Nonlinear model for the carotid artery disease 10‐year risk prediction by fusing conventional cardiovascular factors to carotid ultrasound image phenotypes: A Japanese diabetes cohort study

Khanna, Narendra N.; Jamthikar, Ankush; Araki, Tadashi; Gupta, Deep; Piga, Matteo; Saba, Luca; Carcassi, Carlo; Nicolaides, Andrew; Laird, John R.; Suri, Harman S.; Gupta, Ajay; Mavrogeni, Sophie; Kitas, George D.; Suri, Jasjit S.

doi:10.1111/echo.14242

Cited by 42 publications

(55 citation statements)

References 107 publications

(134 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We believe that the AtheroRisk-Integrated ML system is efficient, accurate, and affordable. Risk stratification performed using EEGS is the first step to prevent higher costs and simplicity in design (4,11,12,29,41). Although the proposed study has clearly met the pre-defined hypothesis, more modifications can be possible to improve the CV/ stroke risk assessment such as conducting a multicenter study.…”

Section: Study Limitations and Future Scopementioning

confidence: 99%

“…Two operators (with 15 years of experience) analyzed the scans. We used the CUS image acquisition protocol presented before (11,12,21,22). The analytical approach and study design for this manuscript are unique with respect to previously published reports using this cohort (11,12,21,22).…”

Section: Study Population and Image Acquisitionmentioning

confidence: 99%

“…The 34 CUSIP were derived using six steps: (I) Initially six current image-based phenotypes such as average cIMT (cIMTave), maximum cIMT (cIMTmax), minimum cIMT (cIMTmin), variability of cIMT (cIMTV), morphological CP area (also called as total plaque area or TPA), and normalized TPA (nTPA) were measured using an AtheroEdge (AtheroPoint, Roseville, USA) (22,(26)(27)(28). (II) In the second step, six integrated 10-year image-based phenotypes also called as CUSIP 10yr such as cIMTave 10yr , cIMTmax 10yr , cIMTmin 10yr , cIMTV 10yr , TPA 10yr , and nTPA 10yr were computed using the mathematical formulation provided in our previous study (12). The subscript "10 year" indicated the 10-year measurement.…”

Section: Cusipmentioning

confidence: 99%

“…Furthermore, the carotid ultrasound image-based phenotypes (CUSIP) such as carotid intima-media thickness (cIMT), carotid plaque (CP), and carotid artery stenosis are considered the most significant biomarkers of CV/stroke events (7)(8)(9)(10). Thus, integrating these CUSIP with CRF can convey a larger power of risk assessment (11)(12)(13). Such risk assessment systems are affordable but do not incorporate the full capabilities of deep learning algorithms which are now emerging as powerful and novel tools in healthcare.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A low-cost machine learning-based cardiovascular/stroke risk assessment system: integration of conventional factors with image phenotypes

Jamthikar¹,

Gupta²,

Khanna³

et al. 2019

Cardiovasc. Diagn. Ther.

Self Cite

View full text Add to dashboard Cite

Background: Most cardiovascular (CV)/stroke risk calculators using the integration of carotid ultrasound image-based phenotypes (CUSIP) with conventional risk factors (CRF) have shown improved risk stratification compared with either method. However such approaches have not yet leveraged the potential of machine learning (ML). Most intelligent ML strategies use follow-ups for the endpoints but are costly and time-intensive. We introduce an integrated ML system using stenosis as an endpoint for training and determine whether such a system can lead to superior performance compared with the conventional ML system. Methods: The ML-based algorithm consists of an offline and online system. The offline system extracts 47 features which comprised of 13 CRF and 34 CUSIP. Principal component analysis (PCA) was used to select the most significant features. These offline features were then trained using the event-equivalent gold standard (consisting of percentage stenosis) using a random forest (RF) classifier framework to generate training coefficients. The online system then transforms the PCA-based test features using offline trained coefficients to predict the risk labels on test subjects. The above ML system determines the area under the curve (AUC) using a 10-fold cross-validation paradigm. The above system so-called "AtheroRisk-Integrated" was compared against "AtheroRisk-Conventional", where only 13 CRF were considered in a feature set. Results: Left and right common carotid arteries of 202 Japanese patients (Toho University, Japan) were retrospectively examined to obtain 395 ultrasound scans. AtheroRisk-Integrated system [AUC =0.80, P<0.0001, 95% confidence interval (CI): 0.77 to 0.84] showed an improvement of ~18% against AtheroRisk-Conventional ML (AUC =0.68, P<0.0001, 95% CI: 0.64 to 0.72). Conclusions: ML-based integrated model with the event-equivalent gold standard as percentage stenosis is powerful and offers low cost and high performance CV/stroke risk assessment.

show abstract

Section: Study Limitations and Future Scopementioning

confidence: 99%

Section: Study Population and Image Acquisitionmentioning

confidence: 99%

Section: Cusipmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A low-cost machine learning-based cardiovascular/stroke risk assessment system: integration of conventional factors with image phenotypes

Jamthikar¹,

Gupta²,

Khanna³

et al. 2019

Cardiovasc. Diagn. Ther.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Based on these recommendations, exercise may be presumed to influence an improved outcome in patients with DCM. If biomarkers or non-invasive imaging modalities could be used for early identification of high-risk patients [46,140], it would be feasible to prescribe personalized exercise programs based on risk stratification. Since exercise may not only mitigate cardiac dysfunction but also improve the outcome of T2DM [36,134,[141][142][143], a therapeutic approach with a tailored exercise prescription would positively impact DCM management in the future.…”

Section: Exercise Is An Early Diagnostic Tool For Prevention and Bettmentioning

confidence: 99%

Exercise as A Potential Therapeutic Target for Diabetic Cardiomyopathy: Insight into the Underlying Mechanisms

Seo

Jang

et al. 2019

IJMS

View full text Add to dashboard Cite

Diabetes mellitus is associated with cardiovascular, ophthalmic, and renal comorbidities. Among these, diabetic cardiomyopathy (DCM) causes the most severe symptoms and is considered to be a major health problem worldwide. Exercise is widely known as an effective strategy for the prevention and treatment of many chronic diseases. Importantly, the onset of complications arising due to diabetes can be delayed or even prevented by exercise. Regular exercise is reported to have positive effects on diabetes mellitus and the development of DCM. The protective effects of exercise include prevention of cardiac apoptosis, fibrosis, oxidative stress, and microvascular diseases, as well as improvement in cardiac mitochondrial function and calcium regulation. This review summarizes the recent scientific findings to describe the potential mechanisms by which exercise may prevent DCM and heart failure.

show abstract

Cardiovascular risk assessment in patients with rheumatoid arthritis using carotid ultrasound B-mode imaging

Jamthikar

Gupta

Puvvula³

et al. 2020

Rheumatol Int

Self Cite

View full text Add to dashboard Cite

Rheumatoid arthritis (RA) is a systemic chronic inflammatory disease that affects synovial joints and has various extraarticular manifestations, including atherosclerotic cardiovascular disease (CVD). Patients with RA experience a higher risk of CVD, leading to increased morbidity and mortality. Inflammation is a common phenomenon in RA and CVD. The pathophysiological association between these diseases is still not clear, and, thus, the risk assessment and detection of CVD in such patients is of clinical importance. Recently, artificial intelligence (AI) has gained prominence in advancing healthcare and, therefore, may further help to investigate the RA-CVD association. There are three aims of this review: (1) to summarize the three pathophysiological pathways that link RA to CVD; (2) to identify several traditional and carotid ultrasound image-based CVD risk calculators useful for RA patients, and (3) to understand the role of artificial intelligence in CVD risk assessment in RA patients. Our search strategy involves extensively searches in PubMed and Web of Science databases using search terms associated with CVD risk assessment in RA patients. A total of 120 peer-reviewed articles were screened for this review. We conclude that (a) two of the three pathways directly affect the atherosclerotic process, leading to heart injury, (b) carotid ultrasound image-based calculators have shown superior performance compared with conventional calculators, and (c) AI-based technologies in CVD risk assessment in RA patients are aggressively being adapted for routine practice of RA patients.

show abstract

Nonlinear model for the carotid artery disease 10‐year risk prediction by fusing conventional cardiovascular factors to carotid ultrasound image phenotypes: A Japanese diabetes cohort study

Cited by 42 publications

References 107 publications

A low-cost machine learning-based cardiovascular/stroke risk assessment system: integration of conventional factors with image phenotypes

A low-cost machine learning-based cardiovascular/stroke risk assessment system: integration of conventional factors with image phenotypes

Exercise as A Potential Therapeutic Target for Diabetic Cardiomyopathy: Insight into the Underlying Mechanisms

Cardiovascular risk assessment in patients with rheumatoid arthritis using carotid ultrasound B-mode imaging

Contact Info

Product

Resources

About