Adaptive, Real-time, Intelligent System to Enhance Self-care of Chronic Disease (ARISES)

Imperial College London

Status: Completed

Conditions: Diabetes Mellitus, Type 1

Treatments: Device: ARISES

Study type: Interventional

Funder types: Other

Identifiers

NCT03643692

18HH4410

Details and patient eligibility

About

The Adaptive, Real-time, Intelligent System to Enhance Self-care of chronic diseases (ARISES) project will use type 1 diabetes (T1DM) as an exemplary case study to demonstrate safety, technical proof of concept and efficacy of a novel mobile platform. Combining wearable sensors and smartphone technology, a range of biological, environmental and behavioural data will be analysed to provide real-time therapeutic and lifestyle decision support. Using Case-Based-Reasoning (CBR), the system will be adaptive and personalised with the ability to learn from previously encountered scenarios. Ultimately, ARISES aims to empower self-management of chronic illness and limit the complications associated suboptimal treatment.

Full description

ARISES will target self-management to optimise glucose control through insulin dose recommendation (therapeutic advice), exercise and stress support, hypoglycaemia prevention through timely snack recommendation and behavioural change through educational support (lifestyle advice).

Semi-structured focus meetings comprised of patients with T1DM, clinicians, engineers and experts in human-computer interaction will provide a forum to establish the essential usability requirements to incorporate into the ARISES mobile interface. The design will focus on ensuring access to decision support is intuitive and efficient while maintaining sight of real-time glycaemia outcomes. The design and implementation of the user-interface will be assessed in a series of usability validation studies.

Clinical studies will be conducted in two phases. The first phase will be an observational study using wearable technologies to collect data and evaluate blood glucose correlations against physiological and environmental case parameters. Useful associations will assist the development of the CBR/machine learning algorithm and identify wearable devices for the final ARISES platform.

Enrollment: 12 patients

Sex: All

Ages: 18+ years old

Volunteers: No Healthy Volunteers

Inclusion criteria

• Adults ≥18years of age
• Diagnosis of T1DM for > 1 year
• Structured education completed in last 3 years and capable of CHO counting
• CBG measured at least twice daily for CGM calibration
• Capacity to follow the protocol and sign the informed consent
• Access to a personal computer/laptop

Exclusion criteria

• Severe episode of hypoglycaemia (requiring 3rd party assistance) in last 6 months
• Diabetic ketoacidosis in the last 6 months prior to enrolment
• Impaired awareness of hypoglycaemia (based on Gold score)
• Pregnant or planning pregnancy over time of study procedures
• Breastfeeding
• Enrolled in other clinical trials
• Active malignancy or being investigated for malignancy
• Suspected or diagnosed endocrinopathy like adrenal insufficiency, unstable thyroidopathy, endocrine tumour
• Gastroparesis
• Autonomic neuropathy
• Macrovascular complications (acute coronary syndrome, transient ischaemic attack, cerebrovascular event within the last 12 months prior to enrolment in the study)
• Visual impairment including unstable proliferative retinopathy
• Reduced manual dexterity
• Inpatient psychiatric treatment
• Abnormal renal function test results (calculated GFR <40 mL/min/1.73m2)
• Liver cirrhosis
• Not tributary to optimization to insulin therapy
• Abuse of alcohol or recreational drugs
• Oral steroids
• Regular use of the paracetamol, beta-blockers or any other medication that the investigator believes is a contraindication to the participant's participation.

Trial design

Primary purpose: Device Feasibility

Allocation: N/A

Interventional model: Single Group Assignment

Masking: None (Open label)

---

12 participants in 1 patient group

ARISES

Experimental group

Description:

Observational study using wearable technologies to collect data and evaluate blood glucose correlations against physiological and environmental case parameters. Useful associations will assist the development of the CBR/machine learning algorithm and identify wearable devices for the final ARISES platform.

Treatment:

Device: ARISES