Deep learning enabled prediction of 5-year survival in pediatric genitourinary rhabdomyosarcoma
Copyright © 2020 Elsevier Ltd. All rights reserved..
BACKGROUND: Genitourinary rhabdomyosarcoma (GU-RMS) is a rare, pediatric malignancy originating from embryonic mesenchyme. Current approaches to prognostication rely upon conventional statistical methods such as Cox proportional hazards (CPH) models and have suboptimal predictive ability. Given the success of deep learning approaches in other specialties, we sought to develop and compare deep learning models with CPH models for the prediction of 5-year survival in pediatric GU-RMS patients.
METHODS: Patients less than 20 years of age with GU-RMS were identified within the Surveillance, Epidemiology, and End Results (SEER) database (1998-2011). Deep neural networks (DNN) were trained and tested on an 80/20 split of the dataset in a 5-fold cross-validated fashion. Multivariable CPH models were developed in parallel. The primary outcomes were 5-year overall survival (OS) and disease-specific survival (DSS). Variables used for prediction were age, sex, race, primary site, histology, degree of tumor extension, tumor size, receipt of surgery, and receipt of radiation. Receiver operating characteristic curve analysis was conducted, and DNN models were tested for calibration.
RESULTS: 277 patients were included. The area under the curve (AUC) for the DNN models was 0.93 for OS and 0.91 for DSS. AUC for the CPH models was 0.82 for OS and 0.84 for DSS. The DNN models were well-calibrated: OS model (slope = 1.02, intercept = -0.06) and DSS model (slope = 0.79, intercept = 0.21).
CONCLUSIONS: A deep learning-based model demonstrated excellent performance, superior to that of CPH models, in the prediction of pediatric GU-RMS survival. Deep learning approaches may enable improved prognostication for patients with rare cancers.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2021 |
|---|---|
| Erschienen: |
2021 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:36 |
|---|---|
| Enthalten in: |
Surgical oncology - 36(2021) vom: 04. März, Seite 23-27 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Bhambhvani, Hriday P [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Artificial intelligence |
|---|
| Anmerkungen: |
Date Completed 19.10.2021 Date Revised 19.10.2021 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1016/j.suronc.2020.11.002 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM318422654 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM318422654 | ||
| 003 | DE-627 | ||
| 005 | 20231225165324.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231225s2021 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.suronc.2020.11.002 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1061.xml |
| 035 | |a (DE-627)NLM318422654 | ||
| 035 | |a (NLM)33276260 | ||
| 035 | |a (PII)S0960-7404(20)30429-1 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Bhambhvani, Hriday P |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Deep learning enabled prediction of 5-year survival in pediatric genitourinary rhabdomyosarcoma |
| 264 | 1 | |c 2021 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Completed 19.10.2021 | ||
| 500 | |a Date Revised 19.10.2021 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a Copyright © 2020 Elsevier Ltd. All rights reserved. | ||
| 520 | |a BACKGROUND: Genitourinary rhabdomyosarcoma (GU-RMS) is a rare, pediatric malignancy originating from embryonic mesenchyme. Current approaches to prognostication rely upon conventional statistical methods such as Cox proportional hazards (CPH) models and have suboptimal predictive ability. Given the success of deep learning approaches in other specialties, we sought to develop and compare deep learning models with CPH models for the prediction of 5-year survival in pediatric GU-RMS patients | ||
| 520 | |a METHODS: Patients less than 20 years of age with GU-RMS were identified within the Surveillance, Epidemiology, and End Results (SEER) database (1998-2011). Deep neural networks (DNN) were trained and tested on an 80/20 split of the dataset in a 5-fold cross-validated fashion. Multivariable CPH models were developed in parallel. The primary outcomes were 5-year overall survival (OS) and disease-specific survival (DSS). Variables used for prediction were age, sex, race, primary site, histology, degree of tumor extension, tumor size, receipt of surgery, and receipt of radiation. Receiver operating characteristic curve analysis was conducted, and DNN models were tested for calibration | ||
| 520 | |a RESULTS: 277 patients were included. The area under the curve (AUC) for the DNN models was 0.93 for OS and 0.91 for DSS. AUC for the CPH models was 0.82 for OS and 0.84 for DSS. The DNN models were well-calibrated: OS model (slope = 1.02, intercept = -0.06) and DSS model (slope = 0.79, intercept = 0.21) | ||
| 520 | |a CONCLUSIONS: A deep learning-based model demonstrated excellent performance, superior to that of CPH models, in the prediction of pediatric GU-RMS survival. Deep learning approaches may enable improved prognostication for patients with rare cancers | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Artificial intelligence | |
| 650 | 4 | |a Machine learning | |
| 650 | 4 | |a Prognostication | |
| 650 | 4 | |a Sarcoma | |
| 650 | 4 | |a Urogenital | |
| 700 | 1 | |a Zamora, Alvaro |e verfasserin |4 aut | |
| 700 | 1 | |a Velaer, Kyla |e verfasserin |4 aut | |
| 700 | 1 | |a Greenberg, Daniel R |e verfasserin |4 aut | |
| 700 | 1 | |a Sheth, Kunj R |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Surgical oncology |d 1997 |g 36(2021) vom: 04. März, Seite 23-27 |w (DE-627)NLM012658448 |x 1879-3320 |7 nnns |
| 773 | 1 | 8 | |g volume:36 |g year:2021 |g day:04 |g month:03 |g pages:23-27 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1016/j.suronc.2020.11.002 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 36 |j 2021 |b 04 |c 03 |h 23-27 | ||