1
|
Matetic A, Kyriacou T, Mamas MA. Machine-learning clustering analysis identifies novel phenogroups in patients with ST-elevation acute myocardial infarction. Int J Cardiol 2024; 411:132272. [PMID: 38880421 DOI: 10.1016/j.ijcard.2024.132272] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/11/2023] [Revised: 06/05/2024] [Accepted: 06/13/2024] [Indexed: 06/18/2024]
Abstract
BACKGROUND Machine learning clustering of patients with ST-elevation acute myocardial infarction (STEMI) may provide important insights into their risk profile, management and prognosis. METHODS All adult discharges for STEMI in the National Inpatient Sample (October 2015 to December 2019) were included, excluding patients with prior myocardial infarction. Machine-learning clustering analysis was used to define clusters based on 21 clinical attributes of interest. Main outcomes of the study were cluster-based comparison of risk profile, in-hospital clinical outcomes and utilization of invasive management. Binomial hierarchical multivariable logistic regression with adjusted odds ratios (aOR) and 95% confidence intervals (95% CI) was used to detect the between-cluster differences. RESULTS Out of overall 470,960 STEMI cases, the machine-learning analysis revealed 4 different clusters with 205,640 (cluster 0: 'behavioural risk cluster'), 146,400 (cluster 1: 'least comorbidity cluster'), 45,100 (cluster 2: 'diabetes with end-organ damage cluster') and 73,820 (cluster 3: 'cardiometabolic cluster') cases. Attributes with the highest importance for clustering were hypertension and diabetes. After multivariable adjustment, patients from 'diabetes with end-organ damage cluster' exhibited the worst mortality, MACCE and ischemic stroke (p < 0.001 for all), as well as the lowest utilization of invasive management (p < 0.001 for all), in comparison to other clusters. Patients from 'behavioural risk cluster' exhibited the best in-hospital prognosis and the highest utilization of invasive management, compared to other clusters (p < 0.001 for all). CONCLUSIONS Machine learning driven clustering of inpatients with STEMI reveals important population subgroups with distinct prevalence, risk profile, prognosis and management. Data driven approaches may identify high risk phenogroups and warrants further study.
Collapse
Affiliation(s)
- Andrija Matetic
- Department of Cardiology, University Hospital of Split, Split, Croatia; Keele Cardiovascular Research Group, Centre for Prognosis Research, Keele University, United Kingdom
| | - Theocharis Kyriacou
- School of Computer Science and Mathematics, Keele University, Keele, United Kingdom
| | - Mamas A Mamas
- Keele Cardiovascular Research Group, Centre for Prognosis Research, Keele University, United Kingdom; National Institute for Health and Care Research (NIHR), Birmingham Biomedical Research Centre, United Kingdom.
| |
Collapse
|
2
|
Gao W, Wang XY, Wang XJ, Huang L. An integrated signature of clinical metrics and immune-related genes as a prognostic indicator for ST-segment elevation myocardial infarction patient survival. Heliyon 2024; 10:e31247. [PMID: 38813183 PMCID: PMC11133808 DOI: 10.1016/j.heliyon.2024.e31247] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/14/2024] [Revised: 04/26/2024] [Accepted: 05/13/2024] [Indexed: 05/31/2024] Open
Abstract
Background The immune-inflammatory pathway plays a critical role in myocardial infarction development. However, few studies have systematically explored immune-related genes in relation to myocardial infarction prognosis using bioinformatic analysis. Our study aims to identify differentially expressed immune-related genes(DEIRGs) in ST-segment elevation myocardial infarction (STEMI) patients and investigate their association with clinical outcomes. Materials and methods We conducted a systematic review of Gene Expression Omnibus datasets, selecting GSE49925, GSE60993, and GSE61144 for analysis. DEIRGs were identified using GEO2R and overlapped across the chosen datasets. Functional enrichment analysis elucidated the DEIRGs' biological functions and pathways. We established an optimal prognostic prediction model using LASSO penalized Cox proportional hazards regression. The signature's clinical utility was evaluated through survival analysis, ROC curve assessment, and decision curve analysis. Additionally, we constructed a prognostic nomogram for survival rate prediction. External validation was performed using our own plasma samples. Results The resulting prognostic signature integrated two dysregulated DEIRGs (S100A12 and IL2RB) and two clinical variables (serum creatinine level and Gensini score). This signature effectively stratified patients into low- and high-risk groups. Survival analysis, ROC curve analysis, and decision curve analysis demonstrated its robust predictive performance and clinical utility within the first two years post-disease onset. External validation confirmed significant outcome differences between risk groups. Conclusions Our study establishes a prognostic signature that combines DEIRGs and clinical variables for STEMI patients. The signature exhibits promising predictive capabilities for patient stratification and survival risk assessment.
Collapse
Affiliation(s)
- Wei Gao
- Department of Heart Center, Tianjin Third Central Hospital, Tianjin, 300170, PR China
- Tianjin Key Laboratory of Extracorporeal Life Support for Critical Diseases, Tianjin Third Central Hospital, Tianjin, 300170, PR China
- Artificial Cell Engineering Technology Research Center, Tianjin, 300170, PR China
- Tianjin Institute of Hepatobiliary Disease, Tianjin, 300170, PR China
| | - Xiao-yan Wang
- Institute of Biomedical Science, Fudan University, Shanghai, 200030, PR China
| | - Xing-jie Wang
- Clinical Laboratory of Tianjin Chest Hospital, Tianjin, 300222, PR China
| | - Lei Huang
- Department of Heart Center, Tianjin Third Central Hospital, Tianjin, 300170, PR China
- Tianjin Key Laboratory of Extracorporeal Life Support for Critical Diseases, Tianjin Third Central Hospital, Tianjin, 300170, PR China
- Artificial Cell Engineering Technology Research Center, Tianjin, 300170, PR China
- Tianjin Institute of Hepatobiliary Disease, Tianjin, 300170, PR China
| |
Collapse
|
3
|
Patel SJ, Yousuf S, Padala JV, Reddy S, Saraf P, Nooh A, Fernandez Gutierrez LMA, Abdirahman AH, Tanveer R, Rai M. Advancements in Artificial Intelligence for Precision Diagnosis and Treatment of Myocardial Infarction: A Comprehensive Review of Clinical Trials and Randomized Controlled Trials. Cureus 2024; 16:e60119. [PMID: 38864061 PMCID: PMC11164835 DOI: 10.7759/cureus.60119] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 05/11/2024] [Indexed: 06/13/2024] Open
Abstract
Coronary artery disease (CAD) is still a serious global health issue that has a substantial impact on death and illness rates. The goal of primary prevention strategies is to lower the risk of developing CAD. Nevertheless, current methods usually rely on simple risk assessment instruments that might overlook significant individual risk factors. This limitation highlights the need for innovative methods that can accurately assess cardiovascular risk and offer personalized preventive care. Recent advances in machine learning and artificial intelligence (AI) have opened up interesting new avenues for optimizing primary preventive efforts for CAD and improving risk prediction models. By leveraging large-scale databases and advanced computational techniques, AI has the potential to fundamentally alter how cardiovascular risk is evaluated and managed. This review looks at current randomized controlled studies and clinical trials that explore the application of AI and machine learning to improve primary preventive measures for CAD. The emphasis is on their ability to recognize and include a range of risk elements in sophisticated risk assessment models.
Collapse
Affiliation(s)
- Syed J Patel
- Internal Medicine, S Nijalingappa Medical College and Hanagal Sri Kumareshwar Hospital and Research Centre, Bagalkot, IND
| | - Salma Yousuf
- Public Health, Jinnah Sindh Medical University, Karachi, PAK
| | | | - Shruta Reddy
- Internal Medicine, Sri Venkata Sai Medical College and Hospital, Mahbubnagar, IND
| | - Pranav Saraf
- Internal Medicine, Sri Ramaswamy Memorial Medical College and Hospital, Kattankulathur, IND
| | - Alaa Nooh
- Internal Medicine, China Medical University, Shenyang, CHN
| | | | | | - Rameen Tanveer
- Internal Medicine, Lakehead University, Thunder Bay, CAN
| | - Manju Rai
- Biotechnology, Shri Venkateshwara University, Gajraula, IND
| |
Collapse
|
4
|
Tang Y, Liu Y, Du Z, Wang Z, Pan S. Prediction of coronary artery lesions in children with Kawasaki syndrome based on machine learning. BMC Pediatr 2024; 24:158. [PMID: 38443868 PMCID: PMC10916227 DOI: 10.1186/s12887-024-04608-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/11/2023] [Accepted: 01/31/2024] [Indexed: 03/07/2024] Open
Abstract
OBJECTIVE Kawasaki syndrome (KS) is an acute vasculitis that affects children < 5 years of age and leads to coronary artery lesions (CAL) in about 20-25% of untreated cases. Machine learning (ML) is a branch of artificial intelligence (AI) that integrates complex data sets on a large scale and uses huge data to predict future events. The purpose of the present study was to use ML to present the model for early risk assessment of CAL in children with KS by different algorithms. METHODS A total of 158 children were enrolled from Women and Children's Hospital, Qingdao University, and divided into 70-30% as the training sets and the test sets for modeling and validation studies. There are several classifiers are constructed for models including the random forest (RF), the logistic regression (LR), and the eXtreme Gradient Boosting (XGBoost). Data preprocessing is analyzed before applying the classifiers to modeling. To avoid the problem of overfitting, the 5-fold cross validation method was used throughout all the data. RESULTS The area under the curve (AUC) of the RF model was 0.925 according to the validation of the test set. The average accuracy was 0.930 (95% CI, 0.905 to 0.956). The AUC of the LG model was 0.888 and the average accuracy was 0.893 (95% CI, 0,837 to 0.950). The AUC of the XGBoost model was 0.879 and the average accuracy was 0.935 (95% CI, 0.891 to 0.980). CONCLUSION The RF algorithm was used in the present study to construct a prediction model for CAL effectively, with an accuracy of 0.930 and AUC of 0.925. The novel model established by ML may help guide clinicians in the initial decision to make a more aggressive initial anti-inflammatory therapy. Due to the limitations of external validation and regional population characteristics, additional research is required to initiate a further application in the clinic.
Collapse
Affiliation(s)
- Yaqi Tang
- Heart Center, Qingdao Women and Children's Hospital, Qingdao University, Qingdao, China
| | - Yuhai Liu
- Dawning International Information Industry Co., Ltd., No. 78 Zhuzhou Road, Laoshan District, Qingdao, China
- Sugon Nanjing Institute, Co., Ltd., No. 519 Chengxin Avenue, Fangyuan Road, Jiangning District, Nanjing, China
| | - Zhanhui Du
- Heart Center, Qingdao Women and Children's Hospital, Qingdao University, Qingdao, China
| | - Zheqi Wang
- School of Mathematics, Jilin University, Changchun, China
| | - Silin Pan
- Heart Center, Qingdao Women and Children's Hospital, Qingdao University, Qingdao, China.
| |
Collapse
|
5
|
Tanaka T, Kojo K, Nagumo Y, Ikeda A, Shimizu T, Fujimoto S, Kakinuma T, Uchida M, Kimura T, Kandori S, Negoro H, Nishiyama H. A new clustering model based on the seminal plasma/serum ratios of multiple trace element concentrations in male patients with subfertility. Reprod Med Biol 2024; 23:e12584. [PMID: 38807752 PMCID: PMC11131575 DOI: 10.1002/rmb2.12584] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/01/2024] [Revised: 04/29/2024] [Accepted: 05/09/2024] [Indexed: 05/30/2024] Open
Abstract
Purpose To investigate whether seminal plasma (SP)/serum ratios of multiple trace elements (TEs) can classify patients with male subfertility. Methods SP/serum ratios of 20 TEs (lithium, sodium, magnesium, phosphorus, sulfur, potassium, calcium, manganese, iron, cobalt, copper, zinc, arsenic, selenium, rubidium, strontium, molybdenum, cesium, barium, and thallium) were calculated for healthy volunteers (n = 4) and those consulting for male subfertility (n = 245). Volunteer semen samples were collected by split ejaculation into early and subsequent fractions, and SP/serum ratio data were compared between fractions. The patients' SP/serum ratio data were used in an unsupervised clustering analysis and qualitatively compared with the data from the fractions of ejaculation from the volunteers. Semen quality parameters and pregnancy outcomes were compared between patient clusters. Results The early fraction of volunteers was characterized by lower phosphorus and arsenic and 18 other higher TEs than the subsequent fraction. Cluster analysis classified patients into four distinct clusters, one sharing characteristics with the early fraction and another with the subsequent fraction. One cluster with the early fraction characteristics had significantly lower semen volume and higher pregnancy rates from spontaneous pregnancies or intrauterine insemination. Conclusions Classification of patients based on SP/serum ratios of multiple TEs represents the dominance of fractions of ejaculation samples.
Collapse
Affiliation(s)
- Takazo Tanaka
- Department of Urology, Faculty of MedicineUniversity of TsukubaTsukubaIbarakiJapan
| | - Kosuke Kojo
- Department of Urology, Faculty of MedicineUniversity of TsukubaTsukubaIbarakiJapan
- Center for Human ReproductionInternational University of Health and Welfare HospitalNasushiobaraTochigiJapan
| | - Yoshiyuki Nagumo
- Department of Urology, Faculty of MedicineUniversity of TsukubaTsukubaIbarakiJapan
| | - Atsushi Ikeda
- Department of Urology, Faculty of MedicineUniversity of TsukubaTsukubaIbarakiJapan
| | - Takuya Shimizu
- Health Care Analysis CenterRenatech Co., Ltd.IseharaKanagawaJapan
| | | | - Toshiyuki Kakinuma
- Center for Human ReproductionInternational University of Health and Welfare HospitalNasushiobaraTochigiJapan
| | - Masahiro Uchida
- Department of UrologyTsukuba Gakuen HospitalTsukubaIbarakiJapan
| | - Tomokazu Kimura
- Department of Urology, Faculty of MedicineUniversity of TsukubaTsukubaIbarakiJapan
| | - Shuya Kandori
- Department of Urology, Faculty of MedicineUniversity of TsukubaTsukubaIbarakiJapan
| | - Hiromitsu Negoro
- Department of Urology, Faculty of MedicineUniversity of TsukubaTsukubaIbarakiJapan
| | - Hiroyuki Nishiyama
- Department of Urology, Faculty of MedicineUniversity of TsukubaTsukubaIbarakiJapan
| |
Collapse
|
6
|
Wang G, Wang C, Huang Z, Sun S, Chen Y. Exosomal circ-0020887 and circ-0009590 as novel biomarkers for the diagnosis and prediction of short-term adverse cardiovascular outcomes in STEMI patients. Open Med (Wars) 2023; 18:20230807. [PMID: 37840751 PMCID: PMC10571521 DOI: 10.1515/med-2023-0807] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/10/2023] [Revised: 08/09/2023] [Accepted: 09/01/2023] [Indexed: 10/17/2023] Open
Abstract
This study attempted to identify exosomal circular RNAs (circRNAs) as diagnostic and prognostic biomarkers for patients with ST-segment elevation myocardial infarction (STEMI). The differentially expressed exosomal circRNAs (DEECs) were screened from microarray dataset (GSE160717 and GSE197137) and RNA-Seq dataset (GSE208194), and the expression levels of DEECs in patients with STEMI were validated using reverse transcription and quantitative real-time PCR. The diagnostic value of DEECs was assessed using receiver operating characteristic curves. The major adverse cardiovascular event (MACE)-free 1-year survival rate was evaluated using the Kaplan-Meier method, and the factors affecting prognosis were determined using Cox regression model analysis. Results showed that four DEECs were screened including exo-circ-0001490, exo-circ-0020887, exo-circ-0009590, and exo-circ-0055440, and only upregulated exo-circ-0020887 and exo-circ-0009590 expression was validated in patients with STEMI. The exo-circ-0020887 and exo-circ-0009590 expression was positively correlated with hs-CRP, LDL-C, cTnI, and CK-MB. The exo-circ-0020887 and exo-circ-0009590 showed good diagnostic efficacy to distinguish STEMI patients from healthy controls (area under the curves: 0.85 and 0.80). STEMI patients with high levels of exo-circ-0020887 and exo-circ-0009590 had lower MACE-free 1-year survival rate, and exo-circ-0020887 and exo-circ-0009590 expression was independent risk factors for adverse prognosis. In summary, upregulation of plasma exo-circ-0020887 and exo-circ-0009590 might act as potential biomarkers for the diagnosis and prediction of short-term adverse cardiovascular outcomes in patients with STEMI.
Collapse
Affiliation(s)
- Guan Wang
- Department of Cardiology, Peking University Shenzhen Hospital, Shenzhen, 518036, China
| | - Chun Wang
- Department of Cardiology, Peking University Shenzhen Hospital, Shenzhen, 518036, China
| | - Zhengyi Huang
- Department of Geriatrics, Shenzhen Longhua District Central Hospital, Shenzhen, 518110, China
| | - Shuai Sun
- Department of Cardiology, Peking University Shenzhen Hospital, Shenzhen, 518036, China
| | - Yanjun Chen
- Department of Cardiology, Peking University Shenzhen Hospital, No. 1120, Lianhua Road, Futian
District, Shenzhen, 518036, China
| |
Collapse
|
7
|
Wang P, Zhang Z, Lin R, Lin J, Liu J, Zhou X, Jiang L, Wang Y, Deng X, Lai H, Xiao H. Machine learning links different gene patterns of viral infection to immunosuppression and immune-related biomarkers in severe burns. Front Immunol 2022; 13:1054407. [PMID: 36518755 PMCID: PMC9742460 DOI: 10.3389/fimmu.2022.1054407] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/26/2022] [Accepted: 11/08/2022] [Indexed: 11/29/2022] Open
Abstract
Introduction Viral infection, typically disregarded, has a significant role in burns. However, there is still a lack of biomarkers and immunotherapy targets related to viral infections in burns. Methods Virus-related genes (VRGs) that were extracted from Gene Oncology (GO) database were included as hallmarks. Through unsupervised consensus clustering, we divided patients into two VRGs molecular patterns (VRGMPs). Weighted gene co-expression network analysis (WGCNA) was performed to study the relationship between burns and VRGs. Random forest (RF), least absolute shrinkage and selection operator (LASSO) regression, and logistic regression were used to select key genes, which were utilized to construct prognostic signatures by multivariate logistic regression. The risk score of the nomogram defined high- and low-risk groups. We compared immune cells, immune checkpoint-related genes, and prognosis between the two groups. Finally, we used network analysis and molecular docking to predict drugs targeting CD69 and SATB1. Expression of CD69 and SATB1 was validated by qPCR and microarray with the blood sample from the burn patient. Results We established two VRGMPs, which differed in monocytes, neutrophils, dendritic cells, and T cells. In WGCNA, genes were divided into 14 modules, and the black module was correlated with VRGMPs. A total of 65 genes were selected by WGCNA, STRING, and differential expression analysis. The results of GO enrichment analysis were enriched in Th1 and Th2 cell differentiation, B cell receptor signaling pathway, alpha-beta T cell activation, and alpha-beta T cell differentiation. Then the 2-gene signature was constructed by RF, LASSO, and LOGISTIC regression. The signature was an independent prognostic factor and performed well in ROC, calibration, and decision curves. Further, the expression of immune cells and checkpoint genes differed between high- and low-risk groups. CD69 and SATB1 were differentially expressed in burns. Discussion This is the first VRG-based signature (including 2 key genes validated by qPCR) for predicting survival, and it could provide vital guidance to achieve optimized immunotherapy for immunosuppression in burns.
Collapse
Affiliation(s)
- Peng Wang
- Department of Burns and Plastic and Cosmetic Surgery, Xi’an Ninth Hospital, Xi’an, China
| | - Zexin Zhang
- Department of Burns and Plastic and Wound Repair Surgery, Xiang’an Hospital of Xiamen University, School of Medicine, Xiamen University, Xiamen, China
| | - Rongjie Lin
- Department of Orthopedics, 900th Hospital of Joint Logistics Support Force, Fuzhou, China
| | - Jiali Lin
- Obstetrics and Gynecology Hospital, Institute of Reproduction and Development, Fudan University, Shanghai, China
| | - Jiaming Liu
- Department of Burns and Plastic and Cosmetic Surgery, Xi’an Ninth Hospital, Xi’an, China
| | - Xiaoqian Zhou
- Department of Burns and Plastic and Cosmetic Surgery, Xi’an Ninth Hospital, Xi’an, China
| | - Liyuan Jiang
- Department of Burns and Plastic and Cosmetic Surgery, Xi’an Ninth Hospital, Xi’an, China
| | - Yu Wang
- Department of Burns and Plastic and Cosmetic Surgery, Xi’an Ninth Hospital, Xi’an, China
| | - Xudong Deng
- Department of Burns and Plastic and Cosmetic Surgery, Xi’an Ninth Hospital, Xi’an, China
| | - Haijing Lai
- Department of Burns and Plastic and Cosmetic Surgery, Xi’an Ninth Hospital, Xi’an, China
| | - Hou’an Xiao
- Department of Burns and Plastic and Cosmetic Surgery, Xi’an Ninth Hospital, Xi’an, China,*Correspondence: Hou’an Xiao,
| |
Collapse
|
8
|
Diagnostic Accuracy of the Deep Learning Model for the Detection of ST Elevation Myocardial Infarction on Electrocardiogram. J Pers Med 2022; 12:jpm12030336. [PMID: 35330336 PMCID: PMC8956114 DOI: 10.3390/jpm12030336] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/19/2022] [Revised: 02/10/2022] [Accepted: 02/22/2022] [Indexed: 11/17/2022] Open
Abstract
We aimed to measure the diagnostic accuracy of the deep learning model (DLM) for ST-elevation myocardial infarction (STEMI) on a 12-lead electrocardiogram (ECG) according to culprit artery sorts. From January 2017 to December 2019, we recruited patients with STEMI who received more than one stent insertion for culprit artery occlusion. The DLM was trained with STEMI and normal sinus rhythm ECG for external validation. The primary outcome was the diagnostic accuracy of DLM for STEMI according to the three different culprit arteries. The outcomes were measured using the area under the receiver operating characteristic curve (AUROC), sensitivity (SEN), and specificity (SPE) using the Youden index. A total of 60,157 ECGs were obtained. These included 117 STEMI-ECGs and 60,040 normal sinus rhythm ECGs. When using DLM, the AUROC for overall STEMI was 0.998 (0.996–0.999) with SEN 97.4% (95.7–100) and SPE 99.2% (98.1–99.4). There were no significant differences in diagnostic accuracy within the three culprit arteries. The baseline wanders in false positive cases (83.7%, 345/412) significantly interfered with the accurate interpretation of ST elevation on an ECG. DLM showed high diagnostic accuracy for STEMI detection, regardless of the type of culprit artery. The baseline wanders of the ECGs could affect the misinterpretation of DLM.
Collapse
|
9
|
Chen J, Liu Z, Ma L, Gao S, Fu H, Wang C, Lu A, Wang B, Gu X. Targeting Epigenetics and Non-coding RNAs in Myocardial Infarction: From Mechanisms to Therapeutics. Front Genet 2022; 12:780649. [PMID: 34987550 PMCID: PMC8721121 DOI: 10.3389/fgene.2021.780649] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/21/2021] [Accepted: 11/30/2021] [Indexed: 12/12/2022] Open
Abstract
Myocardial infarction (MI) is a complicated pathology triggered by numerous environmental and genetic factors. Understanding the effect of epigenetic regulation mechanisms on the cardiovascular disease would advance the field and promote prophylactic methods targeting epigenetic mechanisms. Genetic screening guides individualised MI therapies and surveillance. The present review reported the latest development on the epigenetic regulation of MI in terms of DNA methylation, histone modifications, and microRNA-dependent MI mechanisms and the novel therapies based on epigenetics.
Collapse
Affiliation(s)
- Jinhong Chen
- Department of TCM, Tianjin University of TCM, Tianjin, China
| | - Zhichao Liu
- Department of TCM, Tianjin University of TCM, Tianjin, China
| | - Li Ma
- Department of TCM, Tianjin University of TCM, Tianjin, China
| | - Shengwei Gao
- Department of TCM, Tianjin University of TCM, Tianjin, China
| | - Huanjie Fu
- Department of TCM, Tianjin University of TCM, Tianjin, China
| | - Can Wang
- Acupuncture Department, The First Affiliated Hospital of Tianjin University of TCM, Tianjin, China
| | - Anmin Lu
- Department of TCM, Tianjin University of TCM, Tianjin, China
| | - Baohe Wang
- Department of Cardiology, The Second Affiliated Hospital of Tianjin University of TCM, Tianjin, China
| | - Xufang Gu
- Department of Cardiology, The Second Affiliated Hospital of Tianjin University of TCM, Tianjin, China
| |
Collapse
|
10
|
Machine Learning Consensus Clustering Approach for Hospitalized Patients with Dysmagnesemia. Diagnostics (Basel) 2021; 11:diagnostics11112119. [PMID: 34829467 PMCID: PMC8619519 DOI: 10.3390/diagnostics11112119] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/23/2021] [Revised: 11/12/2021] [Accepted: 11/13/2021] [Indexed: 11/17/2022] Open
Abstract
BACKGROUND The objectives of this study were to classify patients with serum magnesium derangement on hospital admission into clusters using unsupervised machine learning approach and to evaluate the mortality risks among these distinct clusters. METHODS Consensus cluster analysis was performed based on demographic information, principal diagnoses, comorbidities, and laboratory data in hypomagnesemia (serum magnesium ≤ 1.6 mg/dL) and hypermagnesemia cohorts (serum magnesium ≥ 2.4 mg/dL). Each cluster's key features were determined using the standardized mean difference. The associations of the clusters with hospital mortality and one-year mortality were assessed. RESULTS In hypomagnesemia cohort (n = 13,320), consensus cluster analysis identified three clusters. Cluster 1 patients had the highest comorbidity burden and lowest serum magnesium. Cluster 2 patients had the youngest age, lowest comorbidity burden, and highest kidney function. Cluster 3 patients had the oldest age and lowest kidney function. Cluster 1 and cluster 3 were associated with higher hospital and one-year mortality compared to cluster 2. In hypermagnesemia cohort (n = 4671), the analysis identified two clusters. Compared to cluster 1, the key features of cluster 2 included older age, higher comorbidity burden, more hospital admissions primarily due to kidney disease, more acute kidney injury, and lower kidney function. Compared to cluster 1, cluster 2 was associated with higher hospital mortality and one-year mortality. CONCLUSION Our cluster analysis identified clinically distinct phenotypes with differing mortality risks in hospitalized patients with dysmagnesemia. Future studies are required to assess the application of this ML consensus clustering approach to care for hospitalized patients with dysmagnesemia.
Collapse
|
11
|
Pattharanitima P, Thongprayoon C, Petnak T, Srivali N, Gembillo G, Kaewput W, Chesdachai S, Vallabhajosyula S, O’Corragain OA, Mao MA, Garovic VD, Qureshi F, Dillon JJ, Cheungpasitporn W. Machine Learning Consensus Clustering Approach for Patients with Lactic Acidosis in Intensive Care Units. J Pers Med 2021; 11:jpm11111132. [PMID: 34834484 PMCID: PMC8623582 DOI: 10.3390/jpm11111132] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/22/2021] [Revised: 10/28/2021] [Accepted: 10/30/2021] [Indexed: 12/15/2022] Open
Abstract
BACKGROUND Lactic acidosis is a heterogeneous condition with multiple underlying causes and associated outcomes. The use of multi-dimensional patient data to subtype lactic acidosis can personalize patient care. Machine learning consensus clustering may identify lactic acidosis subgroups with unique clinical profiles and outcomes. METHODS We used the Medical Information Mart for Intensive Care III database to abstract electronic medical record data from patients admitted to intensive care units (ICU) in a tertiary care hospital in the United States. We included patients who developed lactic acidosis (defined as serum lactate ≥ 4 mmol/L) within 48 h of ICU admission. We performed consensus clustering analysis based on patient characteristics, comorbidities, vital signs, organ supports, and laboratory data to identify clinically distinct lactic acidosis subgroups. We calculated standardized mean differences to show key subgroup features. We compared outcomes among subgroups. RESULTS We identified 1919 patients with lactic acidosis. The algorithm revealed three best unique lactic acidosis subgroups based on patient variables. Cluster 1 (n = 554) was characterized by old age, elective admission to cardiac surgery ICU, vasopressor use, mechanical ventilation use, and higher pH and serum bicarbonate. Cluster 2 (n = 815) was characterized by young age, admission to trauma/surgical ICU with higher blood pressure, lower comorbidity burden, lower severity index, and less vasopressor use. Cluster 3 (n = 550) was characterized by admission to medical ICU, history of liver disease and coagulopathy, acute kidney injury, lower blood pressure, higher comorbidity burden, higher severity index, higher serum lactate, and lower pH and serum bicarbonate. Cluster 3 had the worst outcomes, while cluster 1 had the most favorable outcomes in terms of persistent lactic acidosis and mortality. CONCLUSIONS Consensus clustering analysis synthesized the pattern of clinical and laboratory data to reveal clinically distinct lactic acidosis subgroups with different outcomes.
Collapse
Affiliation(s)
- Pattharawin Pattharanitima
- Department of Internal Medicine, Faculty of Medicine, Thammasat University, Pathum Thani 12121, Thailand
- Correspondence: (P.P.); (C.T.); (W.C.)
| | - Charat Thongprayoon
- Division of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USA; (V.D.G.); (F.Q.); (J.J.D.)
- Correspondence: (P.P.); (C.T.); (W.C.)
| | - Tananchai Petnak
- Division of Pulmonary and Pulmonary Critical Care Medicine, Faculty of Medicine, Ramathibodi Hospital, Mahidol University, Bangkok 10400, Thailand;
| | - Narat Srivali
- Division of Pulmonary Medicine, St. Agnes Hosipital, Baltimore, MD 21229, USA;
| | - Guido Gembillo
- Unit of Nephrology and Dialysis, Department of Clinical and Experimental Medicine, University of Messina, 98125 Messina, Italy;
| | - Wisit Kaewput
- Department of Military and Community Medicine, Phramongkutklao College of Medicine, Bangkok 10400, Thailand;
| | - Supavit Chesdachai
- Division of Infectious Disease, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USA;
| | - Saraschandra Vallabhajosyula
- Section of Cardiovascular Medicine, Department of Medicine, Wake Forest University School of Medicine, Winston-Salem, NC 27101, USA;
| | - Oisin A. O’Corragain
- Department of Thoracic Medicine and Surgery, Temple University Hospital, Philadelphia, PA 19140, USA;
| | - Michael A. Mao
- Division of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Jacksonville, FL 32224, USA;
| | - Vesna D. Garovic
- Division of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USA; (V.D.G.); (F.Q.); (J.J.D.)
| | - Fawad Qureshi
- Division of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USA; (V.D.G.); (F.Q.); (J.J.D.)
| | - John J. Dillon
- Division of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USA; (V.D.G.); (F.Q.); (J.J.D.)
| | - Wisit Cheungpasitporn
- Division of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USA; (V.D.G.); (F.Q.); (J.J.D.)
- Correspondence: (P.P.); (C.T.); (W.C.)
| |
Collapse
|
12
|
Pinto LCS, Mello APQ, Izar MCO, Damasceno NRT, Neto AMF, França CN, Caixeta A, Bianco HT, Póvoa RMS, Moreira FT, Bacchin ASF, Fonseca FA. Main differences between two highly effective lipid-lowering therapies in subclasses of lipoproteins in patients with acute myocardial infarction. Lipids Health Dis 2021; 20:124. [PMID: 34587943 PMCID: PMC8482657 DOI: 10.1186/s12944-021-01559-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/03/2021] [Accepted: 09/13/2021] [Indexed: 11/26/2022] Open
Abstract
Background Large observational studies have shown that small, dense LDL subfractions are related to atherosclerotic cardiovascular disease. This study assessed the effects of two highly effective lipid-lowering therapies in the atherogenic subclasses of lipoproteins in subjects with ST-segment elevation myocardial infarction (STEMI). Methods Patients of both sexes admitted with their first myocardial infarction and submitted to pharmacoinvasive strategy (N = 101) were included and randomized using a central computerized system to receive a daily dose of simvastatin 40 mg plus ezetimibe 10 mg or rosuvastatin 20 mg for 30 days. Intermediate-density lipoprotein (IDL) and low-density lipoprotein (LDL) subfractions were analysed by polyacrylamide gel electrophoresis (Lipoprint System) on the first (D1) and 30th days (D30) of lipid-lowering therapy. Changes in LDL and IDL subfractions between D1 and D30 were compared between the lipid-lowering therapies (Mann-Whitney U test). Results The classic lipid profile was similar in both therapy arms at D1 and D30. At D30, the achievement of lipid goals was comparable between lipid-lowering therapies. Cholesterol content in atherogenic subclasses of LDL (p = 0.043) and IDL (p = 0.047) decreased more efficiently with simvastatin plus ezetimibe than with rosuvastatin. Conclusions Lipid-lowering therapy with simvastatin plus ezetimibe was associated with a better pattern of lipoprotein subfractions than rosuvastatin monotherapy. This finding was noted despite similar effects in the classic lipid profile and may contribute to residual cardiovascular risk. Trial registration ClinicalTrials.gov, NCT02428374, registered on 28/09/2014.
Collapse
Affiliation(s)
- Leticia C S Pinto
- Escola Paulista de Medicina, Setor de Lípides, Aterosclerose e Biologia Vascular, Universidade Federal de São Paulo, UNIFESP, Rua Loefgren 1350, São Paulo, SP, 04040-001, Brazil
| | - Ana P Q Mello
- Escola Paulista de Medicina, Setor de Lípides, Aterosclerose e Biologia Vascular, Universidade Federal de São Paulo, UNIFESP, Rua Loefgren 1350, São Paulo, SP, 04040-001, Brazil
| | - Maria C O Izar
- Escola Paulista de Medicina, Setor de Lípides, Aterosclerose e Biologia Vascular, Universidade Federal de São Paulo, UNIFESP, Rua Loefgren 1350, São Paulo, SP, 04040-001, Brazil
| | | | - Antonio M F Neto
- Instituto de Física, Universidade de São Paulo, USP, São Paulo, Brazil
| | | | - Adriano Caixeta
- Escola Paulista de Medicina, Setor de Lípides, Aterosclerose e Biologia Vascular, Universidade Federal de São Paulo, UNIFESP, Rua Loefgren 1350, São Paulo, SP, 04040-001, Brazil
| | - Henrique T Bianco
- Escola Paulista de Medicina, Setor de Lípides, Aterosclerose e Biologia Vascular, Universidade Federal de São Paulo, UNIFESP, Rua Loefgren 1350, São Paulo, SP, 04040-001, Brazil
| | - Rui M S Póvoa
- Escola Paulista de Medicina, Setor de Lípides, Aterosclerose e Biologia Vascular, Universidade Federal de São Paulo, UNIFESP, Rua Loefgren 1350, São Paulo, SP, 04040-001, Brazil
| | - Flavio T Moreira
- Escola Paulista de Medicina, Setor de Lípides, Aterosclerose e Biologia Vascular, Universidade Federal de São Paulo, UNIFESP, Rua Loefgren 1350, São Paulo, SP, 04040-001, Brazil
| | - Amanda S F Bacchin
- Escola Paulista de Medicina, Setor de Lípides, Aterosclerose e Biologia Vascular, Universidade Federal de São Paulo, UNIFESP, Rua Loefgren 1350, São Paulo, SP, 04040-001, Brazil
| | - Francisco A Fonseca
- Escola Paulista de Medicina, Setor de Lípides, Aterosclerose e Biologia Vascular, Universidade Federal de São Paulo, UNIFESP, Rua Loefgren 1350, São Paulo, SP, 04040-001, Brazil.
| |
Collapse
|
13
|
Clinically Distinct Subtypes of Acute Kidney Injury on Hospital Admission Identified by Machine Learning Consensus Clustering. Med Sci (Basel) 2021; 9:medsci9040060. [PMID: 34698185 PMCID: PMC8544570 DOI: 10.3390/medsci9040060] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/17/2021] [Revised: 09/19/2021] [Accepted: 09/21/2021] [Indexed: 12/22/2022] Open
Abstract
Background: We aimed to cluster patients with acute kidney injury at hospital admission into clinically distinct subtypes using an unsupervised machine learning approach and assess the mortality risk among the distinct clusters. Methods: We performed consensus clustering analysis based on demographic information, principal diagnoses, comorbidities, and laboratory data among 4289 hospitalized adult patients with acute kidney injury at admission. The standardized difference of each variable was calculated to identify each cluster’s key features. We assessed the association of each acute kidney injury cluster with hospital and one-year mortality. Results: Consensus clustering analysis identified four distinct clusters. There were 1201 (28%) patients in cluster 1, 1396 (33%) patients in cluster 2, 1191 (28%) patients in cluster 3, and 501 (12%) patients in cluster 4. Cluster 1 patients were the youngest and had the least comorbidities. Cluster 2 and cluster 3 patients were older and had lower baseline kidney function. Cluster 2 patients had lower serum bicarbonate, strong ion difference, and hemoglobin, but higher serum chloride, whereas cluster 3 patients had lower serum chloride but higher serum bicarbonate and strong ion difference. Cluster 4 patients were younger and more likely to be admitted for genitourinary disease and infectious disease but less likely to be admitted for cardiovascular disease. Cluster 4 patients also had more severe acute kidney injury, lower serum sodium, serum chloride, and serum bicarbonate, but higher serum potassium and anion gap. Cluster 2, 3, and 4 patients had significantly higher hospital and one-year mortality than cluster 1 patients (p < 0.001). Conclusion: Our study demonstrated using machine learning consensus clustering analysis to characterize a heterogeneous cohort of patients with acute kidney injury on hospital admission into four clinically distinct clusters with different associated mortality risks.
Collapse
|
14
|
Machine Learning Consensus Clustering of Hospitalized Patients with Admission Hyponatremia. Diseases 2021; 9:diseases9030054. [PMID: 34449583 PMCID: PMC8395840 DOI: 10.3390/diseases9030054] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/04/2021] [Revised: 07/28/2021] [Accepted: 07/29/2021] [Indexed: 01/12/2023] Open
Abstract
Background: The objective of this study was to characterize patients with hyponatremia at hospital admission into clusters using an unsupervised machine learning approach, and to evaluate the short- and long-term mortality risk among these distinct clusters. Methods: We performed consensus cluster analysis based on demographic information, principal diagnoses, comorbidities, and laboratory data among 11,099 hospitalized adult hyponatremia patients with an admission serum sodium below 135 mEq/L. The standardized mean difference was utilized to identify each cluster’s key features. We assessed the association of each hyponatremia cluster with hospital and one-year mortality using logistic and Cox proportional hazard analysis, respectively. Results: There were three distinct clusters of hyponatremia patients: 2033 (18%) in cluster 1, 3064 (28%) in cluster 2, and 6002 (54%) in cluster 3. Among these three distinct clusters, clusters 3 patients were the youngest, had lowest comorbidity burden, and highest kidney function. Cluster 1 patients were more likely to be admitted for genitourinary disease, and have diabetes and end-stage kidney disease. Cluster 1 patients had the lowest kidney function, serum bicarbonate, and hemoglobin, but highest serum potassium and prevalence of acute kidney injury. In contrast, cluster 2 patients were the oldest and were more likely to be admitted for respiratory disease, have coronary artery disease, congestive heart failure, stroke, and chronic obstructive pulmonary disease. Cluster 2 patients had lowest serum sodium and serum chloride, but highest serum bicarbonate. Cluster 1 patients had the highest hospital mortality and one-year mortality, followed by cluster 2 and cluster 3, respectively. Conclusion: We identified three clinically distinct phenotypes with differing mortality risks in a heterogeneous cohort of hospitalized hyponatremic patients using an unsupervised machine learning approach.
Collapse
|