TOPLINE:
A patient-facing voice-based conversational artificial intelligence (VBAI) application that provided autonomous basal insulin titration improved time to optimal insulin dosing, insulin adherence, and glycemic control among adults with type 2 diabetes compared with standard care.
METHODOLOGY:
- The trial was conducted at four primary care clinics at an academic medical center from March 2021 to December 2022.
- Thirty-two adults with type 2 diabetes requiring once-daily basal insulin initiation or adjustment (mean baseline A1c, 9.6%) were randomly assigned to use the VBAI app or to standard care for 8 weeks.
TAKEAWAY:
- Time to optimal insulin dose was 15 days with the VBAI app vs > 56 days with standard care (P = .006).
- Insulin adherence (based on log data) was 82.9% with the VBAI app vs 50.2% with standard care (P = .01).
- Glycemic control (mean fasting blood glucose < 130 mg/dL at 8 weeks) was achieved by 81.3% of participants using the VBAI app vs 25% of those receiving standard care (P = .005).
- Mean fasting glucose levels dropped by 45.9 mg/dL with VBAI but increased by 23.0 mg/dL with standard care (P = .001).
- There were no episodes of severe hyperglycemia or hypoglycemia in either group. There were 11 and 10 episodes of nonsevere hypoglycemia in the VBAI and standard care groups, respectively.
- On the 5-item Problem Areas in Diabetes (PAID-5) scale, a survey on diabetes-related emotional distress, scores dropped by a mean of 1.9 points with VBAI while increasing by 1.7 points with standard care (P = .03).
IN PRACTICE:
- "To our knowledge, this study marks the first time VBAI has been used to autonomously adjust medication doses based on a protocol preapproved by a clinician."
- "These findings suggest that digital health tools can be useful for medication titration and that voice user interfaces can be effective for patient facing digital technologies."
SOURCE:
The study was published online on December 1, 2023, in JAMA Network Open. The first author is Ashwin Nayak, MD, MS, of the Division of Hospital Medicine at Stanford University, Stanford, California.
LIMITATIONS:
The short duration of the study precluded use of A1c to measure glycemic control. Self-reported log data were used. No comparison was made with other insulin titration apps. Only English-speaking persons were included.
DISCLOSURES:
Nayak and two co-authors reported owning stock in UpDoc outside the submitted work. UpDoc is an early-stage company that was founded 3 months after this trial was completed and did not fund the trial.
Miriam E. Tucker is a freelance journalist based in the Washington, DC, area. She is a regular contributor to Medscape, with other work appearing in the Washington Post, NPR's Shots blog, and Diabetes Forecast magazine. She is on Twitter @MiriamETucker.
"type" - Google News
December 01, 2023 at 10:56PM
https://ift.tt/wsnu0cL
AI Aids Type 2 Diabetes Insulin Dosing - Medscape
"type" - Google News
https://ift.tt/6eLN38F
https://ift.tt/8pofSBw
Bagikan Berita Ini
0 Response to "AI Aids Type 2 Diabetes Insulin Dosing - Medscape"
Post a Comment