Assessing cardiovascular risks from a mid-thigh CT image: a tree-based machine learning approach using radiodensitometric distributions

Abstract

The nonlinear trimodal regression analysis (NTRA) method based on radiodensitometric CT distributions was recently developed and assessed for the quantification of lower extremity function and nutritional parameters in aging subjects. However, the use of the NTRA method for building predictive models of cardiovascular health was not explored; in this regard, the present study reports the use of NTRA parameters for classifying elderly subjects with coronary heart disease (CHD), cardiovascular disease (CVD), and chronic heart failure (CHF) using multivariate logistic regression and three tree-based machine learning (ML) algorithms. Results from each model were assembled as a typology of four classification metrics: total classification score, classification by tissue type, tissuebased feature importance, and classification by age. The predictive utility of this method was modelled using CHF incidence data. ML models employing the random forests algorithm yielded the highest classification performance for all analyses, and overall classification scores for all three conditions were excellent: CHD (AUCROC: 0.936); CVD (AUCROC: 0.914); CHF (AUCROC: 0.994). Longitudinal assessment for modelling the prediction of CHF incidence was likewise robust (AUCROC: 0.993). The present work introduces a substantial step forward in the construction of non-invasive, standardizable tools for associating adipose, loose connective, and lean tissue changes with cardiovascular health outcomes in elderly individuals.The progressive degeneration of skeletal muscle is consistently identified as an independent risk factor for significant morbidity, disability, and mortality in aging individuals 1-7 . Defined as sarcopenia, recent literature has interrogated its mediating and moderating roles in a wide range of adverse health outcomes, including its role in the etiology of cardiovascular pathophysiology. Catabolic inflammatory cytokine production and characteristic adiposity from the progression of sarcopenia have been linked with the onset of diabetes 8 , hypertension 9 , and dyslipidemia 10 -all of which are well-established risk factors for coronary heart disease (CHD) 11 and all-type cardiovascular disease (CVD) [12][13][14][15] . Chronic heart failure (CHF) patients frequently develop cardiac cachexia, a similar muscle wasting condition whose advanced stage has been implicated as an accelerated analogue of sarcopenic muscle degeneration 16 . Indeed, the progression of sarcopenia in older CHF patients may be considerably entangled with embedded cachexic effects 16,17 . While literature cites the associations and potential causal mechanisms between cardiovascular pathophysiology and downstream changes in skeletal muscle form and function 18 , validating standardized predictive models for these conditions remains debated. Furthermore, incorporating more nuanced quantitative methods for the non-invasive prediction of these events remains a priority in literature. Identifying such a methodology would further establish the generalizability of ...

Home-Based Functional Electrical Stimulation of Human Permanent Denervated Muscles: A Narrative Review on Diagnostics, Managements, Results and Byproducts Revisited 2020

“…We determined the gross anatomy of the thigh muscles and the extent of their atrophy/degeneration using quantitative muscle color computed tomography (QMC-CT) [ 21 , 27 , 28 , 29 ]. QMC-CT uses the Hounsfield units for tissue characterization.…”

Machine learning to predict mortality after rehabilitation among patients with severe stroke

“…Tree-based algorithms are empowerments of a simpler decision tree that can make it stronger and let it achieve higher accuracy in the prediction tasks 36 – 38 . They belong to the so-called supervised learning, which consists in making a classifier learn from the data by providing it with the classes of each subject.…”

“…Second, our ML analysis was fully addressed to a tree-based approach. While other classifiers can be employed, a fully tree-based approach and, in general, decision tree-based algorithms have already shown in literature their great potential 36 – 38 . Third, despite having performed a validation internally through the cross-validation, the models were not externally validated in an independent dataset and thus overfitting cannot be ruled out.…”

Improving Prosthetic Selection and Predicting BMD from Biometric Measurements in Patients Receiving Total Hip Arthroplasty

“…ML is a subset of artificial intelligence and consists of the capacity of a computer to learn from training/past data in order to make predictions, and classification or regression analyses on new/test data. Many applications are present in the literature representing the implementation of ML algorithms with healthcare data: Ricciardi et al applied it to study fetal well-being [ 18 ], Stanzione et al and Romeo et al applied ML in radiomics processes [ 19 , 20 ], and Ricciardi et al performed ML studies for the diagnosis and prognosis of patients affected by coronary artery disease [ 21 , 22 ]. Haeberle et al, recently, conducted a review of ML in the orthopedic field, as well as Cabitza et al, who stated that there has been a 10-fold increase in reports mentioning ML in the last 20 years [ 23 , 24 ].…”