Comparison of multiple linear regression and machine learning in predicting fear of cancer recurrence in newly diagnosed breast cancer patients

FANG Chao; LI Yang; XIONG Meidi; LIU Qianqian; CHENG Yuping; ZHANG Chunhua

doi:10.14188/j.1671-8852.2023.0670

您当前的位置：

首页 >

文章列表页 >

Comparison of multiple linear regression and machine learning in predicting fear of cancer recurrence in newly diagnosed breast cancer patients

更新时间：2026-11-05

- Comparison of multiple linear regression and machine learning in predicting fear of cancer recurrence in newly diagnosed breast cancer patients
- Medical Journal of Wuhan University Vol. 46, Issue 7, Pages: 883-889(2025)
- 作者机构：
  
  1.武汉大学中南医院，麻醉科，湖北武汉 430071
  2.武汉大学中南医院，内分泌科，湖北武汉 430071
  3.武汉大学中南医院，护理部，湖北武汉 430071
  4.武汉大学中南医院，甲乳外科，湖北武汉 430071
- 作者简介：
- 基金信息：
- DOI：10.14188/j.1671-8852.2023.0670
  CLC： R743.33
- Received：11 December 2023，
  
  Published：25 July 2025
- 稿件说明：
移动端阅览
方超,李洋,熊梅棣等.多重线性回归与机器学习在预测初诊乳腺癌患者癌症复发恐惧的比较[J].武汉大学学报（医学版）,2025,46(07):883-889.

FANG Chao,LI Yang,XIONG Meidi,et al.Comparison of multiple linear regression and machine learning in predicting fear of cancer recurrence in newly diagnosed breast cancer patients[J].Medical Journal of Wuhan University,2025,46(07):883-889.
方超,李洋,熊梅棣等.多重线性回归与机器学习在预测初诊乳腺癌患者癌症复发恐惧的比较[J].武汉大学学报（医学版）,2025,46(07):883-889. DOI： 10.14188/j.1671-8852.2023.0670.

FANG Chao,LI Yang,XIONG Meidi,et al.Comparison of multiple linear regression and machine learning in predicting fear of cancer recurrence in newly diagnosed breast cancer patients[J].Medical Journal of Wuhan University,2025,46(07):883-889. DOI： 10.14188/j.1671-8852.2023.0670.

摘要

目的

采用轻量级梯度提升机(LightGBM)、极端梯度提升(XGBoost)、决策树(DT)、随机森林(RF)4种机器学习模型与多元线性模型（MLR）分析初诊乳腺癌患者癌症复发恐惧的影响因素。

方法

采用一般资料调查表、恐惧疾病进展简化量表、社会支持评定量表及医学应对问卷对339例乳腺癌患者进行调查。采用单因素及相关性分析筛选危险因素，基于XGBoost、LightGBM、DT、RF算法及MLR分别建立预测模型，使用平均绝对误差(MAE)、均方根误差(RMSE)及决定系数(

²)等指标比较预测性能。

结果

基于4种机器学习与MLR预测模型显示患者职业、工作状态、家庭人均月收入、社会支持水平及医学应对方式的面对和回避是初诊乳腺癌患者癌症复发恐惧的主要影响因素。

结论

基于机器学习算法尤其是LightGBM建立的风险预测模型具有较好的效能，医务人员可以根据预测模型结果制定相应的干预措施，以降低患者癌症复发恐惧水平，从而提高患者生活质量。

Abstract

Objective

To analyze the factors affecting the fear of cancer recurrence in breast cancer patients using four machine learning models and multiple linear regression: light gradient boosting machine (LightGBM)

extreme gradient boosting (XGBoost)

decision tree (DT)

and random forest (RF)

and compare them with multiple linear regression (MLR).

Methods

The 339 newly diagnosed breast cancer patients were investigated by the general data questionnaire

fear of progression questionnaire⁃short form (FoP⁃Q⁃SF)

social support rating scale (SSRS)

and medical coping modes questionnaire (MCMQ). Single⁃factor and correlation analyses were used to screen risk factors. Predictive models were built b

ased on XGBoost

LightGBM

RF algorithms

and MLR analysis. Their predictive performance was compared using mean absolute error (MAE)

root mean squared error (RMSE)

and coefficient of determination (also known as

²).

Results

Based on four machine learning models and MLR predictions

occupation

employment status

monthly per capita household income

level of social support

and coping strategies (facing and avoiding) were the primary factors influencing fear of cancer recurrence in newly diagnosed breast cancer patients.

Conclusion

The risk prediction model built based on machine learning algorithms

especially LightGBM

has good performance. Healthcare professionals can formulate corresponding intervention measures based on the results of the prediction model to reduce patients' fear of cancer recurrence

thereby improving their quality of life.

关键词

Keywords

references

中国抗癌协会乳腺癌专业委员会 . 中国乳腺癌筛查与早期诊断指南 [J ] . 中国癌症杂志 , 2022 , 32 ( 4 ): 363 ⁃ 372 .

Breast Cancer Specialized Committee of the Chinese Anti⁃Cancer Association . Screening and early diagnosis of breast cancer in China: A practice guideline [J ] . China Oncol , 2022 , 32 ( 4 ): 363 ⁃ 372 .

SUNG H , FERLAY J , SIEGEL R L , et al . Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries [J ] . CA Cancer J Clin , 2021 , 71 ( 3 ): 209 ⁃ 249 .

FENG R M , ZONG Y N , CAO S M , et al . Current cancer situation in China: Good or bad news from the 2018 Global Cancer Statistics? [J ] . Cancer Commun , 2019 , 39 ( 1 ): 22 .

BIDSTRUP P E , JOHANSEN C , KROMAN N , et al . Effect of a nurse navigation intervention on mental symptoms in patients with psychological vulnerability and breast cancer: The REBECCA randomized clinical trial [J ] . JAMA Netw Open , 2023 , 6 ( 6 ): e2319591 .

TAUBER N M , O'TOOLE M S , JENSEN A B , et al . ConquerFear⁃Group: A randomized controlled trial of an online⁃delivered group⁃based psychological intervention for fear of cancer recurrence in breast cancer survivors [J ] . Psychooncology , 2023 , 32 ( 9 ): 1424 ⁃ 1432 .

SCHAPIRA L , ZHENG Y , GELBER S I , et al . Trajectories of fear of cancer recurrence in young breast cancer survivors [J ] . Cancer , 2022 , 128 ( 2 ): 335 ⁃ 343 .

YANG Y , SUN H W , LUO X , et al . Network connectivity between fear of cancer recurrence, anxiety, and depression in breast cancer patients [J ] . J Affect Disord , 2022 , 309 : 358 ⁃ 367 .

AKECHI T , YAMAGUCHI T , UCHIDA M , et al . Smartphone psychotherapy reduces fear of cancer recurrence among breast cancer survivors: A fully decentralized randomized controlled clinical trial (J⁃SUPPORT 1703 study) [J ] . J Clin Oncol , 2023 , 41 ( 5 ): 1069 ⁃ 1078 .

LIU J L , GRIVA K , MAHENDRAN R . Latent profiles of fear of cancer recurrence and associations with physical and mental health outcomes [J ] . Ann Behav Med , 2023 , 57 ( 9 ): 743 ⁃ 752 .

CLIFT A K , DODWELL D , LORD S , et al . Development and internal⁃external validation of statistical and machine learning models for breast cancer prognostication: Cohort study [J ] . BMJ , 2023 , 381 : e073800 .

MEHNERT A , HERSCHBACH P , BERG P , et al . Fear of progression in breast cancer patients: Validation of the short form of the Fear of Progression Questionnaire (FoP⁃Q⁃SF) [J ] . Z Psychosom Med Psychother , 2006 , 52 ( 3 ): 274 ⁃ 288 .

KOCH⁃GALLENKAMP L , BERTRAM H , EBERLE A , et al . Fear of recurrence in long⁃term cancer survivors⁃Do cancer type, sex, time since diagnosis, and social support matter? [J ] . Health Psychol , 2016 , 35 ( 12 ): 1329 ⁃ 1333 .

吴奇云 , 叶志霞 , 李丽 , 等 . 癌症患者恐惧疾病进展简化量表的汉化及信效度分析 [J ] . 中华护理杂志 , 2015 , 50 ( 12 ): 1515 ⁃ 1519 .

WU Q Y , YE Z X , LI L , et al . Reliability and validity of Chinese version of Fear of Progression Questionnaire⁃Short Form for cancer patients [J ] . Chin J Nurs , 2015 , 50 ( 12 ): 1515 ⁃ 1519 .

肖水源 . 《社会支持评定量表》的理论基础与研究应用 [J ] . 临床精神医学杂志 , 1994 , 4 ( 2 ): 98 ⁃ 100 .

XIAO S Y . Theoretical basis and research application of Social Support Rating Scale [J ] . J Clin Psychiatry , 1994 , 4 ( 2 ): 98 ⁃ 100 .

FEIFEL H , STRACK S , NAGY V T . Degree of life⁃threat and differential use of coping modes [J ] . J Psychosom Res , 1987 , 31 ( 1 ): 91 ⁃ 99 .

沈晓红 , 姜乾金 . 医学应对方式问卷中文版701例测试报告 [J ] . 中国行为医学科学 , 2000 , 9 ( 1 ): 22 ⁃ 24 .

SHEN X H , JIANG Q J . Report on the Chinese version of the medical coping modes questionnaire based on 701 cases [J ] . Chinese Journal of Behavioral Medicine Science , 2000 , 9 ( 1 ): 22 ⁃ 24 .

CHO D , CHU Q , LU Q . Associations among physical symptoms, fear of cancer recurrence, and emotional well⁃being among Chinese American breast cancer survivors: A path model [J ] . Support Care Cancer , 2018 , 26 ( 6 ): 1755 ⁃ 1761 .

MAHEU C , SINGH M , TOCK W L , et al . Fear of cancer recurrence, health anxiety, worry, and uncertainty: A scoping review about their conceptualization and measurement within breast cancer survivorship research [J ] . Front Psychol , 2021 , 12 : 644932 .

VACHON E , KRUEGER E , CHAMPION V L , et al . The impact of fear of cancer recurrence on healthcare utilization among long⁃term breast cancer survivors recruited through ECOG⁃ACRIN trials [J ] . Psychooncology , 2021 , 30 ( 3 ): 279 ⁃ 286 .

GORMLEY M , KNOBF M T , VORDERSTRASSE A , et al . Exploring the effects of genomic testing on fear of cancer recurrence among breast cancer survivors [J ] . Psychooncology , 2021 , 30 ( 8 ): 1322 ⁃ 1331 .

KLONTZAS M E , VOLITAKIS E , AYDINGÖZ Ü , et al . Machine learning identifies factors related to early joint space narrowing in dysplastic and non⁃dysplastic hips [J ] . Eur Radiol , 2022 , 32 ( 1 ): 542 ⁃ 550 .

NGUYEN V L , NGUYEN H D , CHO Y S , et al . Comparison of multivariate linear regression and a machine learning algorithm developed for prediction of precision warfarin dosing in a Korean population [J ] . J Thromb Haemost , 2021 , 19 ( 7 ): 1676 ⁃ 1686 .

LIN Z M , CHOU W C , CHENG Y H , et al . Predicting nanoparticle delivery to tumors using machine learning and artificial intelligence approaches [J ] . Int J Nanomed , 2022 , 17 : 1365 ⁃ 1379 .

ZAPF M A C , FABBRI D V , ANDREWS J , et al . Development of a machine learning model to predict intraoperative transfusion and guide type and screen ordering [J ] . J Clin Anesth , 2023 , 91 : 111272 .

CHEN S H , MEI R R , TAN C X , et al . Psychological resilience and related influencing factors in postoperative non⁃small cell lung cancer patients: A cross⁃sectional study [J ] . Psychooncology , 2020 , 29 ( 11 ): 1815 ⁃ 1822 .

DEUNING⁃SMIT E , CUSTERS J A E , MIROŠEVIČ Š , et al . Prospective longitudinal study on fear of cancer recurrence in patients newly diagnosed with head and neck cancer: Course, trajectories, and associated factors [J ] . Head Neck , 2022 , 44 ( 4 ): 914 ⁃ 925 .

DU R F , WANG P P , MA L X , et al . Health⁃related quality of life and associated factors in patients with myocardial infarction after returning to work: A cross⁃sectional study [J ] . Health Qual Life Outcomes , 2020 , 18 ( 1 ): 190 .

YEUNG N C Y , LU Q . Social constraints and fear of recurrence among Chinese American breast cancer survivors: An exploration of psychosocial mediators [J ] . Psychooncology , 2022 , 31 ( 1 ): 98 ⁃ 106 .

SORIANO E C , OTTO A K , LOSAVIO S T , et al . Fear of cancer recurrence and inhibited disclosure: Testing the social⁃cognitive processing model in couples coping with breast cancer [J ] . Ann Behav Med , 2021 , 55 ( 3 ): 192 ⁃ 202 .

TAHER R , CARR NJ , VANDERPUYE N , et al . Fear of Cancer Recurrence in peritoneal malignancy patients following treatment: A cross⁃sectional study [J ] . J Cancer Surviv , 2023 , 17 ( 2 ): 300 ⁃ 308 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Prediction of prognosis for lung metastases in bladder cancer using multiple machine learning models

Expression and prognostic significance of TP63 in breast cancer based on bioinformatics analysis

Gut flora mediates the association between immune cells and HER2+ breast cancer: A mediated Mendelian randomization study

Risk assessment models of tic disorders with comorbid attention deficit hyperactivity disorder based on machine learning

Exploring the differences between CASIA2 and Pentacam in preoperative evaluation of cataracts: A comparison based on measurements of anterior chamber volume, corneal thickness, and pupil diameter

Related Author

FANG Chao

ZHANG Chunhua

XU Ran

CHEN Si'an

WU Jinhai

ZENG Xiheng

LEI Dong

CHEN Yanfei

Related Institution

Department of Urologic Oncology, Cancer Hospital of Guangzhou Medical University

Hubei Cancer Clinical Study Center

Department of Radiation and Medical Oncology, Zhongnan Hospital of Wuhan University

Hubei Key Laboratory of Tumor Biological Behaviors

Xinzhou District Hospital of Traditional Chinese Medicine ＆ Xinzhou Branch of Zhongnan Hospital of Wuhan University

AI问答

⁰