A synthetic oversampling-based customized ResNet51-Conv1D framework for early colorectal cancer prediction using structured clinical data from the PLCO screening trial

Sep 22, 2026

Timely diagnosis of colorectal cancer (CRC) is critical to reduce global cancer deaths. This study proposes a personalized one-dimensional residual network (ResNet51-Conv1D) designed for structured clinical data, addressing limitations of existing AI models that often depend on imaging and perform inconsistently on real clinical records. Using PLCO screening data from 154,892 participants (55–74 years), it applies block segmentation and oversampling via SMOTE and ADASYN to mitigate class imbalance. Results show improved CRC sensitivity and minority-class detection stability through combined segmentation and imbalance-handling strategies.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages20

Reading Time50 min

AccessFree to download

Abstract

Keywords

Introduction

Prasath etal. BMC Medical Informatics and Decision Making (2026) 26:175 [https://doi.org/10.1186/s12911-026-03470-9](https://doi.org/10.1186/s12911-026-03470-9) BMC Medical Informatics and Decision Making RESEARCH Open Access A synthetic oversampling-based customized ResNet51-Conv1D framework for early colorectal cancer prediction using structured clinical data from the PLCO screening trial S. Thanga Prasath1, M. M. Asha2*, B. Nagarajan3, Rajkumar Yesuraj4, K. Prathapchandran5 and Y. Sreeraman6 Abstract Timely diagnosis of colorectal cancer (CRC) is crucial in reducing global cancer deaths. Physicians will benefit significantly by developing an automated prediction system using advanced technology to detect CRC at an early stage. Besides, existing AI-based diagnostics models primarily rely on imaging data, and their effectiveness is inconsistent when applied to clinical data. This study recommends a personalized one-dimensional residual network (ResNet51-Conv1D) structure adapted for structured clinical data analysis to learn hierarchical feature associations from a large-scale structured PLCO dataset. In this study, structured data were used, including nearly 1,54,892 participants aged 55 to 74, composed of 76,679 men and 78,213 women. The suggested model applies block segmentation to preserve the dependency between local features and employs two oversampling methods, SMOTE and ADASYN, in order to address class imbalance and improve representation of minority classes. The statistical effect of oversampling was determined by analyzing the model’s performance before and after oversampling. Before oversampling, the model’s CRC detection metrics were less accurate (recall = 1 . 83%; F1-score = 2 . 50%) . When block segmentation was incorporated with a standard SMOTE and ADASYN oversampling methods, the sensitivity of CRC improved significantly. SMOTE with 40 and 50 segments performed best, with MCC values of 89. 59% and 88. 04%, balanced accuracy scores of 94.43% and 93. 23%, and G-mean scores of 94.43% and 93. 23% . Furthermore, ADASYN enhanced cancer detection robustness with MCC values of 83. 33% and G-average scores of 90.41% . These results demonstrate that combining structured feature segmentation with imbalancehandling strategies improves model stability and minority-class detection, showing that the ResNet51-Conv1D framework is a reliable and efficient approach for early CRC detection using imbalanced structured clinical data. Keywords Colorectal cancer prediction, ResNet51-Conv1D, Synthetic oversampling, SMOTE, ADASYN, Block segmentation, Imbalanced datasets, Deep learning *Correspondence: M. M. Asha [asha_mm@apollouniversity.edu.in](asha_mm@apollouniversity.edu.in) Full list of author information is available at the end of the article © The Author(s) 2026. Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit [http://creati](http://creati)[vecommons.org/licenses/by-nc-nd/4.0/](vecommons.org/licenses/by-nc-nd/4.0/.)[.](vecommons.org/licenses/by-nc-nd/4.0/.) Prasath et al. BMC Medical Informatic

FAQs

Why is early colorectal cancer diagnosis important?

Early CRC diagnosis improves patient survival, as early-stage CRC has a much higher five-year survival rate than later stages.

What problem does the study address with existing AI diagnostic models?

Existing AI diagnostic models often rely on imaging data and their effectiveness can be inconsistent when applied to structured clinical data.

How does the proposed framework improve performance for imbalanced data?

It uses block segmentation to preserve local feature dependencies and applies two synthetic oversampling methods, SMOTE and ADASYN, to address class imbalance and enhance minority-class representation.

Sep 22, 2026

Upload by Pentious