Establishment of a decision tree prediction model for symptom groups and influencing factors in patients with tracheotomy after operation for head and neck cancer
10.3760/cma.j.cn115682-20230428-01661
- VernacularTitle:头颈癌术后气管切开患者症状群及其影响因素决策树预测模型的建立
- Author:
Shuyun WANG
1
;
Zhiyu LIU
;
Yanrong SHI
;
Peiei WANG
;
Nannan WU
;
Xuemei WANG
Author Information
1. 郑州大学第一附属医院咽喉头颈外科，郑州 450000
- Keywords:
Head and neck neoplasms;
Tracheotomy;
Symptom group;
Decision tree model
- From:
Chinese Journal of Modern Nursing
2023;29(22):3002-3008
- CountryChina
- Language:Chinese
-
Abstract:
Objective:To investigate the symptom groups and influencing factors in patients with tracheotomy after operation for head and neck cancer and to provide reference for developing accurate symptom management strategies.Methods:Using the convenient sampling method, a total of 289 patients with head and neck cancer who received treatment or reexamination in the First Affiliated Hospital of Zhengzhou University from April 2020 to January 2023 were selected as the research objects. The patients were assessed with the general information questionnaire and M.D. Anderson Symptom Inventory-Head and Neck (MDASI-HN). Exploratory factor analysis was used to analyze the symptom groups of patients with head and neck cancer after tracheotomy, and single factor analysis and decision tree were used to construct the prediction model of each symptom group. A total of 289 questionnaires were sent out in this study, 18 invalid questionnaires were excluded, and 271 valid questionnaires were finally recovered, with an effective recovery rate of 93.8%.Results:Three symptom groups were extracted, including sleep-body symptom group, head and neck cancer radiotherapy-psychological symptom group and head and neck cancer specific symptom group. The decision tree prediction model showed that the core factors affecting the symptoms of patients with tracheotomy after head and neck cancer were disease stage and operation mode, followed by preoperative emotional problems, marital status and main caregivers. The overall correct percentages of the model were 61.6%, 67.2% and 62.0%, respectively, and the correct prediction rates of the non-occurrence candidate symptom groups were respectively 96.1%, 86.4% and 62.4%, indicating a good fitting effect.Conclusions:There are multiple symptom groups in patients with tracheotomy after head and neck cancer surgery. The disease stage and surgical method are the core influencing factors of each symptom group. The decision tree model is helpful for medical staff to effectively identify people with high incidence of various symptom groups and formulate precise intervention plans.
