ESPEYB19 10. Type 1 Diabetes Advances in clinical practice (2 abstracts)
10.9. Comparison of insulin dose adjustments made by artificial intelligence based decision support system and by physicians in people with type 1 diabetes using multiple daily injections therapy
Nimri R , Tirosh A , Muller I , Shtrit Y , Kraljević I , Alonso MM , Milicic T , Saboo B , Deeb A , Christoforidis A , den Brinker M , Bozzetto L , Bolla AM , Krcma M , Rabini RA , Tabba S , Vazeou-Gerasimidi A , Maltoni G , Giani E , Dotan I , Liberty IF , Toledano Y , Kordonouri O , Bratina N , Dovc K , Biester T , Atlas E & Phillip M
Diabetes Technol Ther. 2022;24:564-572. doi: https://pubmed.ncbi.nlm.nih.gov/35325567/
Brief Summary: This physician survey-based study compared insulin dose recommendations between an artificial intelligence-based decision support system (ED-DSS) and 20 experienced physicians from 11 countries. Using data from 17 individuals with type 1 diabetes (T1D) treated with multiple daily insulin injections (MDI), the proportion of agreement and disagreement for insulin dose adjustment observed between the ED-DSS and physicians was statistically non-inferior to that among physicians.
This study explored one specific area of T1D management, insulin dose adjustments, in individuals using MDI. This typically requires healthcare professionals to provide constant advice and support to the patients and families during clinic appointments and in between visits.
Artificial intelligence is becoming an attractive tool in several medical fields, and previous studies provided interesting data for its role for T1D management, primarily for dose adjustments in patients using insulin pumps (1,2). The Endo.Digital (ED-DDS), used in this study, is a software designed to provide a comprehensive analysis of individual glucose control and advice on insulin treatment plan (1). Of interest, recommendations for insulin dose adjustments made by this automated system did not differ significantly from those given by expert physicians regarding the direction of change, and they were even more cautious for the magnitude of change in insulin dose adjustments.
Although based on data reviewed by a limited number of clinicians from different centres, these results support the use of an automated system as a tool which could be implemented in clinical practice to assist health care professional in managing people with T1D using MDI therapy, especially when and where accessibility to expert clinics is limited.
References: 1. Nimri R, Battelino T, Laffel LM, Slover RH, Schatz D, Weinzimer SA, Dovc K, Danne T, Phillip M; NextDREAM Consortium. Insulin dose optimization using an automated artificial intelligence-based decision support system in youths with type 1 diabetes. Nat Med. 2020 Sep;26(9):1380–1384. 2. Nimri R, Oron T, Muller I, Kraljevic I, Alonso MM, Keskinen P, et al. Adjustment of Insulin Pump Settings in Type 1 Diabetes Management: Advisor Pro Device Compared to Physicians’ Recommendations. J Diabetes Sci Technol 2022;16:364–372.
Volume 19
Article tools
My recent searches
My recently viewed abstracts
Authors
ESPE Yearbook of Paediatric Endocrinology
ISSN 1662-4009 (Online)
© Bioscientifica 2024 |
Privacy policy |
Cookie settings
BiosciAbstracts
Bioscientifica Abstracts is the gateway to a series of products that provide a permanent, citable record of abstracts for biomedical and life science conferences.
Find out more