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

Missing data imputation using statistical and machine learning methods in a real breast cancer problem.

José M Jerez1, Ignacio Molina, Pedro J García-Laencina

  • 1Departamento de Lenguajes y Ciencias de la Computación, Universidad de Málaga, E.T.S.I. Informática, Campus de Teatinos s/n, 29071 Málaga, Spain. jja@lcc.uma.es

Artificial Intelligence in Medicine
|July 20, 2010
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Kaplan-Meier Approach01:24

Kaplan-Meier Approach

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,...
Cancer Survival Analysis01:21

Cancer Survival Analysis

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...

You might also read

Related Articles

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

Sort by
Same author

Optimising prescription for metastatic breast cancer patients through a three-level submaximal exercise test protocol.

Disability and rehabilitation·2026
Same author

Imaging of the Placenta and Umbilical Cord: What Radiologists in Common Practice Need to Know.

Radiographics : a review publication of the Radiological Society of North America, Inc·2026
Same author

Dynamic thymidine kinase activity independently captures treatment-specific biological response and is independently associated with outcomes in endocrine-resistant HR+ /HER2 - metastatic breast cancer: A translational analysis of the GEICAM/2013-02 PEARL trial.

European journal of cancer (Oxford, England : 1990)·2026
Same author

Sensitivity to endocrine therapy index predicts benefit from weekly adjuvant paclitaxel for hormone receptor-positive breast cancer in the GEICAM/9906 trial.

Clinical cancer research : an official journal of the American Association for Cancer Research·2026
Same author

Dual ctDNA and CTCs analysis for minimal residual disease detection and relapse monitoring in early-stage breast cancer.

NPJ breast cancer·2026
Same author

3D-Printed Portable Video-Ooculography Device (UNySi cam): A New Tool for Eye Movement Assessment.

Otology & neurotology : official publication of the American Otological Society, American Neurotology Society [and] European Academy of Otology and Neurotology·2026

Machine learning imputation methods significantly improved breast cancer recurrence prediction accuracy compared to statistical methods. This enhances prognosis accuracy by effectively handling missing data in patient records.

Area of Science:

  • Biostatistics
  • Machine Learning in Healthcare
  • Oncology Data Analysis

Background:

  • Missing data imputation is critical for utilizing complete patient datasets in medical research.
  • Discarding records with missing values can lead to biased or incomplete analyses.
  • Accurate imputation is essential for reliable prediction of disease recurrence.

Purpose of the Study:

  • To evaluate and compare the performance of various statistical and machine learning imputation methods.
  • To assess the effectiveness of these methods in predicting breast cancer recurrence using a real-world dataset.
  • To determine the optimal imputation strategy for enhancing prognostic accuracy.

Main Methods:

  • Applied statistical imputation methods (mean, hot-deck, multiple imputation) and machine learning methods (MLP, SOM, KNN).

Related Experiment Videos

  • Utilized a comprehensive dataset from the 'El Álamo-I' project, including 3679 women with operable invasive breast cancer.
  • Compared imputation performance against listwise deletion (LD) using artificial neural networks (ANNs) for relapse prediction accuracy.

    • Main Results:

    • Machine learning imputation methods significantly outperformed statistical methods in predicting patient outcomes.
    • Higher Area Under the ROC Curve (AUC) values were observed for MLP, KNN, and SOM compared to the LD model.
    • Friedman's test indicated a significant difference in AUC values across imputation methods (p=0.0091).

    Conclusions:

    • Machine learning techniques are superior for imputing missing values in breast cancer datasets.
    • These methods substantially improve prognosis accuracy compared to traditional statistical imputation.
    • The findings support the use of advanced machine learning for robust medical data analysis and prediction.