A Prediction Model for Preoperative Risk Assessment in Endometrial Cancer Utilizing Clinical and Molecular Variables

Erin A Salinas; Marina D Miller; Andreea M Newtson; Deepti Sharma; Megan E McDonald; Matthew E Keeney; Brian J Smith; David P Bender; Michael J Goodheart; Kristina W Thiel; Eric J Devor; Kimberly K Leslie; Jesus Gonzalez Bosquet

doi:10.3390/ijms20051205

Back

A Prediction Model for Preoperative Risk Assessment in Endometrial Cancer Utilizing Clinical and Molecular Variables

Journal article

Open access

Peer reviewed

A Prediction Model for Preoperative Risk Assessment in Endometrial Cancer Utilizing Clinical and Molecular Variables

Erin A Salinas, Marina D Miller, Andreea M Newtson, Deepti Sharma, Megan E McDonald, Matthew E Keeney, Brian J Smith, David P Bender, Michael J Goodheart, Kristina W Thiel, …

International journal of molecular sciences, Vol.20(5), p.1205

03/09/2019

DOI: 10.3390/ijms20051205

PMCID: PMC6429416

PMID: 30857319

Files and links (1)

url

https://doi.org/10.3390/ijms20051205View

Published (Version of record) Open Access

Abstract

The utility of comprehensive surgical staging in patients with low risk disease has been questioned. Thus, a reliable means of determining risk would be quite useful. The aim of our study was to create the best performing prediction model to classify endometrioid endometrial cancer (EEC) patients into low or high risk using a combination of molecular and clinical-pathological variables. We then validated these models with publicly available datasets. Analyses between low and high risk EEC were performed using clinical and pathological data, gene and miRNA expression data, gene copy number variation and somatic mutation data. Variables were selected to be included in the prediction model of risk using cross-validation analysis; prediction models were then constructed using these variables. Model performance was assessed by area under the curve (AUC). Prediction models were validated using appropriate datasets in The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO) databases. A prediction model with only clinical variables performed at 88%. Integrating clinical and molecular data improved prediction performance up to 97%. The best prediction models included clinical, miRNA expression and/or somatic mutation data, and stratified pre-operative risk in EEC patients. Integrating molecular and clinical data improved the performance of prediction models to over 95%, resulting in potentially useful clinical tests.

Prognosis

Risk Assessment

Humans

Middle Aged

Gene Expression Regulation, Neoplastic

Gene Expression Profiling

Endometrial Neoplasms - diagnosis

DNA Copy Number Variations

Endometrial Neoplasms - genetics

Neoplasm Invasiveness - pathology

Endometrial Neoplasms - surgery

Endometrial Neoplasms - pathology

Female

MicroRNAs - genetics

Mutation

Neoplasm Invasiveness - genetics

Preoperative Period

Details

Title: Subtitle: A Prediction Model for Preoperative Risk Assessment in Endometrial Cancer Utilizing Clinical and Molecular Variables
Creators: Erin A Salinas - Compass Oncology, Portland, OR 97227, USA. Erin.Salinas@compassoncology.com
Marina D Miller - Department of Obstetrics and Gynecology, University of Iowa Hospitals and Clinics, Iowa City, IA 52242, USA. marina-miller@uiowa.edu
Andreea M Newtson - Division of Gynecologic Oncology, Department of Obstetrics and Gynecology, University of Iowa Hospitals and Clinics, Iowa City, IA 52242, USA. andreea-newtson@uiowa.edu
Deepti Sharma - Department of Obstetrics and Gynecology, University of Kentucky, Lexington, KY 52242, USA. dsh274@uky.edu
Megan E McDonald - Division of Gynecologic Oncology, Department of Obstetrics and Gynecology, University of Iowa Hospitals and Clinics, Iowa City, IA 52242, USA. megan-e-mcdonald@uiowa.edu
Matthew E Keeney - Winfield Pathology Consultants, Central DuPage Hospital, Winfield, IL 60190, USA. mekeeney@llu.edu
Brian J Smith - Holden Comprehensive Cancer Center, University of Iowa Hospitals and Clinics, Iowa City, IA 52242, USA. brian-j-smith@uiowa.edu
David P Bender - Holden Comprehensive Cancer Center, University of Iowa Hospitals and Clinics, Iowa City, IA 52242, USA. david-bender@uiowa.edu
Michael J Goodheart - Holden Comprehensive Cancer Center, University of Iowa Hospitals and Clinics, Iowa City, IA 52242, USA. michael-goodheart@uiowa.edu
Kristina W Thiel - Department of Obstetrics and Gynecology, University of Iowa Hospitals and Clinics, Iowa City, IA 52242, USA. kristina-thiel@uiowa.edu
Eric J Devor - Department of Obstetrics and Gynecology, University of Iowa Hospitals and Clinics, Iowa City, IA 52242, USA. eric-devor@uiowa.edu
Kimberly K Leslie - Holden Comprehensive Cancer Center, University of Iowa Hospitals and Clinics, Iowa City, IA 52242, USA. kimberly-leslie@uiowa.edu
Jesus Gonzalez Bosquet - Holden Comprehensive Cancer Center, University of Iowa Hospitals and Clinics, Iowa City, IA 52242, USA. jesus-gonzalezbosquet@uiowa.edu
Resource Type: Journal article
Publication Details: International journal of molecular sciences, Vol.20(5), p.1205
DOI: 10.3390/ijms20051205
PMID: 30857319
PMCID: PMC6429416
NLM abbreviation: Int J Mol Sci
ISSN: 1661-6596
eISSN: 1422-0067
Publisher: Switzerland
Grant note: P30CA086862 / National Institutes of Health Basic research fund / Department of Obstetrics & Gynecology at the University of Iowa R01CA184101 / National Institutes of Health R01CA99908 / National Institutes of Health P30 CA086862 / NCI NIH HHS
Language: English
Date published: 03/09/2019
Academic Unit: Biostatistics; Obstetrics and Gynecology; Holden Comprehensive Cancer Center
Record Identifier: 9983931810702771

Metrics

36 Record Views

12 Times Cited - Web of Science