• Home
  • Search
  • Augmenting small biomedical datasets using generative AI methods based on self-organizing neural networks
  • Cite Icon7
  • https://doi.org/10.1093/bib/bbae640Copy DOI Icon

Augmenting small biomedical datasets using generative AI methods based on self-organizing neural networks

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Small sample sizes in biomedical research often led to poor reproducibility and challenges in translating findings into clinical applications. This problem stems from limited study resources, rare diseases, ethical considerations in animal studies, costly expert diagnosis, and others. As a contribution to the problem, we propose a novel generative algorithm based on self-organizing maps (SOMs) to computationally increase sample sizes. The proposed unsupervised generative algorithm uses neural networks to detect inherent structure even in small multivariate datasets, distinguishing between sparse “void” and dense “cloud” regions. Using emergent SOMs (ESOMs), the algorithm adapts to high-dimensional data structures and generates for each original data point k new points by randomly selecting positions within an adapted hypersphere with distances based on valid neighborhood probabilities. Experiments on artificial and biomedical (omics) datasets show that the generated data preserve the original structure without introducing artifacts. Random forests and support vector machines cannot distinguish between generated and original data, and the variables of original and generated data sets are not statistically different. The method successfully augments small group sizes, such as transcriptomics data from a rare form of leukemia and lipidomics data from arthritis research. The novel ESOM-based generative algorithm presents a promising solution for enhancing sample sizes in small or rare case datasets, even when limited training data are available. This approach can address challenges associated with small sample sizes in biomedical research, offering a tool for improving the reliability and robustness of scientific findings in this field. Availability: R library “Umatrix” (https://cran.r-project.org/package=Umatrix).

Similar Papers
  • Discussion
  • Citations3

Prediction models: stepwise development and simultaneous validation is a step back

  • Aug 01, 2021
  • Journal of Clinical Epidemiology
  • Georg Heinze +4
  • Research Article

Considerations of sample size in medical research

  • Apr 01, 2008
  • Journal of the American Academy of Physician Assistants
  • John W Waterbor +1
  • Book Chapter
  • Citations9

ESOM Visualizations for Quality Assessment in Clustering

  • Jan 01, 2016
  • Alfred Ultsch +2
  • Conference Article

The Applications of Self-Organizing Maps in Protein Mass Spectrometry High-Throughput Analysis

  • Apr 06, 2012
  • Xiuming Zou +1
  • PDF
  • Research Article
  • Citations6

A nonparametric Bayesian method of translating machine learning scores to probabilities in clinical decision support

  • Aug 07, 2017
  • BMC Bioinformatics
  • Brian Connolly +4
  • Research Article

Yüksek Boyut Düşük Örneklem Genişliğine Sahip Verilerin Sınıflandırılmasında Random Ferns: Bir Benzetim Çalışması

  • Jan 01, 2022
  • Turkiye Klinikleri Journal of Biostatistics
  • Ülger Aydoğan Culha +1
  • Research Article
  • Citations4

Similarity-Principle-Based Machine Learning Method for Clinical Trials and Beyond

  • Jul 18, 2022
  • Statistics in Biopharmaceutical Research
  • Susan Hwang +1
  • Research Article
  • Citations42

Implementation of Visual Clustering Strategy in Self-Organizing Map for Wear Studies Samples Printed Using FDM

  • Apr 30, 2022
  • Traitement du Signal
  • Latchoumi Thamarai Pugazhendhi +2
  • Research Article
  • Citations27

Location‐only and use‐availability data: analysis methods converge

  • Oct 24, 2013
  • Journal of Animal Ecology
  • Lyman Mcdonald +3
  • PDF
  • Research Article
  • Citations9

Autoregressive Prediction with Rolling Mechanism for Time Series Forecasting with Small Sample Size

  • Jan 01, 2014
  • Mathematical Problems in Engineering
  • Zhihua Wang +2
  • PDF
  • Research Article
  • Citations1589

Machine learning algorithm validation with a limited sample size.

  • Nov 07, 2019
  • PLOS ONE
  • Andrius Vabalas +3
  • Research Article
  • Citations1

Assessing the impact of restricted follow-up and small sample sizes on survival estimations in prostate cancer using registry data.

  • Mar 01, 2016
  • Journal of Clinical Oncology
  • Dhvani Shah +5
  • PDF
  • Research Article
  • Citations18

Research on an intelligent diagnosis method of mechanical faults for small sample data sets

  • Dec 20, 2022
  • Scientific Reports
  • Jun Zhao +7
  • Research Article
  • Citations9

Fractal analysis based on the continuous wavelet transform and lithofacies classification from well-logs data using the self-organizing map neural network

  • Nov 29, 2011
  • Arabian Journal of Geosciences
  • Leila Aliouane +2
  • PDF
  • Research Article
  • Citations3

Open set task augmentation facilitates generalization of deep neural networks trained on small data sets

  • Dec 09, 2021
  • Neural Computing and Applications
  • Wadhah Zai El Amri +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.