IPMI: Machine Learning-Aided Identification of Parametrial Invasion in Women with Early-Stage Cervical Cancer

Phasit Charoenkwan,Prapaporn Suprasert,Watshara Shoombuatong,Tanarat Muangmool,Kittipat Charoenkwan,Chalaithorn Nantasupha

doi:10.3390/diagnostics11081454

Phasit Charoenkwan, Prapaporn Suprasert + Show 4 more

Open Access

https://doi.org/10.3390/diagnostics11081454

Copy DOI

Journal: Diagnostics	Publication Date: Aug 12, 2021
Citations: 7	License type: CC BY 4.0

Affiliation: Chiang Mai University, Mahidol University

Abstract

Radical hysterectomy is a recommended treatment for early-stage cervical cancer. However, the procedure is associated with significant morbidities resulting from the removal of the parametrium. Parametrial cancer invasion (PMI) is found in a minority of patients but the efficient system used to predict it is lacking. In this study, we develop a novel machine learning (ML)-based predictive model based on a random forest model (called iPMI) for the practical identification of PMI in women. Data of 1112 stage IA-IIA cervical cancer patients who underwent primary surgery were collected and considered as the training dataset, while data from an independent cohort of 116 consecutive patients were used as the independent test dataset. Based on these datasets, iPMI-Econ was then developed by using basic clinicopathological data available prior to surgery, while iPMI-Power was also introduced by adding pelvic node metastasis and uterine corpus invasion to the iPMI-Econ. Both 10-fold cross-validations and independent test results showed that iPMI-Power outperformed other well-known ML classifiers (e.g., logistic regression, decision tree, k-nearest neighbor, multi-layer perceptron, naive Bayes, support vector machine, and extreme gradient boosting). Upon comparison, it was found that iPMI-Power was effective and had a superior performance to other well-known ML classifiers in predicting PMI. It is anticipated that the proposed iPMI may serve as a cost-effective and rapid approach to guide important clinical decision-making.

Highlights

We propose a novel machine learning (ML)-based predictive model called iPMI for the practical identification of Parametrial cancer invasion (PMI) in women with early-stage cervical cancer who are candidates for primary radical surgery
Adenocarcinoma histology was independently associated with a lower risk of PMI with the adjusted odds ratio of 0.49 (95% confidence interval 0.31–0.78) compared to squamous cell carcinoma histology
The random forest (RF) model performing on the balanced dataset achieved a higher cross-validation AUC than the RF model performing on the imbalanced dataset. These results indicated that the performance of the RF model improved when the synthetic minority oversampling technique (SMOTE) oversampling technique was applied for adding samples to the PMI group

Summary

Introduction

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. Cervical cancer is the fourth most common cancer in women following breast, colorectal, and lung cancers. It is the fourth leading cause of death from cancer [1]. Cancer cells’ ability to invade surrounding tissues as well as metastasize to regional lymph nodes and distant organs is responsible for more than 90% of cancer-associated deaths [2]. Cervical cancer usually spreads in a stepwise fashion from primary cervical tumor to adjacent structures including the parametrium, vagina, urinary bladder, and rectum. The cancer cells can metastasize to regional lymph nodes and distant sites [3]

Objectives

Methods

Results

Discussion

Conclusion