Revital Nimri1, Tal Oron1, Ido Muller2, Ivana Kraljevic3, Montserrat Martín Alonso4, Paivi Keskinen5, Tanja Milicic6, Asaf Oren7,8, Athanasios Christoforidis9, Marieke den Brinker10, Lutgarda Bozzetto11, Andrea Mario Bolla12, Michal Krcma13, Rosa Anna Rabini14, Shadi Tabba15, Lizl Smith16, Andriani Vazeou17, Giulio Maltoni18, Elisa Giani19, Eran Atlas2, Moshe Phillip1,8. 1. The Jesse Z and Sara Lea Shafer Institute for Endocrinology and Diabetes, National Center for Childhood Diabetes, Schneider Children's Medical Center of Israel, Petah, Tikva, Israel. 2. DreaMed Diabetes Ltd, Petah Tiqva, Israel. 3. Department of Endocrinology and Diabetes, UHC Zagreb, School of Medicine, University of Zagreb, Zagreb, Croatia. 4. Department of Pediatrics, Children's Endocrinology Unit, University Hospital of Salamanca, Spain. 5. Department of Pediatrics, University Hospital of Tampere, Finland. 6. Clinic for Endocrinology, Diabetes and Metabolic Diseases, Clinical Center of Serbia, Faculty of Medicine University of Belgrade, Serbia. 7. Pediatric Endocrinology and Diabetes Unit, Dana-Dwek Children's Hospital, Tel Aviv Sourasky Medical Center, Israel. 8. Sackler School of Medicine, Tel Aviv University, Israel. 9. Pediatric Department, Aristotle University of Thessaloniki, Hippokratio General Hospital, Thessaloniki, Greece. 10. Department of Pediatrics, Division of Pediatric Endocrinology and Diabetology, Antwerp University Hospital and University of Antwerp, Belgium. 11. Department of Clinical Medicine and Surgery, University of Naples "Federico II", Italy. 12. Diabetes Research Institute, IRCCS San Raffaele Hospital, Milan, Italy. 13. Department of Internal Medicine, Diabetes and Endocrinology Unit, University Hospital Pilsen, Faculty of Medicine in Pilsen, Charles University, Czech Republic. 14. Department of Diabetology, Hospital Mazzoni, Ascoli Piceno, Italy. 15. Children's Hospital of the King's Daughters, Eastern Virginia Medical School, Norfolk, VA, USA. 16. Department of Internal Medicine, Division of Endocrinology, University of Pretoria, South Africa. 17. A' Department of Pediatrics, Diabetes Center, P&A Kyriakou, Athens, Greece. 18. Department of Pediatrics, University Hospital of Bologna Sant'Orsola-Malpighi Polyclinic, Italy. 19. Department of Biomedical Sciences, Humanitas Clinical and Research Center-IRCCS and Humanitas University, Milan, Italy.
Abstract
AIMS: To compare insulin dose adjustments made by physicians to those made by an artificial intelligence-based decision support system, the Advisor Pro, in people with type 1 diabetes (T1D) using an insulin pump and self-monitoring blood glucose (SMBG). METHODS: This was a multinational, non-interventional study surveying 17 physicians from 11 countries. Each physician was asked to provide insulin dose adjustments for the settings of the pump including basal rate, carbohydrate-to-insulin ratios (CRs), and correction factors (CFs) for 15 data sets of pumps and SMBG of people with T1D (mean age 18.4 ± 4.8 years; eight females; mean glycated hemoglobin 8.2% ± 1.4% [66 ± 11mmol/mol]). The recommendations were compared among the physicians and between the physicians and the Advisor Pro. The study endpoint was the percentage of comparison points for which there was an agreement on the direction of insulin dose adjustments. RESULTS: The percentage (mean ± SD) of agreement among the physicians on the direction of insulin pump dose adjustments was 51.8% ± 9.2%, 54.2% ± 6.4%, and 49.8% ± 11.6% for the basal, CR, and CF, respectively. The automated recommendations of the Advisor Pro on the direction of insulin dose adjustments were comparable )49.5% ± 6.4%, 55.3% ± 8.7%, and 47.6% ± 14.4% for the basal rate, CR, and CF, respectively( and noninferior to those provided by physicians. The mean absolute difference in magnitude of change between physicians was 17.1% ± 13.1%, 14.6% ± 8.4%, and 23.9% ± 18.6% for the basal, CR, and CF, respectively, and comparable to the Advisor Pro 11.7% ± 9.7%, 10.1% ± 4.5%, and 25.5% ± 19.5%, respectively, significant for basal and CR. CONCLUSIONS: Considerable differences in the recommendations for changes in insulin dosing were observed among physicians. Since automated recommendations by the Advisor Pro were similar to those given by physicians, it could be considered a useful tool to manage T1D.
AIMS: To compare insulin dose adjustments made by physicians to those made by an artificial intelligence-based decision support system, the Advisor Pro, in people with type 1 diabetes (T1D) using an insulin pump and self-monitoring blood glucose (SMBG). METHODS: This was a multinational, non-interventional study surveying 17 physicians from 11 countries. Each physician was asked to provide insulin dose adjustments for the settings of the pump including basal rate, carbohydrate-to-insulin ratios (CRs), and correction factors (CFs) for 15 data sets of pumps and SMBG of people with T1D (mean age 18.4 ± 4.8 years; eight females; mean glycated hemoglobin 8.2% ± 1.4% [66 ± 11mmol/mol]). The recommendations were compared among the physicians and between the physicians and the Advisor Pro. The study endpoint was the percentage of comparison points for which there was an agreement on the direction of insulin dose adjustments. RESULTS: The percentage (mean ± SD) of agreement among the physicians on the direction of insulin pump dose adjustments was 51.8% ± 9.2%, 54.2% ± 6.4%, and 49.8% ± 11.6% for the basal, CR, and CF, respectively. The automated recommendations of the Advisor Pro on the direction of insulin dose adjustments were comparable )49.5% ± 6.4%, 55.3% ± 8.7%, and 47.6% ± 14.4% for the basal rate, CR, and CF, respectively( and noninferior to those provided by physicians. The mean absolute difference in magnitude of change between physicians was 17.1% ± 13.1%, 14.6% ± 8.4%, and 23.9% ± 18.6% for the basal, CR, and CF, respectively, and comparable to the Advisor Pro 11.7% ± 9.7%, 10.1% ± 4.5%, and 25.5% ± 19.5%, respectively, significant for basal and CR. CONCLUSIONS: Considerable differences in the recommendations for changes in insulin dosing were observed among physicians. Since automated recommendations by the Advisor Pro were similar to those given by physicians, it could be considered a useful tool to manage T1D.
Entities:
Keywords:
Advisor Pro; automated decision support; insulin pump settings adjustments; self-monitoring of blood glucose; type 1 diabetes
Authors: Richard M Bergenstal; Mary Johnson; Rebecca Passi; Anuj Bhargava; Natalie Young; Davida F Kruger; Eran Bashan; Stanley G Bisgaier; Deanna J Marriott Isaman; Israel Hodish Journal: Lancet Date: 2019-02-23 Impact factor: 79.321
Authors: Kellee M Miller; Nicole C Foster; Roy W Beck; Richard M Bergenstal; Stephanie N DuBose; Linda A DiMeglio; David M Maahs; William V Tamborlane Journal: Diabetes Care Date: 2015-06 Impact factor: 19.112
Authors: Nicole C Foster; Roy W Beck; Kellee M Miller; Mark A Clements; Michael R Rickels; Linda A DiMeglio; David M Maahs; William V Tamborlane; Richard Bergenstal; Elizabeth Smith; Beth A Olson; Satish K Garg Journal: Diabetes Technol Ther Date: 2019-01-18 Impact factor: 6.118
Authors: Nicole Y Xu; Kevin T Nguyen; Ashley Y DuBord; John Pickup; Jennifer L Sherr; Hazhir Teymourian; Eda Cengiz; Barry H Ginsberg; Claudio Cobelli; David Ahn; Riccardo Bellazzi; B Wayne Bequette; Laura Gandrud Pickett; Linda Parks; Elias K Spanakis; Umesh Masharani; Halis K Akturk; John S Melish; Sarah Kim; Gu Eon Kang; David C Klonoff Journal: J Diabetes Sci Technol Date: 2022-05-02
Authors: Ryan L Melvin; Matthew G Broyles; Elizabeth W Duggan; Sonia John; Andrew D Smith; Dan E Berkowitz Journal: Front Digit Health Date: 2022-04-25
Authors: Trisha Shang; Jennifer Y Zhang; B Wayne Bequette; Jennifer K Raymond; Gerard Coté; Jennifer L Sherr; Jessica Castle; John Pickup; Yarmela Pavlovic; Juan Espinoza; Laurel H Messer; Tim Heise; Carlos E Mendez; Sarah Kim; Barry H Ginsberg; Umesh Masharani; Rodolfo J Galindo; David C Klonoff Journal: J Diabetes Sci Technol Date: 2021-07