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

Stereotype Content Model02:16

Stereotype Content Model

13.0K
The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...
13.0K
Classification of Illness01:17

Classification of Illness

9.4K
The meaning of illness is individualized to each person who experiences an alteration in health. In contrast, disease is a medical term indicating a pathological change in the structure and function of the body or mind. It is a condition that has specific symptoms and boundaries.
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...
9.4K
Classification of Systems-II01:31

Classification of Systems-II

638
Continuous-time systems have continuous input and output signals, with time measured continuously. These systems are generally defined by differential or algebraic equations. For instance, in an RC circuit, the relationship between input and output voltage is expressed through a differential equation derived from Ohm's law and the capacitor relation,
638
Classification of Systems-I01:26

Classification of Systems-I

725
Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
725
How Data are Classified: Categorical Data01:11

How Data are Classified: Categorical Data

28.8K
A variable, usually notated by capital letters such as X and Y, is a characteristic or measurement that can be determined for each member of a population. Data are the actual values of variables. They may be numbers, or they may be words. Datum is a single value.
Data are classified based on whether they are measurable or not. Categorical data cannot be measured; instead, it can be divided into categories. For example, if Y denotes a person's party affiliation, some examples of Y include...
28.8K
Ranks01:02

Ranks

584
Unlike parametric methods, nonparametric statistics are ideal for nominal and ordinal data, requiring fewer assumptions about the population's nature or distribution. This makes nonparametric methods easier to apply and interpret, as they do not depend on parameters like mean or standard deviation. One common approach in nonparametric analysis is to sort data according to a specific criterion. For instance, we might arrange weather data from hottest to coldest days in a month or rank cities...
584

You might also read

Related Articles

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

Sort by
Same author

Predicting 30-Day Postoperative Mortality and American Society of Anesthesiologists Physical Status Using Retrieval-Augmented Large Language Models: Development and Validation Study.

Journal of medical Internet research·2025
Same author

Estimating sample means and standard deviations from the log-normal distribution using medians and quartiles: evaluating reporting requirements for primary and secondary endpoints of meta-analyses in anesthesiology.

Canadian journal of anaesthesia = Journal canadien d'anesthesie·2025
Same author

Taylor Series Approximation for Accurate Generalized Confidence Intervals of Ratios of Log-Normal Standard Deviations for Meta-Analysis Using Means and Standard Deviations in Time Scale.

Pharmaceutical statistics·2025
Same author

Generalized Confidence Intervals for Ratios of Standard Deviations Based on Log-Normal Distribution when Times Follow Weibull Distributions.

Journal of medical systems·2024
Same author

Novel Solution for Using Neural Networks for Kidney Boundary Extraction in 2D Ultrasound Data.

Biomolecules·2023
Same author

Training a Deep Contextualized Language Model for International Classification of Diseases, 10th Revision Classification via Federated Learning: Model Development and Validation Study.

JMIR medical informatics·2022

Related Experiment Video

Updated: Apr 23, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

1.3K

Classifying American Society of Anesthesiologists Physical Status With a Low-Rank-Adapted Large Language Model:

Min-Chia Chen1, Shanq-Jang Ruan1, Jo-Hsin Wu2

  • 1Department of Electronic and Computer Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan.

Journal of Medical Internet Research
|April 21, 2026
PubMed
Summary

This study fine-tuned a large language model (LLM) using Low-Rank Adaptation (LoRA) for American Society of Anesthesiologists Physical Status (ASA-PS) classification. While the LoRA-LLM improved performance over other LLMs, traditional machine learning models showed superior predictive accuracy.

Keywords:
American Society of Anesthesiologists Physical Statuselectronic health recordslarge language modelslow-rank adaptationnatural language processing.parameter-efficient fine-tuning

More Related Videos

A Protocol for Comprehensive Assessment of Bulbar Dysfunction in Amyotrophic Lateral Sclerosis ALS
12:43

A Protocol for Comprehensive Assessment of Bulbar Dysfunction in Amyotrophic Lateral Sclerosis ALS

Published on: February 21, 2011

37.6K

Related Experiment Videos

Last Updated: Apr 23, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

1.3K
A Protocol for Comprehensive Assessment of Bulbar Dysfunction in Amyotrophic Lateral Sclerosis ALS
12:43

A Protocol for Comprehensive Assessment of Bulbar Dysfunction in Amyotrophic Lateral Sclerosis ALS

Published on: February 21, 2011

37.6K

Area of Science:

  • Artificial Intelligence in Medicine
  • Clinical Decision Support Systems
  • Natural Language Processing in Healthcare

Background:

  • The American Society of Anesthesiologists Physical Status (ASA-PS) classification is crucial for preoperative risk assessment but is subjective and time-consuming.
  • Large language models (LLMs) can process electronic health records (EHRs), but efficient adaptations for clinical tasks like ASA-PS prediction are underexplored.
  • Low-Rank Adaptation (LoRA) offers a parameter-efficient method for fine-tuning LLMs, enabling development of lightweight, explainable AI tools for clinical workflows.

Purpose of the Study:

  • To develop and evaluate a LoRA-fine-tuned LLaMA-3 model for classifying ASA-PS from preoperative clinical narratives.
  • To benchmark the LoRA-LLaMA-3 model against traditional machine learning classifiers and other domain-specific LLMs.
  • To assess the model's ability to provide clinician-readable rationales for ASA-PS predictions.

Main Methods:

  • Preoperative EHR notes were reformatted into instruction-response prompts for ASA-PS classification (I-V).
  • A LLaMA-3 model was fine-tuned using LoRA with mixed-precision training and evaluated on a hold-out test set.
  • Performance was compared against random forest, XGBoost, SVM, fastText, BioBERT, ClinicalBERT, and untuned LLaMA-3 using micro/macro F1-scores and MCC.

Main Results:

  • The LoRA-LLaMA-3 model achieved a micro-F1 score of 0.780 and MCC of 0.533, outperforming other LLM baselines but with lower macro-F1 scores (0.316).
  • Extreme Gradient Boosting (XGBoost) achieved the highest performance (micro-F1: 0.815, MCC: 0.613).
  • The LoRA model generated pertinent explanations, enhancing decision transparency, while untuned LLaMA-3 performed poorly.

Conclusions:

  • LoRA fine-tuning significantly improved LLaMA-3 for ASA-PS classification, offering better micro-level performance and explainability than other LLMs.
  • Traditional machine learning models, particularly XGBoost, demonstrated superior overall predictive performance.
  • This LoRA-based approach provides a practical, resource-efficient framework for deploying explainable LLMs in clinical classification tasks.