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 Jun 13;4(3):e299.
doi: 10.1002/mco2.299. eCollection 2023 Jun.

Diagnosis of acute myocardial infarction using a combination of circulating circular RNA cZNF292 and clinical information based on machine learning

Qiulian Zhou  1   2 , Jes-Niels Boeckel  3   4 , Jianhua Yao  5   6 , Juan Zhao  1   2   7 , Yuzheng Bai  1 , Yicheng Lv  1 , Meiyu Hu  1 , Danni Meng  1 , Yuan Xie  8 , Pujiao Yu  8 , Peng Xi  8 , Jiahong Xu  8 , Yi Zhang  5 , Stefanie Dimmeler  3 , Junjie Xiao  1   2
Affiliations

Diagnosis of acute myocardial infarction using a combination of circulating circular RNA cZNF292 and clinical information based on machine learning

Qiulian Zhou et al. MedComm (2020). .

Abstract

Circulating circular RNAs (circRNAs) are emerging as novel biomarkers for cardiovascular diseases (CVDs). Machine learning can provide optimal predictions on the diagnosis of diseases. Here we performed a proof-of-concept study to determine if combining circRNAs with an artificial intelligence approach works in diagnosing CVD. We used acute myocardial infarction (AMI) as a model setup to prove the claim. We determined the expression level of five hypoxia-induced circRNAs, including cZNF292, cAFF1, cDENND4C, cTHSD1, and cSRSF4, in the whole blood of coronary angiography positive AMI and negative non-AMI patients. Based on feature selection by using lasso with 10-fold cross validation, prediction model by logistic regression, and ROC curve analysis, we found that cZNF292 combined with clinical information (CM), including age, gender, body mass index, heart rate, and diastolic blood pressure, can predict AMI effectively. In a validation cohort, CM + cZNF292 can separate AMI and non-AMI patients, unstable angina and AMI patients, acute coronary syndromes (ACS), and non-ACS patients. RNA stability study demonstrated that cZNF292 was stable. Knockdown of cZNF292 in endothelial cells or cardiomyocytes showed anti-apoptosis effects in oxygen glucose deprivation/reoxygenation. Thus, we identify circulating cZNF292 as a potential biomarker for AMI and construct a prediction model "CM + cZNF292."

Keywords: acute myocardial infarction; biomarker; cZNF292; circular RNA; machine learning.

PubMed Disclaimer

Conflict of interest statement

Authors have no conflict of interests to disclose.

Figures

FIGURE 1
FIGURE 1
Quantitative reverse‐transcription polymerase chain reaction (qRT‐PCR) analysis of whole blood levels of cZNF292, cAFF1, cDENND4C, and cSRSF4 in acute myocardial infarction (AMI) and non‐AMI patients. n = 33 for non‐AMI (here refers to negative for coronary angiography); n = 42 for AMI (here refers to positive for coronary angiography).
FIGURE 2
FIGURE 2
Feature importance test and ROC curve for discovery cohort: (A) the feature importance test results based on Bagging Decision Trees; (B) ROC curve for cZNF292 (blue line) and clinical information (CM) + cZNF292 (red line). CM means a clinical model, including age, gender, body mass index (BMI), heart rate, and diastolic blood pressure (DBP). n = 33 for non‐acute myocardial infarction (AMI) (here refers to negative for coronary angiography); n = 42 for AMI (here refers to positive for coronary angiography).
FIGURE 3
FIGURE 3
cZNF292 is stable in human whole blood: (A) the mean CT value of cZNF292 in human whole blood treated with directly isolated, incubated for 24 h at RT, or frozen and thawed for five cycles before isolating RNA. n = 5 for directly isolated; n = 5 for 24 h RT; n = 5 for 5× thaw/freeze; (B) semiquantitative polymerase chain reaction (PCR) analysis of cZNF292 in human whole blood; (C) quantification of cZNF292 and ZNF292 after RNase R digestion by qPCR. n = 3 for Control; n = 3 for RNase R.
FIGURE 4
FIGURE 4
Quantitative reverse‐transcription polymerase chain reaction (qRT‐PCR) analysis and ROC curve of whole blood levels of cZNF292 in validation study: (A) qRT‐PCR analysis of whole blood levels of cZNF292 and cSRSF4 in non‐acute myocardial infarction (AMI) (here refers to unstable angina (UA) or stable angina) and AMI patients. n = 63 for non‐AMI; n = 75 for AMI; (B) ROC curve of AMI and non‐AMI patients for cZNF292 (blue line) and clinical information (CM) + cZNF292 (red line). n = 63 for non‐AMI; n = 75 for AMI; (C) qRT‐PCR analysis of whole blood levels of cZNF292 and cSRSF4 in UA and AMI patients. n = 15 for UA; n = 75 for AMI; (D) ROC curve of AMI and UA patients for cZNF292 (blue line) and CM + cZNF292 (red line). n = 15 for UA; n = 75 for AMI; (E) qRT‐PCR analysis of whole blood levels of cZNF292 and cSRSF4 in non‐acute coronary syndromes (ACS) (here refers to stable angina) and ACS patients (including UA and AMI). n = 48 for non‐ACS; n = 90 for ACS. (F) ROC curve of ACS and non‐ACS patients for cZNF292 (blue line) and CM + cZNF292 (red line). n = 48 for non‐ACS; n = 90 for ACS. CM means a clinical model, including age, gender, body mass index (BMI), heart rate, and diastolic blood pressure (DBP).
FIGURE 5
FIGURE 5
siRNA‐mediated silencing of cZNF292 inhibits apoptosis in human umbilical vein endothelial cell (HUVEC) and human embryonic stem cell–derived cardiomyocyte (hESC‐CM): (A) q‐polymerase chain reaction (PCR) analysis of cZNF292 in HUVEC treated with oxygen glucose deprivation/re‐oxygenation (OGD/R) (n = 6/group); (B) qPCR analysis of cZNF292 in HUVEC treated with siRNA cZNF292 (n = 6/group); (C) the TUNEL staining analysis of HUVEC apoptosis in OGD/R model treated with cZNF292 siRNA (n = 6/group); (D) qPCR analysis of cZNF292 in hESC‐CM treated with OGD/R (n = 6/group); (E) qPCR analysis of cZNF292 in hESC‐CM treated with siRNA cZNF292 (n = 6/group); (F) the TUNEL staining analysis of hESC‐CM apoptosis in OGD/R model treated with cZNF292 siRNA (n = 6/group). Scale bar: 100 μm in parts (C) and (F).
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Feng Y, Huang W, Paul C, et al. Mitochondrial nucleoid in cardiac homeostasis: bidirectional signaling of mitochondria and nucleus in cardiac diseases. Basic Res Cardiol. 2021;116(1):49. - PMC - PubMed
    1. Jusic A, Devaux Y, EU‐CardioRNA COST Action (CA17129) . Mitochondrial noncoding RNA‐regulatory network in cardiovascular disease. Basic Res Cardiol. 2020;115(3):23. - PubMed
    1. Deftereos SG, Beerkens FJ, Dangas GD, et al. Colchicine in cardiovascular disease: in‐depth review. Circulation. 2022;145(1):61‐78. - PMC - PubMed
    1. Gonzalez A, de Boer RA, Richards AM, et al. Cardiac remodelling—Part 1: From cells and tissues to circulating biomarkers. A review from the study group on biomarkers of the Heart Failure Association of the European Society of Cardiology. Eur J Heart Fail. 2022;24(6):927‐943. - PubMed
    1. Wang GK, Zhu JQ, Zhang JT, et al. Circulating microRNA: a novel potential biomarker for early diagnosis of acute myocardial infarction in humans. Eur Heart J. 2010;31(6):659‐666. - PubMed