Machine Learning Evaluation of Biliary Atresia Patients to Predict Long-Term Outcome after the Kasai Procedure

Kasai portoenterostomy (KP) represents the first-line treatment for biliary atresia (BA). The purpose was to compare the accuracy of quantitative parameters extracted from laboratory tests, US imaging, and MR imaging studies using machine learning (ML) algorithms to predict the long-term medical out...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Martina Caruso, Carlo Ricciardi, Gregorio Delli Paoli, Fabiola Di Dato, Leandro Donisi, Valeria Romeo, Mario Petretta, Raffaele Iorio, Giuseppe Cesarelli, Arturo Brunetti, Simone Maurea
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	artificial intelligence bilirubin ultrasound magnetic resonance shear-wave elastography Technology T Biology (General) QH301-705.5
Acceso en línea:	https://doaj.org/article/55cbc0ed547f48119409b0707aad259a
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:55cbc0ed547f48119409b0707aad259a
record_format	dspace
spelling	oai:doaj.org-article:55cbc0ed547f48119409b0707aad259a2021-11-25T16:46:22ZMachine Learning Evaluation of Biliary Atresia Patients to Predict Long-Term Outcome after the Kasai Procedure10.3390/bioengineering81101522306-5354https://doaj.org/article/55cbc0ed547f48119409b0707aad259a2021-10-01T00:00:00Zhttps://www.mdpi.com/2306-5354/8/11/152https://doaj.org/toc/2306-5354Kasai portoenterostomy (KP) represents the first-line treatment for biliary atresia (BA). The purpose was to compare the accuracy of quantitative parameters extracted from laboratory tests, US imaging, and MR imaging studies using machine learning (ML) algorithms to predict the long-term medical outcome in native liver survivor BA patients after KP. Twenty-four patients were evaluated according to clinical and laboratory data at initial evaluation (median follow-up = 9.7 years) after KP as having ideal (<i>n</i> = 15) or non-ideal (<i>n</i> = 9) medical outcomes. Patients were re-evaluated after an additional 4 years and classified in group 1 (<i>n</i> = 12) as stable and group 2 (<i>n</i> = 12) as non-stable in the disease course. Laboratory and quantitative imaging parameters were merged to test ML algorithms. Total and direct bilirubin (TB and DB), as laboratory parameters, and US stiffness, as an imaging parameter, were the only statistically significant parameters between the groups. The best algorithm in terms of accuracy, sensitivity, specificity, and AUCROC was naive Bayes algorithm, selecting only laboratory parameters (TB and DB). This preliminary ML analysis confirms the fundamental role of TB and DB values in predicting the long-term medical outcome for BA patients after KP, even though their values may be within the normal range. Physicians should be alert when TB and DB values change slightly.Martina CarusoCarlo RicciardiGregorio Delli PaoliFabiola Di DatoLeandro DonisiValeria RomeoMario PetrettaRaffaele IorioGiuseppe CesarelliArturo BrunettiSimone MaureaMDPI AGarticleartificial intelligencebilirubinultrasoundmagnetic resonanceshear-wave elastographyTechnologyTBiology (General)QH301-705.5ENBioengineering, Vol 8, Iss 152, p 152 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	artificial intelligence bilirubin ultrasound magnetic resonance shear-wave elastography Technology T Biology (General) QH301-705.5
spellingShingle	artificial intelligence bilirubin ultrasound magnetic resonance shear-wave elastography Technology T Biology (General) QH301-705.5 Martina Caruso Carlo Ricciardi Gregorio Delli Paoli Fabiola Di Dato Leandro Donisi Valeria Romeo Mario Petretta Raffaele Iorio Giuseppe Cesarelli Arturo Brunetti Simone Maurea Machine Learning Evaluation of Biliary Atresia Patients to Predict Long-Term Outcome after the Kasai Procedure
description	Kasai portoenterostomy (KP) represents the first-line treatment for biliary atresia (BA). The purpose was to compare the accuracy of quantitative parameters extracted from laboratory tests, US imaging, and MR imaging studies using machine learning (ML) algorithms to predict the long-term medical outcome in native liver survivor BA patients after KP. Twenty-four patients were evaluated according to clinical and laboratory data at initial evaluation (median follow-up = 9.7 years) after KP as having ideal (<i>n</i> = 15) or non-ideal (<i>n</i> = 9) medical outcomes. Patients were re-evaluated after an additional 4 years and classified in group 1 (<i>n</i> = 12) as stable and group 2 (<i>n</i> = 12) as non-stable in the disease course. Laboratory and quantitative imaging parameters were merged to test ML algorithms. Total and direct bilirubin (TB and DB), as laboratory parameters, and US stiffness, as an imaging parameter, were the only statistically significant parameters between the groups. The best algorithm in terms of accuracy, sensitivity, specificity, and AUCROC was naive Bayes algorithm, selecting only laboratory parameters (TB and DB). This preliminary ML analysis confirms the fundamental role of TB and DB values in predicting the long-term medical outcome for BA patients after KP, even though their values may be within the normal range. Physicians should be alert when TB and DB values change slightly.
format	article
author	Martina Caruso Carlo Ricciardi Gregorio Delli Paoli Fabiola Di Dato Leandro Donisi Valeria Romeo Mario Petretta Raffaele Iorio Giuseppe Cesarelli Arturo Brunetti Simone Maurea
author_facet	Martina Caruso Carlo Ricciardi Gregorio Delli Paoli Fabiola Di Dato Leandro Donisi Valeria Romeo Mario Petretta Raffaele Iorio Giuseppe Cesarelli Arturo Brunetti Simone Maurea
author_sort	Martina Caruso
title	Machine Learning Evaluation of Biliary Atresia Patients to Predict Long-Term Outcome after the Kasai Procedure
title_short	Machine Learning Evaluation of Biliary Atresia Patients to Predict Long-Term Outcome after the Kasai Procedure
title_full	Machine Learning Evaluation of Biliary Atresia Patients to Predict Long-Term Outcome after the Kasai Procedure
title_fullStr	Machine Learning Evaluation of Biliary Atresia Patients to Predict Long-Term Outcome after the Kasai Procedure
title_full_unstemmed	Machine Learning Evaluation of Biliary Atresia Patients to Predict Long-Term Outcome after the Kasai Procedure
title_sort	machine learning evaluation of biliary atresia patients to predict long-term outcome after the kasai procedure
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/55cbc0ed547f48119409b0707aad259a
work_keys_str_mv	AT martinacaruso machinelearningevaluationofbiliaryatresiapatientstopredictlongtermoutcomeafterthekasaiprocedure AT carloricciardi machinelearningevaluationofbiliaryatresiapatientstopredictlongtermoutcomeafterthekasaiprocedure AT gregoriodellipaoli machinelearningevaluationofbiliaryatresiapatientstopredictlongtermoutcomeafterthekasaiprocedure AT fabioladidato machinelearningevaluationofbiliaryatresiapatientstopredictlongtermoutcomeafterthekasaiprocedure AT leandrodonisi machinelearningevaluationofbiliaryatresiapatientstopredictlongtermoutcomeafterthekasaiprocedure AT valeriaromeo machinelearningevaluationofbiliaryatresiapatientstopredictlongtermoutcomeafterthekasaiprocedure AT mariopetretta machinelearningevaluationofbiliaryatresiapatientstopredictlongtermoutcomeafterthekasaiprocedure AT raffaeleiorio machinelearningevaluationofbiliaryatresiapatientstopredictlongtermoutcomeafterthekasaiprocedure AT giuseppecesarelli machinelearningevaluationofbiliaryatresiapatientstopredictlongtermoutcomeafterthekasaiprocedure AT arturobrunetti machinelearningevaluationofbiliaryatresiapatientstopredictlongtermoutcomeafterthekasaiprocedure AT simonemaurea machinelearningevaluationofbiliaryatresiapatientstopredictlongtermoutcomeafterthekasaiprocedure
_version_	1718412955080458240

Machine Learning Evaluation of Biliary Atresia Patients to Predict Long-Term Outcome after the Kasai Procedure

Ejemplares similares