Cardiovascular disease detection using machine learning and carotid/femoral arterial imaging frameworks in rheumatoid arthritis patients
Abstract The study proposes a novel machine learning (ML) paradigm for cardiovascular disease (CVD) detection in individuals at medium to high cardiovascular risk using data from a Greek cohort of 542 individuals with rheumatoid arthritis, or diabetes mellitus, and/or arterial hypertension, using conventional or office-based, laboratory-based blood biomarkers and carotid/femoral ultrasound image-based phenotypes. Two kinds of data (CVD risk factors and presence of CVD—defined as stroke, or myocardial infarction, or coronary artery syndrome, or peripheral artery disease, or coronary heart disease) as ground truth, were collected at two-time points: (i) at visit 1 and (ii) at visit 2 after 3 years. The CVD risk factors were divided into three clusters (conventional or office-based, laboratory-based blood biomarkers, carotid ultrasound image-based phenotypes) to study their effect on the ML classifiers. Three kinds of ML classifiers (Random Forest, Support Vector Machine, and Linear Discriminant Analysis) were applied in a two-fold cross-validation framework using the data augmented by synthetic minority over-sampling technique (SMOTE) strategy. The performance of the ML classifiers was recorded. In this cohort with overall 46 CVD risk factors (covariates) implemented in an online cardiovascular framework, that requires calculation time less than 1 s per patient, a mean accuracy and area-under-the-curve (AUC) of 98.40% and 0.98 (p < 0.0001) for CVD presence detection at visit 1, and 98.39% and 0.98 (p < 0.0001) at visit 2, respectively. The performance of the cardiovascular framework was significantly better than the classical CVD risk score. The ML paradigm proved to be powerful for CVD prediction in individuals at medium to high cardiovascular risk..
Medienart: |
Artikel |
---|
Erscheinungsjahr: |
2022 |
---|---|
Erschienen: |
2022 |
Enthalten in: |
Zur Gesamtaufnahme - volume:42 |
---|---|
Enthalten in: |
Rheumatology international - 42(2022), 2 vom: 11. Jan., Seite 215-239 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Konstantonis, George [VerfasserIn] |
---|
Links: |
Volltext [lizenzpflichtig] |
---|
Themen: |
And machine learning |
---|
Anmerkungen: |
© The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2021 |
---|
doi: |
10.1007/s00296-021-05062-4 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
OLC2077914661 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | OLC2077914661 | ||
003 | DE-627 | ||
005 | 20230508110627.0 | ||
007 | tu | ||
008 | 221220s2022 xx ||||| 00| ||eng c | ||
024 | 7 | |a 10.1007/s00296-021-05062-4 |2 doi | |
035 | |a (DE-627)OLC2077914661 | ||
035 | |a (DE-He213)s00296-021-05062-4-p | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
082 | 0 | 4 | |a 610 |q VZ |
100 | 1 | |a Konstantonis, George |e verfasserin |4 aut | |
245 | 1 | 0 | |a Cardiovascular disease detection using machine learning and carotid/femoral arterial imaging frameworks in rheumatoid arthritis patients |
264 | 1 | |c 2022 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ohne Hilfsmittel zu benutzen |b n |2 rdamedia | ||
338 | |a Band |b nc |2 rdacarrier | ||
500 | |a © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2021 | ||
520 | |a Abstract The study proposes a novel machine learning (ML) paradigm for cardiovascular disease (CVD) detection in individuals at medium to high cardiovascular risk using data from a Greek cohort of 542 individuals with rheumatoid arthritis, or diabetes mellitus, and/or arterial hypertension, using conventional or office-based, laboratory-based blood biomarkers and carotid/femoral ultrasound image-based phenotypes. Two kinds of data (CVD risk factors and presence of CVD—defined as stroke, or myocardial infarction, or coronary artery syndrome, or peripheral artery disease, or coronary heart disease) as ground truth, were collected at two-time points: (i) at visit 1 and (ii) at visit 2 after 3 years. The CVD risk factors were divided into three clusters (conventional or office-based, laboratory-based blood biomarkers, carotid ultrasound image-based phenotypes) to study their effect on the ML classifiers. Three kinds of ML classifiers (Random Forest, Support Vector Machine, and Linear Discriminant Analysis) were applied in a two-fold cross-validation framework using the data augmented by synthetic minority over-sampling technique (SMOTE) strategy. The performance of the ML classifiers was recorded. In this cohort with overall 46 CVD risk factors (covariates) implemented in an online cardiovascular framework, that requires calculation time less than 1 s per patient, a mean accuracy and area-under-the-curve (AUC) of 98.40% and 0.98 (p < 0.0001) for CVD presence detection at visit 1, and 98.39% and 0.98 (p < 0.0001) at visit 2, respectively. The performance of the cardiovascular framework was significantly better than the classical CVD risk score. The ML paradigm proved to be powerful for CVD prediction in individuals at medium to high cardiovascular risk. | ||
650 | 4 | |a Cardiovascular risk estimation | |
650 | 4 | |a Cardiovascular disease | |
650 | 4 | |a Three-year follow-up | |
650 | 4 | |a Conventional risk factors | |
650 | 4 | |a Ultrasound | |
650 | 4 | |a And machine learning | |
700 | 1 | |a Singh, Krishna V. |0 (orcid)0000-0003-4311-8730 |4 aut | |
700 | 1 | |a Sfikakis, Petros P. |0 (orcid)0000-0001-5484-2930 |4 aut | |
700 | 1 | |a Jamthikar, Ankush D. |0 (orcid)0000-0002-3030-7236 |4 aut | |
700 | 1 | |a Kitas, George D. |0 (orcid)0000-0002-0828-6176 |4 aut | |
700 | 1 | |a Gupta, Suneet K. |0 (orcid)0000-0001-7935-8598 |4 aut | |
700 | 1 | |a Saba, Luca |0 (orcid)0000-0003-2870-3771 |4 aut | |
700 | 1 | |a Verrou, Kleio |4 aut | |
700 | 1 | |a Khanna, Narendra N. |0 (orcid)0000-0002-6935-0039 |4 aut | |
700 | 1 | |a Ruzsa, Zoltan |0 (orcid)0000-0002-2474-5723 |4 aut | |
700 | 1 | |a Sharma, Aditya M. |0 (orcid)0000-0003-1756-2504 |4 aut | |
700 | 1 | |a Laird, John R. |0 (orcid)0000-0003-2095-2191 |4 aut | |
700 | 1 | |a Johri, Amer M. |0 (orcid)0000-0001-7044-8212 |4 aut | |
700 | 1 | |a Kalra, Manudeep |0 (orcid)0000-0001-9938-7476 |4 aut | |
700 | 1 | |a Protogerou, Athanasios |0 (orcid)0000-0002-3825-532X |4 aut | |
700 | 1 | |a Suri, Jasjit S. |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Rheumatology international |d Springer Berlin Heidelberg, 1981 |g 42(2022), 2 vom: 11. Jan., Seite 215-239 |w (DE-627)129098183 |w (DE-600)8286-7 |w (DE-576)014434903 |x 0172-8172 |7 nnns |
773 | 1 | 8 | |g volume:42 |g year:2022 |g number:2 |g day:11 |g month:01 |g pages:215-239 |
856 | 4 | 1 | |u https://doi.org/10.1007/s00296-021-05062-4 |z lizenzpflichtig |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a SYSFLAG_A | ||
912 | |a GBV_OLC | ||
912 | |a SSG-OLC-PHA | ||
912 | |a SSG-OLC-DE-84 | ||
951 | |a AR | ||
952 | |d 42 |j 2022 |e 2 |b 11 |c 01 |h 215-239 |