Cargando…

Machine Learning for Recurrence Prediction of Gynecologic Cancers Using Lynch Syndrome-Related Screening Markers

SIMPLE SUMMARY: Recurrent patients with gynecologic cancer experience a difficult situation when using immune checkpoint inhibitors based on mismatch repair gene immunohistochemistry and microsatellite instability. Six machine learning algorithms were used to create predictive models with seven pros...

Descripción completa

Detalles Bibliográficos
Autores principales: Kim, Byung Wook, Choi, Min Chul, Kim, Min Kyu, Lee, Jeong-Won, Kim, Min Tae, Noh, Joseph J., Park, Hyun, Jung, Sang Geun, Joo, Won Duk, Song, Seung Hun, Lee, Chan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8616351/
https://www.ncbi.nlm.nih.gov/pubmed/34830824
http://dx.doi.org/10.3390/cancers13225670
_version_ 1784604326641008640
author Kim, Byung Wook
Choi, Min Chul
Kim, Min Kyu
Lee, Jeong-Won
Kim, Min Tae
Noh, Joseph J.
Park, Hyun
Jung, Sang Geun
Joo, Won Duk
Song, Seung Hun
Lee, Chan
author_facet Kim, Byung Wook
Choi, Min Chul
Kim, Min Kyu
Lee, Jeong-Won
Kim, Min Tae
Noh, Joseph J.
Park, Hyun
Jung, Sang Geun
Joo, Won Duk
Song, Seung Hun
Lee, Chan
author_sort Kim, Byung Wook
collection PubMed
description SIMPLE SUMMARY: Recurrent patients with gynecologic cancer experience a difficult situation when using immune checkpoint inhibitors based on mismatch repair gene immunohistochemistry and microsatellite instability. Six machine learning algorithms were used to create predictive models with seven prospective features (four MMR IHC [MLH1, MSH2, MSH6, and PMS2], MSI, Age 60, and tumor size). The experimental results showed that the RF-based model performed best at predicting gynecologic cancer recurrence, with AUCs of 0.818 and 0.826 for the 5-fold cross-validation (CV) and 5-fold CV with 10 repetitions, respectively. This provides novel and baseline results of patients with recurrent gynecologic cancer using immune checkpoint inhibitors by using machine learning methods based on Lynch syndrome-related screening markers. ABSTRACT: To support the implementation of genome-based precision medicine, we developed machine learning models that predict the recurrence of patients with gynecologic cancer in using immune checkpoint inhibitors (ICI) based on clinical and pathologic characteristics, including Lynch syndrome-related screening markers such as immunohistochemistry (IHC) and microsatellite instability (MSI) tests. To accomplish our goal, we reviewed the patient demographics, clinical data, and pathological results from their medical records. Then we identified seven potential characteristics (four MMR IHC [MLH1, MSH2, MSH6, and PMS2], MSI, Age 60, and tumor size). Following that, predictive models were built based on these variables using six machine learning algorithms: logistic regression (LR), support vector machine (SVM), naive Bayes (NB), random forest (RF), gradient boosting (GB), and extreme gradient boosting (EGB) (XGBoost). The experimental results showed that the RF-based model performed best at predicting gynecologic cancer recurrence, with AUCs of 0.818 and 0.826 for the 5-fold cross-validation (CV) and 5-fold CV with 10 repetitions, respectively. This study provides novel and baseline results about predicting the recurrence of gynecologic cancer in patients using ICI by using machine learning methods based on Lynch syndrome-related screening markers.
format Online
Article
Text
id pubmed-8616351
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-86163512021-11-26 Machine Learning for Recurrence Prediction of Gynecologic Cancers Using Lynch Syndrome-Related Screening Markers Kim, Byung Wook Choi, Min Chul Kim, Min Kyu Lee, Jeong-Won Kim, Min Tae Noh, Joseph J. Park, Hyun Jung, Sang Geun Joo, Won Duk Song, Seung Hun Lee, Chan Cancers (Basel) Article SIMPLE SUMMARY: Recurrent patients with gynecologic cancer experience a difficult situation when using immune checkpoint inhibitors based on mismatch repair gene immunohistochemistry and microsatellite instability. Six machine learning algorithms were used to create predictive models with seven prospective features (four MMR IHC [MLH1, MSH2, MSH6, and PMS2], MSI, Age 60, and tumor size). The experimental results showed that the RF-based model performed best at predicting gynecologic cancer recurrence, with AUCs of 0.818 and 0.826 for the 5-fold cross-validation (CV) and 5-fold CV with 10 repetitions, respectively. This provides novel and baseline results of patients with recurrent gynecologic cancer using immune checkpoint inhibitors by using machine learning methods based on Lynch syndrome-related screening markers. ABSTRACT: To support the implementation of genome-based precision medicine, we developed machine learning models that predict the recurrence of patients with gynecologic cancer in using immune checkpoint inhibitors (ICI) based on clinical and pathologic characteristics, including Lynch syndrome-related screening markers such as immunohistochemistry (IHC) and microsatellite instability (MSI) tests. To accomplish our goal, we reviewed the patient demographics, clinical data, and pathological results from their medical records. Then we identified seven potential characteristics (four MMR IHC [MLH1, MSH2, MSH6, and PMS2], MSI, Age 60, and tumor size). Following that, predictive models were built based on these variables using six machine learning algorithms: logistic regression (LR), support vector machine (SVM), naive Bayes (NB), random forest (RF), gradient boosting (GB), and extreme gradient boosting (EGB) (XGBoost). The experimental results showed that the RF-based model performed best at predicting gynecologic cancer recurrence, with AUCs of 0.818 and 0.826 for the 5-fold cross-validation (CV) and 5-fold CV with 10 repetitions, respectively. This study provides novel and baseline results about predicting the recurrence of gynecologic cancer in patients using ICI by using machine learning methods based on Lynch syndrome-related screening markers. MDPI 2021-11-12 /pmc/articles/PMC8616351/ /pubmed/34830824 http://dx.doi.org/10.3390/cancers13225670 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Kim, Byung Wook
Choi, Min Chul
Kim, Min Kyu
Lee, Jeong-Won
Kim, Min Tae
Noh, Joseph J.
Park, Hyun
Jung, Sang Geun
Joo, Won Duk
Song, Seung Hun
Lee, Chan
Machine Learning for Recurrence Prediction of Gynecologic Cancers Using Lynch Syndrome-Related Screening Markers
title Machine Learning for Recurrence Prediction of Gynecologic Cancers Using Lynch Syndrome-Related Screening Markers
title_full Machine Learning for Recurrence Prediction of Gynecologic Cancers Using Lynch Syndrome-Related Screening Markers
title_fullStr Machine Learning for Recurrence Prediction of Gynecologic Cancers Using Lynch Syndrome-Related Screening Markers
title_full_unstemmed Machine Learning for Recurrence Prediction of Gynecologic Cancers Using Lynch Syndrome-Related Screening Markers
title_short Machine Learning for Recurrence Prediction of Gynecologic Cancers Using Lynch Syndrome-Related Screening Markers
title_sort machine learning for recurrence prediction of gynecologic cancers using lynch syndrome-related screening markers
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8616351/
https://www.ncbi.nlm.nih.gov/pubmed/34830824
http://dx.doi.org/10.3390/cancers13225670
work_keys_str_mv AT kimbyungwook machinelearningforrecurrencepredictionofgynecologiccancersusinglynchsyndromerelatedscreeningmarkers
AT choiminchul machinelearningforrecurrencepredictionofgynecologiccancersusinglynchsyndromerelatedscreeningmarkers
AT kimminkyu machinelearningforrecurrencepredictionofgynecologiccancersusinglynchsyndromerelatedscreeningmarkers
AT leejeongwon machinelearningforrecurrencepredictionofgynecologiccancersusinglynchsyndromerelatedscreeningmarkers
AT kimmintae machinelearningforrecurrencepredictionofgynecologiccancersusinglynchsyndromerelatedscreeningmarkers
AT nohjosephj machinelearningforrecurrencepredictionofgynecologiccancersusinglynchsyndromerelatedscreeningmarkers
AT parkhyun machinelearningforrecurrencepredictionofgynecologiccancersusinglynchsyndromerelatedscreeningmarkers
AT jungsanggeun machinelearningforrecurrencepredictionofgynecologiccancersusinglynchsyndromerelatedscreeningmarkers
AT joowonduk machinelearningforrecurrencepredictionofgynecologiccancersusinglynchsyndromerelatedscreeningmarkers
AT songseunghun machinelearningforrecurrencepredictionofgynecologiccancersusinglynchsyndromerelatedscreeningmarkers
AT leechan machinelearningforrecurrencepredictionofgynecologiccancersusinglynchsyndromerelatedscreeningmarkers