Skip to content

Evaluation of the artificial intelligence (AI) for predicting optimized insulin dosage in diabetic patients

Evaluation of the artificial intelligence (AI) for predicting optimized insulin dosage in diabetic patients

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
JPRN
Registry ID
JPRN-jRCT1022240017
Enrollment
130
Registered
2024-08-07
Start date
2024-08-07
Completion date
Unknown
Last updated
2026-06-29

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Type 2 Diabetes

Interventions

None listed

Sponsors

Katagiri Hideki
Lead Sponsor

Eligibility

Sex/Gender
All

Inclusion criteria

Inclusion criteria: Clinical data of hospitalized type 2 diabetes patients who received insulin therapy from diabetologists will be collected, provided they meet all the following eligibility criteria and do not fall under any exclusion criteria. Eligibility Criteria: (1) Patients using ultra-rapid-acting insulin and long-acting insulin (insulin glargine, insulin degludec) (2) Patients aged 20 years or older (3) Patients who have provided written consent to participate in the study (4) Patients with a hospital stay of 7 days or more

Exclusion criteria

Exclusion criteria: (1) Patients who are pregnant or may be pregnant (2) Patients with or suspected of having diabetic gastroparesis (3) Patients with severe diabetic autonomic neuropathy (4) Patients with pre-proliferative diabetic retinopathy or proliferative diabetic retinopathy, or suspected of having these conditions (5) Patients undergoing continuous subcutaneous insulin infusion therapy or continuous intravenous insulin infusion (6) Patients who have not been discharged since undergoing general anesthesia surgery (7) Patients with missing data in the specified input data without any reason such as tests (8) Patients whose primary purpose is not blood glucose control (9) For cases from Tohoku University Hospital, data from hospitalizations before 2021 (as these data may have been used for the training of the experimental device)

Design outcomes

Primary

MeasureTime frame
Correct rate: Rate when the difference between the test device and the units prescribed by diabetologists is within the acceptable range.

Contacts

Public ContactKei Takahashi

Tohoku University Graduate School of Medicine

kei.takahashi.b4@tohoku.ac.jp+81-22-717-7611

Outcome results

None listed

Source: JPRN (via WHO ICTRP) · Data processed: Jul 3, 2026