Abstract
Purpose
The efficacy of adjuvant chemotherapy in elderly breast cancer patients is currently controversial. This study aims to provide personalized adjuvant chemotherapy recommendations using deep learning (DL).
Methods
Six models with various causal inference approaches were trained to make individualized chemotherapy recommendations. Patients who received actual treatment recommended by DL models were compared with those who did not. Inverse probability treatment weighting (IPTW) was used to reduce bias. Linear regression, IPTW-adjusted risk difference (RD), and SurvSHAP(t) were used to interpret the best model.
Results
A total of 5352 elderly breast cancer patients were included. The median (interquartile range) follow-up time was 52 (30–80) months. Among all models, the balanced individual treatment effect for survival data (BITES) performed best. Treatment according to following BITES recommendations was associated with survival benefit, with a multivariate hazard ratio (HR) of 0.78 (95% confidence interval (CI): 0.64–0.94), IPTW-adjusted HR of 0.74 (95% CI: 0.59–0.93), RD of 12.40% (95% CI: 8.01–16.90%), IPTW-adjusted RD of 11.50% (95% CI: 7.16–15.80%), difference in restricted mean survival time (dRMST) of 12.44 (95% CI: 8.28–16.60) months, IPTW-adjusted dRMST of 7.81 (95% CI: 2.93–11.93) months, and p value of the IPTW-adjusted Log-rank test of 0.033. By interpreting BITES, the debiased impact of patient characteristics on adjuvant chemotherapy was quantified, which mainly included breast cancer subtype, tumor size, number of positive lymph nodes, TNM stages, histological grades, and surgical type.
Conclusion
Our results emphasize the potential of DL models in guiding adjuvant chemotherapy decisions for elderly breast cancer patients.
Similar content being viewed by others
Data availability
This study analyzed public datasets that can be found here: the Surveillance, Epidemiology, and End Results Program (https://seer.cancer.gov/index.html).
References
Singh D, Vignat J, Lorenzoni V, Eslahi M, Ginsburg O, Lauby-Secretan B, Arbyn M, Basu P, Bray F, Vaccarella S (2023) Global estimates of incidence and mortality of cervical cancer in 2020: a baseline analysis of the WHO Global Cervical Cancer Elimination Initiative. Lancet Glob Health 11(2):e197–e206
Morgan JL, George J, Holmes G, Martin C, Reed MWR, Ward S, Walters SJ, Cheung KL, Audisio RA, Wyld L (2020) Breast cancer surgery in older women: outcomes of the Bridging Age Gap in Breast Cancer study. Br J Surg 107(11):1468–1479
Wu Y, Qi Y, Yang J, Yang R, Lui W, Huang Y, Zhao X, Chen R, He T, Lu S et al (2022) Effect of adjuvant chemotherapy on the survival outcomes of elderly breast cancer: a retrospective cohort study based on SEER database. J Evid Based Med 15(4):354–364
Fadda GM, Santeufemia DA, Basso SM, Tozzoli R, Falcomer F, Lumachi F (2016) Adjuvant treatment of early breast cancer in the elderly. Med Chem 12(3):280–284
Lichtman SM, Cirrincione CT, Hurria A, Jatoi A, Theodoulou M, Wolff AC, Gralow J, Morganstern DE, Magrinat G, Cohen HJ et al (2016) Effect of pretreatment renal function on treatment and clinical outcomes in the adjuvant treatment of older women with breast cancer: alliance A171201, an Ancillary Study of CALGB/CTSU 49907. J Clin Oncol 34(7):699–705
Elkin EB, Hurria A, Mitra N, Schrag D, Panageas KS (2006) Adjuvant chemotherapy and survival in older women with hormone receptor-negative breast cancer: assessing outcome in a population-based, observational cohort. J Clin Oncol 24(18):2757–2764
Abdel-Razeq H, Abu Rous F, Abuhijla F, Abdel-Razeq N, Edaily S (2022) Breast cancer in geriatric patients: current landscape and future prospects. Clin Interv Aging 17:1445–1460
Tamirisa N, Lin H, Shen Y, Shaitelman SF, Sri Karuturi M, Giordano SH, Babiera G, Bedrosian I (2020) Association of chemotherapy with survival in elderly patients with multiple comorbidities and estrogen receptor-positive, node-positive breast cancer. JAMA Oncol 6(10):1548–1554
Muss HB, Polley MC, Berry DA, Liu H, Cirrincione CT, Theodoulou M, Mauer AM, Kornblith AB, Partridge AH, Dressler LG et al (2019) Randomized trial of standard adjuvant chemotherapy regimens versus capecitabine in older women with early breast cancer: 10-year update of the CALGB 49907 trial. J Clin Oncol 37(26):2338–2348
Hankey BF, Ries LA, Edwards BK (1999) The surveillance, epidemiology, and end results program: a national resource. Cancer Epidemiol Biomarkers Prev 8(12):1117–1121
von Elm E, Altman DG, Egger M, Pocock SJ, Gøtzsche PC, Vandenbroucke JP (2007) The Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) statement: guidelines for reporting observational studies. Lancet 370(9596):1453–1457
Chia Z, Lee RXN, Cardoso MJ, Cheung KL, Parks RM (2023) Oncoplastic breast surgery in older women with primary breast cancer: systematic review. Br J Surg 110(10):1309–1315
Hotsinpiller Wj, Everett As, Richman Js, Parker C, Boggs Dh (2021) Rates of margin positive resection with breast conservation for invasive breast cancer using the NCDB. Breast 60:86–89
De la Cruz Ku G, Karamchandani M, Chambergo-Michilot D, Narvaez-Rojas AR, Jonczyk M, Príncipe-Meneses FS, Posawatz D, Nardello S, Chatterjee A (2022) Does breast-conserving surgery with radiotherapy have a better survival than mastectomy? A meta-analysis of more than 1,500,000 patients. Ann Surg Oncol 29(10):6163–6188
Mierzwa ML, Nyati MK, Morgan MA, Lawrence TS (2010) Recent advances in combined modality therapy. Oncologist 15(4):372–381
Schrod S, Schäfer A, Solbrig S, Lohmayer R, Gronwald W, Oefner PJ, Beißbarth T, Spang R, Zacharias HU, Altenbuchinger M (2022) BITES: balanced individual treatment effect for survival data. Bioinformatics 38:i60–i67
Nagpal C, Goswami M, Dufendach KA, Dubrawski AW (2022) Counterfactual phenotyping with censored time-to-events. Proceedings of the 28th ACM SIGKDD conference on knowledge discovery and data mining
Katzman J, Shaham U, Cloninger A, Bates J, Jiang T, Kluger Y (2016) Deep survival: a deep cox proportional hazards network. ArXiv abs/1606.00931
Lechner M (2018) Modified causal forests for estimating heterogeneous causal effects. CEPR discussion paper series
Krzyzi’nski M, Spytek M, Baniecki H, Biecek P (2022) SurvSHAP(t): time-dependent explanations of machine learning survival models. Knowl Based Syst 262:110234
Battisti NML, De Glas N, Soto-Perez-de-Celis E, Liposits G, Bringuier M, Walko C, Lichtman SM, Aapro M, Cheung KL, Biganzoli L et al (2022) Chemotherapy and gene expression profiling in older early luminal breast cancer patients: an International Society of Geriatric Oncology systematic review. Eur J Cancer 172:158–170
Zhao N, Rosen JM (2022) Breast cancer heterogeneity through the lens of single-cell analysis and spatial pathologies. Semin Cancer Biol 82:3–10
Luo H, Zhuang F, Xie R, Zhu H, Wang D (2023) A survey on causal inference for recommendation. ArXiv abs/2303.11666
Yao L, Chu Z, Li S, Li Y, Gao J, Zhang A (2020) A survey on causal inference. ACM Trans Knowl Discov Data (TKDD) 15:1–46
Künzel SR, Sekhon JS, Bickel PJ, Yu B (2019) Metalearners for estimating heterogeneous treatment effects using machine learning. Proc Natl Acad Sci U S A 116(10):4156–4165
Johansson FD, Shalit U, Kallus N, Sontag DA (2020) Generalization bounds and representation learning for estimation of potential outcomes and causal effects. J Mach Learn Res 23(166):161–166
Zhu E, Shi W, Chen Z, Wang J, Ai P, Wang X, Zhu M, Xu Z, Xu L, Sun X et al (2023) Reasoning and causal inference regarding surgical options for patients with low-grade gliomas using machine learning: a SEER-based study. Cancer Med 12(22):20878–20891
Peng Y, Hu T, Cheng L, Tong F, Cao Y, Liu P, Zhou B, Liu M, Liu H, Guo J et al (2021) Evaluating and balancing the risk of breast cancer-specific death and other cause-specific death in elderly breast cancer patients. Front Oncol 11:578880
Elomrani F, Zine M, Afif M, L’Annaz S, Ouziane I, Mrabti H, Errihani H (2015) Management of early breast cancer in older women: from screening to treatment. Breast Cancer 7:165–171
Muss HB, Berry DA, Cirrincione CT, Theodoulou M, Mauer AM, Kornblith AB, Partridge AH, Dressler LG, Cohen HJ, Becker HP et al (2009) Adjuvant chemotherapy in older women with early-stage breast cancer. N Engl J Med 360(20):2055–2065
Huttunen T, Leidenius M, Jahkola T, Mattson J, Suominen S, Meretoja T (2022) Delay in the initiation of adjuvant chemotherapy in patients with breast cancer with mastectomy with or without immediate breast reconstruction. BJS Open 6(4):zrac096
Eck DL, McLaughlin SA, Terkonda SP, Rawal B, Perdikis G (2015) Effects of immediate reconstruction on adjuvant chemotherapy in breast cancer patients. Ann Plast Surg 74(Suppl 4):S201–S203
Yao K, Sisco M, Bedrosian I (2016) Contralateral prophylactic mastectomy: current perspectives. Int J Womens Health 8:213–223
Lechner M: Modified Causal Forests for Estimating Heterogeneous Causal Effects. CEPR Discussion Paper Series 2018
Cook P, Yin G, Ayeni FE, Eslick GD, Edirimanne S (2023) Does immediate breast reconstruction lead to a delay in adjuvant chemotherapy for breast cancer? A meta-analysis and systematic review. Clin Breast Cancer 23(5):e285–e295
Mukai Y, Taira N, Kajiwara Y, Iwamoto T, Kitaguchi Y, Saiga M, Watanabe S, Shien T, Doihara H, Kimata Y (2023) Impact of immediate breast reconstruction on survival of breast cancer patients: a single-center observational study. Acta Med Okayama 77(3):281–290
Funding
This work was supported by the Medical discipline Construction Health Committee of Project of Pudong Shanghai (Grant No.: PWYgV2021-02).
Author information
Authors and Affiliations
Contributions
Critical revision of the manuscript for important intellectual content: EZ, DS, JW, CH, HP, and ZA. Statistical analysis: EZ and ZA. Obtained funding: DS and ZA. Administrative, technical, or material support: EZ, LZ, WS, ZX, PA, DS, and ZA. Supervision: DS and ZA.
Corresponding author
Ethics declarations
Conflict of interest
All authors declare no conflict of interest.
Ethical approval
The studies involving human participants were approved by the national cancer institution.
Informed consent
Written informed consent for participation was not required for this study in accordance with national legislation and institutional requirements.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zhu, E., Zhang, L., Wang, J. et al. Deep learning-guided adjuvant chemotherapy selection for elderly patients with breast cancer. Breast Cancer Res Treat 205, 97–107 (2024). https://doi.org/10.1007/s10549-023-07237-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10549-023-07237-y