Iterative random forest-based identification of a novel population with high risk of complications post non-cardiac surgery

Abstract Assessing the risk of postoperative cardiovascular events before performing non-cardiac surgery is clinically important. The current risk score systems for preoperative evaluation may not adequately represent a small subset of high-risk populations. Accordingly, this study aimed at applying...

Full description

Saved in:
Bibliographic Details
Main Authors: Tomohisa Seki, Toru Takiguchi, Yu Akagi, Hiromasa Ito, Kazumi Kubota, Kana Miyake, Masafumi Okada, Yoshimasa Kawazoe
Format: Article
Language:English
Published: Nature Portfolio 2024-11-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-024-78482-4
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850196075086872576
author Tomohisa Seki
Toru Takiguchi
Yu Akagi
Hiromasa Ito
Kazumi Kubota
Kana Miyake
Masafumi Okada
Yoshimasa Kawazoe
author_facet Tomohisa Seki
Toru Takiguchi
Yu Akagi
Hiromasa Ito
Kazumi Kubota
Kana Miyake
Masafumi Okada
Yoshimasa Kawazoe
author_sort Tomohisa Seki
collection DOAJ
description Abstract Assessing the risk of postoperative cardiovascular events before performing non-cardiac surgery is clinically important. The current risk score systems for preoperative evaluation may not adequately represent a small subset of high-risk populations. Accordingly, this study aimed at applying iterative random forest to analyze combinations of factors that could potentially be clinically valuable in identifying these high-risk populations. To this end, we used the Japan Medical Data Center database, which includes claims data from Japan between January 2005 and April 2021, and employed iterative random forests to extract factor combinations that influence outcomes. The analysis demonstrated that a combination of a prior history of stroke and extremely low LDL-C levels was associated with a high non-cardiac postoperative risk. The incidence of major adverse cardiovascular events in the population characterized by the incidence of previous stroke and extremely low LDL-C levels was 15.43 events per 100 person-30 days [95% confidence interval, 6.66–30.41] in the test data. At this stage, the results only show correlation rather than causation; however, these findings may offer valuable insights for preoperative risk assessment in non-cardiac surgery.
format Article
id doaj-art-b96751a2d0a4445a9299d49a07f00d5e
institution OA Journals
issn 2045-2322
language English
publishDate 2024-11-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-b96751a2d0a4445a9299d49a07f00d5e2025-08-20T02:13:35ZengNature PortfolioScientific Reports2045-23222024-11-0114111110.1038/s41598-024-78482-4Iterative random forest-based identification of a novel population with high risk of complications post non-cardiac surgeryTomohisa Seki0Toru Takiguchi1Yu Akagi2Hiromasa Ito3Kazumi Kubota4Kana Miyake5Masafumi Okada6Yoshimasa Kawazoe7Department of Healthcare Information Management, The University of Tokyo HospitalDepartment of Healthcare Information Management, The University of Tokyo HospitalDepartment of Biomedical Informatics, Graduate School of Medicine, The University of TokyoDepartment of Healthcare Information Management, The University of Tokyo HospitalDepartment of Healthcare Information Management, The University of Tokyo HospitalDepartment of Healthcare Information Management, The University of Tokyo HospitalDepartment of Healthcare Information Management, The University of Tokyo HospitalDepartment of Healthcare Information Management, The University of Tokyo HospitalAbstract Assessing the risk of postoperative cardiovascular events before performing non-cardiac surgery is clinically important. The current risk score systems for preoperative evaluation may not adequately represent a small subset of high-risk populations. Accordingly, this study aimed at applying iterative random forest to analyze combinations of factors that could potentially be clinically valuable in identifying these high-risk populations. To this end, we used the Japan Medical Data Center database, which includes claims data from Japan between January 2005 and April 2021, and employed iterative random forests to extract factor combinations that influence outcomes. The analysis demonstrated that a combination of a prior history of stroke and extremely low LDL-C levels was associated with a high non-cardiac postoperative risk. The incidence of major adverse cardiovascular events in the population characterized by the incidence of previous stroke and extremely low LDL-C levels was 15.43 events per 100 person-30 days [95% confidence interval, 6.66–30.41] in the test data. At this stage, the results only show correlation rather than causation; however, these findings may offer valuable insights for preoperative risk assessment in non-cardiac surgery.https://doi.org/10.1038/s41598-024-78482-4Perioperative riskMachine learningIterative random forestsNon-cardiac surgery
spellingShingle Tomohisa Seki
Toru Takiguchi
Yu Akagi
Hiromasa Ito
Kazumi Kubota
Kana Miyake
Masafumi Okada
Yoshimasa Kawazoe
Iterative random forest-based identification of a novel population with high risk of complications post non-cardiac surgery
Scientific Reports
Perioperative risk
Machine learning
Iterative random forests
Non-cardiac surgery
title Iterative random forest-based identification of a novel population with high risk of complications post non-cardiac surgery
title_full Iterative random forest-based identification of a novel population with high risk of complications post non-cardiac surgery
title_fullStr Iterative random forest-based identification of a novel population with high risk of complications post non-cardiac surgery
title_full_unstemmed Iterative random forest-based identification of a novel population with high risk of complications post non-cardiac surgery
title_short Iterative random forest-based identification of a novel population with high risk of complications post non-cardiac surgery
title_sort iterative random forest based identification of a novel population with high risk of complications post non cardiac surgery
topic Perioperative risk
Machine learning
Iterative random forests
Non-cardiac surgery
url https://doi.org/10.1038/s41598-024-78482-4
work_keys_str_mv AT tomohisaseki iterativerandomforestbasedidentificationofanovelpopulationwithhighriskofcomplicationspostnoncardiacsurgery
AT torutakiguchi iterativerandomforestbasedidentificationofanovelpopulationwithhighriskofcomplicationspostnoncardiacsurgery
AT yuakagi iterativerandomforestbasedidentificationofanovelpopulationwithhighriskofcomplicationspostnoncardiacsurgery
AT hiromasaito iterativerandomforestbasedidentificationofanovelpopulationwithhighriskofcomplicationspostnoncardiacsurgery
AT kazumikubota iterativerandomforestbasedidentificationofanovelpopulationwithhighriskofcomplicationspostnoncardiacsurgery
AT kanamiyake iterativerandomforestbasedidentificationofanovelpopulationwithhighriskofcomplicationspostnoncardiacsurgery
AT masafumiokada iterativerandomforestbasedidentificationofanovelpopulationwithhighriskofcomplicationspostnoncardiacsurgery
AT yoshimasakawazoe iterativerandomforestbasedidentificationofanovelpopulationwithhighriskofcomplicationspostnoncardiacsurgery