Developing a Stacked Ensemble-Based Classification Scheme to Predict Second Primary Cancers in Head and Neck Cancer Survivors

Chi-Chang Chang; Tse-Hung Huang; Pei-Wei Shueng; Ssu-Han Chen; Chun-Chia Chen; Chi-Jie Lu; Yi-Ju Tseng

doi:10.3390/ijerph182312499

Developing a Stacked Ensemble-Based Classification Scheme to Predict Second Primary Cancers in Head and Neck Cancer Survivors

Int J Environ Res Public Health. 2021 Nov 27;18(23):12499. doi: 10.3390/ijerph182312499.

Authors

Chi-Chang Chang^{1

2}, Tse-Hung Huang^{3

4

5

6}, Pei-Wei Shueng^{7

8}, Ssu-Han Chen^{9

10}, Chun-Chia Chen^{11

12}, Chi-Jie Lu^{13

14

15}, Yi-Ju Tseng¹⁶

Affiliations

¹ School of Medical Informatics, Chung Shan Medical University & IT Office, Chung Shan Medical University Hospital, Taichung 40201, Taiwan.
² Department of Information Management, Ming Chuan University, Taoyuan 33300, Taiwan.
³ Department of Traditional Chinese Medicine, Chang Gung Memorial Hospital, Keelung 20401, Taiwan.
⁴ School of Traditional Chinese Medicine, Chang Gung University, Taoyuan 33300, Taiwan.
⁵ School of Nursing, National Taipei University of Nursing and Health Sciences, Taipei 11200, Taiwan.
⁶ Graduate Institute of Health Industry Technology, Chang Gung University of Science and Technology, Taoyuan 33300, Taiwan.
⁷ Department of Radiology, Division of Radiation Oncology, Far Eastern Memorial Hospital, New Taipei 22060, Taiwan.
⁸ Faculty of Medicine, School of Medicine, National Yang Ming Chiao Tung University, Taipei 22060, Taiwan.
⁹ Department of Industrial Engineering and Management, Ming Chi University of Technology, New Taipei 24330, Taiwan.
¹⁰ Center for Artificial Intelligence & Data Science, Ming Chi University of Technology, New Taipei 24330, Taiwan.
¹¹ Institute of Medicine, Chung Shan Medical University, Taichung 40201, Taiwan.
¹² Department of Surgery, Division of Plastic Surgery, Chung Shan Medical University Hospital, Taichung 40201, Taiwan.
¹³ Graduate Institute of Business Administration, Fu Jen Catholic University, New Taipei 242062, Taiwan.
¹⁴ Artificial Intelligence Development Center, Fu Jen Catholic University, New Taipei 242062, Taiwan.
¹⁵ Department of Information Management, Fu Jen Catholic University, New Taipei 242062, Taiwan.
¹⁶ Department of Information Management, National Central University, Taoyuan 32031, Taiwan.

Abstract

Despite a considerable expansion in the present therapeutic repertoire for other malignancy managements, mortality from head and neck cancer (HNC) has not significantly improved in recent decades. Moreover, the second primary cancer (SPC) diagnoses increased in patients with HNC, but studies providing evidence to support SPCs prediction in HNC are lacking. Several base classifiers are integrated forming an ensemble meta-classifier using a stacked ensemble method to predict SPCs and find out relevant risk features in patients with HNC. The balanced accuracy and area under the curve (AUC) are over 0.761 and 0.847, with an approximately 2% and 3% increase, respectively, compared to the best individual base classifier. Our study found the top six ensemble risk features, such as body mass index, primary site of HNC, clinical nodal (N) status, primary site surgical margins, sex, and pathologic nodal (N) status. This will help clinicians screen HNC survivors before SPCs occur.

Keywords: head and neck cancer; risk prediction; second primary cancers; stacked ensemble-based classification scheme.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Body Mass Index
Head and Neck Neoplasms*
Humans
Neoplasms, Second Primary* / diagnosis
Neoplasms, Second Primary* / epidemiology
Risk Factors
Survivors