A novel nomogram for peritoneal mesothelioma predicts survival

Nicholas P. Schaub, Meghna Alimchandani, Martha Quezado, Phil Kalina, John S. Eberhardt, Marybeth S. Hughes, Tatiana Beresnev, Raffit Hassan, David L. Bartlett, Steven K. Libutti, James F. Pingpank, Richard E. Royal, Udai S. Kammula, Prakash Pandalai, Giao Q. Phan, Alexander Stojadinovic, Udo Rudloff, H. Richard Alexander, Itzhak Avital

Research output: Contribution to journalArticle

27 Citations (Scopus)

Abstract

Background: Malignant peritoneal mesothelioma (MPM) is a rare disease treated with cytoreductive surgery (CRS) and hyperthermic intraperitoneal chemotherapy (HIPEC). Estimation of personalized survival times can potentially guide treatment and surveillance. Methods: We analyzed 104 patients who underwent CRS and cisplatin-based HIPEC for MPM. By means of 25 demographic, laboratory, operative, and histopathological variables, we developed a novel nomogram using machine-learned Bayesian belief networks with stepwise training, testing, and cross-validation. Results: The mean peritoneal carcinomatosis index (PCI) was 15, and 66 % of patients had a completeness of cytoreduction (CC) score of 0 or 1. Eighty-seven percent of patients had epithelioid histology. The median follow-up time was 49 (1-195) months. The 3- and 5-year overall survivals (OS) were 58 and 46 %, respectively. The histological subtype, pre-CRS PCI, and preoperative serum CA-125 had the greatest impact on OS and were included in the nomogram. The mean areas under the receiver operating characteristic curve for the 10-fold cross-validation of the 3- and 5-year models were 0.77 and 0.74, respectively. The graphical calculator or nomogram uses color coding to assist the clinician in quickly estimating individualized patient-specific survival before surgery. Conclusions: Machine-learned Bayesian belief network analysis generated a novel nomogram predicting 3- and 5-year OS in patients treated with CRS and HIPEC for MPM. Pre-CRS estimation of survival times may potentially individualize patient care by influencing the use of systemic therapy and frequency of diagnostic imaging, and might prevent CRS in patients unlikely to achieve favorable outcomes despite surgical intervention.

Original languageEnglish (US)
Pages (from-to)555-561
Number of pages7
JournalAnnals of Surgical Oncology
Volume20
Issue number2
DOIs
StatePublished - Feb 2013

Fingerprint

Nomograms
Mesothelioma
Survival
Drug Therapy
Carcinoma
Diagnostic Imaging
Rare Diseases
ROC Curve
Cisplatin
Histology
Patient Care
Color
Demography
Therapeutics
Serum
Malignant Mesothelioma

ASJC Scopus subject areas

  • Surgery
  • Oncology

Cite this

Schaub, N. P., Alimchandani, M., Quezado, M., Kalina, P., Eberhardt, J. S., Hughes, M. S., ... Avital, I. (2013). A novel nomogram for peritoneal mesothelioma predicts survival. Annals of Surgical Oncology, 20(2), 555-561. https://doi.org/10.1245/s10434-012-2651-5

A novel nomogram for peritoneal mesothelioma predicts survival. / Schaub, Nicholas P.; Alimchandani, Meghna; Quezado, Martha; Kalina, Phil; Eberhardt, John S.; Hughes, Marybeth S.; Beresnev, Tatiana; Hassan, Raffit; Bartlett, David L.; Libutti, Steven K.; Pingpank, James F.; Royal, Richard E.; Kammula, Udai S.; Pandalai, Prakash; Phan, Giao Q.; Stojadinovic, Alexander; Rudloff, Udo; Alexander, H. Richard; Avital, Itzhak.

In: Annals of Surgical Oncology, Vol. 20, No. 2, 02.2013, p. 555-561.

Research output: Contribution to journalArticle

Schaub, NP, Alimchandani, M, Quezado, M, Kalina, P, Eberhardt, JS, Hughes, MS, Beresnev, T, Hassan, R, Bartlett, DL, Libutti, SK, Pingpank, JF, Royal, RE, Kammula, US, Pandalai, P, Phan, GQ, Stojadinovic, A, Rudloff, U, Alexander, HR & Avital, I 2013, 'A novel nomogram for peritoneal mesothelioma predicts survival', Annals of Surgical Oncology, vol. 20, no. 2, pp. 555-561. https://doi.org/10.1245/s10434-012-2651-5
Schaub NP, Alimchandani M, Quezado M, Kalina P, Eberhardt JS, Hughes MS et al. A novel nomogram for peritoneal mesothelioma predicts survival. Annals of Surgical Oncology. 2013 Feb;20(2):555-561. https://doi.org/10.1245/s10434-012-2651-5
Schaub, Nicholas P. ; Alimchandani, Meghna ; Quezado, Martha ; Kalina, Phil ; Eberhardt, John S. ; Hughes, Marybeth S. ; Beresnev, Tatiana ; Hassan, Raffit ; Bartlett, David L. ; Libutti, Steven K. ; Pingpank, James F. ; Royal, Richard E. ; Kammula, Udai S. ; Pandalai, Prakash ; Phan, Giao Q. ; Stojadinovic, Alexander ; Rudloff, Udo ; Alexander, H. Richard ; Avital, Itzhak. / A novel nomogram for peritoneal mesothelioma predicts survival. In: Annals of Surgical Oncology. 2013 ; Vol. 20, No. 2. pp. 555-561.
@article{08c5a9320ea54ad3b9ff7ecd309c5efd,
title = "A novel nomogram for peritoneal mesothelioma predicts survival",
abstract = "Background: Malignant peritoneal mesothelioma (MPM) is a rare disease treated with cytoreductive surgery (CRS) and hyperthermic intraperitoneal chemotherapy (HIPEC). Estimation of personalized survival times can potentially guide treatment and surveillance. Methods: We analyzed 104 patients who underwent CRS and cisplatin-based HIPEC for MPM. By means of 25 demographic, laboratory, operative, and histopathological variables, we developed a novel nomogram using machine-learned Bayesian belief networks with stepwise training, testing, and cross-validation. Results: The mean peritoneal carcinomatosis index (PCI) was 15, and 66 {\%} of patients had a completeness of cytoreduction (CC) score of 0 or 1. Eighty-seven percent of patients had epithelioid histology. The median follow-up time was 49 (1-195) months. The 3- and 5-year overall survivals (OS) were 58 and 46 {\%}, respectively. The histological subtype, pre-CRS PCI, and preoperative serum CA-125 had the greatest impact on OS and were included in the nomogram. The mean areas under the receiver operating characteristic curve for the 10-fold cross-validation of the 3- and 5-year models were 0.77 and 0.74, respectively. The graphical calculator or nomogram uses color coding to assist the clinician in quickly estimating individualized patient-specific survival before surgery. Conclusions: Machine-learned Bayesian belief network analysis generated a novel nomogram predicting 3- and 5-year OS in patients treated with CRS and HIPEC for MPM. Pre-CRS estimation of survival times may potentially individualize patient care by influencing the use of systemic therapy and frequency of diagnostic imaging, and might prevent CRS in patients unlikely to achieve favorable outcomes despite surgical intervention.",
author = "Schaub, {Nicholas P.} and Meghna Alimchandani and Martha Quezado and Phil Kalina and Eberhardt, {John S.} and Hughes, {Marybeth S.} and Tatiana Beresnev and Raffit Hassan and Bartlett, {David L.} and Libutti, {Steven K.} and Pingpank, {James F.} and Royal, {Richard E.} and Kammula, {Udai S.} and Prakash Pandalai and Phan, {Giao Q.} and Alexander Stojadinovic and Udo Rudloff and Alexander, {H. Richard} and Itzhak Avital",
year = "2013",
month = "2",
doi = "10.1245/s10434-012-2651-5",
language = "English (US)",
volume = "20",
pages = "555--561",
journal = "Annals of Surgical Oncology",
issn = "1068-9265",
publisher = "Springer New York",
number = "2",

}

TY - JOUR

T1 - A novel nomogram for peritoneal mesothelioma predicts survival

AU - Schaub, Nicholas P.

AU - Alimchandani, Meghna

AU - Quezado, Martha

AU - Kalina, Phil

AU - Eberhardt, John S.

AU - Hughes, Marybeth S.

AU - Beresnev, Tatiana

AU - Hassan, Raffit

AU - Bartlett, David L.

AU - Libutti, Steven K.

AU - Pingpank, James F.

AU - Royal, Richard E.

AU - Kammula, Udai S.

AU - Pandalai, Prakash

AU - Phan, Giao Q.

AU - Stojadinovic, Alexander

AU - Rudloff, Udo

AU - Alexander, H. Richard

AU - Avital, Itzhak

PY - 2013/2

Y1 - 2013/2

N2 - Background: Malignant peritoneal mesothelioma (MPM) is a rare disease treated with cytoreductive surgery (CRS) and hyperthermic intraperitoneal chemotherapy (HIPEC). Estimation of personalized survival times can potentially guide treatment and surveillance. Methods: We analyzed 104 patients who underwent CRS and cisplatin-based HIPEC for MPM. By means of 25 demographic, laboratory, operative, and histopathological variables, we developed a novel nomogram using machine-learned Bayesian belief networks with stepwise training, testing, and cross-validation. Results: The mean peritoneal carcinomatosis index (PCI) was 15, and 66 % of patients had a completeness of cytoreduction (CC) score of 0 or 1. Eighty-seven percent of patients had epithelioid histology. The median follow-up time was 49 (1-195) months. The 3- and 5-year overall survivals (OS) were 58 and 46 %, respectively. The histological subtype, pre-CRS PCI, and preoperative serum CA-125 had the greatest impact on OS and were included in the nomogram. The mean areas under the receiver operating characteristic curve for the 10-fold cross-validation of the 3- and 5-year models were 0.77 and 0.74, respectively. The graphical calculator or nomogram uses color coding to assist the clinician in quickly estimating individualized patient-specific survival before surgery. Conclusions: Machine-learned Bayesian belief network analysis generated a novel nomogram predicting 3- and 5-year OS in patients treated with CRS and HIPEC for MPM. Pre-CRS estimation of survival times may potentially individualize patient care by influencing the use of systemic therapy and frequency of diagnostic imaging, and might prevent CRS in patients unlikely to achieve favorable outcomes despite surgical intervention.

AB - Background: Malignant peritoneal mesothelioma (MPM) is a rare disease treated with cytoreductive surgery (CRS) and hyperthermic intraperitoneal chemotherapy (HIPEC). Estimation of personalized survival times can potentially guide treatment and surveillance. Methods: We analyzed 104 patients who underwent CRS and cisplatin-based HIPEC for MPM. By means of 25 demographic, laboratory, operative, and histopathological variables, we developed a novel nomogram using machine-learned Bayesian belief networks with stepwise training, testing, and cross-validation. Results: The mean peritoneal carcinomatosis index (PCI) was 15, and 66 % of patients had a completeness of cytoreduction (CC) score of 0 or 1. Eighty-seven percent of patients had epithelioid histology. The median follow-up time was 49 (1-195) months. The 3- and 5-year overall survivals (OS) were 58 and 46 %, respectively. The histological subtype, pre-CRS PCI, and preoperative serum CA-125 had the greatest impact on OS and were included in the nomogram. The mean areas under the receiver operating characteristic curve for the 10-fold cross-validation of the 3- and 5-year models were 0.77 and 0.74, respectively. The graphical calculator or nomogram uses color coding to assist the clinician in quickly estimating individualized patient-specific survival before surgery. Conclusions: Machine-learned Bayesian belief network analysis generated a novel nomogram predicting 3- and 5-year OS in patients treated with CRS and HIPEC for MPM. Pre-CRS estimation of survival times may potentially individualize patient care by influencing the use of systemic therapy and frequency of diagnostic imaging, and might prevent CRS in patients unlikely to achieve favorable outcomes despite surgical intervention.

UR - http://www.scopus.com/inward/record.url?scp=84878859983&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878859983&partnerID=8YFLogxK

U2 - 10.1245/s10434-012-2651-5

DO - 10.1245/s10434-012-2651-5

M3 - Article

C2 - 23233234

AN - SCOPUS:84878859983

VL - 20

SP - 555

EP - 561

JO - Annals of Surgical Oncology

JF - Annals of Surgical Oncology

SN - 1068-9265

IS - 2

ER -