Trajectory analysis of sleep disorders and anxiety-depression in female breast cancer patients undergoing chemotherapy: based on group-based Multi-Trajectory Model and machine learning

BACKGROUND: Sleep disorders and anxiety-depression symptoms can significantly impair the quality of life and treatment adherence among breast cancer patients undergoing chemotherapy, while also increasing the risk of disease recurrence and mortality. Early identification of the progression trajectory and underlying causes of these symptoms is essential for providing personalized interventions for deteriorating cases. OBJECTIVE: This study aims to analyze the trajectories of sleep disorders and anxiety-depression symptoms in breast cancer patients during chemotherapy using a group-based Multi-Trajectory Model (GBMTM) and to identify influencing factors through machine learning. METHODS: Prospective data from 150 breast cancer patients undergoing four cycles of chemotherapy were collected. A GBMTM was employed to identify distinct trajectories, with 70 predictive variables included in the analysis. Least Absolute Shrinkage and Selection Operator (LASSO) regression was used to select the optimal subset of variables. Seven machine learning models were compared, and the optimal model was chosen for result interpretation using SHAP (SHapley Additive exPlanations) analysis. RESULTS: Among breast cancer patients undergoing chemotherapy, two distinct trajectories of sleep disorders and anxiety-depression symptoms were identified: the "stable group" (74.7%) and the "deteriorating group" (25.3%). SHAP analysis revealed that high levels of C-reactive protein, high uric acid, high hemoglobin, smoking, presence of invasive cancer with ductal carcinoma in situ, prior chemotherapy, being married, regular menstrual cycles in the past, and lack of family history were significant risk factors associated with the "deteriorating group." CONCLUSION: Our findings indicate two distinct trajectories of sleep disorders and anxiety-depression symptoms in breast cancer patients undergoing chemotherapy, with the majority falling into the "stable group". The identified risk factors associated with the "deteriorating group" should be closely monitored to facilitate early intervention and improve patient outcomes. TRIAL REGISTRATION: The trial was registered on Chinese Clinical Trial Registry (Trial ID: ChiCTR2300077667 on 15 November 2023; available at https://www.chictr.org.cn/).

Authors

Institutions

Publication Details

Journal
BMC Medical Informatics and Decision Making
Published
2026-06-30
DOI
https://doi.org/10.1186/s12911-026-03672-1
Primary Topic
Cancer survivorship and care
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Trajectory analysis of sleep disorders and anxiety-depression in female breast cancer patients undergoing chemotherapy: based on group-based Multi-Trajectory Model and machine learning

Yuan Li, Zhizhen Tao, Tumalisi Kayishaer, Chao Tian et al.
BMC Medical Informatics and Decision Making
Cancer survivorship and care
article

Trajectory analysis of sleep disorders and anxiety-depression in female breast cancer patients undergoing chemotherapy: based on group-based Multi-Trajectory Model and machine learning

Yuan Li, Zhizhen Tao, Tumalisi Kayishaer, Chao Tian, Xinyu Zhao, Yinqing Yang, Yi Yang, Xiuying Hu, Bingmei Zhu, Jie Chu, Jinshu Han, Jiang Yuan
article en

Abstract

BACKGROUND: Sleep disorders and anxiety-depression symptoms can significantly impair the quality of life and treatment adherence among breast cancer patients undergoing chemotherapy, while also increasing the risk of disease recurrence and mortality. Early identification of the progression trajectory and underlying causes of these symptoms is essential for providing personalized interventions for deteriorating cases. OBJECTIVE: This study aims to analyze the trajectories of sleep disorders and anxiety-depression symptoms in breast cancer patients during chemotherapy using a group-based Multi-Trajectory Model (GBMTM) and to identify influencing factors through machine learning. METHODS: Prospective data from 150 breast cancer patients undergoing four cycles of chemotherapy were collected. A GBMTM was employed to identify distinct trajectories, with 70 predictive variables included in the analysis. Least Absolute Shrinkage and Selection Operator (LASSO) regression was used to select the optimal subset of variables. Seven machine learning models were compared, and the optimal model was chosen for result interpretation using SHAP (SHapley Additive exPlanations) analysis. RESULTS: Among breast cancer patients undergoing chemotherapy, two distinct trajectories of sleep disorders and anxiety-depression symptoms were identified: the "stable group" (74.7%) and the "deteriorating group" (25.3%). SHAP analysis revealed that high levels of C-reactive protein, high uric acid, high hemoglobin, smoking, presence of invasive cancer with ductal carcinoma in situ, prior chemotherapy, being married, regular menstrual cycles in the past, and lack of family history were significant risk factors associated with the "deteriorating group." CONCLUSION: Our findings indicate two distinct trajectories of sleep disorders and anxiety-depression symptoms in breast cancer patients undergoing chemotherapy, with the majority falling into the "stable group". The identified risk factors associated with the "deteriorating group" should be closely monitored to facilitate early intervention and improve patient outcomes. TRIAL REGISTRATION: The trial was registered on Chinese Clinical Trial Registry (Trial ID: ChiCTR2300077667 on 15 November 2023; available at https://www.chictr.org.cn/).

BMC Medical Informatics and Decision Making
University of Electronic Science and Technology of China (CN), Sichuan University (CN), West China Hospital of Sichuan University (CN), Sichuan Cancer Hospital (CN), Chengdu University of Traditional Chinese Medicine (CN)
Good health and well-being
Openalex Percentile: Top 8%
Cancer survivorship and care
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.