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

Actuarial Approach01:20

Actuarial Approach

336
The actuarial approach, a statistical method originally developed for life insurance risk assessment, is widely used to calculate survival rates in clinical and population studies. This method accounts for participants lost to follow-up or those who die from causes unrelated to the study, ensuring a more accurate representation of survival probabilities.
Consider the example of a high-risk surgical procedure with significant early-stage mortality. A two-year clinical study is conducted,...
336
Kaplan-Meier Approach01:24

Kaplan-Meier Approach

662
The Kaplan-Meier estimator is a non-parametric method used to estimate the survival function from time-to-event data. In medical research, it is frequently employed to measure the proportion of patients surviving for a certain period after treatment. This estimator is fundamental in analyzing time-to-event data, making it indispensable in clinical trials, epidemiological studies, and reliability engineering. By estimating survival probabilities, researchers can evaluate treatment effectiveness,...
662
Cancer Survival Analysis01:21

Cancer Survival Analysis

805
Cancer survival analysis focuses on quantifying and interpreting the time from a key starting point, such as diagnosis or the initiation of treatment, to a specific endpoint, such as remission or death. This analysis provides critical insights into treatment effectiveness and factors that influence patient outcomes, helping to shape clinical decisions and guide prognostic evaluations. A cornerstone of oncology research, survival analysis tackles the challenges of skewed, non-normally...
805
Improving Translational Accuracy02:07

Improving Translational Accuracy

15.3K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
15.3K
Improving Translational Accuracy02:07

Improving Translational Accuracy

3.7K
3.7K
Comparing the Survival Analysis of Two or More Groups01:20

Comparing the Survival Analysis of Two or More Groups

674
Survival analysis is a cornerstone of medical research, used to evaluate the time until an event of interest occurs, such as death, disease recurrence, or recovery. Unlike standard statistical methods, survival analysis is particularly adept at handling censored data—instances where the event has not occurred for some participants by the end of the study or remains unobserved. To address these unique challenges, specialized techniques like the Kaplan-Meier estimator, log-rank test, and...
674

You might also read

Related Articles

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

Sort by
Same author

Application-driven pedagogical knowledge optimization of open-source LLMs via reinforcement learning and supervised fine-tuning.

Frontiers in artificial intelligence·2026
Same author

Mapping Access to Nicotine Vaping Products for Smoking Cessation: Pharmacist Needs and Practice Implications in South-East Melbourne.

Health promotion journal of Australia : official journal of Australian Association of Health Promotion Professionals·2026
Same author

Sentinel surveillance of vaping and emerging nicotine product use among university students: protocol for a longitudinal cohort study.

BMC public health·2026
Same author

Generative intelligence explores the chemical space of ten million catalysts.

Chemical science·2026
Same author

General practice communication: experiences of older Greek patients with limited English proficiency.

BJGP open·2026
Same author

Correlation thresholds in the steady states of particle systems and spin glasses.

Physical review. E·2026

Related Experiment Video

Updated: Feb 28, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.9K

Using Transfer Learning for Improved Mortality Prediction in a Data-Scarce Hospital Setting.

Thomas Desautels1, Jacob Calvert1, Jana Hoffman1

  • 1Department of Research, Dascena, Inc, Hayward, CA, USA.

Biomedical Informatics Insights
|June 23, 2017
PubMed
Summary

Transfer learning significantly reduces the data needed for clinical decision support (CDS) systems to predict patient mortality. This machine learning technique allows accurate risk scoring at new hospitals with minimal data, saving time and resources.

Keywords:
AUROCMachine learningclinical decision supportmortality predictiontransfer learning

Related Experiment Videos

Last Updated: Feb 28, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.9K

Area of Science:

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

Background:

  • Algorithm-based clinical decision support (CDS) systems require site-specific training data to accurately predict patient outcomes.
  • A lack of sufficient data can lead to underperformance of machine learning models, limiting their widespread adoption.
  • The initial data burden hinders the immediate use of machine learning-based risk scoring systems in new clinical settings.

Purpose of the Study:

  • To implement and evaluate a statistical transfer learning technique to reduce the data requirements for CDS systems at new hospital sites.
  • To assess the effectiveness of transfer learning in specializing the AutoTriage mortality prediction algorithm for a target institution with scarce data.
  • To compare the performance of transfer learning with traditional methods and evaluate the reduction in data collection time.

Main Methods:

  • Utilized a statistical transfer learning technique, leveraging a large "source" dataset to train a model for a "target" site with limited data.
  • Applied the transfer learning technique to the AutoTriage mortality prediction algorithm using patient data from Beth Israel Deaconess Medical Center (source) and University of California San Francisco Medical Center (target).
  • Evaluated model performance using the area under the receiver operating characteristic (AUROC) curve and compared it to the Modified Early Warning Score.

Main Results:

  • The amount of training data needed to achieve an AUROC of 0.80 for mortality prediction decreased from over 4000 patients to fewer than 220 patients at the target site.
  • The transfer learning approach achieved superior performance (AUROC > 0.80) compared to the Modified Early Warning Score (AUROC: 0.76).
  • This reduction in data requirement corresponds to a decrease in clinical data collection time from approximately 6 months to less than 10 days.

Conclusions:

  • Transfer learning is a valuable technique for specializing CDS systems to new hospital sites efficiently.
  • This method significantly reduces the need for extensive, time-consuming, and expensive data collection efforts at target institutions.
  • The findings demonstrate the potential of transfer learning to accelerate the deployment and improve the accessibility of accurate machine learning-based risk prediction tools in healthcare.