A novel nomogram for peritoneal mesothelioma predicts survival

Our plain-English summary of A novel nomogram for peritoneal mesothelioma predicts survival, by N.P. Schaub, M. Alimchandani, M. Quezado, et al (Annals of Surgical Oncology, 2013).

The study

• Authors: N.P. Schaub, M. Alimchandani, M. Quezado, P. Kalina, J.S. Eberhardt, M.S. Hughes, T. Beresnev, R. Hassan, D.L. Bartlett, S.K. Libutti, J.F. Pingpank, R.E. Royal, U.S. Kammula, P. Pandalai, G.Q. Phan, A. Stojadinovic, U. Rudloff, H.R. Alexander, I. Avital
• Journal: Annals of Surgical Oncology
• Published: 2013;20(2):555-61
• Cited by: 42 articles, as counted by NIH iCite
• Read it: PubMed · Publisher · Free full text

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.

In plain English

This study reviewed 104 patients with malignant peritoneal mesothelioma (mesothelioma of the abdominal lining) treated between 1994 and 2010. Their treatment was surgery to remove as much tumor as possible, followed by heated cisplatin chemotherapy circulated inside the abdomen (HIPEC). Using a database kept over time, the authors used machine-learning software (Bayesian belief networks) to build a chart, or nomogram, that estimates 3- and 5-year survival. The article does not discuss asbestos exposure. Overall, 58% of patients were alive at 3 years and 46% at 5 years, and median survival was 52.0 months. Three factors had the greatest influence on survival: the extent of abdominal tumor before surgery (the peritoneal cancer index), the blood level of the marker CA-125 before surgery, and the detailed tissue subtype of the tumor. When the models were tested on held-out data, their accuracy scores (area under the curve) were 0.77 for 3 years and 0.74 for 5 years. The authors concluded that they had built the first such tool for these patients. They noted that the study was retrospective and that the tool should be checked in other data sets and prospectively.

We wrote this plain-English summary from the full article with the help of AI, and a second AI model checked each sentence against the article. It is not the authors' wording; the abstract and the article are their own account.

What the study did and found

• Design: Retrospective analysis of a prospectively maintained patient database, used to develop a survival-prediction model (machine-learned Bayesian belief networks) with 10-fold cross-validation
• Who was studied: 104 patients with histologically proven malignant peritoneal mesothelioma who underwent cytoreductive surgery and HIPEC between 1994 and 2010
• Exposure: No asbestos exposure was studied. The study examined treatment: cytoreductive surgery plus hyperthermic intraperitoneal chemotherapy with cisplatin (250–450 mg/m2 at 40–42 C for 90 minutes), with some patients also receiving early postoperative intraperitoneal chemotherapy (EPIC)
• Main results:
  • Among all 104 patients, 3-year overall survival was 58% and 5-year overall survival was 46%; median overall survival was 52.0 months (range 1–195)
  • 3- and 5-year progression-free survival was 26% and 13%, respectively
  • Median pre-surgery peritoneal cancer index was 15 (range 3–36); 69 patients (66.3%) had a completeness of cytoreduction score of 0 or 1
  • Sixty-nine patients (66.3%) received EPIC. Median overall survival was 67 months with EPIC and 35 months without it, a difference that was not statistically significant (p = 0.345)
  • Median overall survival was 103 months for patients who had a second surgery and HIPEC (11 patients) and 48 months for those who did not (p = 0.047)
  • The three variables with the greatest influence on overall survival were pre-surgery peritoneal cancer index, preoperative serum CA-125, and detailed histological subtype
  • Mean area under the curve in 10-fold cross-validation was 0.77 for the 3-year model and 0.74 for the 5-year model
  • For the 5-year model, positive predictive value was 73.9% and negative predictive value was 73.3%
• The authors' conclusion: The authors concluded that they had constructed the first clinical assessment tool (nomogram) to predict survival in patients treated with cytoreductive surgery and HIPEC for malignant peritoneal mesothelioma. They suggested that estimating survival before surgery may help individualize treatment and follow-up.
• Limitations the authors state:
  • No patients in the cohort had lymph node positivity, so this factor could not be included in the model
  • Chemotherapy regimens before and after surgery were not standardized
  • The study was retrospective, and the model should be validated in other data sets and prospectively
  • Small numbers and selection bias among patients who qualified for a second surgery prevent definitive conclusions about repeat surgery

Topics

The National Library of Medicine indexes this study under subjects our site covers: Mesothelioma, Peritoneal mesothelioma.

Medical terms in this study, explained in our Lexicon: Peritoneal Mesothelioma, Cytoreductive Surgery, HIPEC, Cisplatin, Completeness of Cytoreduction (CC) Score, Epithelioid, Histology, Overall Survival.

Related studies

• Preoperative Thrombocytosis Predicts Shortened Survival in Patients with Malignant Peritoneal Mesothelioma Undergoing Operative Cytoreduction and Hyperthermic Intraperitoneal Chemotherapy — Y.C. Li, T. Khashab, et al. (2017)
• Malignant Peritoneal Mesothelioma: National Practice Patterns, Outcomes, and Predictors of Survival — V. Verma, R.L. Sleightholm, et al. (2018)
• A Novel Tool for Predicting Major Complications After Cytoreductive Surgery with Hyperthermic Intraperitoneal Chemotherapy — J.M. Baumgartner, T.G. Kwong, et al. (2016)
• A Nomogram to Predict Prognosis in Malignant Pleural Mesothelioma — S. Wang, K. Ma, et al. (2018)
• Repeat cytoreductive surgery and heated intraperitoneal chemotherapy may offer survival benefit for intraperitoneal mesothelioma: a single institution experience — J. Wong, A.L. Koch, et al. (2014)
• Treatment factors associated with long-term survival after cytoreductive surgery and regional chemotherapy for patients with malignant peritoneal mesothelioma — H.R. Alexander, D.L. Bartlett, et al. (2013)

Browse more research in Annals of Surgical Oncology, or return to medical research.