Comparison of Insulin Dose Adjustments Made by Artificial Intelligence-Based Decision Support Systems and by Physicians in People with Type 1 Diabetes Using Multiple Daily Injections Therapy

Nimri, Revital; Tirosh, Amir; Muller, Ido; Shtrit, Yael; Kraljević, Ivana; Alonso, Montserrat Martín; Miličić, Tanja; Saboo, Banshi; Deeb, Asma; Christoforidis, Athanasios; Brinker, Marieke den; Bozzetto, Lutgarda; Bolla, Andrea Mario; Krčma, Michal; Rabini, R. A.; Tabba, Shadi; Vazeou-Gerasimidi, Adriani; Maltoni, Giulio; Giani, Elisa; Dotan, Idit; Liberty, Idit F.; Toledano, Yoel; Kordonouri, Olga; Bratina, Nataša; Dovč, Klemen; Biester, Torben; Atlas, Eran; Phillip, Moshe

doi:10.1089/dia.2021.0566

Cited by 13 publications

(9 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Endo.Digital DSS (version 2, DreaMed Diabetes Ltd) carries out a similar purpose for users of MDI. While the majority of studies conducted by Nimri et al were non-interventional and compared insulin dose adjustments using these DSSs with those made by physicians using retrospective data, [37][38][39] one study evaluated real-time remote insulin adjustments by the DreamMed Advisor Pro to physicians every 3 weeks over a 6-month period, demonstrating similar levels of glycaemic control in children and adolescents using a pump and CGM. 40 However, one limitation of this system is the intention to help clinicians with therapy adjustments, instead of providing them directly to the patient.…”

Section: Discussionmentioning

confidence: 99%

Adaptive bolus calculators for people with type 1 diabetes: A systematic review

Unsworth,

Avari,

Lett

et al. 2023

Diabetes Obesity Metabolism

View full text Add to dashboard Cite

AimTo conduct a systematic review of studies assessing adaptive insulin bolus calculators for people with type 1 diabetes (T1D).MethodsElectronic databases (Medline, Embase and Web of Science) were systematically searched from date of inception to 13 October 2022 for single‐arm or randomized controlled studies assessing adaptive bolus calculators only, in children or adults with T1D on multiple daily injections or insulin pumps with glycaemic outcomes reported. The Clinicaltrials.gov registry was searched for recently completed studies evaluating decision support in T1D. The quality of extracted studies was assessed using the Standard Quality Assessment criteria and the Cochrane Risk of Bias assessment tool.ResultsSix studies were identified. Extracted data were synthesized in a descriptive review because of heterogeneity. All the studies were small feasibility studies or were not suitably powered, and all were deemed to be at a high risk of performance and detection bias because they were unblinded. Overall, these studies did not show a significant glycaemic improvement. Two studies showed a reduction in postprandial time below range or an incremental change in blood glucose concentration; however, these were in controlled environments over a short duration.ConclusionsThere are limited clinical trials evaluating adaptive bolus calculators. Although results from small trials or in‐silico data are promising, further studies are required to support personalized and adaptive management of T1D.

show abstract

Section: Discussionmentioning

confidence: 99%

Adaptive bolus calculators for people with type 1 diabetes: A systematic review

Unsworth,

Avari,

Lett

et al. 2023

Diabetes Obesity Metabolism

View full text Add to dashboard Cite

show abstract

“…Table S1 reports the decision‐support systems for therapy parameter adjustments previously tested in MDI and non‐automated pump clinical trials. In particular, authors developed the decision‐support systems using a case‐based reasoning method 41,42 evaluated in clinical studies, 43–45 artificial intelligence approaches 46–48 evaluated in clinical studies, 46–49 and retrospective optimization‐based approaches 50,51 evaluated in clinical studies 50,52 . No significant differences were obtained in the glycaemic outcomes with the use of these decision‐support systems in clinical studies (Table S1).…”

Section: Decision‐support Systems For Therapy Settings Adjustmentsmentioning

confidence: 99%

Postprandial glucose‐management strategies in type 1 diabetes: Current approaches and prospects with precision medicine and artificial intelligence

Jafar,

Pasqua

2024

Diabetes Obesity Metabolism

View full text Add to dashboard Cite

Postprandial glucose control can be challenging for individuals with type 1 diabetes, and this can be attributed to many factors, including suboptimal therapy parameters (carbohydrate ratios, correction factors, basal doses) because of physiological changes, meal macronutrients and engagement in postprandial physical activity. This narrative review aims to examine the current postprandial glucose‐management strategies tested in clinical trials, including adjusting therapy settings, bolusing for meal macronutrients, adjusting pre‐exercise and postexercise meal boluses for postprandial physical activity, and other therapeutic options, for individuals on open‐loop and closed‐loop therapies. Then we discuss their challenges and future avenues. Despite advancements in insulin delivery devices such as closed‐loop systems and decision‐support systems, many individuals with type 1 diabetes still struggle to manage their glucose levels. The main challenge is the lack of personalized recommendations, causing suboptimal postprandial glucose control. We suggest that postprandial glucose control can be improved by (i) providing personalized recommendations for meal macronutrients and postprandial activity; (ii) including behavioural recommendations; (iii) using other personalized therapeutic approaches (e.g. glucagon‐like peptide‐1 receptor agonists, sodium‐glucose co‐transporter inhibitors, amylin analogues, inhaled insulin) in addition to insulin therapy; and (iv) integrating an interpretability report to explain to individuals about changes in treatment therapy and behavioural recommendations. In addition, we suggest a future avenue to implement precision recommendations for individuals with type 1 diabetes utilizing the potential of deep reinforcement learning and foundation models (such as GPT and BERT), employing different modalities of data including diabetes‐related and external background factors (i.e. behavioural, environmental, biological and abnormal events).

show abstract

“…The use of artificial pancreas systems also facilitates normality for both parents and children who experience injections or insulin pumps or any other modality. [24][25][26][27] In their most advanced form, AI-DSS could deliver advice directly to the individual with diabetes, reducing diabetes-related burden and costs. AI-DSS have, therefore, the potential to improve clinical outcomes and may increase access to diabetes care, especially with a rising prevalence of diabetes combined with a growing global shortage of health care professionals.…”

Section: Technology In Diabetes Closed Loops and Continuous Glucose M...mentioning

confidence: 99%

“…These tools can support person‐tailored treatment decisions for a wide range of individuals treated with different treatment modalities. Currently, several AI‐DSS are being investigated and can provide dosing adjustment recommendations, based on continuous glucose monitoring or glucometer data, whether individuals are treated with injections or insulin pumps or any other modality 24–27 . In their most advanced form, AI‐DSS could deliver advice directly to the individual with diabetes, reducing diabetes‐related burden and costs.…”

Section: Clinical Uses Of Artificial Intelligence‐based Decision Supp...mentioning

confidence: 99%