Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 May 9;12(10):3354.
doi: 10.3390/jcm12103354.

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

Tatsuya Nakachi  1 , Masahisa Yamane  2 , Koichi Kishi  3 , Toshiya Muramatsu  4 , Hisayuki Okada  5 , Yuji Oikawa  6 , Ryohei Yoshikawa  7 , Tomohiro Kawasaki  8 , Hiroyuki Tanaka  9 , Osamu Katoh  10
Affiliations

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

Tatsuya Nakachi et al. J Clin Med. .

Abstract

(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.

Keywords: chronic total coronary occlusion; machine learning; percutaneous coronary intervention.

PubMed Disclaimer

Conflict of interest statement

Katoh has served as a consultant for Asahi Intecc, Nipro, and Canon medical. Oikawa has received remuneration for lecturing from Abbott Medical Japan, Boston Scientific Japan, Medtronic Japan, NIPRO Corporation, TERUMO Corporation and other remunerations such as gifts from KANEKA Medix Corporation and Orbus Neich Medical. Yoshikawa has received remuneration for lecturing from TERUMO Corporation, Abbott Medical Japan, Kaneka Medix Corporation, KANEKA Medix Corporation, NIPRO Corporation, and Orbus Neich Medical. Kawasaki has received remuneration for lecturing from Abbott Medical Japan, Boston Scientific Japan, Japan Lifeline, Medtronic Japan, and AMGEN. All other authors have reported that they have no relationships relevant to the contents of this paper to disclose.

Figures

Figure 1
Figure 1
Areas under the ROC (a) and PR (b) curves for machine learning models to predict CTO-PCI failure. Abbreviations: PR, precision/recall; ROC, receiver operating characteristics; XGBoost, extreme gradient boosting.
Figure 2
Figure 2
Areas under the ROC (a) and PR (b) curves comparing the best ML model with existing prediction scores for CTO-PCI failure. Abbreviations: CTO, chronic total occlusion; ML, machine learning; PCI, percutaneous coronary intervention; PR, precision/recall; ROC, receiver operating characteristics; XGBoost, extreme gradient boosting.
Figure 3
Figure 3
Observed versus predicted risk of CTO-PCI failure on XGBoost. Abbreviations: CTO, chronic total occlusion; PCI, percutaneous coronary intervention; XGBoost, extreme gradient boosting.
Figure 4
Figure 4
The importance matrix plot for XGBoost. Abbreviations: CABG, coronary artery bypass grafting; CTO, chronic total occlusion; XGBoost, extreme gradient boosting.
See this image and copyright information in PMC

References

    1. Tsao C.W., Aday A.W., Almarzooq Z.I., Alonso A., Beaton A.Z., Bittencourt M.S., Boehme A.K., Buxton A.E., Carson A.P., Commodore-Mensah Y., et al. Heart Disease and Stroke Statistics—2022 Update: A Report from the American Heart Association. Circulation. 2022;145:e153–e639. doi: 10.1161/CIR.0000000000001052. - DOI - PubMed
    1. Morino Y., Abe M., Morimoto T., Kimura T., Hayashi Y., Muramatsu T., Ochiai M., Noguchi Y., Kato K., Shibata Y., et al. Predicting Successful Guidewire Crossing through Chronic Total Occlusion of Native Coronary Lesions within 30 Minutes: The J-CTO (Multicenter CTO Registry in Japan) Score as a Difficulty Grading and Time Assessment Tool. JACC Cardiovasc. Interv. 2011;4:213–221. doi: 10.1016/j.jcin.2010.09.024. - DOI - PubMed
    1. Christopoulos G., Kandzari D.E., Yeh R.W., Jaffer F.A., Karmpaliotis D., Wyman M.R., Alaswad K., Lombardi W., Grantham J.A., Moses J., et al. Development and validation of a novel scoring system for predicting technical success of chronic total occlusion percutaneous coronary interventions: The PROGRESS CTO (Prospective Global Registry for the Study of Chronic Total Occlusion Intervention) Score. JACC Cardiovasc. Interv. 2016;9:1–9. doi: 10.1016/j.jcin.2015.09.022. - DOI - PubMed
    1. Alessandrino G., Chevalier B., Lefèvre T., Sanguineti F., Garot P., Unterseeh T., Hovasse T., Morice M.C., Louvard Y. A clinical and angiographic scoring system to predict the probability of successful first-attempt percutaneous coronary intervention in patients with total chronic coronary occlusion. JACC Cardiovasc. Interv. 2015;8:1540–1548. doi: 10.1016/j.jcin.2015.07.009. - DOI - PubMed
    1. Szijgyarto Z., Rampat R., Werner G.S., Ho C., Reifart N., Lefevre T., Louvard Y., Avran A., Kambis M., Buettner H.J., et al. Derivation and Validation of a Chronic Total Coronary Occlusion Intervention Procedural Success Score from the 20,000-Patient EuroCTO Registry: The EuroCTO (CASTLE) Score. JACC Cardiovasc. Interv. 2019;12:335–342. doi: 10.1016/j.jcin.2018.11.020. - DOI - PubMed

LinkOut - more resources