CoChat
Sign Up
Cited by 32Artificial Intelligence in HealthcareMetabolomics and Mass Spectrometry StudiesCerebrovascular and Carotid Artery Diseases

Machine learning approaches for biomarker discovery to predict large-artery atherosclerosis

Open access
Sun, Ting-Hsuan, Wang, Chia-Chun, Wu, Ya-Lun, Hsu, Kai-Cheng, Lee, Tsong-Hai·2023·Scientific Reports
DOI 10.1038/s41598-023-42338-0PMC PMC10499778
Open this paper in CoChat — free accountOpen PDF

Abstract

Large-artery atherosclerosis (LAA) is a leading cause of cerebrovascular disease. However, LAA diagnosis is costly and needs professional identification. Many metabolites have been identified as biomarkers of specific traits. However, there are inconsistent findings regarding suitable biomarkers for the prediction of LAA. In this study, we propose a new method integrates multiple machine learning algorithms and feature selection method to handle multidimensional data. Among the six machine learning models, logistic regression (LR) model exhibited the best prediction performance. The value of area under the receiver operating characteristic curve (AUC) was 0.92 when 62 features were incorporated in the external validation set for the LR model. In this model, LAA could be well predicted by clinical risk factors including body mass index, smoking, and medications for controlling diabetes, hypertension, and hyperlipidemia as well as metabolites involved in aminoacyl-tRNA biosynthesis and lipid metabolism. In addition, we found that 27 features were present among the five adopted models that could provide good results. If these 27 features were used in the LR model, an AUC value of 0.93 could be achieved. Our study has demonstrated the effectiveness of combining machine learning algorithms with recursive feature elimination and cross-validation methods for biomarker identification. Moreover, we have shown that using shared features can yield more reliable correlations than either model, which can be valuable for future identification of LAA.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41598-023-42338-0

Cites

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • During training, model performance was evaluated using 10-fold, 3-repeats stratified k-fold cross-validation and F2-score.

    “During training, model performance was evaluated using 10-fold, 3-repeats stratified k-fold cross-validation and F2-score (ie, instead of F1-score) as it penalizes false negatives.24,25”

    From Development of a Real-time Force-based Algorithm for Infusion Failure Detection (2024) · cites this paper as [24]

    The Methods section (Model evaluation metrics; page unavailable) reports stratified tenfold cross-validation on the training set. It does not report three repeats or use of the F2-score; instead, it names accuracy, AUC, recall, and precision as its evaluation metrics. (LLM, conf=0.90)

    Experimental — accuracy not yet measured

  • During tuning, all models showcased strong PR-AUC and ROC-AUC which speaks to the model's robustness and ability to generalize past the training set.

    “During tuning, all models showcased strong PR-AUC and ROC-AUC which speaks to the model's robustness and ability to generalize past the training set (Figure 5).24”

    From Development of a Real-time Force-based Algorithm for Infusion Failure Detection (2024) · cites this paper as [24]

    The Results sections on model performance and feature selection report ROC-AUC values and use cross-validation and external validation to assess robustness and generalization (page not provided). They do not report PR-AUC, and the decision tree performed poorly on external validation, so the claim that all models had strong results on both measures is not supported. (LLM, conf=0.88)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

No citation lists for this paper

No citation lists for this paper yet — checked again daily.

References 75 · Cited by 32

Research works printed but not linked: 67

  1. [1]Ko, Y., et al. MRI-based Algorithm for Acute Ischemic Stroke Subtype Classification. 2014(2287–6391 (Print)). PMC4200592 25328874
  2. [2]Cole, J. W. Large Artery Atherosclerotic Occlusive Disease. 2017(1538–6899 (Electronic)). PMC5898962 28157748
  3. [3]Young, J. L., U. Libby P Fau-Schönbeck, & U. Schönbeck. Cytokines in the pathogenesis of atherosclerosis. 2002(0340–6245 (Print)). 12362224
  4. [4]Chapman, M. J. From pathophysiology to targeted therapy for atherothrombosis: a role for the combination of statin and aspirin in secondary prevention. 2007(0163–7258 (Print)). 17070923
  5. [5]Stoll, G., & Bendszus, M. Inflammation and atherosclerosis: Novel insights into plaque formation and destabilization. 2006(1524–4628 (Electronic)). 16741184
  6. [6]Emsley, H. C. & Tyrrell, P. J. Inflammation and infection in clinical stroke. 2002(0271–678X (Print)). 12468886
  7. [8]Elkind, M. S. Inflammation, atherosclerosis, and stroke. 2006(1074–7931 (Print)). 16688015
  8. [9]Bodi, V., et al.Metabolomics in the diagnosis of acute myocardial ischemia. 2013(1937–5395 (Electronic)). 23990264
  9. [10]Mas, S., et al.Local non-esterified fatty acids correlate with inflammation in atheroma plaques of patients with type 2 diabetes. 2010(1939–327X (Electronic)). PMC2874689 20200316
  10. [11]Paik, M. J., et al.The free fatty acid metabolome in cerebral ischemia following human mesenchymal stem cell transplantation in rats. 2009(1873–3492 (Electronic)). 19161994
  11. [12]Yu, B., et al.Genome-wide association study of a heart failure related metabolomic profile among African Americans in the Atherosclerosis Risk in Communities (ARIC) study. 2013(1098–2272 (Electronic)). PMC4079107 23934736
  12. [13]Walsh, M. C. et al.Impact of geographical region on urinary metabolomic and plasma fatty acid profiles in subjects with the metabolic syndrome across Europe: the LIPGENE study. 2014(1475–2662 (Electronic)). 24047691
  13. [14]Yap, I. K., et al.Metabolome-wide association study identifies multiple biomarkers that discriminate north and south Chinese populations at differing risks of cardiovascular disease: INTERMAP study. 2010(1535–3907 (Electronic)). PMC3117148 20853909
  14. [15]Ahmad, S., et al.Assessment of Risk Factors and Biomarkers Associated With Risk of Cardiovascular Disease Among Women Consuming a Mediterranean Diet. 2018(2574–3805 (Electronic)). PMC6324327 30646282
  15. [16]Shrivastava AK C-reactive protein, inflammation and coronary heart disease Egypt. Heart J. 2015 67 2 89 97 10.1016/j.ehj.2014.11.005 · DOI
  16. [17]Bent Re Fau-Wheeler, M.T., et al.Systematic Comparison of Digital Electrocardiograms From Healthy Athletes and Patients With Hypertrophic Cardiomyopathy. 2015(1558–3597 (Electronic)). 26046742
  17. [18]Arsenault, B. J., et al.Visceral adipose tissue accumulation, cardiorespiratory fitness, and features of the metabolic syndrome. 2007(0003–9926 (Print)). 17646606
  18. [19]Ngo, D., et al.Aptamer-Based Proteomic Profiling Reveals Novel Candidate Biomarkers and Pathways in Cardiovascular Disease. 2016(1524–4539 (Electronic)). PMC4963294 27444932
  19. [20]Latha S Performance analysis of machine learning and deep learning architectures on early stroke detection using carotid artery ultrasound images Front. Aging Neurosci. 2021 13 828214 10.3389/fnagi.2021.828214 35153728 PMC8830903 · DOI
  20. [21]Fan J The prediction of asymptomatic carotid atherosclerosis with electronic health records: a comparative study of six machine learning models BMC Med. Inform. Decis. Mak. 2021 21 1 115 10.1186/s12911-021-01480-3 33820531 PMC8020544 · DOI
  21. [22]Coelewij L Serum metabolomic signatures can predict subclinical atherosclerosis in patients with systemic lupus erythematosus Arterioscler. Thromb. Vasc. Biol. 2021 41 4 1446 1458 10.1161/ATVBAHA.120.315321 33535791 PMC7610443 · DOI
  22. [23]Cui S Machine learning identifies metabolic signatures that predict the risk of recurrent angina in remitted patients after percutaneous coronary intervention: A multicenter prospective cohort study Adv. Sci. (Weinh) 2021 8 10 2003893 10.1002/advs.202003893 34026445 PMC8132066 · DOI
  23. [24]Barnett, H. J., et al.Benefit of carotid endarterectomy in patients with symptomatic moderate or severe stenosis. North American Symptomatic Carotid Endarterectomy Trial Collaborators. 1998(0028–4793 (Print)). 9811916
  24. [26]Harris, C. R., et al.Array programming with NumPy. 2020(1476–4687 (Electronic)). PMC7759461 32939066
  25. [28]Hunter JD Matplotlib: A 2D graphics environment Comput. Sci. Eng. 2007 9 3 90 95 10.1109/MCSE.2007.55 · DOI · Paper page
  26. [30]Pollard, T. A.-O., et al.tableone: An open source Python package for producing summary statistics for research papers. 2018(2574–2531 (Electronic)). PMC6951995 31984317
  27. [31]Virtanen, P., et al.SciPy 1.0: fundamental algorithms for scientific computing in Python. 2020(1548–7105 (Electronic)). PMC7056644 32015543
  28. [34]Vapnik, C. A. Support vector networks. Mach. Learn.20(3), 273–297 (1995).
  29. [35]Chang, W. et al.A Machine-Learning-Based Prediction Method for Hypertension Outcomes Based on Medical Data. LID—10.3390/diagnostics9040178 [doi] LID—178. 2019(2075–4418 (Print)). PMC6963807 31703364 · DOI
  30. [37]Bauer E Kohavi R An empirical comparison of voting classification algorithms: bagging, boosting, and variants Mach. Learn. 1999 36 1 105 139 10.1023/A:1007515423169 · DOI
  31. [38]Díaz-Uriarte, R., Alvarez de Andrés, S. Gene selection and classification of microarray data using random forest. 2006(1471–2105 (Electronic)). PMC1363357 16398926
  32. [39]Pal M Random forest classifier for remote sensing classification Int. J. Remote Sens. 2005 26 1 217 222 10.1080/01431160412331269698 · DOI
  33. [40]Gray, K. R. et al.Random forest-based similarity measures for multi-modal classification of Alzheimer's disease. 2013(1095–9572 (Electronic)). PMC3516432 23041336
  34. [41]Chen, T. and Guestrin, C. XGBoost: A Scalable Tree Boosting System. 2016. arXiv:1603.02754. · arXiv
  35. [43]Le, N. Q., Nguyen, T. T., & Ou, Y. Y. Identifying the molecular functions of electron transport proteins using radial basis function networks and biochemical properties. 2017(1873–4243 (Electronic)). 28285094
  36. [44]Ding, Y., Wilkins, D. Improving the performance of SVM-RFE to select genes in microarray data. 2006(1471–2105 (Electronic)). PMC1683561 17118133
  37. [46]Govindarajan M Chandrasekaran R Evaluation of k-nearest neighbor classifier performance for direct marketing Expert Syst. Appl. 2010 37 1 253 258 10.1016/j.eswa.2009.04.055 · DOI
  38. [47]Pham-Gia T Hung TL The mean and median absolute deviations Math. Comput. Model. 2001 34 7 921 936 10.1016/S0895-7177(01)00109-1 · DOI
  39. [48]Jiang, Y., et al.Cardiovascular Disease Prediction by Machine Learning Algorithms Based on Cytokines in Kazakhs of China. 2021(1179–1349 (Print)). PMC8200454 34135637
  40. [49]Cui, J., et al.Machine Learning-Based Model for Predicting Incidence and Severity of Acute Ischemic Stroke in Anterior Circulation Large Vessel Occlusion. 2021(1664–2295 (Print)). PMC8675605 34925213
  41. [50]Wang JC Bennett M Aging and atherosclerosis Circ. Res. 2012 111 2 245 259 10.1161/CIRCRESAHA.111.261388 22773427 · DOI
  42. [51]Tesauro, M., et al.Arterial ageing: from endothelial dysfunction to vascular calcification. 2017(1365–2796 (Electronic)). 28345303
  43. [52]Dzau, V. J. Mechanism of the interaction of hypertension and hypercholesterolemia in atherogenesis: The effects of antihypertensive agents. 1988(0002–8703 (Print)). 3202079
  44. [53]Alanazi, E.A.-O., Abdou, A.A.-O. & Luo, J.A.-O.X. Predicting Risk of Stroke From Lab Tests Using Machine Learning Algorithms: Development and Evaluation of Prediction Models. 2021(2561–326X (Electronic)). PMC8686476 34860663
  45. [54]Nishi, H., et al.Predicting Clinical Outcomes of Large Vessel Occlusion Before Mechanical Thrombectomy Using Machine Learning. 2019(1524–4628 (Electronic)). 31409267
  46. [55]Wang, J.A.-O., et al.Prediction of large vessel occlusion for ischaemic stroke by using the machine learning model random forests. 2022(2059–8696 (Electronic)). PMC9067264 34702747
  47. [56]Ohya, Y., et al.Causes of ischemic stroke in young adults versus non-young adults: A multicenter hospital-based observational study. 2022(1932–6203 (Electronic)). PMC9278748 35830430
  48. [57]Lusis AJ Atherosclerosis Nature 2000 407 6801 233 241 10.1038/35025203 11001066 PMC2826222 · DOI
  49. [58]Packham, M. A. & Mustard, J. F. The role of platelets in the development and complications of atherosclerosis. 1986(0037–1963 (Print)). 3511536
  50. [59]Xia, J., et al.MetaboAnalyst: a web server for metabolomic data analysis and interpretation. 2009(1362–4962 (Electronic)). PMC2703878 19429898
  51. [60]Kuksis, A., Fau-Myher, J. J., et al.Decreased plasma phosphatidylcholine/free cholesterol ratio as an indicator of risk for ischemic vascular disease. 1982(0276–5047 (Print)). 7115204
  52. [61]Paapstel, K., et al.Inverse relations of serum phosphatidylcholines and lysophosphatidylcholines with vascular damage and heart rate in patients with atherosclerosis. 2018(1590–3729 (Electronic)). 28986077
  53. [62]Moxon, J. V., et al.Baseline serum phosphatidylcholine plasmalogen concentrations are inversely associated with incident myocardial infarction in patients with mixed peripheral artery disease presentations. 2017(1879–1484 (Electronic)). 28728066
  54. [63]Zaric, B. L., et al.Atherosclerosis Linked to Aberrant Amino Acid Metabolism and Immunosuppressive Amino Acid Catabolizing Enzymes. 2020(1664–3224 (Electronic)). PMC7549398 33117340
  55. [64]Grajeda-Iglesias, C. & Aviram, M. Specific Amino Acids Affect Cardiovascular Diseases and Atherogenesis via Protection against Macrophage Foam Cell Formation: Review Article. LID—10.5041/RMMJ.10337 [doi] LID—e0022. 2018(2076–9172 (Print)). PMC6115485 29944113 · DOI
  56. [65]Baldo-Enzi G Tryptophan and atherosclerosis Recent Advances in Tryptophan Research 1996 Springer 429 432 8906301
  57. [66]Li, Y., et al.Regulating the balance between the kynurenine and serotonin pathways of tryptophan metabolism. 2017(1742–4658 (Electronic)). 28118532
  58. [67]Sun, L., et al.Metabolic Reprogramming in Immune Response and Tissue Inflammation. 2020(1524–4636 (Electronic)). PMC7484156 32698683
  59. [68]Kokol, P.A.-O., Kokol, M., Zagoranski, S. Machine learning on small size samples: A synthetic knowledge synthesis. 2022(2047–7163 (Electronic)). PMC10358596 35220816
  60. [69]Weng, S.A.-O., et al.Can machine-learning improve cardiovascular risk prediction using routine clinical data? 2017(1932–6203 (Electronic)). PMC5380334 28376093
  61. [70]Terrada, O., et al. Classification and Prediction of atherosclerosis diseases using machine learning algorithms. in 2019 5th International Conference on Optimization and Applications (ICOA) (2019).
  62. [71]Lyu, J., et al.A potent risk model for predicting new-onset acute coronary syndrome in patients with type 2 diabetes mellitus in Northwest China. 2020(1432–5233 (Electronic)). PMC7220880 32008161
  63. [72]Sakellarios, A. I., et al. Prediction of atherosclerotic disease progression combining computational modelling with machine learning. in 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) (2020). 33018578
  64. [73]Du, Z.A.-O., et al.Accurate Prediction of Coronary Heart Disease for Patients with Hypertension From Electronic Health Records with Big Data and Machine-Learning Methods: Model Development and Performance Evaluation. 2020(2291–9694 (Print)). PMC7381262 32628616
  65. [74]Brajesh Kumar, D. H. M. Comprehensive analysis of atherosclerosis disease prediction using machine learning. Ann. Roman. Soc. Cell Biol. 25(4), 17962–17975 (2021).
  66. [75]Huang, G. et al.Development and validation of a carotid atherosclerosis risk prediction model based on a Chinese population. 2022(2297–055X (Print)). PMC9380015 35983181
  67. [76]Chen, Z. et al.Prediction of atherosclerosis using machine learning based on operations research. 2022(1551–0018 (Electronic)). 35430846

Authors
Sun, T.-H., Wang, C.-C., Wu, Y.-L., Hsu, K.-C., & Lee, T.-H.
Affiliations
  • China Medical University Hospital (TW)
  • China Medical University (TW)
  • Chang Gung University (TW)
Corresponding author
  • Hsu, Kai-Cheng
  • Lee, Tsong-Hai
ORCID
Venue
Scientific Reports
Publisher
Springer Science and Business Media LLC
Published
2023-09-13
Volume
13
Issue
1
Pages
15139-15139
ISSN
2045-2322 (ISSN-L)
DOI
10.1038/s41598-023-42338-0
PMC
PMC10499778
OpenAlex
W4386712278
Cited by
32
References
75
Citations by year
2026: 6 · 2025: 13 · 2024: 13
FWCI
7.18
Type
journal article
Language
en
Open access
Licence
Locations
  • Scientific Reports (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • China Medical University and China Medical University Hospital (DMR-112-124)
  • Linkou Chang Gung Memorial Hospital (CMRPG3E2131)
Topics
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Metabolomics and Mass Spectrometry Studies
  • Health Sciences › Medicine › Pulmonary and Respiratory Medicine › Cerebrovascular and Carotid Artery Diseases
Keywords
large artery atherosclerosis, biomarker discovery, cerebrovascular disease, metabolomics, logistic regression, recursive feature elimination, feature selection, aminoacyl-tRNA biosynthesis, lipid metabolism, clinical risk factors
MeSH terms
Machine Learning, Algorithms, Arteries, Humans, Biomedical Research, Atherosclerosis

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review