Open Access

ARTICLE

Employing a Backpropagation Neural Network for Predicting Fear of Cancer Recurrence among Non-Small Cell Lung Cancer Patients

Man Liu¹, Zhuoheng Lv^1,#, Hongjing Wang^2,*, Lu Liu^1,*
1 National Cancer Center/National Clinical Research Center for Cancer (NCRCC)/Thoracic Surgery, Cancer Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, 100021, China
2 Arrhythmia Diagnostic and Treatment Center, Qingdao Hiser Hospital Affiliated of Qingdao University (Qingdao Traditional Chinese Medicine Hospital), Qingdao, 266000, China
* Corresponding Author: Hongjing Wang. Email: ; Lu Liu. Email:
# Co-first authors
(This article belongs to the Special Issue: Multidisciplinary Clinical Health Psychology for Cancer Experience
Psychologie clinique multidisciplinaire de la santé pour l'expérience du cancer)

Psycho-Oncologie https://doi.org/10.32604/po.2024.054098

Received 18 May 2024; Accepted 24 September 2024; Published online 18 October 2024

Abstract

Objective: Non-small cell lung cancer (NSCLC) patients often experience significant fear of recurrence. To facilitate precise identification and appropriate management of this fear, this study aimed to compare the efficacy and accuracy of a Backpropagation Neural Network (BPNN) against logistic regression in modeling fear of cancer recurrence prediction. Methods: Data from 596 NSCLC patients, collected between September 2023 and December 2023 at the Cancer Hospital of the Chinese Academy of Medical Sciences, were analyzed. Nine clinically and statistically significant variables, identified via univariate logistic regression, were inputted into both BPNN and logistic regression models developed on a training set (N = 427) and validated on an independent set (N = 169). Model performances were assessed using Area Under the Receiver Operating Characteristic (ROC) Curve and Decision Curve Analysis (DCA) in both sets. Results: The BPNN model, incorporating nine selected variables, demonstrated superior performance over logistic regression in the training set (AUC = 0.842 vs. 0.711, p < 0.001) and validation set (0.7 vs. 0.675, p < 0.001). Conclusion: The BPNN model outperforms logistic regression in accurately predicting fear of cancer recurrence in NSCLC patients, offering an advanced approach for fear assessment.

---

Keywords

Backpropagation neural network; non-small cell lung cancer; cancer recurrence anxiety; predictive analytics

---