Skip to main content
SpringerLink
Log in

A Novel Machine-Learning Approach to Predict Recurrence After Resection of Colorectal Liver Metastases

  • Hepatobiliary Tumors
  • Published:
Annals of Surgical Oncology Aims and scope Submit manuscript

Abstract

Background

Surgical resection of hepatic metastases remains the only potentially curative treatment option for patients with colorectal liver metastases (CRLM). Widely adopted prognostic tools may oversimplify the impact of model parameters relative to long-term outcomes.

Methods

Patients with CRLM who underwent a hepatectomy between 2001 and 2018 were identified in an international, multi-institutional database. Bootstrap resampling methodology used in tandem with multivariable mixed-effects logistic regression analysis was applied to construct a prediction model that was validated and compared with scores proposed by Fong and Vauthey.

Results

Among 1406 patients who underwent hepatic resection of CRLM, 842 (59.9%) had recurrence. The full model (based on age, sex, primary tumor location, T stage, receipt of chemotherapy before hepatectomy, lymph node metastases, number of metastatic lesions in the liver, size of the largest hepatic metastases, carcinoembryonic antigen [CEA] level and KRAS status) had good discriminative ability to predict 1-year (area under the receiver operating curve [AUC], 0.693; 95% confidence interval [CI], 0.684–0.704), 3-year (AUC, 0.669; 95% CI, 0.661–0.677), and 5-year (AUC, 0.669; 95% CI, 0.661–0.679) risk of recurrence. Studies analyzing validation cohorts demonstrated similar model performance, with excellent model accuracy. In contrast, the AUCs for the Fong and Vauthey scores to predict 1-year recurrence were only 0.527 (95% CI, 0.514–0.538) and 0.525 (95% CI, 0.514–0.533), respectively. Similar trends were noted for 3- and 5-year recurrence.

Conclusion

The proposed clinical score, derived via machine learning, which included clinical characteristics and morphologic data, as well as information on KRAS status, accurately predicted recurrence after CRLM resection with good discrimination and prognostic ability.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3

Similar content being viewed by others

References

  1. Bray F, Ferlay J, Soerjomataram I, Siegel RL, Torre LA, Jemal A. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin. 2018;68:394–424.

    Article  Google Scholar 

  2. White A, Joseph D, Rim SH, Johnson CJ, Coleman MP, Allemani C. Colon cancer survival in the United States by race and stage (2001–2009): findings from the CONCORD-2 study. Cancer. 2017;123(Suppl 24):5014–36.

    Article  Google Scholar 

  3. Engstrand J, Nilsson H, Stromberg C, Jonas E, Freedman J. Colorectal cancer liver metastases: a population-based study on incidence, management, and survival. BMC Cancer. 2018;18:78.

    Article  Google Scholar 

  4. Sahara K, Tsilimigras DI, Paredes AZ, et al. Development and validation of a real-time mortality risk calculator before, during, and after hepatectomy: an analysis of the ACS NSQIP database. HPB Oxford. 2019.

  5. Fong Y, Fortner J, Sun RL, Brennan MF, Blumgart LH. Clinical score for predicting recurrence after hepatic resection for metastatic colorectal cancer: Analysis of 1001 consecutive cases. Ann Surg. 1999;230:309–18.

    Article  CAS  Google Scholar 

  6. Brudvik KW, Jones RP, Giuliante F, et al. RAS mutation clinical risk score to predict survival after resection of colorectal liver metastases. Ann Surg. 2019;269:120–6.

    Article  Google Scholar 

  7. Mann CD, Metcalfe MS, Leopardi LN, Maddern GJ. The clinical risk score: emerging as a reliable preoperative prognostic index in hepatectomy for colorectal metastases. Arch Surg. 2004;139:1168–72.

    Article  Google Scholar 

  8. Beamish P, Lemke M, Li J, et al. Validation of clinical risk score for colorectal liver metastases resected in a contemporary multicenter cohort. HPB Oxford. 2017;19:675–81.

    Article  Google Scholar 

  9. Ayez N, Lalmahomed ZS, van der Pool AE, et al. Is the clinical risk score for patients with colorectal liver metastases still useable in the era of effective neoadjuvant chemotherapy? Ann Surg Oncol. 2011;18:2757–63.

    Article  Google Scholar 

  10. Balachandran VP, Arora A, Gonen M, et al. A validated prognostic multigene expression assay for overall survival in resected colorectal cancer liver metastases. Clin Cancer Res. 2016;22:2575–82.

    Article  CAS  Google Scholar 

  11. Margonis GA, Kim Y, Spolverato G, et al. Association between specific mutations in KRAS codon 12 and colorectal liver metastasis. JAMA Surg. 2015;150:722–9.

    Article  Google Scholar 

  12. Winter D. Colorectal liver metastasis resection outcomes defined by molecular biology. JAMA Surg. 2015;150:729.

    Article  Google Scholar 

  13. Margonis GA, Buettner S, Andreatos N, et al. Association of BRAF mutations with survival and recurrence in surgically treated patients with metastatic colorectal liver cancer. JAMA Surg. 2018;153:e180996.

    Article  Google Scholar 

  14. Tsilimigras DI, Ntanasis-Stathopoulos I, Bagante F, et al. Clinical significance and prognostic relevance of KRAS, BRAF, PI3K, and TP53 genetic mutation analysis for resectable and unresectable colorectal liver metastases: a systematic review of the current evidence. Surg Oncol. 2018;27:280–8.

    Article  Google Scholar 

  15. Margonis GA, Spolverato G, Kim Y, Karagkounis G, Choti MA, Pawlik TM. Effect of KRAS mutation on long-term outcomes of patients undergoing hepatic resection for colorectal liver metastases. Ann Surg Oncol. 2015;22:4158–65.

    Article  Google Scholar 

  16. Moons KG, Altman DG, Reitsma JB, et al. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): explanation and elaboration. Ann Intern Med. 2015;162:W1–73.

    Article  Google Scholar 

  17. Oussoultzoglou E, Rosso E, Fuchshuber P, et al. Perioperative carcinoembryonic antigen measurements to predict curability after liver resection for colorectal metastases: a prospective study. Arch Surg. 2008;143:1150–8; discussion 1158–9.

    Article  Google Scholar 

  18. van Buuren S. Multiple imputation of discrete and continuous data by fully conditional specification. Stat Methods Med Res. 2007;16:219–42.

    Article  Google Scholar 

  19. Graham JW, Olchowski AE, Gilreath TD. How many imputations are really needed? Some practical clarifications of multiple imputation theory. Prev Sci. 2007;8:206–13.

    Article  Google Scholar 

  20. McCleary L. Using multiple imputation for analysis of incomplete data in clinical research. Nurs Res. 2002;51:339–43.

    Article  Google Scholar 

  21. Breiman L. Bagging predictors. Mach Learn. 1996;24:123–40.

    Google Scholar 

  22. American Cancer Society. Global cancer facts and figures, 2018. Retrieved 15 February 2020 at https://www.cancer.org/content/dam/cancer-org/research/cancer-facts-and-statistics/global-cancer-facts-and-figures/global-cancer-facts-and-figures-4th-edition.pdf.

  23. Adam R, Kitano Y. Multidisciplinary approach of liver metastases from colorectal cancer. Ann Gastroenterol Surg. 2019;3:50–6.

    Article  Google Scholar 

  24. Schreckenbach T, Malkomes P, Bechstein WO, Woeste G, Schnitzbauer AA, Ulrich F. The clinical relevance of the Fong and the Nordlinger scores in the era of effective neoadjuvant chemotherapy for colorectal liver metastasis. Surg Today. 2015;45:1527–34.

    Article  CAS  Google Scholar 

  25. Sasaki K, Margonis GA, Wilson A, et al. Prognostic implication of KRAS status after hepatectomy for colorectal liver metastases varies according to primary colorectal tumor location. Ann Surg Oncol. 2016;23:3736–43.

    Article  Google Scholar 

  26. Adam R, Delvart V, Pascal G, et al. Rescue surgery for unresectable colorectal liver metastases downstaged by chemotherapy: A model to predict long-term survival. Ann Surg. 2004;240:644–57.

    Article  Google Scholar 

  27. Margonis GA, Sasaki K, Gholami S, et al. Genetic and morphological evaluation (GAME) score for patients with colorectal liver metastases. Br J Surg. 2018;105:1210–20.

    Article  CAS  Google Scholar 

  28. Nordlinger B, Guiguet M, Vaillant JC, et al. Surgical resection of colorectal carcinoma metastases to the liver: a prognostic scoring system to improve case selection, based on 1568 patients. Association Francaise de Chirurgie. Cancer. 1996;77:1254–62.

    Article  CAS  Google Scholar 

  29. Konopke R, Kersting S, Distler M, et al. Prognostic factors and evaluation of a clinical score for predicting survival after resection of colorectal liver metastases. Liver Int. 2009;29:89–102.

    Article  Google Scholar 

  30. Dupre A, Rehman A, Jones RP, et al. Validation of clinical prognostic scores for patients treated with curative-intent for recurrent colorectal liver metastases. J Surg Oncol. 2018;117:1330–6.

    Article  Google Scholar 

  31. Li P, Stuart EA, Allison DB. Multiple imputation: a flexible tool for handling missing data. JAMA. 2015;314:1966–7.

    Article  CAS  Google Scholar 

  32. Schomaker M, Heumann C. Bootstrap inference when using multiple imputation. Stat Med. 2018;37:2252–66.

    Article  Google Scholar 

  33. Fakih MG. Metastatic colorectal cancer: current state and future directions. J Clin Oncol. 2015;33:1809–24.

    Article  CAS  Google Scholar 

  34. Pawlik TM, Schulick RD, Choti MA. Expanding criteria for resectability of colorectal liver metastases. Oncologist. 2008;13:51–64.

    Article  Google Scholar 

  35. Harrison XA, Donaldson L, Correa-Cano ME, et al. A brief introduction to mixed effects modelling and multi-model inference in ecology. PeerJ. 2018;6:e4794.

    Article  Google Scholar 

  36. Pavlou M, Ambler G, Seaman S, Omar RZ. A note on obtaining correct marginal predictions from a random intercepts model for binary outcomes. BMC Med Res Methodol. 2015;15:59.

    Article  Google Scholar 

  37. Sterne JA, White IR, Carlin JB, et al. Multiple imputation for missing data in epidemiological and clinical research: potential and pitfalls. BMJ. 2009;338:b2393.

    Article  Google Scholar 

  38. Schafer JL. Multiple imputation: a primer. Stat Methods Med Res. 1999;8:3–15.

    Article  CAS  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Surgery, Division of Surgical Oncology, The Ohio State University Wexner Medical Center and James Comprehensive Cancer Center, Columbus, OH, USA

    Anghela Z. Paredes MD, MS, J. Madison Hyer MS, Diamantis I. Tsilimigras MD, Amika Moro MD & Timothy M. Pawlik MD, MPH, MTS, PhD, FACS, FRACS (Hon.)

  2. Department of Surgery, University of Verona, Verona, Italy

    Fabio Bagante MD, Alfredo Guglielmi MD & Andrea Ruzzenente MD

  3. Department of Surgery, Fundeni Clinical Institute, Bucharest, Romania

    Sorin Alexandrescu MD

  4. Department of Surgery, Stanford University, Stanford, CA, USA

    Eleftherios A. Makris MD & George A. Poultsides MD

  5. Department of General Surgery, Cleveland Clinic Foundation, Cleveland, OH, USA

    Kazunari Sasaki MD & Federico N. Aucejo MD

  6. Department of Surgery, The Urban Meyer III and Shelley Meyer Chair for Cancer Research, The Ohio State University, Wexner Medical Center, Columbus, OH, USA

    Timothy M. Pawlik MD, MPH, MTS, PhD, FACS, FRACS (Hon.)

Authors
  1. Anghela Z. Paredes MD, MS
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. J. Madison Hyer MS
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Diamantis I. Tsilimigras MD
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Amika Moro MD
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Fabio Bagante MD
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Alfredo Guglielmi MD
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Andrea Ruzzenente MD
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Sorin Alexandrescu MD
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Eleftherios A. Makris MD
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. George A. Poultsides MD
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Kazunari Sasaki MD
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. Federico N. Aucejo MD
    View author publications

    You can also search for this author in PubMed Google Scholar

  13. Timothy M. Pawlik MD, MPH, MTS, PhD, FACS, FRACS (Hon.)
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Timothy M. Pawlik MD, MPH, MTS, PhD, FACS, FRACS (Hon.).

Ethics declarations

Disclosure

There are no conflicts of interest.

Additional information

Publisher's Note

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

Electronic supplementary material

Below is the link to the electronic supplementary material.

Fig. S1 Paredes–Pawlik online calculator (PDF 202 kb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Paredes, A.Z., Hyer, J.M., Tsilimigras, D.I. et al. A Novel Machine-Learning Approach to Predict Recurrence After Resection of Colorectal Liver Metastases. Ann Surg Oncol 27, 5139–5147 (2020). https://doi.org/10.1245/s10434-020-08991-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1245/s10434-020-08991-9

Search

Navigation