• Je něco špatně v tomto záznamu ?

Machine Learning-Assisted Recurrence Prediction for Patients With Early-Stage Non-Small-Cell Lung Cancer

A. Janik, M. Torrente, L. Costabello, V. Calvo, B. Walsh, C. Camps, SK. Mohamed, AL. Ortega, V. Nováček, B. Massutí, P. Minervini, MRG. Campelo, E. Del Barco, J. Bosch-Barrera, E. Menasalvas, M. Timilsina, M. Provencio

. 2023 ; 7 (-) : e2200062. [pub] -

Jazyk angličtina Země Spojené státy americké

Typ dokumentu časopisecké články, práce podpořená grantem

Perzistentní odkaz   https://www.medvik.cz/link/bmc23016946

PURPOSE: Stratifying patients with cancer according to risk of relapse can personalize their care. In this work, we provide an answer to the following research question: How to use machine learning to estimate probability of relapse in patients with early-stage non-small-cell lung cancer (NSCLC)? MATERIALS AND METHODS: For predicting relapse in 1,387 patients with early-stage (I-II) NSCLC from the Spanish Lung Cancer Group data (average age 65.7 years, female 24.8%, male 75.2%), we train tabular and graph machine learning models. We generate automatic explanations for the predictions of such models. For models trained on tabular data, we adopt SHapley Additive exPlanations local explanations to gauge how each patient feature contributes to the predicted outcome. We explain graph machine learning predictions with an example-based method that highlights influential past patients. RESULTS: Machine learning models trained on tabular data exhibit a 76% accuracy for the random forest model at predicting relapse evaluated with a 10-fold cross-validation (the model was trained 10 times with different independent sets of patients in test, train, and validation sets, and the reported metrics are averaged over these 10 test sets). Graph machine learning reaches 68% accuracy over a held-out test set of 200 patients, calibrated on a held-out set of 100 patients. CONCLUSION: Our results show that machine learning models trained on tabular and graph data can enable objective, personalized, and reproducible prediction of relapse and, therefore, disease outcome in patients with early-stage NSCLC. With further prospective and multisite validation, and additional radiological and molecular data, this prognostic model could potentially serve as a predictive decision support tool for deciding the use of adjuvant treatments in early-stage lung cancer.

000      
00000naa a2200000 a 4500
001      
bmc23016946
003      
CZ-PrNML
005      
20231026105440.0
007      
ta
008      
231013s2023 xxu f 000 0|eng||
009      
AR
024    7_
$a 10.1200/CCI.22.00062 $2 doi
035    __
$a (PubMed)37428988
040    __
$a ABA008 $b cze $d ABA008 $e AACR2
041    0_
$a eng
044    __
$a xxu
100    1_
$a Janik, Adrianna $u Accenture Labs, Dublin, Ireland $1 https://orcid.org/0000000243874563
245    10
$a Machine Learning-Assisted Recurrence Prediction for Patients With Early-Stage Non-Small-Cell Lung Cancer / $c A. Janik, M. Torrente, L. Costabello, V. Calvo, B. Walsh, C. Camps, SK. Mohamed, AL. Ortega, V. Nováček, B. Massutí, P. Minervini, MRG. Campelo, E. Del Barco, J. Bosch-Barrera, E. Menasalvas, M. Timilsina, M. Provencio
520    9_
$a PURPOSE: Stratifying patients with cancer according to risk of relapse can personalize their care. In this work, we provide an answer to the following research question: How to use machine learning to estimate probability of relapse in patients with early-stage non-small-cell lung cancer (NSCLC)? MATERIALS AND METHODS: For predicting relapse in 1,387 patients with early-stage (I-II) NSCLC from the Spanish Lung Cancer Group data (average age 65.7 years, female 24.8%, male 75.2%), we train tabular and graph machine learning models. We generate automatic explanations for the predictions of such models. For models trained on tabular data, we adopt SHapley Additive exPlanations local explanations to gauge how each patient feature contributes to the predicted outcome. We explain graph machine learning predictions with an example-based method that highlights influential past patients. RESULTS: Machine learning models trained on tabular data exhibit a 76% accuracy for the random forest model at predicting relapse evaluated with a 10-fold cross-validation (the model was trained 10 times with different independent sets of patients in test, train, and validation sets, and the reported metrics are averaged over these 10 test sets). Graph machine learning reaches 68% accuracy over a held-out test set of 200 patients, calibrated on a held-out set of 100 patients. CONCLUSION: Our results show that machine learning models trained on tabular and graph data can enable objective, personalized, and reproducible prediction of relapse and, therefore, disease outcome in patients with early-stage NSCLC. With further prospective and multisite validation, and additional radiological and molecular data, this prognostic model could potentially serve as a predictive decision support tool for deciding the use of adjuvant treatments in early-stage lung cancer.
650    _2
$a lidé $7 D006801
650    _2
$a mužské pohlaví $7 D008297
650    _2
$a ženské pohlaví $7 D005260
650    _2
$a senioři $7 D000368
650    12
$a nemalobuněčný karcinom plic $x diagnóza $x terapie $7 D002289
650    12
$a nádory plic $x diagnóza $x terapie $7 D008175
650    _2
$a lokální recidiva nádoru $x diagnóza $7 D009364
650    _2
$a strojové učení $7 D000069550
650    _2
$a prognóza $7 D011379
655    _2
$a časopisecké články $7 D016428
655    _2
$a práce podpořená grantem $7 D013485
700    1_
$a Torrente, Maria $u Medical Oncology Department, Hospital Universitario Puerta de Hierro Majadahonda, Madrid, Spain $1 https://orcid.org/0000000187917660
700    1_
$a Costabello, Luca $u Accenture Labs, Dublin, Ireland $1 https://orcid.org/0000000207209347
700    1_
$a Calvo, Virginia $u Medical Oncology Department, Hospital Universitario Puerta de Hierro Majadahonda, Madrid, Spain
700    1_
$a Walsh, Brian $u Data Science Institute, University of Galway, Galway, Ireland $u Insight Centre for Data Analytics, University of Galway, Galway, Ireland
700    1_
$a Camps, Carlos $u Hospital General de Valencia, Valencia, Spain $1 https://orcid.org/0000000206485403
700    1_
$a Mohamed, Sameh K $u Data Science Institute, University of Galway, Galway, Ireland $u Insight Centre for Data Analytics, University of Galway, Galway, Ireland $1 https://orcid.org/0000000326592406
700    1_
$a Ortega, Ana L $u Hospital Universitario de Jaén, Jaén, Spain $1 https://orcid.org/0000000257273371
700    1_
$a Nováček, Vít $u Data Science Institute, University of Galway, Galway, Ireland $u Insight Centre for Data Analytics, University of Galway, Galway, Ireland $u Faculty of Informatics, Masaryk University, Brno, Czech Republic $u Masaryk Memorial Cancer Institute, Brno, Czech Republic
700    1_
$a Massutí, Bartomeu $u Hospital General Universitario de Alicante, Alicante, Spain
700    1_
$a Minervini, Pasquale $u University College London, London, United Kingdom $1 https://orcid.org/000000028442602X
700    1_
$a Campelo, M Rosario Garcia $u Complejo Hospitalario Universitario A Coruña, A Coruña, Spain
700    1_
$a Del Barco, Edel $u Hospital Universitario de Salamanca, Salamanca, Spain
700    1_
$a Bosch-Barrera, Joaquim $u Institut Català d'Oncologia, Hospital Universitari Dr. Josep Trueta, Girona, Spain $1 https://orcid.org/0000000208937821
700    1_
$a Menasalvas, Ernestina $u Polytechnic University of Madrid, Madrid, Spain $1 https://orcid.org/0000000256156798 $7 xx0010626
700    1_
$a Timilsina, Mohan $u Data Science Institute, University of Galway, Galway, Ireland $u Insight Centre for Data Analytics, University of Galway, Galway, Ireland $1 https://orcid.org/0000000338869898
700    1_
$a Provencio, Mariano $u Medical Oncology Department, Hospital Universitario Puerta de Hierro Majadahonda, Madrid, Spain $1 https://orcid.org/0000000163157919
773    0_
$w MED00214015 $t JCO clinical cancer informatics $x 2473-4276 $g Roč. 7, č. - (2023), s. e2200062
856    41
$u https://pubmed.ncbi.nlm.nih.gov/37428988 $y Pubmed
910    __
$a ABA008 $b sig $c sign $y - $z 0
990    __
$a 20231013 $b ABA008
991    __
$a 20231026105435 $b ABA008
999    __
$a ok $b bmc $g 2000460 $s 1203308
BAS    __
$a 3
BAS    __
$a PreBMC-MEDLINE
BMC    __
$a 2023 $b 7 $c - $d e2200062 $e - $i 2473-4276 $m JCO clinical cancer informatics $n JCO Clin Cancer Inform $x MED00214015
LZP    __
$a Pubmed-20231013

Najít záznam

Citační ukazatele

Možnosti archivace