Advertisement

Development of a machine learning algorithm to predict complications of total laparoscopic anterior resection and natural orifice specimen extraction surgery in rectal cancer

  • Author Footnotes
    1 Ran Wei and Xu Guan equally contributed as first authors.
    Ran Wei
    Footnotes
    1 Ran Wei and Xu Guan equally contributed as first authors.
    Affiliations
    Department of Colorectal Surgery, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China
    Search for articles by this author
  • Author Footnotes
    1 Ran Wei and Xu Guan equally contributed as first authors.
    Xu Guan
    Footnotes
    1 Ran Wei and Xu Guan equally contributed as first authors.
    Affiliations
    Department of Colorectal Surgery, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China
    Search for articles by this author
  • Enrui Liu
    Affiliations
    Department of Colorectal Surgery, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China
    Search for articles by this author
  • Weiyuan Zhang
    Affiliations
    Department of Colorectal Surgery, The Second Affiliated Hospital of Harbin Medical University, Harbin, China
    Search for articles by this author
  • Jingfang Lv
    Affiliations
    Department of Colorectal Surgery, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China
    Search for articles by this author
  • Haiyang Huang
    Affiliations
    Department of Colorectal Surgery, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China
    Search for articles by this author
  • Zhixun Zhao
    Affiliations
    Department of Colorectal Surgery, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China
    Search for articles by this author
  • Haipeng Chen
    Affiliations
    Department of Colorectal Surgery, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China
    Search for articles by this author
  • Zheng Liu
    Affiliations
    Department of Colorectal Surgery, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China
    Search for articles by this author
  • Zheng Jiang
    Correspondence
    Corresponding author.
    Affiliations
    Department of Colorectal Surgery, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China
    Search for articles by this author
  • Xishan Wang
    Correspondence
    Corresponding author.
    Affiliations
    Department of Colorectal Surgery, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China
    Search for articles by this author
  • Author Footnotes
    1 Ran Wei and Xu Guan equally contributed as first authors.
Published:January 09, 2023DOI:https://doi.org/10.1016/j.ejso.2023.01.007

      Abstract

      Background

      Total laparoscopic anterior resection (tLAR) and natural orifice specimen extraction surgery (NOSES) has been widely adopted in the treatment of rectal cancer (RC). However, no study has been performed to predict the short-term outcomes of tLAR using machine learning algorithms to analyze a national cohort.

      Methods

      Data from consecutive RC patients who underwent tLAR were collected from the China NOSES Database (CNDB). The random forest (RF), extreme gradient boosting (XGBoost), support vector machine (SVM), deep neural network (DNN), logistic regression (LR) and K-nearest neighbor (KNN) algorithms were used to develop risk models to predict short-term complications of tLAR. The area under the receiver operating characteristic curve (AUROC), Gini coefficient, specificity and sensitivity were calculated to assess the performance of each risk model. The selected factors from the models were evaluated by relative importance.

      Results

      A total of 4313 RC patients were identified, and 667 patients (15.5%) developed postoperative complications. The machine learning model of XGBoost showed more promising results in the prediction of complication than other models (AUROC 0.90, P < 0.001). The performance was similar when internal and external validation was used. In the XGBoost model, the top four influential factors were the distance from the lower edge of the tumor to the anus, age at diagnosis, surgical time and comorbidities. In risk stratification analysis, the rate of postoperative complications in the high-risk group was significantly higher than in the medium- and low-risk groups (P < 0.001).

      Conclusion

      The machine learning model shows potential benefits in predicting the risk of complications in RC patients after tLAR. This novel approach can provide reliable individual information for surgical treatment recommendations.

      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 European Journal of Surgical Oncology
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      References

        • Park J.S.
        • Kang H.
        • Park S.Y.
        • Kim H.J.
        • Lee I.T.
        • Choi G.S.
        Long-term outcomes after Natural Orifice Specimen Extraction versus conventional laparoscopy-assisted surgery for rectal cancer: a matched case-control study.
        Annals of surgical treatment and research. 2018; 94 (Epub 2018/01/16) (PubMed PMID: 29333423; PubMed Central PMCID: PMCPMC5765275): 26-35https://doi.org/10.4174/astr.2018.94.1.26
        • Chang S.C.
        • Chen H.C.
        • Chen Y.C.
        • Ke T.W.
        • Tsai Y.Y.
        • Wang H.M.
        • et al.
        Long-term oncologic outcomes of laparoscopic anterior resections for cancer with natural orifice versus conventional specimen extraction: a case-control study.
        Dis Colon Rectum. 2020; 63 (Epub 2020/07/22) (PubMed PMID: 32692072): 1071-1079https://doi.org/10.1097/dcr.0000000000001622
        • Kim H.J.
        • Choi G.S.
        • Park J.S.
        • Park S.Y.
        • Ryuk J.P.
        • Yoon S.H.
        Transvaginal specimen extraction versus conventional minilaparotomy after laparoscopic anterior resection for colorectal cancer: mid-term results of a case-matched study.
        Surg Endosc. 2014; 28 (Epub 2014/02/26) (PubMed PMID: 24566749): 2342-2348https://doi.org/10.1007/s00464-014-3466-1
        • Lu Z.
        • Chen H.
        • Zhang M.
        • Guan X.
        • Zhao Z.
        • Jiang Z.
        • et al.
        Safety and survival outcomes of transanal natural orifice specimen extraction using prolapsing technique for patients with middle- to low-rectal cancer.
        Chinese journal of cancer research = Chung-kuo yen cheng yen chiu. 2020; 32 (Epub 2020/11/24) (PubMed PMID: 33223760; PubMed Central PMCID: PMCPMC7666784): 654-664https://doi.org/10.21147/j.issn.1000-9604.2020.05.10
        • Cheng C.C.
        • Hsu Y.R.
        • Chern Y.J.
        • Tsai W.S.
        • Hung H.Y.
        • Liao C.K.
        • et al.
        Minimally invasive right colectomy with transrectal natural orifice extraction: could this be the next step forward?.
        Tech Coloproctol. 2020; 24 (Epub 2020/07/08) (PubMed PMID: 32632708; PubMed Central PMCID: PMCPMC7536150): 1197-1205https://doi.org/10.1007/s10151-020-02282-x
        • Wang Q.
        • Xia D.
        • Bai W.
        • Wang E.
        • Sun J.
        • Huang M.
        • et al.
        Development of a prognostic score for recommended TACE candidates with hepatocellular carcinoma: a multicentre observational study.
        J Hepatol. 2019; 70 (Epub 2019/01/21) (PubMed PMID: 30660709): 893-903https://doi.org/10.1016/j.jhep.2019.01.013
        • van den Bosch T.
        • Warps A.K.
        • de Nerée Tot Babberich M.P.M.
        • Stamm C.
        • Geerts B.F.
        • Vermeulen L.
        • et al.
        Predictors of 30-day mortality among Dutch patients undergoing colorectal cancer surgery, 2011-2016.
        JAMA Netw Open. 2021; 4 (Epub 2021/04/27) (PubMed PMID: 33900400; PubMed Central PMCID: PMCPMC8076964 employee of Pacmed outside the submitted work. Dr Geerts reported holding shares in Healthplus.ai BV and stock options in Sensulin LLC; serving as an unpaid advisor to Mode Sensors; and serving as a paid consultant for and receiving research grants from Edwards Lifesciences LLC, Philips NV, and NLC BV. Dr Tanis reported receiving grants from LifeCell and Allergan outside the submitted work. No other disclosures were reported.)e217737https://doi.org/10.1001/jamanetworkopen.2021.7737
        • Guan X.
        • Ma C.X.
        • Quan J.C.
        • Li S.
        • Zhao Z.X.
        • Chen H.P.
        • et al.
        A clinical model to predict the risk of synchronous bone metastasis in newly diagnosed colorectal cancer: a population-based study.
        BMC Cancer. 2019; 19 (Epub 2019/07/19) (PubMed PMID: 31315606; PubMed Central PMCID: PMCPMC6637577): 704https://doi.org/10.1186/s12885-019-5912-x
        • He C.
        • Sun S.
        • Zhang Y.
        • Lin X.
        • Li S.
        Score for the overall survival probability of patients with pancreatic adenocarcinoma of the body and tail after surgery: a novel nomogram-based risk assessment.
        Front Oncol. 2020; 10 (Epub 2020/05/20) (PubMed PMID: 32426278; PubMed Central PMCID: PMCPMC7212341): 590https://doi.org/10.3389/fonc.2020.00590
        • Guan X.
        • Hu X.
        • Jiang Z.
        • Wei Y.
        • Sun D.
        • Wu M.
        • et al.
        Short-term and oncological outcomes of natural orifice specimen extraction surgery (NOSES) for colorectal cancer in China: a national database study of 5055 patients.
        Sci Bull. 2022; 67: 1331-1334https://doi.org/10.1016/j.scib.2022.05.014
        • Guan X.
        • Liu Z.
        • Longo A.
        • Cai J.C.
        • Tzu-Liang Chen W.
        • Chen L.C.
        • et al.
        International consensus on natural orifice specimen extraction surgery (NOSES) for colorectal cancer.
        Gastroenterology report. 2019; 7 (Epub 2019/02/23) (PubMed PMID: 30792863; PubMed Central PMCID: PMCPMC6375350): 24-31https://doi.org/10.1093/gastro/goy055
        • Xie F.
        • Ong M.E.H.
        • Liew J.
        • Tan K.B.K.
        • Ho A.F.W.
        • Nadarajan G.D.
        • et al.
        Development and assessment of an interpretable machine learning triage tool for estimating mortality after emergency admissions.
        JAMA Netw Open. 2021; 4 (Epub 2021/08/28) (PubMed PMID: 34448870; PubMed Central PMCID: PMCPMC8397930 method of determining a risk score for triage (US 13/791,764 US 2014/0257122 A1) and a patent for method of predicting acute cardiopulmonary events and survivability of a patient (US 8668644 US 8,932,220 B2). Dr Liu reported receiving grants from Duke–National University of Singapore Medical School, the Estate of Tan Sri Khoo Teck Puat, and Singapore National Medical Research Council during the conduct of the study. No other disclosures were reported)e2118467https://doi.org/10.1001/jamanetworkopen.2021.18467
        • Azur M.J.
        • Stuart E.A.
        • Frangakis C.
        • Leaf P.J.
        Multiple imputation by chained equations: what is it and how does it work?.
        Int J Methods Psychiatr Res. 2011; 20 (Epub 2011/04/19) (PubMed PMID: 21499542; PubMed Central PMCID: PMCPMC3074241): 40-49https://doi.org/10.1002/mpr.329
        • Jiang Y.
        • Xie J.
        • Han Z.
        • Liu W.
        • Xi S.
        • Huang L.
        • et al.
        Immunomarker support vector machine classifier for prediction of gastric cancer survival and adjuvant chemotherapeutic benefit.
        Clin Cancer Res : an official journal of the American Association for Cancer Research. 2018; 24 (Epub 2018/07/26) (PubMed PMID: 30042208): 5574-5584https://doi.org/10.1158/1078-0432.ccr-18-0848
        • Scanlon L.A.
        • O'Hara C.
        • Garbett A.
        • Barker-Hewitt M.
        • Barriuso J.
        Developing an agnostic risk prediction model for early AKI detection in cancer patients.
        Cancers. 2021; 13 (Epub 2021/08/28) (PubMed PMID: 34439336; PubMed Central PMCID: PMCPMC8393922)https://doi.org/10.3390/cancers13164182
        • Liu W.C.
        • Li Z.Q.
        • Luo Z.W.
        • Liao W.J.
        • Liu Z.L.
        • Liu J.M.
        Machine learning for the prediction of bone metastasis in patients with newly diagnosed thyroid cancer.
        Cancer Med. 2021; 10 (Epub 2021/03/13) (PubMed PMID: 33709570; PubMed Central PMCID: PMCPMC8026946): 2802-2811https://doi.org/10.1002/cam4.3776
        • Breiman
        Random forests.
        Mach Learn. 2001; 45 (2001): 5-32
        • Peter Bühlmann
        • Torsten Hothorn.
        Boosting algorithms: regularization, prediction and model fitting[J].
        Stat Sci. 2007; 22: 477-505
        • Ben-Hur A.
        • Horn D.
        • Siegelmann H.T.
        • Vapnik V.
        [IEEE comput. Soc 15th international conference on pattern recognition - barcelona, Spain (3-7 sept 2000)] proceedings 15th international conference on pattern recognition.
        ICPR-2000 - A support vector clustering method. 2000; 2: 724-727
        • Jaewook L.
        • Daewon L.
        An improved cluster labeling method for support vector clustering.
        IEEE Trans Pattern Anal Mach Intell. 2005; 27 (Epub 2005/03/08) (PubMed PMID: 15747800): 461-464https://doi.org/10.1109/tpami.2005.47
        • Matheny M.E.
        • Ricket I.
        • Goodrich C.A.
        • Shah R.U.
        • Stabler M.E.
        • Perkins A.M.
        • et al.
        Development of electronic health record-based prediction models for 30-day readmission risk among patients hospitalized for acute myocardial infarction.
        JAMA Netw Open. 2021; 4 (Epub 2021/01/30) (PubMed PMID: 33512518; PubMed Central PMCID: PMCPMC7846941 National Institutes of Health (NIH) National Heart, Lung, and Blood Institute (NHLBI) during the conduct of the study. Dr Shah reported receiving grants from the NIH/NHLBI, personal fees from the American College of Cardiology, and other from Women As One outside the submitted work. Dr Stabler reported receiving grants from the NIH during the conduct of the study. Dr Dorn reported receiving grants from the NIH during the conduct of the study. Dr Bray reported receiving grants from the NIH during the conduct of the study. Dr Chapman reported receiving grants from NIH during the conduct of the study, personal fees from IBM consultancy, and nonfinancial support from the Health Fidelity scientific board outside the submitted work. No other disclosures were reported)e2035782https://doi.org/10.1001/jamanetworkopen.2020.35782
        • Steyerberg E.W.
        Validation in prediction research: the waste by data splitting.
        J Clin Epidemiol. 2018; 103 (Epub 2018/08/01) (PubMed PMID: 30063954): 131-133https://doi.org/10.1016/j.jclinepi.2018.07.010
        • Shung D.L.
        • Au B.
        • Taylor R.A.
        • Tay J.K.
        • Laursen S.B.
        • Stanley A.J.
        • et al.
        Validation of a machine learning model that outperforms clinical risk scoring systems for upper gastrointestinal bleeding.
        Gastroenterology. 2020; 158 (Epub 2019/09/29) (PubMed PMID: 31562847; PubMed Central PMCID: PMCPMC7004228): 160-167https://doi.org/10.1053/j.gastro.2019.09.009
        • Lundberg S.M.
        • Erion G.G.
        • Lee S.I.
        Consistent individualized feature attribution for tree ensembles.
        2018
        • Bratzler D.W.
        • Houck P.M.
        Antimicrobial prophylaxis for surgery: an advisory statement from the national surgical infection prevention Project.
        Clin Infect Dis : an official publication of the Infectious Diseases Society of America. 2004; 38 (Epub 2004/07/01) (PubMed PMID: 15227616): 1706-1715https://doi.org/10.1086/421095
        • Xue B.
        • Li D.
        • Lu C.
        • King C.R.
        • Wildes T.
        • Avidan M.S.
        • et al.
        Use of machine learning to develop and evaluate models using preoperative and intraoperative data to identify risks of postoperative complications.
        JAMA Netw Open. 2021; 4 (Epub 2021/03/31) (PubMed PMID: 33783520; PubMed Central PMCID: PMCPMC8010590 National Institute of General Medical Sciences during the conduct of the study. Dr Wildes reported receiving grants from the National Institute of Nursing Research during the conduct of the study. Dr Kannampallil reported receiving personal fees from Pfizer Inc outside the submitted work. No other disclosures were reported)e212240https://doi.org/10.1001/jamanetworkopen.2021.2240
        • Merath K.
        • Hyer J.M.
        • Mehta R.
        • Farooq A.
        • Bagante F.
        • Sahara K.
        • et al.
        Use of machine learning for prediction of patient risk of postoperative complications after liver, pancreatic, and colorectal surgery.
        J Gastrointest Surg : official journal of the Society for Surgery of the Alimentary Tract. 2020; 24 (Epub 2019/08/07) (PubMed PMID: 31385172): 1843-1851https://doi.org/10.1007/s11605-019-04338-2
        • Corey K.M.
        • Kashyap S.
        • Lorenzi E.
        • Lagoo-Deenadayalan S.A.
        • Heller K.
        • Whalen K.
        • et al.
        Development and validation of machine learning models to identify high-risk surgical patients using automatically curated electronic health record data (Pythia): a retrospective, single-site study.
        PLoS Med. 2018; 15 (Epub 2018/11/28) (PubMed PMID: 30481172; PubMed Central PMCID: PMCPMC6258507)e1002701https://doi.org/10.1371/journal.pmed.1002701