Inpatient and Outpatient Technologies to Assist in the Management of Insulin Dosing

New regulatory thinking is needed for AI-based personalised drug and cell therapies in precision oncology

Until recently the application of artificial intelligence (AI) in precision oncology was confined to activities in drug development and had limited impact on the personalisation of therapy. Now, a number of approaches have been proposed for the personalisation of drug and cell therapies with AI applied to therapy design, planning and delivery at the patient's bedside. Some drug and cell-based therapies are already tuneable to the individual to optimise efficacy, to reduce toxicity, to adapt the dosing regime, to design combination therapy approaches and, preclinically, even to personalise the receptor design of cell therapies. Developments in AI-based healthcare are accelerating through the adoption of foundation models, and generalist medical AI models have been proposed. The application of these approaches in therapy design is already being explored and realistic short-term advances include the application to the personalised design and delivery of drugs and cell therapies. With this pace of development, the limiting step to adoption will likely be the capacity and appropriateness of regulatory frameworks. This article explores emerging concepts and new ideas for the regulation of AI-enabled personalised cancer therapies in the context of existing and in development governance frameworks.

The Effectiveness of an App (Insulia) in Recommending Basal Insulin Doses for French Patients With Type 2 Diabetes Mellitus: Longitudinal Observational Study

BACKGROUND

For patients with type 2 diabetes (T2D), calculating the daily dose of basal insulin may be challenging. Insulia is a digital remote monitoring solution that uses clinical algorithms to recommend basal insulin doses. A predecessor device was evaluated in the TeleDiab-2 randomized controlled trial, showing that a higher percentage of patients using the app achieved their target fasting blood glucose (FBG) level compared to the control group, and insulin doses were adjusted to higher levels without hypoglycemia.

OBJECTIVE

This study aims to analyze how the glycemic control of Insulia users has evolved when using the app in a real-life setting in France.

METHODS

A retrospective observational analysis of data collected through the device in adult French patients with T2D treated with basal insulin and oral antihyperglycemic agents using the system for ≥6 months was conducted. Analyses were descriptive and distinguished the results in a subpopulation of regular and compliant users of the app. Glycemic outcomes were estimated considering the percentage of patients who achieved their individualized FBG target between 5.5 and 6 months following the initiation of device use, the frequency of hypoglycemia resulting in a treatment change over the 6-month period of exposure, and the evolution of the average hemoglobin A_1c (HbA_1c) level over the same period.

RESULTS

Of the 484 users, 373 (77.1%) performed at least one dose calculation. A total of 221 (59.2%) users were men. When app use started, the mean age, BMI, HbA_1c, and basal insulin dose were 55.8 (SD 11.9) years, 30.6 (SD 5.9) kg/m², 10.1% (SD 2.0%), and 25.5 (SD 15.8) IU/day, respectively. Over a median use duration of 5.0 (95% CI 3.8-5.7) months, patients used the system 5.8 (SD 1.6) times per week on average, and 73.4% of their injected doses were consistent with the app's suggested doses. Among regular and compliant user patients (n=91, ≥5 measurements/week and ≥80% adherence to calculated doses), 60% (55/91) achieved the FBG target (±5%) at 6 months (5.5-6 months) versus 51.5% (145/282) of the other patients (P=.15). There was an increase in the proportion of patients achieving their target FBG for regular and compliant users (+1.86% every 2 weeks) without clear improvement in other patients. A logistic model did not identify the variables that were significantly associated with this outcome among regular and compliant users. In the overall population, the incidence of reported hypoglycemia decreased simultaneously (-0.16%/month). Among 82 patients, the mean HbA_1c decreased from 9.9% to 7.2% at 6 months.

CONCLUSIONS

An improvement in glycemic control as measured by the percentage of patients reaching their FBG individualized target range without increasing hypoglycemic risk was observed in patients using the Insulia app, especially among regular users following the dose recommendations of the algorithm.