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

Artificial neural network in pharmacoeconomics.

Sebastian Polak1, Agnieszka Skowron, Aleksander Mendyk

  • 1Department of Pharmacoepidemiology and Pharmacoeconomics, Faculty of Pharmacy, Collegium Medicum, Jagiellonian University, Medyczna 9 Str., 30-688 Kraków. mfpolak@cyf-kr.edu.pl

Studies in Health Technology and Informatics
|February 19, 2005
PubMed
Summary

Artificial neural networks (ANNs) can predict patient survival time for non-small cell lung cancer, improving pharmacoeconomic analysis. This AI approach achieved an 82% prediction accuracy, outperforming traditional logistic regression models.

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

Insight into human allogeneic CAR-T therapy: an open-access dataset.

Drug discovery today·2026
Same author

Development and Implementation of a Hinderance-based In Vitro Model for Porous Membranes.

The AAPS journal·2026
Same author

Relating plaque psoriasis barrier function changes with the underlying skin morphology and physiology.

Journal of pharmaceutical sciences·2026
Same author

Explainable AI in Pharmaceutics: Grad-CAM Analysis of Surface Dissolution Imaging Using Convolutional Neural Networks.

Pharmaceutics·2026
Same author

Dataset of xenobiotics human renal clearance values.

Database : the journal of biological databases and curation·2026
Same author

Virtual Bioequivalence Assessment of Long-acting Injectable Suspensions Using PBPK Modeling: Part 1. Impact of particle Size on Formulation Variability.

The AAPS journal·2026

Area of Science:

  • Health Economics
  • Biostatistics
  • Artificial Intelligence

Background:

  • Pharmacoeconomics evaluates medical product costs and consequences for decision-makers.
  • Cost-effectiveness analysis is a common pharmacoeconomic tool, comparing alternatives with similar outcomes.
  • Predicting medical effects is crucial for extrapolating pharmacoeconomic analysis results.

Purpose of the Study:

  • To utilize artificial neural networks (ANNs) for predicting medical effects, specifically patient survival time.
  • To enhance the extrapolation capabilities of pharmacoeconomic analyses through AI-driven predictions.
  • To assess the efficacy of ANNs in predicting survival outcomes for advanced non-small cell lung cancer (NSCLC) patients.

Main Methods:

  • A database of 100 non-small cell lung cancer (NSCLC) patients (stage IIIB/IV) was analyzed.

Related Experiment Videos

  • Artificial neural networks (ANNs), including back-propagation and fuzzy-logic models, were employed for prediction.
  • A 10-fold cross-validation method was used, and results were compared to logistic regression.

    • Main Results:

    • The ANN system predicted patient survival time, classifying outcomes as survival >= 35 weeks (1) or < 35 weeks (0).
    • The best-performing ANN model achieved an 82% prediction score.
    • This prediction accuracy surpassed that of a standard logistic regression model.

    Conclusions:

    • Artificial neural networks demonstrate significant potential for predicting patient survival in advanced NSCLC.
    • ANNs can enhance the accuracy and applicability of pharmacoeconomic analyses by improving medical effect prediction.
    • The study highlights the value of AI in health economics and clinical outcome prediction.