Integration of Genomic and Clinical Retrospective Data to Predict Endometrioid Endometrial Cancer Recurrence
Endometrial cancer (EC) incidence and mortality continues to rise. Molecular profiling of EC promises improvement of risk assessment and treatment selection. However, we still lack robust and accurate models to predict those at risk of failing treatment. The objective of this pilot study is to creat...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | International Journal of Molecular Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1422-0067/23/24/16014 |
| _version_ | 1797457234145312768 |
|---|---|
| author | Jesus Gonzalez-Bosquet Sofia Gabrilovich Megan E. McDonald Brian J. Smith Kimberly K. Leslie David D. Bender Michael J. Goodheart Eric Devor |
| author_facet | Jesus Gonzalez-Bosquet Sofia Gabrilovich Megan E. McDonald Brian J. Smith Kimberly K. Leslie David D. Bender Michael J. Goodheart Eric Devor |
| author_sort | Jesus Gonzalez-Bosquet |
| collection | DOAJ |
| description | Endometrial cancer (EC) incidence and mortality continues to rise. Molecular profiling of EC promises improvement of risk assessment and treatment selection. However, we still lack robust and accurate models to predict those at risk of failing treatment. The objective of this pilot study is to create models with clinical and genomic data that will discriminate patients with EC at risk of disease recurrence. We performed a pilot, retrospective, case–control study evaluating patients with EC, endometrioid type: 7 with recurrence of disease (cases), and 55 without (controls). RNA was extracted from frozen specimens and sequenced (RNAseq). Genomic features from RNAseq included transcriptome expression, genomic, and structural variation. Feature selection for variable reduction was performed with univariate ANOVA with cross-validation. Selected variables, informative for EC recurrence, were introduced in multivariate lasso regression models. Validation of models was performed in machine-learning platforms (ML) and independent datasets (TCGA). The best performing prediction models (out of >170) contained the same lncRNA features (AUC of 0.9, and 95% CI: 0.75, 1.0). Models were validated with excellent performance in ML platforms and good performance in an independent dataset. Prediction models of EC recurrence containing lncRNA features have better performance than models with clinical data alone. |
| first_indexed | 2024-03-09T16:19:18Z |
| format | Article |
| id | doaj.art-f7723f82118a4f9e9a83de775313f14d |
| institution | Directory Open Access Journal |
| issn | 1661-6596 1422-0067 |
| language | English |
| last_indexed | 2024-03-09T16:19:18Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | International Journal of Molecular Sciences |
| spelling | doaj.art-f7723f82118a4f9e9a83de775313f14d2023-11-24T15:31:24ZengMDPI AGInternational Journal of Molecular Sciences1661-65961422-00672022-12-0123241601410.3390/ijms232416014Integration of Genomic and Clinical Retrospective Data to Predict Endometrioid Endometrial Cancer RecurrenceJesus Gonzalez-Bosquet0Sofia Gabrilovich1Megan E. McDonald2Brian J. Smith3Kimberly K. Leslie4David D. Bender5Michael J. Goodheart6Eric Devor7Department of Obstetrics and Gynecology, University of Iowa, 200 Hawkins Dr., Iowa City, IA 52242, USADepartment of Obstetrics and Gynecology, University of Iowa, 200 Hawkins Dr., Iowa City, IA 52242, USADepartment of Obstetrics and Gynecology, University of Iowa, 200 Hawkins Dr., Iowa City, IA 52242, USADepartment of Biostatistics, University of Iowa, 145 N Riverside Dr., Iowa City, IA 52242, USADivision of Molecular Medicine, Departments of Internal Medicine and Obstetrics and Gynecology, The University of New Mexico Comprehensive Cancer Center, 915 Camino de Salud, CRF 117, Albuquerque, NM 87131, USADepartment of Obstetrics and Gynecology, University of Iowa, 200 Hawkins Dr., Iowa City, IA 52242, USADepartment of Obstetrics and Gynecology, University of Iowa, 200 Hawkins Dr., Iowa City, IA 52242, USADepartment of Obstetrics and Gynecology, University of Iowa, 200 Hawkins Dr., Iowa City, IA 52242, USAEndometrial cancer (EC) incidence and mortality continues to rise. Molecular profiling of EC promises improvement of risk assessment and treatment selection. However, we still lack robust and accurate models to predict those at risk of failing treatment. The objective of this pilot study is to create models with clinical and genomic data that will discriminate patients with EC at risk of disease recurrence. We performed a pilot, retrospective, case–control study evaluating patients with EC, endometrioid type: 7 with recurrence of disease (cases), and 55 without (controls). RNA was extracted from frozen specimens and sequenced (RNAseq). Genomic features from RNAseq included transcriptome expression, genomic, and structural variation. Feature selection for variable reduction was performed with univariate ANOVA with cross-validation. Selected variables, informative for EC recurrence, were introduced in multivariate lasso regression models. Validation of models was performed in machine-learning platforms (ML) and independent datasets (TCGA). The best performing prediction models (out of >170) contained the same lncRNA features (AUC of 0.9, and 95% CI: 0.75, 1.0). Models were validated with excellent performance in ML platforms and good performance in an independent dataset. Prediction models of EC recurrence containing lncRNA features have better performance than models with clinical data alone.https://www.mdpi.com/1422-0067/23/24/16014endometrial cancerrecurrencepredictionmachine learning |
| spellingShingle | Jesus Gonzalez-Bosquet Sofia Gabrilovich Megan E. McDonald Brian J. Smith Kimberly K. Leslie David D. Bender Michael J. Goodheart Eric Devor Integration of Genomic and Clinical Retrospective Data to Predict Endometrioid Endometrial Cancer Recurrence International Journal of Molecular Sciences endometrial cancer recurrence prediction machine learning |
| title | Integration of Genomic and Clinical Retrospective Data to Predict Endometrioid Endometrial Cancer Recurrence |
| title_full | Integration of Genomic and Clinical Retrospective Data to Predict Endometrioid Endometrial Cancer Recurrence |
| title_fullStr | Integration of Genomic and Clinical Retrospective Data to Predict Endometrioid Endometrial Cancer Recurrence |
| title_full_unstemmed | Integration of Genomic and Clinical Retrospective Data to Predict Endometrioid Endometrial Cancer Recurrence |
| title_short | Integration of Genomic and Clinical Retrospective Data to Predict Endometrioid Endometrial Cancer Recurrence |
| title_sort | integration of genomic and clinical retrospective data to predict endometrioid endometrial cancer recurrence |
| topic | endometrial cancer recurrence prediction machine learning |
| url | https://www.mdpi.com/1422-0067/23/24/16014 |
| work_keys_str_mv | AT jesusgonzalezbosquet integrationofgenomicandclinicalretrospectivedatatopredictendometrioidendometrialcancerrecurrence AT sofiagabrilovich integrationofgenomicandclinicalretrospectivedatatopredictendometrioidendometrialcancerrecurrence AT meganemcdonald integrationofgenomicandclinicalretrospectivedatatopredictendometrioidendometrialcancerrecurrence AT brianjsmith integrationofgenomicandclinicalretrospectivedatatopredictendometrioidendometrialcancerrecurrence AT kimberlykleslie integrationofgenomicandclinicalretrospectivedatatopredictendometrioidendometrialcancerrecurrence AT daviddbender integrationofgenomicandclinicalretrospectivedatatopredictendometrioidendometrialcancerrecurrence AT michaeljgoodheart integrationofgenomicandclinicalretrospectivedatatopredictendometrioidendometrialcancerrecurrence AT ericdevor integrationofgenomicandclinicalretrospectivedatatopredictendometrioidendometrialcancerrecurrence |