Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Insulin: Dosing Regimen and Adverse Effects01:16

Insulin: Dosing Regimen and Adverse Effects

330
Insulin-replacement therapy usually includes both long-acting insulin (basal) and short-acting insulin (to cater to postprandial needs). In a diverse group of type 1 diabetes patients, the average daily insulin dose is typically 0.5-0.7 units/kg body weight. However, obese patients and pubertal adolescents may need more due to insulin resistance.
The basal dose constitutes about 40%-50% of the total daily dose, with the rest as premeal insulin. The mealtime insulin dose should mirror...
330
Insulin Formulations: Types and Delivery01:27

Insulin Formulations: Types and Delivery

329
Insulin preparations are categorized by their duration of action into short-acting and long-acting types. Two strategies are used to modify insulin's absorption and pharmacokinetic profile: slowing the absorption post-subcutaneous injection, or altering human insulin's amino acid sequence or protein structure. These changes retain the insulin's ability to bind to the insulin receptor, but alter its behavior in solution or after injection.
Short-acting insulins are divided into...
329
Insulin: Biosynthesis, Chemistry, and Preparation01:25

Insulin: Biosynthesis, Chemistry, and Preparation

701
The endoplasmic reticulum (ER) of pancreatic β-cells synthesizes preproinsulin, which consists of a signal peptide, A and B chains, and a C-peptide. Preproinsulin is then cleaved and folded into proinsulin, which translocates to the Golgi apparatus for sorting and packaging into secretory granules. In these granules, enzymatic clipping generates insulin and C-peptide.
Damage or functional impairment of β-cells inhibits insulin production, leading to diabetes. Diabetes treatment...
701
Hypoglycemia and Glucagon01:15

Hypoglycemia and Glucagon

482
Without prolonged fasting, healthy individuals maintain blood glucose levels above 3.5 mM due to a well-adapted neuroendocrine counterregulatory system that effectively prevents acute hypoglycemia, a potentially life-threatening condition. The primary clinical scenarios for hypoglycemia encompass diabetes treatment, inappropriate production of endogenous insulin or insulin-like substances by tumors, and the use of glucose-lowering agents in non-diabetic individuals. Notably, hypoglycemia in the...
482
Diabetes Mellitus: Overview and Type I Subtype01:22

Diabetes Mellitus: Overview and Type I Subtype

4.0K
Diabetes mellitus is a chronic metabolic disorder characterized by high blood glucose levels due to inadequate insulin production, insulin resistance, or both. The condition affects millions worldwide and can significantly impact their health and quality of life.
Type 1 diabetes is an autoimmune disease in which the immune system mistakenly attacks and destroys the insulin-producing beta cells in the pancreas. As a result, the body is unable to produce sufficient insulin, and individuals with...
4.0K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

SmartAlert - Implementing Machine Learning-Driven Clinical Decision Support for Inpatient Laboratory Utilization Reduction.

NEJM AI·2026
Same author

Why and How to Monitor Deployed AI Systems in Health Care.

NEJM catalyst innovations in care delivery·2026
Same author

BRIDGE: benchmarking large language models for understanding real-world clinical practice texts.

Nature biomedical engineering·2026
Same author

Mapping the local effectiveness of mass drug administration for malaria using transportability methods.

Nature health·2026
Same author

Micro-randomization trial design under operational constraints.

Contemporary clinical trials·2026
Same author

What the AI era doctor should know: a scoping review of proposed artificial intelligence competencies for medical education.

NPJ digital medicine·2026

Related Experiment Video

Updated: Oct 27, 2025

Improving IV Insulin Administration in a Community Hospital
12:08

Improving IV Insulin Administration in a Community Hospital

Published on: June 11, 2012

19.1K

Machine learning for initial insulin estimation in hospitalized patients.

Minh Nguyen1, Ivana Jankovic2, Laurynas Kalesinskas1

  • 1Department of Biomedical Data Science, Stanford University, School of Medicine, Stanford, California, USA.

Journal of the American Medical Informatics Association : JAMIA
|July 19, 2021
PubMed
Summary

Machine learning accurately predicts inpatient insulin doses using electronic health records, outperforming standard guidelines. This data-driven approach improves total daily dose (TDD) estimation for better glucose control.

Keywords:
clinical decision supportdiabetes mellitusinsulinmachine learningmedical informatics

More Related Videos

Homogeneous Time-resolved Förster Resonance Energy Transfer-based Assay for Detection of Insulin Secretion
07:30

Homogeneous Time-resolved Förster Resonance Energy Transfer-based Assay for Detection of Insulin Secretion

Published on: May 10, 2018

9.4K
Studying the Hypothalamic Insulin Signal to Peripheral Glucose Intolerance with a Continuous Drug Infusion System into the Mouse Brain
08:32

Studying the Hypothalamic Insulin Signal to Peripheral Glucose Intolerance with a Continuous Drug Infusion System into the Mouse Brain

Published on: January 4, 2018

10.5K

Related Experiment Videos

Last Updated: Oct 27, 2025

Improving IV Insulin Administration in a Community Hospital
12:08

Improving IV Insulin Administration in a Community Hospital

Published on: June 11, 2012

19.1K
Homogeneous Time-resolved Förster Resonance Energy Transfer-based Assay for Detection of Insulin Secretion
07:30

Homogeneous Time-resolved Förster Resonance Energy Transfer-based Assay for Detection of Insulin Secretion

Published on: May 10, 2018

9.4K
Studying the Hypothalamic Insulin Signal to Peripheral Glucose Intolerance with a Continuous Drug Infusion System into the Mouse Brain
08:32

Studying the Hypothalamic Insulin Signal to Peripheral Glucose Intolerance with a Continuous Drug Infusion System into the Mouse Brain

Published on: January 4, 2018

10.5K

Area of Science:

  • Medical Informatics
  • Machine Learning in Healthcare
  • Clinical Decision Support

Background:

  • Insulin dosing for inpatients has a narrow therapeutic window and significant individual variability.
  • Current guideline-based recommendations may not provide optimal or accurate initial total daily dose (TDD) predictions.
  • Data-driven analytic tools are needed to support adaptive and predictive insulin dosing strategies.

Purpose of the Study:

  • To evaluate the accuracy of machine learning (ML) algorithms in predicting initial inpatient insulin TDD compared to existing guideline-based methods.
  • To assess ML's ability to identify patients requiring more than 6 units of TDD and to predict their precise TDD.
  • To leverage electronic health records (EHRs) for improved insulin dose prediction.

Main Methods:

  • An ensemble ML algorithm (regularized regression, random forest, gradient boosted trees) was trained using EHR data from 16,848 inpatients (2008-2020).
  • The study focused on patients achieving target blood glucose control (100-180 mg/dL) on a given day.
  • Model performance was evaluated for predicting patients needing >6 units TDD and their specific TDDs, comparing against standard weight-based calculations.

Main Results:

  • The ensemble ML model achieved an area under the receiver-operating characteristic curve of 0.85 for classifying patients requiring >6 units TDD.
  • For patients needing >6 units TDD, ML significantly reduced mean absolute percent error in dose prediction from 136%-329% (standard calculators) to 51% (full ensemble model).
  • Weight-based regression models improved prediction accuracy to 60%, with the full ensemble model further enhancing it.

Conclusions:

  • ML models utilizing EHR data can accurately identify inpatients likely to require >6 units TDD.
  • ML approaches provide more accurate individual insulin dose estimations than standard guidelines and practices.
  • These findings support the use of ML for adaptive, data-driven insulin dosing in inpatient settings.