Development and Validation of Models to Predict Lymph Node Metastasis in Early Gastric Cancer Using Logistic Regression and Gradient Boosting Machine Methods

A machine learning model for predicting the lymph node metastasis of early gastric cancer not meeting the endoscopic curability criteria

BACKGROUND

We developed a machine learning (ML) model to predict the risk of lymph node metastasis (LNM) in patients with early gastric cancer (EGC) who did not meet the existing Japanese endoscopic curability criteria and compared its performance with that of the most common clinical risk scoring system, the eCura system.

METHODS

We used data from 4,042 consecutive patients with EGC from 21 institutions who underwent endoscopic submucosal dissection (ESD) and/or surgery between 2010 and 2021. All resected EGCs were histologically confirmed not to satisfy the current Japanese endoscopic curability criteria. Of all patients, 3,506 constituted the training cohort to develop the neural network-based ML model, and 536 constituted the validation cohort. The performance of our ML model, as measured by the area under the receiver operating characteristic curve (AUC), was compared with that of the eCura system in the validation cohort.

RESULTS

LNM rates were 14% (503/3,506) and 7% (39/536) in the training and validation cohorts, respectively. The ML model identified patients with LNM with an AUC of 0.83 (95% confidence interval, 0.76-0.89) in the validation cohort, while the eCura system identified patients with LNM with an AUC of 0.77 (95% confidence interval, 0.70-0.85) (P = 0.006, DeLong's test).

CONCLUSIONS

Our ML model performed better than the eCura system for predicting LNM risk in patients with EGC who did not meet the existing Japanese endoscopic curability criteria. We developed a neural network-based machine learning model that predicts the risk of lymph node metastasis in patients with early gastric cancer who did not meet the endoscopic curability criteria.

Intratumoural and peritumoural CT-based radiomics for diagnosing lepidic-predominant adenocarcinoma in patients with pure ground-glass nodules: a machine learning approach

AIM

To develop and validate a diagnostic model utilising machine-learning algorithms that differentiates lepidic predominant adenocarcinoma (LPA) from other pathological subtypes in patients with pure ground-glass nodules (pGGNs).

MATERIALS AND METHODS

This bicentric study was conducted across two medical centres and included 151 patients diagnosed with lung adenocarcinoma based on histopathological confirmation of pGGNs. The training cohort consisted of 99 patients from Institution 1, while the test cohort included 52 patients from Institution 2. Radiomics features were extracted from both tumours and the 2 mm peritumoural parenchyma. The tumoural and peritumoural radiomics were designated as Modeltumoural and Modelperitumoural, respectively. The diagnostic efficacy of various models was evaluated through the receiver operating characteristic (ROC) curve analysis. Subsequently, a machine-learning-based prediction model that combined Modeltumoural, Modelperitumoural, and Modelclinical-radiological was developed to differentiate LPA from other pathological subtypes in patients with pGGNs.

RESULTS

Modeltumoural achieved area under the curve (AUC) values of 0.762 and 0.783 in the training and validation sets, respectively. Modelperitumoural attained AUCs of 0.742 and 0.667, and Modelclinical-radiological generated an AUC of 0.727 and 0.739 in the training and validation sets, respectively. Among the machine-learning models evaluated, gradient boosting machines demonstrated the best diagnostic efficacy, with accuracy, AUC, F1 score, and log loss values of 0.885, 0.956, 0.943, and 0.260, respectively.

CONCLUSION

The combined model based on machine learning that incorporated tumour and peritumoural parenchyma, as well as clinical and imaging characteristics, may offer benefits in assessing the pathological subtype of pGGNs.

The Application of Artificial Intelligence to Cancer Research: A Comprehensive Guide

Advancements in AI have notably changed cancer research, improving patient care by enhancing detection, survival prediction, and treatment efficacy. This review covers the role of Machine Learning, Soft Computing, and Deep Learning in oncology, explaining key concepts and algorithms (like SVM, Naïve Bayes, and CNN) in a clear, accessible manner. It aims to make AI advancements understandable to a broad audience, focusing on their application in diagnosing, classifying, and predicting various cancer types, thereby underlining AI's potential to better patient outcomes. Moreover, we present a tabular summary of the most significant advances from the literature, offering a time-saving resource for readers to grasp each study's main contributions. The remarkable benefits of AI-powered algorithms in cancer care underscore their potential for advancing cancer research and clinical practice. This review is a valuable resource for researchers and clinicians interested in the transformative implications of AI in cancer care.