To determine the predictive and prognostic value of a panel of systemic inflammatory response (SIR) biomarkers relative to established clinicopathological variables in order to improve patient selection for a more efficient delivery of perioperative systemic therapy. Several blood-based systemic inflammatory response SIR-biomarkers have previously been evaluated with respect to their predictive and prognostic value in urothelial carcinoma of the bladder (UCB). Despite promising results, all single SIR-biomarkers failed to meaningfully improve the discriminatory ability of established models.
The preoperative serum levels of a panel of SIR-biomarkers, including the albumin-globulin ratio, neutrophil-lymphocyte ratio, De Ritis ratio, monocyte-lymphocyte ratio and the modified Glasgow Prognostic Score were assessed in 4,199 patients treated with radical cystectomy for clinically non-metastatic UCB. Patients were randomly divided in a training and testing cohort. A machine-learning based variable selection approach (LASSO regression) was used for the fitting of several multivariable predictive and prognostic models. The outcomes of interest included prediction of upstaging to MIBC, lymph node involvement, pT3/4 disease, cancer-specific survival and recurrence-free survival. The discriminatory ability of each model was either quantified by the area under the curve (AUC) of receiver operating curves (ROC) or by the C-index. After validation and calibration of each model, a nomogram was created and decision curve analysis (DCA) was used to evaluate the clinical net-benefit.
For all outcome parameters, at least one SIR-biomarker was selected by the machine-learning process to be of high discriminatory power during the fitting of the models. In the testing cohort, model performance evaluation for preoperative prediction of lymph node metastasis, ≥pT3 disease and upstaging to MIBC showed a 200-fold bootstrap corrected AUC of 67.3%, 73% and 65.8%, respectively. For postoperative prognosis of cancer-specific survival and recurrence-free survival, a 200-fold bootstrap corrected C-index of 73.3% and 72.2%, respectively, was found. However, even the most predictive combinations of SIR-biomarkers only marginally increased to discriminatory ability of the respective model in comparison to established clinicopathological variables.
While our machine-learning approach for fitting of the models with the highest discriminatory ability incorporated several previously validated SIR-biomarkers, these failed to improve the discriminatory ability of the models to a clinically meaningful degree. While the prognostic and predictive value of such cheap and ready-available biomarkers warrants further evaluation in the age of immunotherapy, additional novel biomarkers are still needed to improve risk stratification.
BJU international. 2021 Mar 01 [Epub ahead of print]
Victor M Schuettfort, David D Andrea, Fahad Quhal, Hadi Mostafaei, Ekaterina Laukhtina, Keiichiro Mori, Frederik König, Michael Rink, Mohammad Abufaraj, Pierre I Karakiewicz, Stefano Luzzago, Morgan Rouprêt, Dmitry Enikeev, Kristin Zimmermann, Marina Deuker, Marco Moschini, Reza Sari Motlagh, Nico C Grossmann, Satoshi Katayama, Benjamin Pradere, Shahrokh F Shariat
Department of Urology, Comprehensive Cancer Center, Medical University of Vienna, Vienna, Austria., Department of Urology, University Medical Center Hamburg-Eppendorf, Hamburg, Germany., Cancer Prognostics and Health Outcomes Unit, Division of Urology, University of Montreal Health Center, Montreal, Canada., Sorbonne Université, Predictive Onco-, Hôpital Pitié-Salpêtrière, GRC n°5, Ap-Hp, F-75013, Paris., Institute for Urology and Reproductive Health, Sechenov University, Moscow, Russia., Clinic for Urology, Central Military Hospital Koblenz, Koblenz, Germany., Department of Urology, Luzerner Kantonsspital, Lucerne, Switzerland.