Survival outcome of cervical cancer patients treated by image-guided brachytherapy: a 'real world' single center experience in Thailand from 2008 to 2018

Prediction of Cervical Cancer Patients' Survival Period with Machine Learning Techniques

OBJECTIVES

The objective of this research is to apply machine learning (ML) algorithms to predict the survival of cervical cancer patients. The aim was to address the limitations of traditional statistical methods, which often fail to provide accurate answers due to the complexity of the problem.

METHODS

This research employed visualization techniques for initial data understanding. Subsequently, ML algorithms were used to develop both classification and regression models for survival prediction. In the classification models, we trained the algorithms to predict the time interval between the initial diagnosis and the patient's death. The intervals were categorized as "<6 months," "6 months to 3 years," "3 years to 5 years," and ">5 years." The regression model aimed to predict survival time (in months). We used attribute weights to gain insights into the model, highlighting features with a significant impact on predictions and offering valuable insights into the model's behavior and decision-making process.

RESULTS

The gradient boosting trees algorithm achieved an 81.55% accuracy in the classification model, while the random forest algorithm excelled in the regression model, with a root mean square error of 22.432. Notably, radiation doses around the affected areas significantly influenced survival duration.

CONCLUSIONS

Machine learning demonstrated the ability to provide high-accuracy predictions of survival periods in both classification and regression problems. This suggests its potential use as a decision-support tool in the process of treatment planning and resource allocation for each patient.

High-Dose-Rate Three-Dimensional Image-Guided Adaptive Brachytherapy (3D IGABT) for Locally Advanced Cervical Cancer (LACC): A Narrative Review on Imaging Modality and Clinical Evidence

Background: Brachytherapy (BT) is a critical component of radiotherapy for locally advanced cervical cancer (LACC), and it has rapidly developed in recent decades. Since the advent of three-dimensional image-guided adaptive brachytherapy (3D-IGABT), magnetic resonance imaging (MRI) has emerged as the primary modality for image guidance. Meanwhile, other imaging modalities, such as computed tomography, 18F-fluorodeoxyglucose positron emission tomography, ultrasound, and their combinations have also been widely studied. Materials and methods: We reviewed studies on different imaging modalities utilized for target delineation and planning. Emerging techniques in IGABT like real-time image guidance and 3D printing were also included. We summarized research on their feasibility and concentrated on their clinical outcomes. Results: MRI-guided BT was the gold standard, and CT-guided BT was the most widely applied. Other modalities have shown feasibility and promising efficacy in dosimetry studies and preliminary outcomes. The longer-term clinical outcomes associated with these approaches require further elucidation. Conclusions: As 3D-IGABT was validated by promising clinical outcomes, the future of BT for LACC is expected to progress toward the refinement of more effective image-guided procedures. Moreover, achieving operational consensus and driving technological advancements to mitigate the inherent limitations associated with different imaging modes remain essential.