Evaluation of machine learning strategies for imaging confirmed prostate cancer recurrence prediction on electronic health records.

Cancer recurrence Ga-68-PSMA PET/CT Machine learning Multivariate analysis Prostate cancer

Journal

Computers in biology and medicine
ISSN: 1879-0534
Titre abrégé: Comput Biol Med
Pays: United States
ID NLM: 1250250

Informations de publication

Date de publication:
Apr 2022
Historique:
received: 21 09 2021
revised: 21 01 2022
accepted: 21 01 2022
pubmed: 9 2 2022
medline: 9 2 2022
entrez: 8 2 2022
Statut: ppublish

Résumé

The main screening parameter to monitor prostate cancer recurrence (PCR) after primary treatment is the serum concentration of prostate-specific antigen (PSA). In recent years, Ga-68-PSMA PET/CT has become an important method for additional diagnostics in patients with biochemical recurrence. While Ga-68-PSMA PET/CT performs better, it is an expensive, invasive, and time-consuming examination. Therefore, in this study, we aim to employ modern multivariate Machine Learning (ML) methods on electronic health records (EHR) of prostate cancer patients to improve the prediction of imaging confirmed PCR (IPCR). We retrospectively analyzed the clinical information of 272 patients, who were examined using Ga-68-PSMA PET/CT. The PSA values ranged from 0 ng/mL to 2270.38 ng/mL with a median PSA level at 1.79 ng/mL. We performed a descriptive analysis using Logistic Regression. Additionally, we evaluated the predictive performance of Logistic Regression, Support Vector Machine, Gradient Boosting, and Random Forest. Finally, we assessed the importance of all features using Ensemble Feature Selection (EFS). The descriptive analysis found significant associations between IPCR and logarithmic PSA values as well as between IPCR and performed hormonal therapy. Our models were able to predict IPCR with an AUC score of 0.78 ± 0.13 (mean ± standard deviation) and a sensitivity of 0.997 ± 0.01. Features such as PSA, PSA doubling time, PSA velocity, hormonal therapy, radiation treatment, and injected activity show high importance for IPCR prediction using EFS. This study demonstrates the potential of employing a multitude of parameters into multivariate ML models to improve identification of non-recurring patients compared to the current focus on the main screening parameter (PSA). We showed that ML models are able to predict IPCR, detectable by Ga-68-PSMA PET/CT, and thereby pave the way for optimized early imaging and treatment.

Sections du résumé

BACKGROUND BACKGROUND
The main screening parameter to monitor prostate cancer recurrence (PCR) after primary treatment is the serum concentration of prostate-specific antigen (PSA). In recent years, Ga-68-PSMA PET/CT has become an important method for additional diagnostics in patients with biochemical recurrence.
PURPOSE OBJECTIVE
While Ga-68-PSMA PET/CT performs better, it is an expensive, invasive, and time-consuming examination. Therefore, in this study, we aim to employ modern multivariate Machine Learning (ML) methods on electronic health records (EHR) of prostate cancer patients to improve the prediction of imaging confirmed PCR (IPCR).
METHODS METHODS
We retrospectively analyzed the clinical information of 272 patients, who were examined using Ga-68-PSMA PET/CT. The PSA values ranged from 0 ng/mL to 2270.38 ng/mL with a median PSA level at 1.79 ng/mL. We performed a descriptive analysis using Logistic Regression. Additionally, we evaluated the predictive performance of Logistic Regression, Support Vector Machine, Gradient Boosting, and Random Forest. Finally, we assessed the importance of all features using Ensemble Feature Selection (EFS).
RESULTS RESULTS
The descriptive analysis found significant associations between IPCR and logarithmic PSA values as well as between IPCR and performed hormonal therapy. Our models were able to predict IPCR with an AUC score of 0.78 ± 0.13 (mean ± standard deviation) and a sensitivity of 0.997 ± 0.01. Features such as PSA, PSA doubling time, PSA velocity, hormonal therapy, radiation treatment, and injected activity show high importance for IPCR prediction using EFS.
CONCLUSION CONCLUSIONS
This study demonstrates the potential of employing a multitude of parameters into multivariate ML models to improve identification of non-recurring patients compared to the current focus on the main screening parameter (PSA). We showed that ML models are able to predict IPCR, detectable by Ga-68-PSMA PET/CT, and thereby pave the way for optimized early imaging and treatment.

Identifiants

DOI: 10.1016/j.compbiomed.2022.105263 PMID: 35131608
pubmed: 35131608
pii: S0010-4825(22)00055-5
doi: 10.1016/j.compbiomed.2022.105263
pii:
doi:

Types de publication

Letter

Langues

eng

Sous-ensembles de citation

IM

Pagination

105263

Informations de copyright

Copyright © 2022 Elsevier Ltd. All rights reserved.

Auteurs

Jacqueline Michelle Beinecke (JM)

Department of Mathematics and Computer Science at the Philipps University Marburg, Germany; Institute for Medical Informatics at the University Medical Center Göttingen, Göttingen, Germany. Electronic address: jacquelinemichelle.beinecke@med.uni-goettingen.de.

Patrick Anders (P)

Department of Nuclear Medicine, University Hospital Marburg, Germany.

Tino Schurrat (T)

Department of Nuclear Medicine, University Hospital Marburg, Germany.

Dominik Heider (D)

Department of Mathematics and Computer Science at the Philipps University Marburg, Germany.

Markus Luster (M)

Department of Nuclear Medicine, University Hospital Marburg, Germany.

Damiano Librizzi (D)

Department of Nuclear Medicine, University Hospital Marburg, Germany.

Anne-Christin Hauschild (AC)

Department of Mathematics and Computer Science at the Philipps University Marburg, Germany; Institute for Medical Informatics at the University Medical Center Göttingen, Göttingen, Germany.

Classifications MeSH