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

Cancer evolution assessment using artificial neural networks.

Cipriana Stefanescu1, L V Boiculese, V Rusu

  • 1Gr.T. Popa University of Medicine and Pharmacy Iaşi, School of Medicine, Biophysics and Nuclear Medicine Department.

Revista Medico-Chirurgicala a Societatii De Medici Si Naturalisti Din Iasi
|February 4, 2005
PubMed
Summary
This summary is machine-generated.

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

Terahertz Imaging for Breast Cancer Detection in Animal Models: A Literature Review with Narrative Synthesis.

Medical sciences (Basel, Switzerland)·2026
Same author

Correction: Jalloul et al. Targeted Alpha Therapy: Exploring the Clinical Insights into [225Ac]Ac-PSMA and Its Relevance Compared with [177Lu]Lu-PSMA in Advanced Prostate Cancer Management. <i>Pharmaceuticals</i> 2025, <i>18</i>, 1215.

Pharmaceuticals (Basel, Switzerland)·2026
Same author

Recommendations on the Clinical Application and Future Potential of α-Particle Therapy: A Comprehensive Review of the Results from the SECURE Project.

Pharmaceuticals (Basel, Switzerland)·2025
Same author

Functional Complexity of Thermogenic Adipose Tissue: From Thermogenesis to Metabolic and Fibroinflammatory Crosstalk.

International journal of molecular sciences·2025
Same author

Targeted Alpha Therapy: Exploring the Clinical Insights into [225Ac]Ac-PSMA and Its Relevance Compared with [177Lu]Lu-PSMA in Advanced Prostate Cancer Management.

Pharmaceuticals (Basel, Switzerland)·2025
Same author

Is Sentinel Lymph Node Biopsy Feasible in Multicentric Breast Cancer? A Case Report and Literature Review.

Life (Basel, Switzerland)·2025
Same journal

Antioxidant Activity of Essential Oil From Carum Carvi L. Cultivated in North-Eastern Romania.

Revista medico-chirurgicala a Societatii de Medici si Naturalisti din Iasi·2018
Same journal

Assessment of In Vitro Antioxidant activity of Some New Ferulic Acid Derivatives.

Revista medico-chirurgicala a Societatii de Medici si Naturalisti din Iasi·2018
Same journal

Fast RP-HPLC Method for the Determination of Bisoprolol.

Revista medico-chirurgicala a Societatii de Medici si Naturalisti din Iasi·2018
Same journal

In Vitro Dissolution Studies of Amiodarone Hydrochloride From Hydroxy-Propyl-β-Cyclodextrin/Amiodarone Inclusion Complex Formulated Into Modified-Release Tablets.

Revista medico-chirurgicala a Societatii de Medici si Naturalisti din Iasi·2018
Same journal

Esthetic Rehabilitation Through CAD/CAM Technology - Case Report.

Revista medico-chirurgicala a Societatii de Medici si Naturalisti din Iasi·2018
Same journal

Correlation Among Chronological Age, Dental Age and Cervical Vertebrae Maturity in Romanian Subjects.

Revista medico-chirurgicala a Societatii de Medici si Naturalisti din Iasi·2018
See all related articles

Artificial Neural Networks (ANNs) can predict cancer survival times when trained with high-quality data. Data homogeneity, quantity, and feature coding are crucial for accurate cancer prognostic models and clinical decision-making.

Area of Science:

  • Computational biology
  • Medical informatics
  • Oncology

Background:

  • Artificial Neural Networks (ANNs) show promise in disease prognosis.
  • Accurate training is essential for ANN utility in predicting patient outcomes.
  • Cancer prognosis remains a critical area for improving clinical decision-making.

Purpose of the Study:

  • To evaluate the application of Artificial Neural Networks (ANNs) for cancer survival time prediction.
  • To assess the impact of data characteristics on ANN performance in cancer prognostics.
  • To explore the utility of ANNs in clinical decision support for various cancer types, starting with breast cancer.

Main Methods:

  • Development and training of Artificial Neural Networks (ANNs) using cancer patient data.

Related Experiment Videos

  • Analysis of data homogeneity, quantity, and feature coding as input parameters.
  • Evaluation of ANN performance in predicting time-to-survival for cancer patients.

    • Main Results:

    • The performance of trained ANNs is significantly influenced by the homogeneity of input data sets.
    • The quantity and coding of data features, relative to their prognostic importance, are decisive factors for ANN accuracy.
    • Initial application to breast cancer demonstrated the feasibility and identified key data requirements.

    Conclusions:

    • Homogeneous, well-coded, and appropriately quantified data are critical for successful ANN-based cancer prognostic models.
    • ANNs hold potential for aiding physicians in clinical decision-making for cancer prognosis.
    • Further research can expand ANN applications to diverse cancer types.