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

You might also read

Related Articles

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

Sort by
Same author

A Gate-Tunable Thermal Persistent Photocurrent Device for In-Sensor Spiking Neural Networks.

ACS applied materials & interfaces·2026
Same author

Inverse Design of Optical Color Routers with Improved Fabrication Compatibility.

Nanomaterials (Basel, Switzerland)·2026
Same author

Meta-amplified dark-field interferometric scattering microscopy.

Nature communications·2026
Same author

Second-harmonic radiation by on-chip integrable mirror-symmetric nanodimers with sub-nanometric plasmonic gap.

Nanophotonics (Berlin, Germany)·2025
Same author

Reconfigurable van der Waals Junction Field Effect Transistor with Anchored Threshold and Enhanced Subthreshold Swing for Complementary Logic.

ACS nano·2024
Same author

Topologically Protected Plasmonic Bound States in the Continuum.

Nano letters·2024

Related Experiment Video

Updated: Sep 14, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.1K

Functionalized Nanofinger Enhances Pretrained Language Model Performance for Ultrafast Early Warning of Heart

Hongming Zhang1, Zerui Liu1, Heming Sun1

  • 1Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, California 90089-0271, United States.

ACS Applied Bio Materials
|July 20, 2025
PubMed
Summary

This study introduces an AI system combining blood biomarker analysis and patient symptoms for accurate early heart attack detection. The novel approach achieves 99.19% accuracy, improving upon traditional methods.

Keywords:
Raman spectroscopyheart attacks diagnosislarge language models (LLMs)machine learningsynthetic data augmentation

More Related Videos

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.6K
Author Spotlight: A Novel Standardized Technique for Real-Time Biomedical Imaging of Acute Myocardial Injury
07:17

Author Spotlight: A Novel Standardized Technique for Real-Time Biomedical Imaging of Acute Myocardial Injury

Published on: March 22, 2024

1.2K

Related Experiment Videos

Last Updated: Sep 14, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.1K
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.6K
Author Spotlight: A Novel Standardized Technique for Real-Time Biomedical Imaging of Acute Myocardial Injury
07:17

Author Spotlight: A Novel Standardized Technique for Real-Time Biomedical Imaging of Acute Myocardial Injury

Published on: March 22, 2024

1.2K

Area of Science:

  • Biomedical Engineering
  • Artificial Intelligence
  • Medical Diagnostics

Background:

  • Heart attacks are a leading global cause of death, necessitating improved early warning systems.
  • Traditional diagnostic methods like ECG and blood tests have limitations in speed and accuracy, often delaying treatment.
  • Previous work established a nanofinger platform for biomarker detection with high true positive rates but limited true negative accuracy.

Purpose of the Study:

  • To enhance early heart attack detection accuracy by integrating AI-driven analysis of patient symptoms with blood biomarker data.
  • To develop a scalable AI-based solution for early-stage heart attack detection, addressing limitations of conventional methods.
  • To adapt the AI approach for broader applications in disease detection.

Main Methods:

  • Integrated AI analysis of patient symptoms (current and historical) with blood biomarker data (BNP).
  • Utilized a fine-tuned pretrained language model to process fused data for diagnostic classification.
  • Employed generative models for data augmentation to enhance model robustness and expand the dataset.

Main Results:

  • Achieved a diagnostic accuracy rate of 99.19%, significantly outperforming conventional methods.
  • Successfully fused multi-modal patient data (biomarkers and symptoms) for improved diagnostic performance.
  • Demonstrated the effectiveness of generative models in augmenting limited clinical data for AI training.

Conclusions:

  • The developed AI system offers a scalable and accurate solution for early heart attack detection.
  • Integration of blood analysis, LLMs, and generative models represents a significant advancement in automated medical diagnosis.
  • The AI framework is adaptable for early detection of other diseases, highlighting its broad healthcare potential.