Uncovering nasopharyngeal carcinoma from chronic rhinosinusitis and healthy subjects using routine medical tests via machine learning
Authors:
Open Access
- 9 September 2022
- journal article
- research article
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 17 (9) , e0274263
Abstract
Nasopharyngeal carcinoma (NPC) is one of the most common types of cancers in South China and Southeast Asia. Clinical data has shown that early detection is essential for improving treatment effectiveness and survival rate. Unfortunately, because the early symptoms of NPC are rather minor and similar to that of diseases such as Chronic Rhinosinusitis (CRS), early detection is a challenge. This paper proposes using machine learning methods to detect NPC using routine medical test data, namely Random Forest (RF), Support Vector Machine (SVM), and Artificial Neural Network (ANN), k-Nearest-Neighbor (KNN) and Logistic Regression (LR). We collected a dataset containing 523 newly diagnosed NPC patients before treatment, 501 newly diagnosed CRS patients before treatment as well as 600 healthy controls. The routine medical test data including age, gender, blood test features, liver function test features, and urine sediment test features. For comparison, we also used data from Epstein-Barr Virus (EBV) antibody tests, which is a specialized test not included among routine medical tests. In our first test, all four methods were tested on classifying NPC vs CRS vs controls; RF gives the best overall performance. Using only routine medical test data, it gives an accuracy of 83.1%, outperforming LR by 12%. In our second test, using only routine medical test data, when classifying NPC vs non-NPC (i.e. CRS or controls), RF achieves an accuracy of 88.2%. In our third test, when classifying NPC vs. controls, RF using only routine test data achieves an accuracy significantly better than RF using only EBV antibody data. Finally, in our last test, RF trained with NPC vs controls, using routine test data only, continued to perform well on an entirely separate dataset. This is a promising result because preliminary NPC detection using routine medical data is easy and inexpensive to implement. We believe this approach will play an important role in the detection and treatment of NPC in the future.Keywords
Funding Information
- National Natural Science Foundation of China (62103152)
- Natural Science Foundation of Guangdong Province (2020A1515010621)
- Guangzhou Applied Basic Research Foundation (202102020360)
This publication has 28 references indexed in Scilit:
- Epstein–Barr virus infection and nasopharyngeal carcinomaAnti-Cancer Drugs, 2015
- Staging of nasopharyngeal carcinoma – The past, the present and the futureOral Oncology, 2014
- Factors influencing the incidence of sinusitis in nasopharyngeal carcinoma patients after intensity-modulated radiation therapyEuropean Archives of Oto-Rhino-Laryngology, 2014
- Nonendemic HPV-Positive Nasopharyngeal Carcinoma: Association With Poor PrognosisInternational Journal of Radiation Oncology - Biology - Physics (IJROBP), 2014
- Evaluation of metabolite profiles as biomarkers for the pharmacological effects of thiazolidinediones in Type 2 diabetes mellitus patients and healthy volunteersBritish Journal of Clinical Pharmacology, 2007
- A metabolomics perspective of human brain tumoursThe FEBS Journal, 2007
- The Enigmatic Epidemiology of Nasopharyngeal CarcinomaCancer Epidemiology, Biomarkers & Prevention, 2006
- Metabolomics applications of FT‐ICR mass spectrometryMass Spectrometry Reviews, 2004
- Metabonomics technologies and their applications in physiological monitoring, drug safety assessment and disease diagnosisBiomarkers, 2004
- Epstein‐barr virus‐specific IgA serum antibodies as an outstanding feature of nasopharyngeal carcinomaInternational Journal of Cancer, 1976