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 Experiment Videos

Predicting Type 2 diabetes using an electronic nose-based artificial neural network analysis.

E I Mohamed1, R Linder, G Perriello

  • 1Human Physiology Division, University Tor Vergata, Rome, Italy.

Diabetes, Nutrition & Metabolism
|November 6, 2002
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Advancing Rapid Acquisition in Lung PET-CT: Protocol Optimisation via Reduced <sup>18</sup>F-FDG Activity and Scan Duration.

Radiography (London, England : 1995)·2026
Same author

Timing matters: Surgery-to-chemotherapy interval and outcomes in ovarian cancer.

European journal of obstetrics, gynecology, and reproductive biology·2025
Same author

Rate of change in upper and lower motor neuron burden is associated with survival in amyotrophic lateral sclerosis.

Journal of neurology·2025
Same author

Improved detection of coronary artery disease by CZT regional coronary blood flow evaluation.

Frontiers in nuclear medicine·2024
Same author

Bioelectrical impedance analysis in patients with posterior vitreous detachment.

European review for medical and pharmacological sciences·2023
Same author

Role of nutrients in modulating microbiota and immunity in COVID-19 disease.

European review for medical and pharmacological sciences·2023
Same journal

Pancreas procurement from multiorgan donors for islet trasplantation.

Diabetes, nutrition & metabolism·2011
Same journal

Outcome of human islet isolation and allotransplantation in 20 consecutive cases.

Diabetes, nutrition & metabolism·2011
Same journal

Resting metabolic rate incremented by pulsating electrostatic field (PESF) therapy.

Diabetes, nutrition & metabolism·2005
Same journal

Effectiveness of an uninterrupted procedure to transfer adolescents with Type 1 diabetes from the Paediatric to the Adult Clinic held in the same hospital: eight-year experience with the Parma protocol.

Diabetes, nutrition & metabolism·2005
Same journal

Prevalence of obstructive sleep apnoea in a sample of obese women: effect of menopause.

Diabetes, nutrition & metabolism·2005
Same journal

Associations among sex hormone binding globulin concentrations and characteristics of the metabolic syndrome in obese women.

Diabetes, nutrition & metabolism·2005
See all related articles

Early detection of Type 2 diabetes is crucial. Electronic nose technology combined with principal component analysis (PCA) successfully identified diabetic patients with 96% accuracy, offering a promising diagnostic tool.

Area of Science:

  • Biomedical Engineering
  • Analytical Chemistry
  • Computational Biology

Background:

  • Diabetes mellitus, particularly Type 2, is a growing global health concern with significant diagnostic delays.
  • Early identification and management of hyperglycemia in Type 2 diabetes are vital for preventing complications.
  • Current diagnostic methods may not capture the full spectrum of metabolic changes, necessitating novel approaches.

Purpose of the Study:

  • To investigate the utility of electronic nose (e-nose) technology for differentiating Type 2 diabetic patients from healthy individuals.
  • To evaluate the effectiveness of various data classification algorithms, including artificial neural networks (ANN), logistic regression (LR), and principal component analysis (PCA), for analyzing e-nose data.
  • To assess the suitability of the "Approximation and Classification of Medical Data" (ACMD) network for medical data classification.

Related Experiment Videos

Main Methods:

  • Urine samples from Type 2 diabetic patients and healthy controls were analyzed using an 8-sensor electronic nose.
  • Generated e-nose patterns were classified using PCA, binary LR analysis, and a self-learning ANN (ACMD network).
  • Classification performance was assessed based on successful identification rates.

Main Results:

  • Principal Component Analysis (PCA) demonstrated distinctclassifications between Type 2 diabetic subjects and controls, achieving a 96.0% successful classification rate.
  • Artificial Neural Network (ANN) analysis, specifically the ACMD network, achieved a 92.0% classification success rate.
  • Logistic Regression (LR) analysis yielded an 88.0% successful classification rate.

Conclusions:

  • Electronic nose technology, coupled with PCA, provides a highly accurate method for distinguishing Type 2 diabetic patients.
  • The ACMD network is effective for classifying medical and clinical data, showing significant potential in diabetes diagnostics.
  • These findings support the development of non-invasive, rapid diagnostic tools for Type 2 diabetes management.