Machine learning-based prediction of breast cancer growth rate in-vivo

Bhattarai, Shristi; Klimov, Sergey; Aleskandarany, Mohammed A; Burrell, Helen; Wormall, Anthony; Green, Andrew R; Rida, Padmashree; Ellis, Ian O; Osan, Remus M; Rakha, Emad A; Aneja, Ritu

Abstract

Background
Determining the rate of breast cancer (BC) growth in vivo, which can predict prognosis, has remained elusive despite its relevance for treatment, screening recommendations and medicolegal practice. We developed a model that predicts the rate of in vivo tumour growth using a unique study cohort of BC patients who had two serial mammograms wherein the tumour, visible in the diagnostic mammogram, was missed in the first screen.

Methods
A serial mammography-derived in vivo growth rate (SM-INVIGOR) index was developed using tumour volumes from two serial mammograms and time interval between measurements. We then developed a machine learning-based surrogate model called Surr-INVIGOR using routinely assessed biomarkers to predict in vivo rate of tumour growth and extend the utility of this approach to a larger patient population. Surr-INVIGOR was validated using an independent cohort.

Results
SM-INVIGOR stratified discovery cohort patients into fast-growing versus slow-growing tumour subgroups, wherein patients with fast-growing tumours experienced poorer BC-specific survival. Our clinically relevant Surr-INVIGOR stratified tumours in the discovery cohort and was concordant with SM-INVIGOR. In the validation cohort, Surr-INVIGOR uncovered significant survival differences between patients with fast-growing and slow-growing tumours.

Conclusion
Our Surr-INVIGOR model predicts in vivo BC growth rate during the pre-diagnostic stage and offers several useful applications.

Citation

Bhattarai, S., Klimov, S., Aleskandarany, M. A., Burrell, H., Wormall, A., Green, A. R., …Aneja, R. (2019). Machine learning-based prediction of breast cancer growth rate in-vivo. British Journal of Cancer, 121, 497–504. https://doi.org/10.1038/s41416-019-0539-x

• Journal Article Type: Article
• Acceptance Date: Jun 27, 2019
• Online Publication Date: Aug 9, 2019
• Publication Date: Aug 9, 2019
• Deposit Date: Sep 13, 2019
• Publicly Available Date: Feb 10, 2020
• Journal: British Journal of Cancer
• Print ISSN: 0007-0920
• Electronic ISSN: 1532-1827
• Publisher: Cancer Research UK
• Peer Reviewed: Peer Reviewed
• Volume: 121
• Pages: 497–504
• DOI: https://doi.org/10.1038/s41416-019-0539-x
• Keywords: Breast cancer; growth rate; predictors; in-vivo; mammograms
• Public URL: https://nottingham-repository.worktribe.com/output/2289484
• Publisher URL: https://www.nature.com/articles/s41416-019-0539-x
• Additional Information: Received: 13 February 2019; Revised: 7 July 2019; Accepted: 11 July 2019; First Online: 9 August 2019; : The authors declare no competing interests.; : This study was approved by theNottingham Research Ethics Committee 2under the title “Development of a molecular genetic classification of breast cancer”. All samples from Nottingham used in this study were pseudoanonymised and collected prior to 2006 and therefore under the Human Tissue Act (UK, 2006), informed patient consent was not needed. Release of data was also pseudoanonymised as per Human Tissue Act regulations. We can declare that this study is complying with Helsinki declaration.; : The study wassupported by grants to R.A. from the National Cancer Institute at the National Institute of Health (U01 CA179671 and R01 CA169127).; : Not applicable; : All the data and results generated during the study can be provided upon journal request.; : This work is published under the standard license to publish agreement. After 12 months the work will become freely available and the license terms will switch to a Creative Commons Attribution 4.0 International (CC BY 4.0).