) after the intervention.

Materials and methods

Study setting The study will be conducted at 4 polyclinics from a primary care clinic cluster taking care of more than 200,000 residents with diabetes in the Eastern region of Singapore.

Study design Sequential explanatory mixed-method study

Quantitative: Multi-arm randomized controlled trial (RCT) at four polyclinics which includes SingHealth Polyclinics at Pasir Ris, Tampines North, Eunos and Sengkang.

Qualitative: In-depth interview among the study participants' and clinician, who are integral part of the study team delivering interventions.

Quantitative: Multi-arm RCT This RCT involves three arms, incorporating a combination of interventions and standard care, as outlined below.

Arm 1: Advanced care with risk communication using an AI enabled tool (PERDICT.AI) + home-based monitoring using PTEC DM (main intervention arm) Arm 2: Usual care + risk communication using an AI enabled tool (PERDICT.AI) Arm 3: Usual care All groups will also receive a diabetes pamphlet.

Randomization Patient participants from each study site will be randomly allocated in a 1:1:1 ratio to one of the above-mentioned arms in an open-label fashion, using computer-generated random numbers for simple randomization of subjects. The nature of the intervention makes impossible to blind patients and research team to participant allocation. The randomization sequence is written and kept in an opaque sealed envelope, which will be labelled with a serial number. The study team will open the sealed envelope once the patient has consented to participate and then will be assigned to the study arms accordingly. All participants will receive a diabetes pamphlet ('Pamphlet - Taking Control of Diabetes').

Study Type

Interventional

Enrollment (Actual)

360

Phase

  • Not Applicable

Contacts and Locations

This section provides the contact details for those conducting the study, and information on where this study is being conducted.

Study Locations

  • Singapore
      • Singapore, Singapore
        • SingHealth Polyclinics

Participation Criteria

Researchers look for people who fit a certain description, called eligibility criteria. Some examples of these criteria are a person's general health condition or prior treatments.

Eligibility Criteria

Ages Eligible for Study

  • Adult
  • Older Adult

Accepts Healthy Volunteers

No

Description

Inclusion Criteria:

  • Type 2 Diabetes Mellitus on follow-up at the study site for at least 12 months
  • Age 36 to 65 years
  • At least one HbA1c reading ≥ 8.0% within the last 6 months
  • Able to read and speak English

Exclusion Criteria:

  • Not a Singapore citizen or permanent resident
  • Pregnant
  • End-stage kidney disease or on renal replacement therapy
  • Known terminal illness
  • Visual and/or hearing impairment
  • Cognitive impairment or mental illness
  • Unable to provide informed consent

Study Plan

This section provides details of the study plan, including how the study is designed and what the study is measuring.

How is the study designed?

Design Details

  • Primary Purpose: Supportive Care
  • Allocation: Randomized
  • Interventional Model: Parallel Assignment
  • Masking: None (Open Label)

Arms and Interventions

Participant Group / Arm
Intervention / Treatment
Experimental: Arm 1
In arm 1, participants will attend the risk communication session utilizing AI module (PERDICT.AI) delivered by the study team integrated with Home-based Diabetes Monitoring (PTEC-DM) providing personalized guidance through teleconsultation in addition to usual care. Screen activity of PERDICT.AI will be recorded using a screen capture software. The entire session will be audio recorded.
Other: Intervention using an AI enabled risk communication tool (PERDICT.AI)
Risk communication using PERDICT.AI dynamically communicates an individual's glycemic control, offering a comparative ranking among peers to enhance motivation and awareness. Furthermore, it assesses the risk of potential complications comparing with peer data with exemplary cases to underscore the consequences of suboptimal management. In addition, it will generate personalized recommendations including medication adjustment and personalized health plans.
Other: Telemonitoring with Primary Tech Enhanced Care (PTEC-DM)
The Primary Tech-Enhanced Care (PTEC) programme focuses on encouraging patients to manage chronic conditions at home through user-friendly kits. The Home Diabetes Monitoring programme (PTEC-DM) enables home-based glucose and blood pressure monitoring once a week using a Bluetooth enabled device. These reading will be securely transmitted to the study team via the app and managed appropriately through teleconsultation. Additionally, participants will receive health nudges, encouragements, and reminders through in-app messages to support their well-being.
Experimental: Arm 2
In arm 2, participants will attend the risk communication session utilising AI module (PERDICT.AI) without PTEC-DM. Screen activity of PERDICT.AI will be recorded using a screen capture software. The entire session will be audio recorded.
Other: Intervention using an AI enabled risk communication tool (PERDICT.AI)
Risk communication using PERDICT.AI dynamically communicates an individual's glycemic control, offering a comparative ranking among peers to enhance motivation and awareness. Furthermore, it assesses the risk of potential complications comparing with peer data with exemplary cases to underscore the consequences of suboptimal management. In addition, it will generate personalized recommendations including medication adjustment and personalized health plans.
No Intervention: Arm 3
Arm 3 will be the active control group, receiving only standard care

What is the study measuring?

Primary Outcome Measures

Outcome Measure
Measure Description
Time Frame
Risk Perception Survey-Diabetes Mellitus (RPS-DM)
Time Frame: through study completion, an average of 12 to 16 months
The RPS-DM consists of 31 questions. The first section assesses risk knowledge (5 items scored on 3-point scale with 1 point for each correct answer; higher score indicates greater knowledge of the risk of getting diabetes complications). The remaining 26 items comprise 5 subscales which can be described as: perceived personal control (4 items scored on 4-point scale); worry (2 items scored on 4-point scale), optimistic bias (2 items scored on 4-point scale); personal disease risk (9 items scored on a 4-point scale; indicates degree of own perceived risk of getting 9 diseases or conditions, plus additional question about whether they have ever had the condition, scored yes/no with 1 point added for yes response); and environmental risk (9 items scored on a 4-point scale). The composite risk perception is the average of the 26 items in the main questionnaire; higher scores indicate greater comparative perceived risk.
through study completion, an average of 12 to 16 months
Health related Quality of life
Time Frame: through study completion, an average of 12 to 16 months
Change in the scores using EQ-5D-5L questionnaire; The EQ-5D-5L tool comprises five dimensions, each describing a different aspect of health: mobility, self-care, usual activities, pain/ discomfort and anxiety/ depression. Each dimension has five response levels (no problems, slight problems, moderate problems, severe problems, unable to/ extreme problems). The proportion of patients reporting each level of problem on each dimension of the EQ-5D will be determined through study completion and compared. EQ VAS (Visual Analogue Scale) provides a quantitative measure of the patient's perception of their overall health. The EQ VAS records the respondent's overall current health on a vertical scale (0-100), where the endpoints are labelled '0-The worst health you can imagine' and '100-The best health you can imagine'.
through study completion, an average of 12 to 16 months
Medication adherence
Time Frame: through study completion, an average of 12 to 16 months
Change in the scores using five item Medication Adherence Report Scale (MARS-5); MARS-5 score was calculated by summing the numeric score (range 1-5) from each question for out of 25 (range 5-25). A higher score indicates better adherence.
through study completion, an average of 12 to 16 months
Summary of Diabetes Self-care Activities (SDSCA) questionnaire
Time Frame: through study completion, an average of 12 to 16 months
SDSCA questionnaire collects data on general diet, specific diet, exercise, blood-glucose testing, foot care, and smoking, using an 8-point Likert-type scale (0-7), which represents the number of days per week when the given self-care activity was performed. Scores are calculated separately for each item and the level of adherence is indicated by the mean score for each dimension.
through study completion, an average of 12 to 16 months
Iowa-Netherlands Comparison Orientation Measure (INCOM)
Time Frame: baseline enrolment
The INCOM is an 11-item measure of one's tendency to make social comparisons. The scale includes such items as: "I always like to know what others in a similar situation would do." Response choices range from 1 (disagree strongly) to 5 (agree strongly). Higher scores indicate more of a tendency to socially compare.
baseline enrolment

Secondary Outcome Measures

Outcome Measure
Measure Description
Time Frame
Cost-effectiveness analysis
Time Frame: through study completion, an average of 12 to 16 months
Unit costs for consultation, laboratory, hospitalization, and pharmacy services, as well as the expenses for home-based monitoring (including a Bluetooth-enabled glucometer, test strips, lancets, and a blood pressure monitor), will be estimated to assess the cost-effectiveness of the advanced care by comparing the incremental costs and health outcomes
through study completion, an average of 12 to 16 months
Views and experiences of risk communication session using PERDICT.AI, PTEC-DM and usual care
Time Frame: 24-48 weeks
in-depth interview with the participants till point of data saturation
24-48 weeks
Exploring clinician' views on utility of combined intervention to improve risk perception
Time Frame: 24-48 weeks
in-depth interview with the study team doctors till point of data saturation
24-48 weeks

Collaborators and Investigators

This is where you will find people and organizations involved with this study.

Sponsor

SingHealth Polyclinics

Collaborators

AISG Health Grand Challenge

Investigators

  • Principal Investigator: Ngiap Chuan Tan, MMed, SingHealth Polyclinics

Publications and helpful links

The person responsible for entering information about the study voluntarily provides these publications. These may be about anything related to the study.

General Publications

Study record dates

These dates track the progress of study record and summary results submissions to ClinicalTrials.gov. Study records and reported results are reviewed by the National Library of Medicine (NLM) to make sure they meet specific quality control standards before being posted on the public website.

Study Major Dates

Study Start (Actual)

July 15, 2024

Primary Completion (Estimated)

December 31, 2026

Study Completion (Estimated)

December 31, 2026

Study Registration Dates

First Submitted

September 16, 2024

First Submitted That Met QC Criteria

September 18, 2024

First Posted (Actual)

September 23, 2024

Study Record Updates

Last Update Posted (Actual)

May 12, 2026

Last Update Submitted That Met QC Criteria

May 7, 2026

Last Verified

May 1, 2026

More Information

Terms related to this study

Additional Relevant MeSH Terms

Other Study ID Numbers

  • 2024-2281

Plan for Individual participant data (IPD)

Plan to Share Individual Participant Data (IPD)?

NO

Drug and device information, study documents

Studies a U.S. FDA-regulated drug product

No

Studies a U.S. FDA-regulated device product

No

product manufactured in and exported from the U.S.

No

This information was retrieved directly from the website clinicaltrials.gov without any changes. If you have any requests to change, remove or update your study details, please contact register@clinicaltrials.gov. As soon as a change is implemented on clinicaltrials.gov, this will be updated automatically on our website as well.

Clinical Trials on Diabetes Mellitus, Type 2

Search Similar Trials

Sponsors and Collaborators

Medical Conditions

Drug Interventions

CROs by country

CROs in Australia

Conditions

Rare Diseases

Drug Interventions

Dietary Supplements

Sponsor/Collaborators

Locations

Subscribe