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

Enhancing diabetes risk stratification through natural language processing: a multimodal data integration approach.

Yaoyan Lu1,2, Tingting Li1, Liyuan Ge1

  • 1School of Public Health, Guilin Medical University, Guilin, China.

Frontiers in Public Health
|June 15, 2026
PubMed
Summary

Related Concept Videos

Diabetes Mellitus: Overview and Type I Subtype01:22

Diabetes Mellitus: Overview and Type I Subtype

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...
Diabetes Mellitus: Type 2 and Gestational01:22

Diabetes Mellitus: Type 2 and Gestational

Type 2 diabetes, characterized by insulin resistance, arises when the insulin receptors on cells lose responsiveness to insulin, diminishing the cell's capacity to take up glucose, resulting in elevated blood glucose levels. To receive a diagnosis of Type 2 diabetes, a series of blood glucose tests are necessary to assess whether the blood glucose falls within normal parameters. If the result is out of the normal range, a patient may be diagnosed as prediabetic or diabetic, depending on the...

You might also read

Related Articles

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

Sort by
Same author

[Molecular characteristics for poor prognosis related renal cell carcinoma with lymph metastases].

Beijing da xue xue bao. Yi xue ban = Journal of Peking University. Health sciences·2026
Same author

A temporal-spectral dual-stream anti-noise bearing fault diagnosis model based on adaptive mode decomposition.

Scientific reports·2026
Same author

A dynamic nomogram and risk classification for predicting prognosis in renal cell carcinoma with venous tumor thrombus.

BMC urology·2026
Same author

Development and testing of a smart empowerment education system for gout patients in suburban areas.

Frontiers in public health·2026
Same author

Research on daily medication and drug efficacy evaluation for chronic diseases based on natural language processing (NLP).

Frontiers in public health·2026
Same author

Research on the spatial-temporal evolution of healthcare resource allocation efficiency in China.

Frontiers in public health·2026
Same journal

Governance absorption of volume-based procurement: study of dual-track implementation in a public hospital.

Frontiers in public health·2026
Same journal

Quality and reliability of cardiac rehabilitation-related short Chinese videos on Douyin and Bilibili: a cross-sectional content analysis.

Frontiers in public health·2026
Same journal

The impact of emotional labor on emotional exhaustion of social workers: a test of the mediating effect of perceived job demands.

Frontiers in public health·2026
Same journal

Clinical nurses as digital guardians: unlocking the key determinants of digital resilience in the AI era.

Frontiers in public health·2026
Same journal

Best evidence summary of digital health interventions for self-management in patients with coronary artery disease.

Frontiers in public health·2026
Same journal

Global prevalence and biopsychosocial correlates of psychological distress among people living with HIV: an updated theory-informed meta-analysis.

Frontiers in public health·2026
See all related articles
This summary is machine-generated.

Integrating Natural Language Processing (NLP) with clinical data significantly improves type 2 diabetes risk prediction by uncovering hidden risk factors from medical text. This approach enhances patient risk assessment for personalized prevention strategies.

Area of Science:

  • Medical Informatics
  • Computational Linguistics
  • Public Health

Background:

  • Type 2 diabetes risk prediction relies on traditional clinical data.
  • Unstructured clinical text contains valuable, yet often unutilized, risk information.
  • Natural Language Processing (NLP) offers a method to extract insights from this text.

Purpose of the Study:

  • To evaluate if integrating NLP-derived features with traditional clinical data improves type 2 diabetes risk prediction.
  • To identify latent risk factors from unstructured medical text using NLP.
  • To assess the performance and generalizability of a hybrid predictive model.

Main Methods:

  • A BERT-based NLP pipeline processed unstructured clinical notes for feature extraction.
  • A hybrid logistic regression model combined NLP features with structured data (BMI, HbA1c, blood pressure).
Keywords:
BERT modeldiabetes mellitusmachine learningnatural language processingpublic health informaticsrisk assessmenttype 2unstructured data

Related Experiment Videos

  • Model performance was validated using accuracy, AUC-ROC, temporal validation, and cross-validation on multiple classifiers.

    • Main Results:

    • NLP identified non-traditional risk factors like sedentary behavior, poor diet, and stress.
    • The integrated NLP model significantly outperformed the structured-only model (AUC: 0.92 vs. 0.83).
    • Key predictors included NLP-identified sedentary behavior, hypertension, elevated HbA1c, and high BMI.

    Conclusions:

    • NLP effectively extracts latent risk information from unstructured clinical text, enhancing diabetes risk prediction.
    • This framework supports more comprehensive patient risk assessment for personalized prevention.
    • Future research should focus on external validation, privacy, and explainable AI.