Predicting cancer-related fatigue in elderly breast cancer patients undergoing chemotherapy: a retrospective machine-learning study incorporating nutritional status, inflammation, and TNM stage_CHINESE JOURNAL OF BASES AND CLINICS IN GENERAL SURGERY

Authors：

WANG Wenxin ¹ , LI Qian ¹ , LIU Yan ² , GUO Qianwen ³ , LI Shumo ¹ ,  HE Min ¹

1. Department of Breast Surgery, The First Affiliated Hospital of Kunming Medical University, Kunming 650032, P. R. China;
2. Department of General Surgery, The First Affiliated Hospital of Kunming Medical University, Kunming 650032, P. R. China;
3. Department of Emergency Medicine, The Third People’s Hospital of Kunming, Kunming 650032, P. R. China;

Corresponding?author：

HE Min, Email: 523130776@qq.com

Keywords：

breast cancer; cancer-related fatigue; machine learning; prediction model

DOI：

10.7507/1007-9424.202605086

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Objective To develop a machine learning-based predictive model for cancer-related fatigue (CRF) in elderly breast cancer patients undergoing chemotherapy. Methods A retrospective analysis was conducted on 366 elderly breast cancer patients who received chemotherapy at the First Affiliated Hospital of Kunming Medical University from January 2022 to December 2025. Patients were divided into a CRF group and a non-CRF group based on CRF status. LASSO (least absolute shrinkage and selection operator) regression was used for variable selection. Three predictive models were constructed using logistic regression (LR), random forest, and support vector machine. Model performance was evaluated, and the optimal model was presented as a Nomogram. Results LASSO regression identified seven variables: TNM stage, nutritional risk screening (NRS) 2002 score, short physical performance battery (SPPB) score, albumin (ALB), interleukin-6 (IL-6), C-reactive protein (CRP), and tumor necrosis factor-α (TNF-α). Among the three models, LR achieved the highest area under the curve value [0.893 (0.861, 0.924)] and F1-score (0.806). TNM stage Ⅲ (OR=4.222) and Ⅳ (OR=4.270), NRS 2002 score (OR=2.972), SPPB score (OR=1.345), levels of IL-6 (OR=1.700), CRP (OR=1.795), TNF-α (OR=1.819) were identified as independent risk factors (P＜0.05), and ALB level was identified as independent protective factor (OR=0.899, P=0.004). The calibration curve of the LR-based Nomogram closely approximated the ideal line, with a concordance index of 0.879 and an overfitting degree of 1.07%. Conclusions CRF in elderly breast cancer patients undergoing chemotherapy is influenced by TNM stage, NRS 2002 score, SPPB score, levels of ALB, IL-6, CRP, and TNF-α. The Nomogram developed in this study demonstrates favorable clinical utility, though further validation is warranted.

Citation： WANG Wenxin, LI Qian, LIU Yan, GUO Qianwen, LI Shumo, HE Min. Predicting cancer-related fatigue in elderly breast cancer patients undergoing chemotherapy: a retrospective machine-learning study incorporating nutritional status, inflammation, and TNM stage. CHINESE JOURNAL OF BASES AND CLINICS IN GENERAL SURGERY, 2026, 33(9): 1246-1253. doi: 10.7507/1007-9424.202605086 Copy

1.	李響, 李恒希, 鄭榮壽, 等. 2024全球癌癥統計數據解讀: 中國與全球對比 [J]. 中國普外基礎與臨床雜志, 2026, 33(8): 1009-1017.
2.	許洋, 張曦, 牛萌, 等. 乳腺癌化療患者隨訪管理的最佳證據總結 [J]. 軍事護理, 2025, 42(10): 99-102, 107.
3.	鄭婉莉, 方馥荔, 楊麗丹. 基于結構方程模型的乳腺癌放療患者癌因性疲乏影響路徑分析 [J]. 醫學理論與實踐, 2026, 39(4): 677-680.
4.	Wei H, He W. Toward precision rehabilitation: a latent profile analysis of social support as a buffer against fatigue and reduced physical activity in breast cancer chemotherapy [J/OL]. Support Care Cancer, 2026, 34(3): 264. doi: 10.1007/s00520-026-10508-1.
5.	Haussmann A, Schmidt ME, Goldschmidt S, et al. Effects of aerobic or resistance exercise on sleep and cancer-related fatigue in patients with breast cancer during or after neoadjuvant chemotherapy: a 3-arm randomized controlled trial [J/OL]. BMC Med, 2026, 24(1): 114. doi: 10.1186/s12916-026-04669-3.
6.	Liu Z, Shen G, Wang M, et al. Development and validation of a machine learning model to predict moderate-to-severe cancer-related fatigue in breast cancer [J/OL]. Support Care Cancer, 2025, 34(1): 36. doi: 10.1007/s00520-025-10258-6.
7.	Beenhakker L, Wijlens KAE, Witteveen A, et al. Development of machine learning models to predict cancer-related fatigue in Dutch breast cancer survivors up to 15 years after diagnosis [J]. J Cancer Surviv, 2025, 19(2): 580-593.
8.	盧辛辛, 呂帝, 劉小華, 等. 乳腺癌患者新輔助治療病理完全緩解療效預測的可解釋性機器學習模型開發與驗證: 一項多中心研究 [J]. 臨床放射學雜志, 2026, 45(2): 265-272.
9.	黃蓉, 黃源, 陶蘋, 等. 不同TNM分期乳腺癌患者規范化治療后生存期生命質量評價 [J]. 中華腫瘤雜志, 2013, 35(1): 71-77.
10.	Guirao García ME, Marín Rodríguez P, Servet Pérez de Lema CM, et al. Unlocking the predictive value of post-neoadjuvant immune biomarkers in breast cancer: neutrophil-to-lymphocyte ratio (NLR) and systemic immune-inflammation index (SII)[J/OL]. Breast Cancer Res Treat, 2026, 216(3): 26. doi: 10.1007/s10549-026-07928-2.
11.	卜志軍, 丁申, 馬文欣, 等. 臨床預測模型構建中的常用樣本量估算方法介紹及實例分析 [J]. 現代中醫臨床, 2024, 31(6): 32-37.
12.	中國抗癌協會乳腺癌專業委員會. 中國抗癌協會乳腺癌診治指南與規范 (2021年版) [J]. 中國癌癥雜志, 2021, 31(10): 954-1040.
13.	張賢賢, 賈智慧, 張利霞, 等. 老年乳腺癌病人化療相關認知障礙現狀及影響因素 [J]. 護理研究, 2020, 34(3): 425-429.
14.	馬群, 徐麗, 楊利娜. 以TTM為導向的認知行為護理干預對乳腺癌術后患者自我管理能力及自我效能感的影響 [J]. 國際護理學雜志, 2025, 44(13): 2311-2315.
15.	楊素娟, 高文思, 楊金霞. 乳腺癌患者化療期間癌因性疲乏發生現狀及危險因素分析 [J]. 中國腫瘤臨床與康復, 2024, 31(11): 719-726.
16.	Brefka S, Dallmeier D, Mühlbauer V, et al. a proposal for the retrospective identification and categorization of older people with functional impairments in scientific studies-recommendations of the Medication and Quality of Life in Frail Older Persons (MedQoL) Research Group [J]. J Am Med Dir Assoc, 2019, 20(2): 138-146.
17.	付思佳, 屈琳琳. 基于虛擬現實技術的正念干預對老年乳腺癌化療患者生活質量和癌因性疲乏的影響研究 [J]. 老年醫學與保健, 2025, 31(1): 42-46,52.
18.	張劍軍, 錢建新. 中國癌癥相關性疲乏臨床實踐診療指南 (2021年版) [J]. 中國癌癥雜志, 2021, 31(9): 852-872.
19.	潘露露, 任玉峰, 陳曉燕, 等. 老年乳腺癌化療患者癌因性疲乏現狀調查及相關因素分析 [J]. 老年醫學與保健, 2024, 30(3): 621-625, 632.
20.	陳媚媚, 魯佩佩. 乳腺癌化療患者癌因性疲乏現狀調查及相關因素分析 [J]. 中國婦幼保健, 2025, 40(14): 2535-2539.
21.	張杰秋, 伍棋, 王艦梅, 等. 基于機器學習的病理組學特征可預測乳腺癌患者對新輔助化療的反應 [J]. 重慶醫科大學學報, 2023, 48(12): 1483-1488.
22.	曹美華, 趙小娟, 吳凱菲, 等. 智隨訪平臺居家衰弱管理方案對乳腺癌術后化療患者衰弱及創傷后成長的影響 [J]. 河北醫藥, 2025, 47(3): 493-496.
23.	楊江波, 朱寬敏, 何友新, 等. 基于抗炎飲食的營養治療模式在乳腺癌化療患者中的應用效果 [J]. 腫瘤代謝與營養電子雜志, 2025, 12(4): 471-477.
24.	Liu Z, Wu T, Zhang W, et al. Global research trends and hotspots in breast cancer related fatigue: a bibliometric investigation [J/OL]. Support Care Cancer, 2026, 34(4): 319. doi: 10.1007/s00520-026-10555-8.
25.	Sun J, Fang X, Shi R, et al. Exploring the current status of barriers to cancer-related fatigue management in Chinese patients with breast cancer and its relationship with self-disclosure and adaptive cognitive emotion regulation strategies: a cross-sectional study from the perspective of emotion self-regulation theory [J/OL]. Support Care Cancer, 2026, 34(3): 239. doi: 10.1007/s00520-026-10480-w.
26.	U?ar GK, Tu?ral A. Cancer-related fatigue and associated factors in breast cancer: special emphasis on cognition [J/OL]. SN Compr Clin Med, 2026, 8(1): 37. doi: 10.1007/s42399-026-02291-1.
27.	李壯, 石歡, 陳潔婷, 等. 芍藥苷靶向EZH2/CCNE1調控細胞周期與炎癥微環境改善乳腺癌化療期癌因性疲乏 [J]. 南方醫科大學學報, 2026, 46(8): 1835-1849.
28.	岳軒妮, 閆慈, 劉新亞. 基于機器學習算法構建乳腺癌患者化療藥物致心血管毒性的風險預測模型 [J]. 中華心血管病雜志, 2025, 53(8): 898-905.

1. 李響, 李恒希, 鄭榮壽, 等. 2024全球癌癥統計數據解讀: 中國與全球對比 [J]. 中國普外基礎與臨床雜志, 2026, 33(8): 1009-1017.
2. 許洋, 張曦, 牛萌, 等. 乳腺癌化療患者隨訪管理的最佳證據總結 [J]. 軍事護理, 2025, 42(10): 99-102, 107.
3. 鄭婉莉, 方馥荔, 楊麗丹. 基于結構方程模型的乳腺癌放療患者癌因性疲乏影響路徑分析 [J]. 醫學理論與實踐, 2026, 39(4): 677-680.
4. Wei H, He W. Toward precision rehabilitation: a latent profile analysis of social support as a buffer against fatigue and reduced physical activity in breast cancer chemotherapy [J/OL]. Support Care Cancer, 2026, 34(3): 264. doi: 10.1007/s00520-026-10508-1.
5. Haussmann A, Schmidt ME, Goldschmidt S, et al. Effects of aerobic or resistance exercise on sleep and cancer-related fatigue in patients with breast cancer during or after neoadjuvant chemotherapy: a 3-arm randomized controlled trial [J/OL]. BMC Med, 2026, 24(1): 114. doi: 10.1186/s12916-026-04669-3.
6. Liu Z, Shen G, Wang M, et al. Development and validation of a machine learning model to predict moderate-to-severe cancer-related fatigue in breast cancer [J/OL]. Support Care Cancer, 2025, 34(1): 36. doi: 10.1007/s00520-025-10258-6.
7. Beenhakker L, Wijlens KAE, Witteveen A, et al. Development of machine learning models to predict cancer-related fatigue in Dutch breast cancer survivors up to 15 years after diagnosis [J]. J Cancer Surviv, 2025, 19(2): 580-593.
8. 盧辛辛, 呂帝, 劉小華, 等. 乳腺癌患者新輔助治療病理完全緩解療效預測的可解釋性機器學習模型開發與驗證: 一項多中心研究 [J]. 臨床放射學雜志, 2026, 45(2): 265-272.
9. 黃蓉, 黃源, 陶蘋, 等. 不同TNM分期乳腺癌患者規范化治療后生存期生命質量評價 [J]. 中華腫瘤雜志, 2013, 35(1): 71-77.
10. Guirao García ME, Marín Rodríguez P, Servet Pérez de Lema CM, et al. Unlocking the predictive value of post-neoadjuvant immune biomarkers in breast cancer: neutrophil-to-lymphocyte ratio (NLR) and systemic immune-inflammation index (SII)[J/OL]. Breast Cancer Res Treat, 2026, 216(3): 26. doi: 10.1007/s10549-026-07928-2.
11. 卜志軍, 丁申, 馬文欣, 等. 臨床預測模型構建中的常用樣本量估算方法介紹及實例分析 [J]. 現代中醫臨床, 2024, 31(6): 32-37.
12. 中國抗癌協會乳腺癌專業委員會. 中國抗癌協會乳腺癌診治指南與規范 (2021年版) [J]. 中國癌癥雜志, 2021, 31(10): 954-1040.
13. 張賢賢, 賈智慧, 張利霞, 等. 老年乳腺癌病人化療相關認知障礙現狀及影響因素 [J]. 護理研究, 2020, 34(3): 425-429.
14. 馬群, 徐麗, 楊利娜. 以TTM為導向的認知行為護理干預對乳腺癌術后患者自我管理能力及自我效能感的影響 [J]. 國際護理學雜志, 2025, 44(13): 2311-2315.
15. 楊素娟, 高文思, 楊金霞. 乳腺癌患者化療期間癌因性疲乏發生現狀及危險因素分析 [J]. 中國腫瘤臨床與康復, 2024, 31(11): 719-726.
16. Brefka S, Dallmeier D, Mühlbauer V, et al. a proposal for the retrospective identification and categorization of older people with functional impairments in scientific studies-recommendations of the Medication and Quality of Life in Frail Older Persons (MedQoL) Research Group [J]. J Am Med Dir Assoc, 2019, 20(2): 138-146.
17. 付思佳, 屈琳琳. 基于虛擬現實技術的正念干預對老年乳腺癌化療患者生活質量和癌因性疲乏的影響研究 [J]. 老年醫學與保健, 2025, 31(1): 42-46,52.
18. 張劍軍, 錢建新. 中國癌癥相關性疲乏臨床實踐診療指南 (2021年版) [J]. 中國癌癥雜志, 2021, 31(9): 852-872.
19. 潘露露, 任玉峰, 陳曉燕, 等. 老年乳腺癌化療患者癌因性疲乏現狀調查及相關因素分析 [J]. 老年醫學與保健, 2024, 30(3): 621-625, 632.
20. 陳媚媚, 魯佩佩. 乳腺癌化療患者癌因性疲乏現狀調查及相關因素分析 [J]. 中國婦幼保健, 2025, 40(14): 2535-2539.
21. 張杰秋, 伍棋, 王艦梅, 等. 基于機器學習的病理組學特征可預測乳腺癌患者對新輔助化療的反應 [J]. 重慶醫科大學學報, 2023, 48(12): 1483-1488.
22. 曹美華, 趙小娟, 吳凱菲, 等. 智隨訪平臺居家衰弱管理方案對乳腺癌術后化療患者衰弱及創傷后成長的影響 [J]. 河北醫藥, 2025, 47(3): 493-496.
23. 楊江波, 朱寬敏, 何友新, 等. 基于抗炎飲食的營養治療模式在乳腺癌化療患者中的應用效果 [J]. 腫瘤代謝與營養電子雜志, 2025, 12(4): 471-477.
24. Liu Z, Wu T, Zhang W, et al. Global research trends and hotspots in breast cancer related fatigue: a bibliometric investigation [J/OL]. Support Care Cancer, 2026, 34(4): 319. doi: 10.1007/s00520-026-10555-8.
25. Sun J, Fang X, Shi R, et al. Exploring the current status of barriers to cancer-related fatigue management in Chinese patients with breast cancer and its relationship with self-disclosure and adaptive cognitive emotion regulation strategies: a cross-sectional study from the perspective of emotion self-regulation theory [J/OL]. Support Care Cancer, 2026, 34(3): 239. doi: 10.1007/s00520-026-10480-w.
26. U?ar GK, Tu?ral A. Cancer-related fatigue and associated factors in breast cancer: special emphasis on cognition [J/OL]. SN Compr Clin Med, 2026, 8(1): 37. doi: 10.1007/s42399-026-02291-1.
27. 李壯, 石歡, 陳潔婷, 等. 芍藥苷靶向EZH2/CCNE1調控細胞周期與炎癥微環境改善乳腺癌化療期癌因性疲乏 [J]. 南方醫科大學學報, 2026, 46(8): 1835-1849.
28. 岳軒妮, 閆慈, 劉新亞. 基于機器學習算法構建乳腺癌患者化療藥物致心血管毒性的風險預測模型 [J]. 中華心血管病雜志, 2025, 53(8): 898-905.

CHINESE JOURNAL OF BASES AND CLINICS IN GENERAL SURGERY

Predicting cancer-related fatigue in elderly breast cancer patients undergoing chemotherapy: a retrospective machine-learning study incorporating nutritional status, inflammation, and TNM stage

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content