Cargando…

Explainable Artificial Intelligence for Prediction of Complete Surgical Cytoreduction in Advanced-Stage Epithelial Ovarian Cancer

Complete surgical cytoreduction (R0 resection) is the single most important prognosticator in epithelial ovarian cancer (EOC). Explainable Artificial Intelligence (XAI) could clarify the influence of static and real-time features in the R0 resection prediction. We aimed to develop an AI-based predic...

Descripción completa

Detalles Bibliográficos
Autores principales: Laios, Alexandros, Kalampokis, Evangelos, Johnson, Racheal, Thangavelu, Amudha, Tarabanis, Constantine, Nugent, David, De Jong, Diederick
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9030484/
https://www.ncbi.nlm.nih.gov/pubmed/35455723
http://dx.doi.org/10.3390/jpm12040607
_version_ 1784692151101161472
author Laios, Alexandros
Kalampokis, Evangelos
Johnson, Racheal
Thangavelu, Amudha
Tarabanis, Constantine
Nugent, David
De Jong, Diederick
author_facet Laios, Alexandros
Kalampokis, Evangelos
Johnson, Racheal
Thangavelu, Amudha
Tarabanis, Constantine
Nugent, David
De Jong, Diederick
author_sort Laios, Alexandros
collection PubMed
description Complete surgical cytoreduction (R0 resection) is the single most important prognosticator in epithelial ovarian cancer (EOC). Explainable Artificial Intelligence (XAI) could clarify the influence of static and real-time features in the R0 resection prediction. We aimed to develop an AI-based predictive model for the R0 resection outcome, apply a methodology to explain the prediction, and evaluate the interpretability by analysing feature interactions. The retrospective cohort finally assessed 571 consecutive advanced-stage EOC patients who underwent cytoreductive surgery. An eXtreme Gradient Boosting (XGBoost) algorithm was employed to develop the predictive model including mostly patient- and surgery-specific variables. The Shapley Additive explanations (SHAP) framework was used to provide global and local explainability for the predictive model. The XGBoost accurately predicted R0 resection (area under curve [AUC] = 0.866; 95% confidence interval [CI] = 0.8–0.93). We identified “turning points” that increased the probability of complete cytoreduction including Intraoperative Mapping of Ovarian Cancer Score and Peritoneal Carcinomatosis Index < 4 and <5, respectively, followed by Surgical Complexity Score > 4, patient’s age < 60 years, and largest tumour bulk < 5 cm in a surgical environment of optimized infrastructural support. We demonstrated high model accuracy for the R0 resection prediction in EOC patients and provided novel global and local feature explainability that can be used for quality control and internal audit.
format Online
Article
Text
id pubmed-9030484
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-90304842022-04-23 Explainable Artificial Intelligence for Prediction of Complete Surgical Cytoreduction in Advanced-Stage Epithelial Ovarian Cancer Laios, Alexandros Kalampokis, Evangelos Johnson, Racheal Thangavelu, Amudha Tarabanis, Constantine Nugent, David De Jong, Diederick J Pers Med Article Complete surgical cytoreduction (R0 resection) is the single most important prognosticator in epithelial ovarian cancer (EOC). Explainable Artificial Intelligence (XAI) could clarify the influence of static and real-time features in the R0 resection prediction. We aimed to develop an AI-based predictive model for the R0 resection outcome, apply a methodology to explain the prediction, and evaluate the interpretability by analysing feature interactions. The retrospective cohort finally assessed 571 consecutive advanced-stage EOC patients who underwent cytoreductive surgery. An eXtreme Gradient Boosting (XGBoost) algorithm was employed to develop the predictive model including mostly patient- and surgery-specific variables. The Shapley Additive explanations (SHAP) framework was used to provide global and local explainability for the predictive model. The XGBoost accurately predicted R0 resection (area under curve [AUC] = 0.866; 95% confidence interval [CI] = 0.8–0.93). We identified “turning points” that increased the probability of complete cytoreduction including Intraoperative Mapping of Ovarian Cancer Score and Peritoneal Carcinomatosis Index < 4 and <5, respectively, followed by Surgical Complexity Score > 4, patient’s age < 60 years, and largest tumour bulk < 5 cm in a surgical environment of optimized infrastructural support. We demonstrated high model accuracy for the R0 resection prediction in EOC patients and provided novel global and local feature explainability that can be used for quality control and internal audit. MDPI 2022-04-10 /pmc/articles/PMC9030484/ /pubmed/35455723 http://dx.doi.org/10.3390/jpm12040607 Text en © 2022 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
Laios, Alexandros
Kalampokis, Evangelos
Johnson, Racheal
Thangavelu, Amudha
Tarabanis, Constantine
Nugent, David
De Jong, Diederick
Explainable Artificial Intelligence for Prediction of Complete Surgical Cytoreduction in Advanced-Stage Epithelial Ovarian Cancer
title Explainable Artificial Intelligence for Prediction of Complete Surgical Cytoreduction in Advanced-Stage Epithelial Ovarian Cancer
title_full Explainable Artificial Intelligence for Prediction of Complete Surgical Cytoreduction in Advanced-Stage Epithelial Ovarian Cancer
title_fullStr Explainable Artificial Intelligence for Prediction of Complete Surgical Cytoreduction in Advanced-Stage Epithelial Ovarian Cancer
title_full_unstemmed Explainable Artificial Intelligence for Prediction of Complete Surgical Cytoreduction in Advanced-Stage Epithelial Ovarian Cancer
title_short Explainable Artificial Intelligence for Prediction of Complete Surgical Cytoreduction in Advanced-Stage Epithelial Ovarian Cancer
title_sort explainable artificial intelligence for prediction of complete surgical cytoreduction in advanced-stage epithelial ovarian cancer
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9030484/
https://www.ncbi.nlm.nih.gov/pubmed/35455723
http://dx.doi.org/10.3390/jpm12040607
work_keys_str_mv AT laiosalexandros explainableartificialintelligenceforpredictionofcompletesurgicalcytoreductioninadvancedstageepithelialovariancancer
AT kalampokisevangelos explainableartificialintelligenceforpredictionofcompletesurgicalcytoreductioninadvancedstageepithelialovariancancer
AT johnsonracheal explainableartificialintelligenceforpredictionofcompletesurgicalcytoreductioninadvancedstageepithelialovariancancer
AT thangaveluamudha explainableartificialintelligenceforpredictionofcompletesurgicalcytoreductioninadvancedstageepithelialovariancancer
AT tarabanisconstantine explainableartificialintelligenceforpredictionofcompletesurgicalcytoreductioninadvancedstageepithelialovariancancer
AT nugentdavid explainableartificialintelligenceforpredictionofcompletesurgicalcytoreductioninadvancedstageepithelialovariancancer
AT dejongdiederick explainableartificialintelligenceforpredictionofcompletesurgicalcytoreductioninadvancedstageepithelialovariancancer