Truace
Subscribe

AI2EPD home activity monitoring system for adherence in type 2 diabetes

Source article: Feasibility of an Activity Control System in Patients with Type 2 Diabetes: Results from a Non-Randomised Controlled Pilot Study

Objective Diabetes mellitus (DM) is a disease that requires continuous, active management by the patient, encompassing lifestyle and activities of daily living (ADL). There is limited evidence and a scarcity of devices that monitor ADL in patients with DM using artificial intelligence-based technology. This study evaluates the feasibility of the AI2EPD home activity monitoring system, focusing on therapeutic adherence in the treatment of people with DM2. Methods A pilot-controlled study was conducted. Vibration…

By the Truvace desk2 min read1 sourcePeer-reviewedTRV-2026-2079· cite & verify
Feasibility of an Activity Control System in Patients with Type 2 Diabetes: Results from a Non-Randomised Controlled Pilot Study
"2018.11.03 Continuous Glucose Monitor 14 day, Washington, DC USA_-2" by tedeytan is licensed under CC BY-SA 2.0. To view a copy of this license, visit https://creativecommons.org/licenses/by-sa/2.0/.
Trace impact readingContested
P 71The P score combines the specificity and measured human impact of the grounded problem claim with the strength of this Trace’s cited sources.

Both sides are scored from claims and sources, not community votes.

G 70The G score combines the specificity and measured human impact of the grounded gain claim with the strength of this Trace’s cited sources.

In brief

Researchers ran a small non-randomised controlled pilot of AI2EPD, a home system combining vibration and motion sensors, activity bracelets and an AI web platform, to support treatment adherence in people with type 2 diabetes. Twenty-one people took part, ten in the intervention arm and eleven in the control arm.

The study suggests that such AI-enabled home monitoring can be accepted by patients, which is a precondition for wider use. But acceptance did not translate into measurable clinical improvement here, so whether the approach helps manage diabetes remains unanswered until larger, adequately powered studies are done.

Main points

  1. The AI2EPD system combined home vibration and motion sensors, physical activity bracelets and an AI web system.
  2. Twenty-one participants were enrolled: 10 in the intervention group and 11 in the control group.
  3. Clinical results were similar across both groups, with no clinical benefit attributable to the intervention.
  4. Evaluation used scales covering usability, medication adherence, comorbidity, self-care, diabetes knowledge, physical activity and quality of life.
  5. The authors call for adequately powered studies to evaluate exploratory adherence and clinical findings.

The gain

Participants in the intervention group found the AI-based home monitoring system easy to use and safe, indicating high acceptance and feasibility for people with type 2 diabetes.

The problem

The pilot found no clinical benefit attributable to the monitoring system, and the only significant HbA1c improvement occurred in the control group.

The rundown

The study targeted a gap: diabetes needs continuous patient-led management of lifestyle and daily activities, yet there is limited evidence and few devices that monitor daily living activities in people with diabetes using artificial intelligence.

Outcomes were assessed with the System Usability Scale, Morisky-Green Test, Charlson Comorbidity Index, a Spanish version of the Summary of Diabetes Self-Care Activities Measure, the Diabetes Knowledge Questionnaire, the International Physical Activity Questionnaire and EuroQol 5D.

On results, the intervention group rated the system easy to use and safe. The only statistically significant within-group HbA1c improvement was in the control group, which the authors say should be interpreted cautiously given the pilot design and multiple exploratory comparisons.

What this doesn’t fix

The study was a small, non-randomised pilot with multiple exploratory comparisons, so its clinical findings must be interpreted with caution and need confirmation in adequately powered studies.

Sources

  1. Peer-reviewedEndocrine Practice2026-10-19

The debate