Advertisement

Predicting ipsilateral recurrence in women treated for ductal carcinoma in situ using machine learning and multivariable logistic regression models

  • Author Footnotes
    2 Both authors have contributed equally to this work.
    Leslie R. Lamb
    Footnotes
    2 Both authors have contributed equally to this work.
    Affiliations
    Division of Breast Imaging, Department of Radiology, Massachusetts General Hospital, 55 Fruit Street (WAC 240), Boston, MA 02114, USA
    Search for articles by this author
  • Author Footnotes
    2 Both authors have contributed equally to this work.
    Sarah Mercaldo
    Footnotes
    2 Both authors have contributed equally to this work.
    Affiliations
    Division of Breast Imaging, Department of Radiology, Massachusetts General Hospital, 55 Fruit Street (WAC 240), Boston, MA 02114, USA
    Search for articles by this author
  • Geunwon Kim
    Affiliations
    Division of Breast Imaging, Department of Radiology, Massachusetts General Hospital, 55 Fruit Street (WAC 240), Boston, MA 02114, USA

    Atrius Health, 133 Brookline Avenue, Boston, MA 02215, USA1
    Search for articles by this author
  • Keegan Hovis
    Affiliations
    Division of Breast Imaging, Department of Radiology, Massachusetts General Hospital, 55 Fruit Street (WAC 240), Boston, MA 02114, USA
    Search for articles by this author
  • Tawakalitu O. Oseni
    Affiliations
    Division of Surgical Oncology, Department of Surgery, Massachusetts General Hospital, 55 Fruit Street, Boston, MA 02114, USA
    Search for articles by this author
  • Manisha Bahl
    Correspondence
    Corresponding author at: Massachusetts General Hospital, 55 Fruit Street, WAC 240, Boston, MA 02114, USA.
    Affiliations
    Division of Breast Imaging, Department of Radiology, Massachusetts General Hospital, 55 Fruit Street (WAC 240), Boston, MA 02114, USA
    Search for articles by this author
  • Author Footnotes
    2 Both authors have contributed equally to this work.
Published:September 15, 2022DOI:https://doi.org/10.1016/j.clinimag.2022.08.023

      Highlights

      • Risk factors for ipsilateral breast cancer recurrence after treatment for ductal carcinoma in situ are young age and dense breast tissue.
      • Endocrine therapy for five or more years reduces ipsilateral breast cancer recurrence risk after treatment for ductal carcinoma in situ.
      • Traditional regression outperformed machine learning for predicting ipsilateral breast cancer recurrence.

      Abstract

      Purpose

      To develop machine learning (ML) and multivariable regression models to predict ipsilateral breast event (IBE) risk after ductal carcinoma in situ (DCIS) treatment.

      Methods

      A retrospective investigation was conducted of patients diagnosed with DCIS from 2007 to 2014 who were followed for a minimum of five years after treatment. Data about each patient were extracted from the medical records. Two ML models (penalized logistic regression and random forest) and a multivariable logistic regression model were developed to evaluate recurrence-related variables.

      Results

      650 women (mean age 56 years, range 27–87) underwent treatment for DCIS and were followed for at least five years after treatment (mean 8.0 years). 5.5% (n = 36) experienced an IBE. With multivariable analysis, the variables associated with higher IBE risk were younger age (adjusted odds ratio [aOR] 0.96, p = 0.02), dense breasts at mammography (aOR 3.02, p = 0.02), and < 5 years of endocrine therapy (aOR 4.48, p = 0.02). The multivariable regression model to predict IBE risk achieved an area under the receiver operating characteristic curve (AUC) of 0.75 (95% CI 0.67–0.84). The penalized logistic regression and random forest models achieved mean AUCs of 0.52 (95% CI 0.42–0.61) and 0.54 (95% CI 0.43–0.65), respectively.

      Conclusion

      Variables associated with higher IBE risk after DCIS treatment include younger age, dense breasts, and <5 years of adjuvant endocrine therapy. The multivariable logistic regression model attained the highest AUC (0.75), suggesting that regression models have a critical role in risk prediction for patients with DCIS.

      Abbreviations:

      aOR (adjusted odds ratio), AUC (area under the receiver operating characteristic curve), BCS (breast-conserving surgery), CI (confidence interval), DCIS (ductal carcinoma in situ), IBE (ipsilateral breast event), ML (machine learning)

      Keywords

      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'

      Subscribe:

      Subscribe to Clinical Imaging
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      References

        • Shehata M.
        • Grimm L.
        • Ballantyne N.
        • Lourenco A.
        • Demello L.R.
        • Kilgore M.R.
        • et al.
        Ductal carcinoma in situ: current concepts in biology, imaging, and treatment.
        J Breast Imaging. 2019; 1: 166-176
        • American Cancer Society
        Cancer facts and figures.
        • Gradishar W.J.
        • Anderson B.O.
        • Abraham J.
        • Aft R.
        • Agnese D.
        • Allison K.H.
        • et al.
        Breast cancer, version 3.2020, NCCN clinical practice guidelines in oncology.
        J Natl Compr Canc Netw. 2020; 18: 452-478
        • Solin L.J.
        Management of ductal carcinoma in situ (DCIS) of the breast: present approaches and future directions.
        Curr Oncol Rep. 2019; 21: 33
        • Silverstein M.J.
        • Lagios M.D.
        Choosing treatment for patients with ductal carcinoma in situ: fine tuning the University of Southern California/Van Nuys Prognostic Index.
        J Natl Cancer Inst Monogr. 2010; 2010: 193-196
        • Rudloff U.
        • Jacks L.M.
        • Goldberg J.I.
        • Wynveen C.A.
        • Brogi E.
        • Patil S.
        • et al.
        Nomogram for predicting the risk of local recurrence after breast-conserving surgery for ductal carcinoma in situ.
        J Clin Oncol. 2010; 28: 3762-3769
        • Bahl M.
        Artificial intelligence: a primer for breast imaging radiologists.
        J Breast Imaging. 2020; 2: 304-314
        • Hovis K.
        • Mercaldo S.
        • Kim G.
        • Lamb L.R.
        • Oseni T.O.
        • Bahl M.
        Contralateral breast cancer after curative-intent treatment for ductal carcinoma in situ: rate and associated clinicopathologial and imaging risk factors.
        Clin Imaging. 2022; 82: 179-192
        • Oseni T.O.
        • Smith B.L.
        • Lehman C.D.
        • Vijapura C.A.
        • Pinnamaneni N.
        • Bahl M.
        Do eligibility criteria for ductal carcinoma in situ (DCIS) active surveillance trials identify patients at low risk for upgrade to invasive carcinoma?.
        Ann Surg Oncol. 2020; 27: 4459-4465
        • Kim G.
        • Mikhael P.G.
        • Oseni T.O.
        • Bahl M.
        Ductal carcinoma in situ on digital mammography versus digital breast tomosynthesis: rates and predictors of pathologic upgrade.
        Eur Radiol. 2020; 30: 6089-6098
        • Lamb L.R.
        • Oseni T.O.
        • Lehman C.D.
        • Bahl M.
        Pre-operative MRI in patients with ductal carcinoma in situ: is MRI useful for identifying additional disease?.
        Eur J Radiol. 2020; 129109130
        • Lamb L.R.
        • Mercaldo S.
        • Oseni T.O.
        • Bahl M.
        Predictors of reexcision following breast-conserving surgery for ductal carcinoma in situ.
        Ann Surg Oncol. 2021; 28: 1390-1397
        • Lamb L.R.
        • Kim G.
        • Oseni T.O.
        • Bahl M.
        Noncalcified ductal carcinoma in situ (DCIS): rate and predictors of upgrade to invasive carcinoma.
        Acad Radiol. 2021; 28: e71-e76
        • Venkatesh S.L.
        • Oseni T.O.
        • Bahl M.
        Symptomatic ductal carcinoma in situ (DCIS): upstaging risk and predictors.
        Clin Imaging. 2020; 73: 101-107
        • Lamb L.R.
        • Lehman C.D.
        • Oseni T.O.
        • Bahl M.
        Ductal carcinoma in situ (DCIS) at breast MRI: predictors of upgrade to invasive carcinoma.
        Acad Radiol. 2020; 27: 1394-1399
        • Sprague B.L.
        • Vacek P.M.
        • Herschorn S.D.
        • James T.A.
        • Geller B.M.
        • Trentham-Dietz A.
        • et al.
        Time-varying risks of second events following a DCIS diagnosis in the population-based Vermont DCIS cohort.
        Breast Cancer Res Treat. 2019; 174: 227-235
        • Subhedar P.
        • Olcese C.
        • Patil S.
        • Morrow M.
        • Van Zee K.J.
        Decreasing recurrence rates for ductal carcinoma in situ: analysis of 2996 women treated with breast-conserving surgery over 30 years.
        Ann Surg Oncol. 2015; 22: 3273-3281
        • Van Zee K.J.
        • Liberman L.
        • Samli B.
        • Tran K.N.
        • McCormick B.
        • Petrek J.A.
        • et al.
        Long term follow-up of women with ductal carcinoma in situ treated with breast-conserving surgery: the effect of age.
        Cancer. 1999; 86: 1757-1767
        • Vicini F.A.
        • Kestin L.L.
        • Goldstein N.S.
        • Chen P.Y.
        • Pettinga J.
        • Frazier R.C.
        • et al.
        Impact of young age on outcome in patients with ductal carcinoma-in-situ treated with breast-conserving therapy.
        J Clin Oncol. 2000; 18: 296-306
        • Habel L.A.
        • Dignam J.J.
        • Land S.R.
        • Salane M.
        • Capra A.M.
        • Julian T.B.
        Mammographic density and breast cancer after ductal carcinoma in situ.
        J Natl Cancer Inst. 2004; 96: 1467-1472
        • Habel L.A.
        • Capra A.M.
        • Achacoso N.S.
        • Janga A.
        • Acton L.
        • Puligandla B.
        • et al.
        Mammographic density and risk of second breast cancer after ductal carcinoma in situ.
        Cancer Epidemiol Biomarkers Prev. 2010; 19: 2488-2495
        • Warnberg F.
        • Garmo H.
        • Emdin S.
        • Hedberg V.
        • Adwall L.
        • Sandelin K.
        • et al.
        Effect of radiotherapy after breast-conserving surgery for ductal carcinoma in situ: 20 years follow-up in the randomized SweDCIS Trial.
        J Clin Oncol. 2014; 32: 3613-3618
        • Cronin P.A.
        • Olcese C.
        • Patil S.
        • Morrow M.
        • Van Zee K.J.
        Impact of age on risk of recurrence of ductal carcinoma in situ: outcomes of 2996 women treated with breast-conserving surgery over 30 years.
        Ann Surg Oncol. 2016; 23: 2816-2824
        • Monticciolo D.L.
        • Newell M.S.
        • Moy L.
        • Niell B.
        • Monsees B.
        • Sickles E.A.
        Breast cancer screening in women at higher-than-average risk: recommendations from the ACR.
        J Am Coll Radiol. 2018; 15: 408-414
        • Cuzick J.
        • Sestak I.
        • Pinder S.E.
        • Ellis I.O.
        • Forsyth S.
        • Bundred N.J.
        • et al.
        Effect of tamoxifen and radiotherapy in women with locally excised ductal carcinoma in situ: long-term results from the UK/ANZ DCIS trial.
        Lancet Oncol. 2011; 12: 21-29
        • Fisher B.
        • Dignam J.
        • Wolmark N.
        • Wickerham D.L.
        • Fisher E.R.
        • Mamounas E.
        • et al.
        Tamoxifen in treatment of intraductal breast cancer: National Surgical Adjuvant Breast and Bowel Project B-24 randomised controlled trial.
        Lancet. 1999; 353: 1993-2000
        • Wapnir I.L.
        • Dignam J.J.
        • Fisher B.
        • Mamounas E.P.
        • Anderson S.J.
        • Julian T.B.
        • et al.
        Long-term outcomes of invasive ipsilateral breast tumor recurrences after lumpectomy in NSABP B-17 and B-24 randomized clinical trials for DCIS.
        J Natl Cancer Inst. 2011; 103: 478-488
        • Mandrekar J.N.
        Receiver operating characteristic curve in diagnostic test assessment.
        J Thorac Oncol. 2010; 5: 1315-1316
        • Christodoulou E.
        • Ma J.
        • Collins G.S.
        • Steyerberg E.W.
        • Verbakel J.Y.
        • Van Calster B.
        A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models.
        J Clin Epidemiol. 2019; 110: 12-22
        • Lynam A.L.
        • Dennis J.M.
        • Owen K.R.
        • Oram R.A.
        • Jones A.G.
        • Shields B.M.
        • et al.
        Logistic regression has similar performance to optimised machine learning algorithms in a clinical setting: application to the discrimination between type 1 and type 2 diabetes in young adults.
        Diagn Progn Res. 2020; 4: 6
        • Liu Y.
        • Chen P.C.
        • Krause J.
        • Peng L.
        How to read articles that use machine learning: users' guides to the medical literature.
        JAMA. 2019; 322: 1806-1816