Skip to main content

Machine-Learning Provides Patient-Specific Prediction of Metastatic Risk Based on Innovative, Mechanobiology Assay

Abstract

Cancer mortality is mostly related to metastasis. Metastasis is currently prognosed via histopathology, disease-statistics, or genetics; those are potentially inaccurate, not rapidly available and require known markers. We had developed a rapid (~ 2 h) mechanobiology-based approach to provide early prognosis of the clinical likelihood for metastasis. Specifically, invasive cell-subsets seeded on impenetrable, physiological-stiffness polyacrylamide gels forcefully indent the gels, while non-invasive/benign cells do not. The number of indenting cells and their attained depths, the mechanical invasiveness, accurately define the metastatic risk of tumors and cell-lines. Utilizing our experimental database, we compare the capacity of several machine learning models to predict the metastatic risk. Models underwent supervised training on individual experiments using classification from literature and commercial-sources for established cell-lines and clinical histopathology reports for tumor samples. We evaluated 2-class models, separating invasive/non-invasive (e.g. benign) samples, and obtained sensitivity and specificity of 0.92 and 1, respectively; this surpasses other works. We also introduce a novel approach, using 5-class models (i.e. normal, benign, cancer-metastatic-non/low/high) that provided average sensitivity and specificity of 0.69 and 0.91. Combining our rapid, mechanical invasiveness assay with machine learning classification can provide accurate and early prognosis of metastatic risk, to support choice of treatments and disease management.

This is a preview of subscription content, access via your institution.

Figure 1
Figure 2
Figure 3

References

  1. 1.

    Albala, D., M. S. Manak, J. S. Varsanik, H. H. Rashid, V. Mouraviev, S. M. Zappala, E. Ette, N. Kella, K. M. Rieger-Christ, G. R. Sant, and A. C. Chander. Clinical proof-of-concept of a novel platform utilizing biopsy-derived live single cells, phenotypic biomarkers, and machine learning toward a precision risk stratification test for prostate cancer grade groups 1 and 2 (Gleason 3 + 3 and 3 + 4). Urology 124:198–206, 2019.

    Article  Google Scholar 

  2. 2.

    Alvarez-Elizondo, M. B., and D. Weihs. Cell-gel mechanical interactions as an approach to rapidly and quantitatively reveal invasive subpopulations of metastatic cancer cells. Tissue Eng. Part C Methods 23:180–187, 2017.

    CAS  Article  Google Scholar 

  3. 3.

    Bur, A. M., A. Holcomb, S. Goodwin, J. Woodroof, O. Karadaghy, Y. Shnayder, K. Kakarala, J. Brant, and M. Shew. Machine learning to predict occult nodal metastasis in early oral squamous cell carcinoma. Oral Oncol. 92:20–25, 2019.

    Article  Google Scholar 

  4. 4.

    Cross, S. E., Y. S. Jin, J. Rao, and J. K. Gimzewski. Nanomechanical analysis of cells from cancer patients. Nat. Nanotechnol. 2:780–783, 2007.

    CAS  Article  Google Scholar 

  5. 5.

    Dvir, L., R. Nissim, M. B. Alvarez-Elizondo, and D. Weihs. Quantitative measures to reveal coordinated cytoskeleton-nucleus reorganization during in vitro invasion of cancer cells. New J. Phys. 17:043010, 2015.

    Article  Google Scholar 

  6. 6.

    Friedl, P., and K. Wolf. Plasticity of cell migration: a multiscale tuning model. J. Cell Biol. 188:11–19, 2010.

    CAS  Article  Google Scholar 

  7. 7.

    Fu, B., P. Liu, J. Lin, L. Deng, K. Hu, and H. Zheng. Predicting invasive disease-free survival for early stage breast cancer patients using follow-up clinical data. IEEE Trans. Biomed. Eng. 66:2053–2064, 2019.

    Article  Google Scholar 

  8. 8.

    Gal, N., D. Lechtman-Goldstein, and D. Weihs. Particle tracking in living cells: a review of the mean square displacement method and beyond. Rheol. Acta 52:425–443, 2013.

    CAS  Article  Google Scholar 

  9. 9.

    Garcea, G., C. P. Neal, C. J. Pattenden, W. P. Steward, and D. P. Berry. Molecular prognostic markers in pancreatic cancer: a systematic review. Eur. J. Cancer 41:2213–2236, 2005.

    CAS  Article  Google Scholar 

  10. 10.

    Giuliano, A. E., K. V. Ballman, L. McCall, P. D. Beitsch, M. B. Brennan, P. R. Kelemen, D. W. Ollila, N. M. Hansen, P. W. Whitworth, P. W. Blumencranz, A. M. Leitch, S. Saha, K. K. Hunt, and M. Morrow. Effect of axillary dissection vs no axillary dissection on 10-year overall survival among women with invasive breast cancer and sentinel node metastasis: the ACOSOG Z0011 (Alliance) randomized clinical trial. JAMA J. Am. Med. Assoc. 318:918–926, 2017.

    Article  Google Scholar 

  11. 11.

    Guck, J., S. Schinkinger, B. Lincoln, F. Wottawah, S. Ebert, M. Romeyke, D. Lenz, H. M. Erickson, R. Ananthakrishnan, D. Mitchell, J. Kas, S. Ulvick, and C. Bilby. Optical deformability as an inherent cell marker for testing malignant transformation and metastatic competence. Biophys. J. 88:3689–3698, 2005.

    CAS  Article  Google Scholar 

  12. 12.

    Katz, S. J., and M. Morrow. Addressing overtreatment in breast cancer. Cancer 119:3584–3588, 2013.

    Article  Google Scholar 

  13. 13.

    Kraning-Rush, C. M., J. P. Califano, and C. A. Reinhart-King. Cellular traction stresses increase with increasing metastatic potential. PLoS ONE 7:e32572, 2012.

    CAS  Article  Google Scholar 

  14. 14.

    Kristal-Muscal, R., L. Dvir, and D. Weihs. Metastatic cancer cells tenaciously indent impenetrable, soft substrates. New J. Phys. 15:035022, 2013.

    CAS  Article  Google Scholar 

  15. 15.

    Massalha, S., and D. Weihs. Metastatic breast cancer cells adhere strongly on varying stiffness substrates, initially without adjusting their morphology. Biomech. Model. Mechanobiol. 16:961–970, 2017.

    Article  Google Scholar 

  16. 16.

    Maulik, U., A. Mukhopadhyay, and D. Chakraborty. Gene-expression-based cancer subtypes prediction through feature selection and transductive SVM. IEEE Trans. Biomed. Eng. 60:1111–1117, 2013.

    Article  Google Scholar 

  17. 17.

    McGuire, William L. G. M. C. prognostic factors and treatment decisions in axillary-node-negative breast cancer. N. Engl. J. Med. 326:1756–1761, 1992.

    CAS  Article  Google Scholar 

  18. 18.

    Merkher, Y., Y. Horesh, Z. Abramov, G. Shleifer, O. Ben-Ishay, Y. Kluger, and D. Weihs. Rapid cancer diagnosis and early prognosis of metastatic risk based on mechanical invasiveness of sampled cells. Ann. Biomed. Eng. 2020. https://doi.org/10.1007/s10439-020-02547-4.

    Article  PubMed  Google Scholar 

  19. 19.

    Merkher, Y., and D. Weihs. Proximity of metastatic cells enhances their mechanobiological invasiveness. Ann. Biomed. Eng. 45:1399–1406, 2017.

    Article  Google Scholar 

  20. 20.

    Molnar, B., F. Sipos, O. Galamb, and Z. Tulassay. Molecular detection of circulating cancer cells role in diagnosis, prognosis and follow-up of colon cancer patients. Dig. Dis. 21:320–325, 2003.

    Article  Google Scholar 

  21. 21.

    Nicolini, A., P. Ferrari, and M. J. Duffy. Prognostic and predictive biomarkers in breast cancer: past, present and future. Semin. Cancer Biol. 52:56–73, 2018.

    CAS  Article  Google Scholar 

  22. 22.

    Nicolò, C., C. Périer, M. Prague, C. Bellera, G. MacGrogan, O. Saut, and S. Benzekry. Machine learning and mechanistic modeling for prediction of metastatic relapse in early-stage breast cancer. JCO Clin. Cancer Inform. 4:259–274, 2020. https://doi.org/10.1200/cci.19.00133.

    Article  PubMed  Google Scholar 

  23. 23.

    Osman, M. H. Predicting survival of pancreatic cancer using supervised machine learning. Ann. Oncol. 29:viii205–viii270, 2018.

    Google Scholar 

  24. 24.

    Pedregosa, F., G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and É. Duchesnay. Scikit-learn: machine learning in python. J. Mach. Learn. Res. 12:2825–2830, 2011.

    Google Scholar 

  25. 25.

    Siegel, R. L., K. D. Miller, and A. Jemal. Cancer statistics, 2019. Cancer J. Clin. 69:7–34, 2019.

    Article  Google Scholar 

  26. 26.

    Smith, R. A., K. S. Andrews, D. Brooks, S. A. Fedewa, D. Manassaram-Baptiste, D. Saslow, O. W. Brawley, and R. C. Wender. Cancer screening in the United States, 2018: a review of current American Cancer Society guidelines and current issues in cancer screening. Cancer J. Clin. 68:297–316, 2018.

    Article  Google Scholar 

  27. 27.

    Su, P.-J., Y.-A. Fang, Y.-C. Chang, Y.-C. Kuo, and Y.-C. Lin. Establish a predictive model for high-risk de novo metastatic prostate cancer patients by machine learning. J. Glob. Oncol. 5:13–13, 2019.

    Article  Google Scholar 

  28. 28.

    Swaminathan, V., K. Mythreye, E. T. O’Brien, A. Berchuck, G. C. Blobe, and R. Superfine. Mechanical stiffness grades metastatic potential in patient tumor cells and in cancer cell lines. Cancer Res. 71:5075–5080, 2011.

    CAS  Article  Google Scholar 

  29. 29.

    Van Rossum, G., and F. L. Drake. Python 3 Reference Manual. Scotts Valley: CreateSpace, 2009.

    Google Scholar 

  30. 30.

    Weigelt, B., J. L. Peterse, and L. J. van ’t Veer. Breast cancer metastasis: markers and models. Nat. Rev. Cancer 5:591–602, 2005.

    CAS  Article  Google Scholar 

  31. 31.

    Weihs, D., and Y. Merkher. A device and method for determining cell indention activity, Patent pending. Patent: PCT/IL2019/050463, 2019.

  32. 32.

    Welch, H. G., and W. C. Black. Overdiagnosis in cancer. JNCI J. Natl. Cancer Inst. 102:605–613, 2010.

    Article  Google Scholar 

  33. 33.

    Yankaskas, C. L., K. N. Thompson, C. D. Paul, M. I. Vitolo, P. Mistriotis, A. Mahendra, V. K. Bajpai, D. J. Shea, K. M. Manto, A. C. Chai, N. Varadarajan, A. Kontrogianni-Konstantopoulos, S. S. Martin, and K. Konstantopoulos. A microfluidic assay for the quantification of the metastatic propensity of breast cancer specimens. Nat. Biomed. Eng. 3:452–465, 2019.

    CAS  Article  Google Scholar 

Download references

Acknowledgments

The work was partially funded by the Israeli Ministry of Science and Technology (MOST) Medical Devices Program (Grant no. 3-17427), the Polak Fund for Applied Research, the Ber-Lehmsdorf Foundation, and the Gerald O. Mann Charitable Foundation.

Conflict of interest

The authors declare no conflicts of interest.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Daphne Weihs.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Associate Editor Joel Stitzel oversaw the review of this article.

Supplementary information

Below is the link to the electronic supplementary material.

Electronic supplementary material 1 (DOCX 913 kb)

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Rozen, R., Weihs, D. Machine-Learning Provides Patient-Specific Prediction of Metastatic Risk Based on Innovative, Mechanobiology Assay. Ann Biomed Eng 49, 1774–1783 (2021). https://doi.org/10.1007/s10439-020-02720-9

Download citation

Keywords

  • Classification models
  • Metastasis prediction
  • Metastasis prognosis
  • Machine learning models