Cargando…

Machine Learning for Prediction of Technical Results of Percutaneous Coronary Intervention for Chronic Total Occlusion

(1) Background: The probability of technical success in percutaneous coronary intervention (PCI) for chronic total occlusion (CTO) represents essential information for specifying the priority of PCI for treatment selection in patients with CTO. However, the predictabilities of existing scores based...

Descripción completa

Detalles Bibliográficos
Autores principales: Nakachi, Tatsuya, Yamane, Masahisa, Kishi, Koichi, Muramatsu, Toshiya, Okada, Hisayuki, Oikawa, Yuji, Yoshikawa, Ryohei, Kawasaki, Tomohiro, Tanaka, Hiroyuki, Katoh, Osamu
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10218988/
https://www.ncbi.nlm.nih.gov/pubmed/37240464
http://dx.doi.org/10.3390/jcm12103354
_version_ 1785048903543947264
author Nakachi, Tatsuya
Yamane, Masahisa
Kishi, Koichi
Muramatsu, Toshiya
Okada, Hisayuki
Oikawa, Yuji
Yoshikawa, Ryohei
Kawasaki, Tomohiro
Tanaka, Hiroyuki
Katoh, Osamu
author_facet Nakachi, Tatsuya
Yamane, Masahisa
Kishi, Koichi
Muramatsu, Toshiya
Okada, Hisayuki
Oikawa, Yuji
Yoshikawa, Ryohei
Kawasaki, Tomohiro
Tanaka, Hiroyuki
Katoh, Osamu
author_sort Nakachi, Tatsuya
collection PubMed
description (1) Background: The probability of technical success in percutaneous coronary intervention (PCI) for chronic total occlusion (CTO) represents essential information for specifying the priority of PCI for treatment selection in patients with CTO. However, the predictabilities of existing scores based on conventional regression analysis remain modest, leaving room for improvements in model discrimination. Recently, machine learning (ML) techniques have emerged as highly effective methods for prediction and decision-making in various disciplines. We therefore investigated the predictability of ML models for technical results of CTO-PCI and compared their performances to the results from existing scores, including J-CTO, CL, and CASTLE scores. (2) Methods: This analysis used data from the Japanese CTO-PCI expert registry, which enrolled 8760 consecutive patients undergoing CTO-PCI. The performance of prediction models was assessed using the area under the receiver operating curve (ROC-AUC). (3) Results: Technical success was achieved in 7990 procedures, accounting for an overall success rate of 91.2%. The best ML model, extreme gradient boosting (XGBoost), outperformed the conventional prediction scores with ROC-AUC (XGBoost 0.760 [95% confidence interval {CI}: 0.740–0.780] vs. J-CTO 0.697 [95%CI: 0.675–0.719], CL 0.662 [95%CI: 0.639–0.684], CASTLE 0.659 [95%CI: 0.636–0.681]; p < 0.005 for all). The XGBoost model demonstrated acceptable concordance between the observed and predicted probabilities of CTO-PCI failure. Calcification was the leading predictor. (4) Conclusions: ML techniques provide accurate, specific information regarding the likelihood of success in CTO-PCI, which would help select the best treatment for individual patients with CTO.
format Online
Article
Text
id pubmed-10218988
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-102189882023-05-27 Machine Learning for Prediction of Technical Results of Percutaneous Coronary Intervention for Chronic Total Occlusion Nakachi, Tatsuya Yamane, Masahisa Kishi, Koichi Muramatsu, Toshiya Okada, Hisayuki Oikawa, Yuji Yoshikawa, Ryohei Kawasaki, Tomohiro Tanaka, Hiroyuki Katoh, Osamu J Clin Med Article (1) Background: The probability of technical success in percutaneous coronary intervention (PCI) for chronic total occlusion (CTO) represents essential information for specifying the priority of PCI for treatment selection in patients with CTO. However, the predictabilities of existing scores based on conventional regression analysis remain modest, leaving room for improvements in model discrimination. Recently, machine learning (ML) techniques have emerged as highly effective methods for prediction and decision-making in various disciplines. We therefore investigated the predictability of ML models for technical results of CTO-PCI and compared their performances to the results from existing scores, including J-CTO, CL, and CASTLE scores. (2) Methods: This analysis used data from the Japanese CTO-PCI expert registry, which enrolled 8760 consecutive patients undergoing CTO-PCI. The performance of prediction models was assessed using the area under the receiver operating curve (ROC-AUC). (3) Results: Technical success was achieved in 7990 procedures, accounting for an overall success rate of 91.2%. The best ML model, extreme gradient boosting (XGBoost), outperformed the conventional prediction scores with ROC-AUC (XGBoost 0.760 [95% confidence interval {CI}: 0.740–0.780] vs. J-CTO 0.697 [95%CI: 0.675–0.719], CL 0.662 [95%CI: 0.639–0.684], CASTLE 0.659 [95%CI: 0.636–0.681]; p < 0.005 for all). The XGBoost model demonstrated acceptable concordance between the observed and predicted probabilities of CTO-PCI failure. Calcification was the leading predictor. (4) Conclusions: ML techniques provide accurate, specific information regarding the likelihood of success in CTO-PCI, which would help select the best treatment for individual patients with CTO. MDPI 2023-05-09 /pmc/articles/PMC10218988/ /pubmed/37240464 http://dx.doi.org/10.3390/jcm12103354 Text en © 2023 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
Nakachi, Tatsuya
Yamane, Masahisa
Kishi, Koichi
Muramatsu, Toshiya
Okada, Hisayuki
Oikawa, Yuji
Yoshikawa, Ryohei
Kawasaki, Tomohiro
Tanaka, Hiroyuki
Katoh, Osamu
Machine Learning for Prediction of Technical Results of Percutaneous Coronary Intervention for Chronic Total Occlusion
title Machine Learning for Prediction of Technical Results of Percutaneous Coronary Intervention for Chronic Total Occlusion
title_full Machine Learning for Prediction of Technical Results of Percutaneous Coronary Intervention for Chronic Total Occlusion
title_fullStr Machine Learning for Prediction of Technical Results of Percutaneous Coronary Intervention for Chronic Total Occlusion
title_full_unstemmed Machine Learning for Prediction of Technical Results of Percutaneous Coronary Intervention for Chronic Total Occlusion
title_short Machine Learning for Prediction of Technical Results of Percutaneous Coronary Intervention for Chronic Total Occlusion
title_sort machine learning for prediction of technical results of percutaneous coronary intervention for chronic total occlusion
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10218988/
https://www.ncbi.nlm.nih.gov/pubmed/37240464
http://dx.doi.org/10.3390/jcm12103354
work_keys_str_mv AT nakachitatsuya machinelearningforpredictionoftechnicalresultsofpercutaneouscoronaryinterventionforchronictotalocclusion
AT yamanemasahisa machinelearningforpredictionoftechnicalresultsofpercutaneouscoronaryinterventionforchronictotalocclusion
AT kishikoichi machinelearningforpredictionoftechnicalresultsofpercutaneouscoronaryinterventionforchronictotalocclusion
AT muramatsutoshiya machinelearningforpredictionoftechnicalresultsofpercutaneouscoronaryinterventionforchronictotalocclusion
AT okadahisayuki machinelearningforpredictionoftechnicalresultsofpercutaneouscoronaryinterventionforchronictotalocclusion
AT oikawayuji machinelearningforpredictionoftechnicalresultsofpercutaneouscoronaryinterventionforchronictotalocclusion
AT yoshikawaryohei machinelearningforpredictionoftechnicalresultsofpercutaneouscoronaryinterventionforchronictotalocclusion
AT kawasakitomohiro machinelearningforpredictionoftechnicalresultsofpercutaneouscoronaryinterventionforchronictotalocclusion
AT tanakahiroyuki machinelearningforpredictionoftechnicalresultsofpercutaneouscoronaryinterventionforchronictotalocclusion
AT katohosamu machinelearningforpredictionoftechnicalresultsofpercutaneouscoronaryinterventionforchronictotalocclusion