Artificial Intelligence Supports Decision Making during Open-Chest Surgery of Rare Congenital Heart Defects

The human right ventricle is barely monitored during open-chest surgery due to the absence of intraoperative imaging techniques capable of elaborating its complex function. Accordingly, artificial intelligence could not be adopted for this specific task. We recently proposed a video-based approach f...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Francesco Paolo Lo Muzio, Giacomo Rozzi, Stefano Rossi, Giovanni Battista Luciani, Ruben Foresti, Aderville Cabassi, Lorenzo Fassina, Michele Miragoli
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	supervised machine learning right ventricle kinematics Tetralogy of Fallot surgery decision making prognosis prediction Medicine R
Acceso en línea:	https://doaj.org/article/aeda63df669940299c381d323914d7ca
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:aeda63df669940299c381d323914d7ca
record_format	dspace
spelling	oai:doaj.org-article:aeda63df669940299c381d323914d7ca2021-11-25T18:01:48ZArtificial Intelligence Supports Decision Making during Open-Chest Surgery of Rare Congenital Heart Defects10.3390/jcm102253302077-0383https://doaj.org/article/aeda63df669940299c381d323914d7ca2021-11-01T00:00:00Zhttps://www.mdpi.com/2077-0383/10/22/5330https://doaj.org/toc/2077-0383The human right ventricle is barely monitored during open-chest surgery due to the absence of intraoperative imaging techniques capable of elaborating its complex function. Accordingly, artificial intelligence could not be adopted for this specific task. We recently proposed a video-based approach for the real-time evaluation of the epicardial kinematics to support medical decisions. Here, we employed two supervised machine learning algorithms based on our technique to predict the patients’ outcomes before chest closure. Videos of the beating hearts were acquired before and after pulmonary valve replacement in twelve Tetralogy of Fallot patients and recordings were properly labeled as the “unhealthy” and “healthy” classes. We extracted frequency-domain-related features to train different supervised machine learning models and selected their best characteristics via 10-fold cross-validation and optimization processes. Decision surfaces were built to classify two additional patients having good and unfavorable clinical outcomes. The k-nearest neighbors and support vector machine showed the highest prediction accuracy; the patients’ class was identified with a true positive rate ≥95% and the decision surfaces correctly classified the additional patients in the “healthy” (good outcome) or “unhealthy” (unfavorable outcome) classes. We demonstrated that classifiers employed with our video-based technique may aid cardiac surgeons in decision making before chest closure.Francesco Paolo Lo MuzioGiacomo RozziStefano RossiGiovanni Battista LucianiRuben ForestiAderville CabassiLorenzo FassinaMichele MiragoliMDPI AGarticlesupervised machine learningright ventricle kinematicsTetralogy of Fallotsurgery decision makingprognosis predictionMedicineRENJournal of Clinical Medicine, Vol 10, Iss 5330, p 5330 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	supervised machine learning right ventricle kinematics Tetralogy of Fallot surgery decision making prognosis prediction Medicine R
spellingShingle	supervised machine learning right ventricle kinematics Tetralogy of Fallot surgery decision making prognosis prediction Medicine R Francesco Paolo Lo Muzio Giacomo Rozzi Stefano Rossi Giovanni Battista Luciani Ruben Foresti Aderville Cabassi Lorenzo Fassina Michele Miragoli Artificial Intelligence Supports Decision Making during Open-Chest Surgery of Rare Congenital Heart Defects
description	The human right ventricle is barely monitored during open-chest surgery due to the absence of intraoperative imaging techniques capable of elaborating its complex function. Accordingly, artificial intelligence could not be adopted for this specific task. We recently proposed a video-based approach for the real-time evaluation of the epicardial kinematics to support medical decisions. Here, we employed two supervised machine learning algorithms based on our technique to predict the patients’ outcomes before chest closure. Videos of the beating hearts were acquired before and after pulmonary valve replacement in twelve Tetralogy of Fallot patients and recordings were properly labeled as the “unhealthy” and “healthy” classes. We extracted frequency-domain-related features to train different supervised machine learning models and selected their best characteristics via 10-fold cross-validation and optimization processes. Decision surfaces were built to classify two additional patients having good and unfavorable clinical outcomes. The k-nearest neighbors and support vector machine showed the highest prediction accuracy; the patients’ class was identified with a true positive rate ≥95% and the decision surfaces correctly classified the additional patients in the “healthy” (good outcome) or “unhealthy” (unfavorable outcome) classes. We demonstrated that classifiers employed with our video-based technique may aid cardiac surgeons in decision making before chest closure.
format	article
author	Francesco Paolo Lo Muzio Giacomo Rozzi Stefano Rossi Giovanni Battista Luciani Ruben Foresti Aderville Cabassi Lorenzo Fassina Michele Miragoli
author_facet	Francesco Paolo Lo Muzio Giacomo Rozzi Stefano Rossi Giovanni Battista Luciani Ruben Foresti Aderville Cabassi Lorenzo Fassina Michele Miragoli
author_sort	Francesco Paolo Lo Muzio
title	Artificial Intelligence Supports Decision Making during Open-Chest Surgery of Rare Congenital Heart Defects
title_short	Artificial Intelligence Supports Decision Making during Open-Chest Surgery of Rare Congenital Heart Defects
title_full	Artificial Intelligence Supports Decision Making during Open-Chest Surgery of Rare Congenital Heart Defects
title_fullStr	Artificial Intelligence Supports Decision Making during Open-Chest Surgery of Rare Congenital Heart Defects
title_full_unstemmed	Artificial Intelligence Supports Decision Making during Open-Chest Surgery of Rare Congenital Heart Defects
title_sort	artificial intelligence supports decision making during open-chest surgery of rare congenital heart defects
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/aeda63df669940299c381d323914d7ca
work_keys_str_mv	AT francescopaololomuzio artificialintelligencesupportsdecisionmakingduringopenchestsurgeryofrarecongenitalheartdefects AT giacomorozzi artificialintelligencesupportsdecisionmakingduringopenchestsurgeryofrarecongenitalheartdefects AT stefanorossi artificialintelligencesupportsdecisionmakingduringopenchestsurgeryofrarecongenitalheartdefects AT giovannibattistaluciani artificialintelligencesupportsdecisionmakingduringopenchestsurgeryofrarecongenitalheartdefects AT rubenforesti artificialintelligencesupportsdecisionmakingduringopenchestsurgeryofrarecongenitalheartdefects AT adervillecabassi artificialintelligencesupportsdecisionmakingduringopenchestsurgeryofrarecongenitalheartdefects AT lorenzofassina artificialintelligencesupportsdecisionmakingduringopenchestsurgeryofrarecongenitalheartdefects AT michelemiragoli artificialintelligencesupportsdecisionmakingduringopenchestsurgeryofrarecongenitalheartdefects
_version_	1718411700988805120

Artificial Intelligence Supports Decision Making during Open-Chest Surgery of Rare Congenital Heart Defects

Ejemplares similares