Research ExplorerPublicationsSelection and evaluation of preoperative systemic inflammato...

Selection and evaluation of preoperative systemic inflammatory response biomarkers model prior to cytoreductive nephrectomy using a machine-learning approach

Standard

Selection and evaluation of preoperative systemic inflammatory response biomarkers model prior to cytoreductive nephrectomy using a machine-learning approach. / Laukhtina, Ekaterina; Schuettfort, Victor M; D'Andrea, David; Pradere, Benjamin; Quhal, Fahad; Mori, Keiichiro; Sari Motlagh, Reza; Mostafaei, Hadi; Katayama, Satoshi; Grossmann, Nico C; Rajwa, Pawel; Karakiewicz, Pierre I; Schmidinger, Manuela; Fajkovic, Harun; Enikeev, Dmitry; Shariat, Shahrokh F.

In: WORLD J UROL, Vol. 40, No. 3, 03.2022, p. 747-754.

Research output: SCORING: Contribution to journal › SCORING: Journal article › Research › peer-review

Harvard

Laukhtina, E, Schuettfort, VM, D'Andrea, D, Pradere, B, Quhal, F, Mori, K, Sari Motlagh, R, Mostafaei, H, Katayama, S, Grossmann, NC, Rajwa, P, Karakiewicz, PI, Schmidinger, M, Fajkovic, H, Enikeev, D & Shariat, SF 2022, 'Selection and evaluation of preoperative systemic inflammatory response biomarkers model prior to cytoreductive nephrectomy using a machine-learning approach', WORLD J UROL, vol. 40, no. 3, pp. 747-754. https://doi.org/10.1007/s00345-021-03844-w

APA

Laukhtina, E., Schuettfort, V. M., D'Andrea, D., Pradere, B., Quhal, F., Mori, K., Sari Motlagh, R., Mostafaei, H., Katayama, S., Grossmann, N. C., Rajwa, P., Karakiewicz, P. I., Schmidinger, M., Fajkovic, H., Enikeev, D., & Shariat, S. F. (2022). Selection and evaluation of preoperative systemic inflammatory response biomarkers model prior to cytoreductive nephrectomy using a machine-learning approach. WORLD J UROL, 40(3), 747-754. https://doi.org/10.1007/s00345-021-03844-w

Vancouver

Laukhtina E, Schuettfort VM, D'Andrea D, Pradere B, Quhal F, Mori K et al. Selection and evaluation of preoperative systemic inflammatory response biomarkers model prior to cytoreductive nephrectomy using a machine-learning approach. WORLD J UROL. 2022 Mar;40(3):747-754. https://doi.org/10.1007/s00345-021-03844-w

Bibtex

@article{73b3936c04a742f4b0d96fe15fcb1a18,
title = "Selection and evaluation of preoperative systemic inflammatory response biomarkers model prior to cytoreductive nephrectomy using a machine-learning approach",
abstract = "INTRODUCTION: This study aimed to determine the prognostic value of a panel of SIR-biomarkers, relative to standard clinicopathological variables, to improve mRCC patient selection for cytoreductive nephrectomy (CN).MATERIAL AND METHODS: A panel of preoperative SIR-biomarkers, including the albumin-globulin ratio (AGR), De Ritis ratio (DRR), and systemic immune-inflammation index (SII), was assessed in 613 patients treated with CN for mRCC. Patients were randomly divided into training and testing cohorts (65/35%). A machine learning-based variable selection approach (LASSO regression) was used for the fitting of the most informative, yet parsimonious multivariable models with respect to prognosis of cancer-specific survival (CSS). The discriminatory ability of the model was quantified using the C-index. After validation and calibration of the model, a nomogram was created, and decision curve analysis (DCA) was used to evaluate the clinical net benefit.RESULTS: SIR-biomarkers were selected by the machine-learning process to be of high discriminatory power during the fitting of the model. Low AGR remained significantly associated with CSS in both training (HR 1.40, 95% CI 1.07-1.82, p = 0.01) and testing (HR 1.78, 95% CI 1.26-2.51, p = 0.01) cohorts. High levels of SII (HR 1.51, 95% CI 1.10-2.08, p = 0.01) and DRR (HR 1.41, 95% CI 1.01-1.96, p = 0.04) were associated with CSS only in the testing cohort. The exclusion of the SIR-biomarkers for the prognosis of CSS did not result in a significant decrease in C-index (- 0.9%) for the training cohort, while the exclusion of SIR-biomarkers led to a reduction in C-index in the testing cohort (- 5.8%). However, SIR-biomarkers only marginally increased the discriminatory ability of the respective model in comparison to the standard model.CONCLUSION: Despite the high discriminatory ability during the fitting of the model with machine-learning approach, the panel of readily available blood-based SIR-biomarkers failed to add a clinical benefit beyond the standard model.",
author = "Ekaterina Laukhtina and Schuettfort, {Victor M} and David D'Andrea and Benjamin Pradere and Fahad Quhal and Keiichiro Mori and {Sari Motlagh}, Reza and Hadi Mostafaei and Satoshi Katayama and Grossmann, {Nico C} and Pawel Rajwa and Karakiewicz, {Pierre I} and Manuela Schmidinger and Harun Fajkovic and Dmitry Enikeev and Shariat, {Shahrokh F}",
note = "{\textcopyright} 2021. The Author(s).",
year = "2022",
month = mar,
doi = "10.1007/s00345-021-03844-w",
language = "English",
volume = "40",
pages = "747--754",
journal = "WORLD J UROL",
issn = "0724-4983",
publisher = "Springer",
number = "3",

}

RIS

TY - JOUR

T1 - Selection and evaluation of preoperative systemic inflammatory response biomarkers model prior to cytoreductive nephrectomy using a machine-learning approach

AU - Laukhtina, Ekaterina

AU - Schuettfort, Victor M

AU - D'Andrea, David

AU - Pradere, Benjamin

AU - Quhal, Fahad

AU - Mori, Keiichiro

AU - Sari Motlagh, Reza

AU - Mostafaei, Hadi

AU - Katayama, Satoshi

AU - Grossmann, Nico C

AU - Rajwa, Pawel

AU - Karakiewicz, Pierre I

AU - Schmidinger, Manuela

AU - Fajkovic, Harun

AU - Enikeev, Dmitry

AU - Shariat, Shahrokh F

N1 - © 2021. The Author(s).

PY - 2022/3

Y1 - 2022/3

N2 - INTRODUCTION: This study aimed to determine the prognostic value of a panel of SIR-biomarkers, relative to standard clinicopathological variables, to improve mRCC patient selection for cytoreductive nephrectomy (CN).MATERIAL AND METHODS: A panel of preoperative SIR-biomarkers, including the albumin-globulin ratio (AGR), De Ritis ratio (DRR), and systemic immune-inflammation index (SII), was assessed in 613 patients treated with CN for mRCC. Patients were randomly divided into training and testing cohorts (65/35%). A machine learning-based variable selection approach (LASSO regression) was used for the fitting of the most informative, yet parsimonious multivariable models with respect to prognosis of cancer-specific survival (CSS). The discriminatory ability of the model was quantified using the C-index. After validation and calibration of the model, a nomogram was created, and decision curve analysis (DCA) was used to evaluate the clinical net benefit.RESULTS: SIR-biomarkers were selected by the machine-learning process to be of high discriminatory power during the fitting of the model. Low AGR remained significantly associated with CSS in both training (HR 1.40, 95% CI 1.07-1.82, p = 0.01) and testing (HR 1.78, 95% CI 1.26-2.51, p = 0.01) cohorts. High levels of SII (HR 1.51, 95% CI 1.10-2.08, p = 0.01) and DRR (HR 1.41, 95% CI 1.01-1.96, p = 0.04) were associated with CSS only in the testing cohort. The exclusion of the SIR-biomarkers for the prognosis of CSS did not result in a significant decrease in C-index (- 0.9%) for the training cohort, while the exclusion of SIR-biomarkers led to a reduction in C-index in the testing cohort (- 5.8%). However, SIR-biomarkers only marginally increased the discriminatory ability of the respective model in comparison to the standard model.CONCLUSION: Despite the high discriminatory ability during the fitting of the model with machine-learning approach, the panel of readily available blood-based SIR-biomarkers failed to add a clinical benefit beyond the standard model.

AB - INTRODUCTION: This study aimed to determine the prognostic value of a panel of SIR-biomarkers, relative to standard clinicopathological variables, to improve mRCC patient selection for cytoreductive nephrectomy (CN).MATERIAL AND METHODS: A panel of preoperative SIR-biomarkers, including the albumin-globulin ratio (AGR), De Ritis ratio (DRR), and systemic immune-inflammation index (SII), was assessed in 613 patients treated with CN for mRCC. Patients were randomly divided into training and testing cohorts (65/35%). A machine learning-based variable selection approach (LASSO regression) was used for the fitting of the most informative, yet parsimonious multivariable models with respect to prognosis of cancer-specific survival (CSS). The discriminatory ability of the model was quantified using the C-index. After validation and calibration of the model, a nomogram was created, and decision curve analysis (DCA) was used to evaluate the clinical net benefit.RESULTS: SIR-biomarkers were selected by the machine-learning process to be of high discriminatory power during the fitting of the model. Low AGR remained significantly associated with CSS in both training (HR 1.40, 95% CI 1.07-1.82, p = 0.01) and testing (HR 1.78, 95% CI 1.26-2.51, p = 0.01) cohorts. High levels of SII (HR 1.51, 95% CI 1.10-2.08, p = 0.01) and DRR (HR 1.41, 95% CI 1.01-1.96, p = 0.04) were associated with CSS only in the testing cohort. The exclusion of the SIR-biomarkers for the prognosis of CSS did not result in a significant decrease in C-index (- 0.9%) for the training cohort, while the exclusion of SIR-biomarkers led to a reduction in C-index in the testing cohort (- 5.8%). However, SIR-biomarkers only marginally increased the discriminatory ability of the respective model in comparison to the standard model.CONCLUSION: Despite the high discriminatory ability during the fitting of the model with machine-learning approach, the panel of readily available blood-based SIR-biomarkers failed to add a clinical benefit beyond the standard model.

U2 - 10.1007/s00345-021-03844-w

DO - 10.1007/s00345-021-03844-w

M3 - SCORING: Journal article

C2 - 34671856

VL - 40

SP - 747

EP - 754

JO - WORLD J UROL

JF - WORLD J UROL

SN - 0724-4983

IS - 3

ER -