Real-world evaluation of an algorithmic machine-learning-guided testing approach in stable chest pain: a multinational, multicohort study

被引:5
作者
Oikonomou, Evangelos K. [1 ]
Aminorroaya, Arya [1 ]
Dhingra, Lovedeep S. [1 ]
Partridge, Caitlin [2 ]
Velazquez, Eric J. [1 ]
Desai, Nihar R. [1 ]
Krumholz, Harlan M. [1 ,3 ]
Miller, Edward J. [1 ]
Khera, Rohan [1 ,3 ,4 ,5 ]
机构
[1] Yale Sch Med, Dept Internal Med, Sect Cardiovasc Med, 333 Cedar St,POB 208017, New Haven, CT 06520 USA
[2] Yale Ctr Clin Invest, 2 Church St South, New Haven, CT 06519 USA
[3] Yale New Haven Hosp, Ctr Outcomes Res & Evaluat, 195 Church St 5th Floor, New Haven, CT 06510 USA
[4] Yale Sch Med, Sect Biomed Informat & Data Sci, 100 Coll St, New Haven, CT 06511 USA
[5] Yale Sch Publ Hlth, Dept Biostat, Sect Hlth Informat, 60 Coll St, New Haven, CT 06510 USA
来源
EUROPEAN HEART JOURNAL - DIGITAL HEALTH | 2024年 / 5卷 / 03期
基金
美国国家卫生研究院;
关键词
Machine learning; Chest pain; Artificial intelligence; Clinical decision support; APPROPRIATE USE CRITERIA; PHENOMAPPING-DERIVED TOOL; COMPUTED-TOMOGRAPHY; CT ANGIOGRAPHY; CORONARY; RISK; BIAS;
D O I
10.1093/ehjdh/ztae023
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
Aims An algorithmic strategy for anatomical vs. functional testing in suspected coronary artery disease (CAD) (Anatomical vs. Stress teSting decIsion Support Tool; ASSIST) is associated with better outcomes than random selection. However, in the real world, this decision is rarely random. We explored the agreement between a provider-driven vs. simulated algorithmic approach to cardiac testing and its association with outcomes across multinational cohorts. Methods and results In two cohorts of functional vs. anatomical testing in a US hospital health system [Yale; 2013-2023; n = 130 196 (97.0%) vs. n = 4020 (3.0%), respectively], and the UK Biobank [n = 3320 (85.1%) vs. n = 581 (14.9%), respectively], we examined outcomes stratified by agreement between the real-world and ASSIST-recommended strategies. Younger age, female sex, Black race, and diabetes history were independently associated with lower odds of ASSIST-aligned testing. Over a median of 4.9 (interquartile range [IQR]: 2.4-7.1) and 5.4 (IQR: 2.6-8.8) years, referral to the ASSIST-recommended strategy was associated with a lower risk of acute myocardial infarction or death (hazard ratio(adjusted): 0.81, 95% confidence interval [CI] 0.77-0.85, P < 0.001 and 0.74 [95% CI 0.60-0.90], P = 0.003, respectively), an effect that remained significant across years, test types, and risk profiles. In post hoc analyses of anatomical-first testing in the Prospective Multicentre Imaging Study for Evaluation of Chest Pain (PROMISE) trial, alignment with ASSIST was independently associated with a 17% and 30% higher risk of detecting CAD in any vessel or the left main artery/proximal left anterior descending coronary artery, respectively. Conclusion In cohorts where historical practices largely favour functional testing, alignment with an algorithmic approach to cardiac testing defined by ASSIST was associated with a lower risk of adverse outcomes. This highlights the potential utility of a data-driven approach in the diagnostic management of CAD.
引用
收藏
页码:303 / 313
页数:11
相关论文
共 50 条
  • [31] Machine learning in a real-world PFO study: analysis of data from multi-centers in China
    Luo, Dongling
    Yang, Ziyang
    Zhang, Gangcheng
    Shen, Qunshan
    Zhang, Hongwei
    Lai, Junxing
    Hu, Hui
    He, Jianxin
    Wu, Shulin
    Zhang, Caojin
    BMC MEDICAL INFORMATICS AND DECISION MAKING, 2022, 22 (01)
  • [32] Comprehensive evaluation of machine learning models for real-world air quality prediction and health risk assessment by AirQ+
    Ebru Koçak
    Earth Science Informatics, 2025, 18 (3)
  • [33] Using machine learning to identify risk factors for pancreatic cancer: a retrospective cohort study of real-world data
    Su, Na
    Tang, Rui
    Zhang, Yice
    Ni, Jiaqi
    Huang, Yimei
    Liu, Chunqi
    Xiao, Yuzhou
    Zhu, Baoting
    Zhao, Yinglan
    FRONTIERS IN PHARMACOLOGY, 2024, 15
  • [34] Forecasting of residential unit's heat demands: a comparison of machine learning techniques in a real-world case study
    Kemper, Neele
    Heider, Michael
    Pietruschka, Dirk
    Haehner, Joerg
    ENERGY SYSTEMS-OPTIMIZATION MODELING SIMULATION AND ECONOMIC ASPECTS, 2023, 16 (1): : 281 - 315
  • [35] Assessment of the effect of a comprehensive chest radiograph deep learning model on radiologist reports and patient outcomes: a real-world observational study
    Jones, Catherine M.
    Danaher, Luke
    Milne, Michael R.
    Tang, Cyril
    Seah, Jarrel
    Oakden-Rayner, Luke
    Johnson, Andrew
    Buchlak, Quinlan D.
    Esmaili, Nazanin
    BMJ OPEN, 2021, 11 (12):
  • [36] Real-World Biomarker Testing and Treatment Patterns Identified Using Machine Learning in Early Non-small Cell Lung Cancer
    Lee, J. M.
    Schulze, K.
    Nedzesky, J.
    Ng, C.
    Ogale, S.
    Johnson, A.
    Hasan, H.
    Secrest, M. H.
    Cohen, A.
    Castellanos, E.
    Estola, E.
    Estevez, M.
    Lee, J. S.
    JOURNAL OF THORACIC ONCOLOGY, 2023, 18 (11) : S555 - S556
  • [37] Machine learning algorithms to predict intraoperative hemorrhage in surgical patients: a modeling study of real-world data in Shanghai, China
    Shi, Ying
    Zhang, Guangming
    Ma, Chiye
    Xu, Jiading
    Xu, Kejia
    Zhang, Wenyi
    Wu, Jianren
    Xu, Liling
    BMC MEDICAL INFORMATICS AND DECISION MAKING, 2023, 23 (01)
  • [38] Developing a machine learning model for predicting venlafaxine active moiety concentration: a retrospective study using real-world evidence
    Chang, Luyao
    Hao, Xin
    Yu, Jing
    Zhang, Jinyuan
    Liu, Yimeng
    Ye, Xuxiao
    Yu, Ze
    Gao, Fei
    Pang, Xiaolu
    Zhou, Chunhua
    INTERNATIONAL JOURNAL OF CLINICAL PHARMACY, 2024, 46 (04) : 899 - 909
  • [39] Applying machine learning techniques to predict the risk of lung metastases from rectal cancer: a real-world retrospective study
    Qiu, Binxu
    Shen, Zixiong
    Yang, Dongliang
    Wang, Quan
    FRONTIERS IN ONCOLOGY, 2023, 13
  • [40] Machine learning algorithms to predict intraoperative hemorrhage in surgical patients: a modeling study of real-world data in Shanghai, China
    Ying Shi
    Guangming Zhang
    Chiye Ma
    Jiading Xu
    Kejia Xu
    Wenyi Zhang
    Jianren Wu
    Liling Xu
    BMC Medical Informatics and Decision Making, 23