The nonlinear trimodal regression analysis (NTRA) method based on radiodensitometric CT images distributions was developed for the quantitative characterization of soft tissue changes according to the lower extremity function of elderly subjects. In this regard, the NTRA method defines 11 subject-specific soft tissue parameters and has illustrated high sensitivity to changes in skeletal muscle form and function. The present work further explores the use of these 11 NTRA parameters in the construction of a machine learning (ML) system to predict body mass indexand isometric leg strength using tree-based regression algorithms. Results obtained from thesemodels demonstrate that when using an ML approach, these soft tissue features have a significant predictive value for these physiological parameters. These results further support the use of NTRA-based ML predictive assessment and support the future investigation of other physiological parametersand comorbidities.

The strong age dependency of many deleterious health outcomes likely reflects the cumulative effects from a variety of risk and protective factors that occur over one's life course. This notion has become increasingly explored in the etiology of chronic disease and associated comorbidities in aging. Our recent work has shown the robust classification of individuals at risk for cardiovascular pathophysiology using CT-based soft tissue radiodensity parameters obtained from nonlinear trimodal regression analysis (NTRA). Past and present lifestyle influences the incidence of comorbidities like hypertension (HTN), diabetes (DM) and cardiac diseases. 2,943 elderly subjects from the AGES-Reykjavik study were sorted into a three-level binary-tree structure defined by: 1) lifestyle factors (smoking and self-reported physical activity level), 2) comorbid HTN or DM, and 3) cardiac pathophysiology. NTRA parameters were extracted from mid-thigh CT cross-sections to quantify radiodensitometric changes in three tissue types: lean muscle, fat, and loose-connective tissue. Between-group differences were assessed at each binary-tree level, which were then used in tree-based machine learning (ML) models to classify subjects with DM or HTN. Classification scores for detecting HTN or DM based on lifestyle factors were excellent (AUCROC: 0.978 and 0.990, respectively). Finally, tissue importance analysis underlined the comparatively-high significance of connective tissue parameters in ML classification, while predictive models of DM onset from five-year longitudinal data gave a classification accuracy of 94.9%. Altogether, this work serves as an important milestone toward the construction of predictive tools for assessing the impact of lifestyle factors and healthy aging based on a single image.

There are two surgical approaches to performing total hip arthroplasty (THA): a cemented or uncemented type of prosthesis. The choice is usually based on the experience of the orthopaedic surgeon and on parameters such as the age and gender of the patient. Using machine learning (ML) techniques on quantitative biomechanical and bone quality data extracted from computed tomography, electromyography and gait analysis, the aim of this paper was, firstly, to help clinicians use patient-specific biomarkers from diagnostic exams in the prosthetic decision-making process. The second aim was to evaluate patient long-term outcomes by predicting the bone mineral density (BMD) of the proximal and distal parts of the femur using advanced image processing analysis techniques and ML. The ML analyses were performed on diagnostic patient data extracted from a national database of 51 THA patients using the Knime analytics platform. The classification analysis achieved 93% accuracy in choosing the type of prosthesis; the regression analysis on the BMD data showed a coefficient of determination of about 0.6. The start and stop of the electromyographic signals were identified as the best predictors. This study shows a patient-specific approach could be helpful in the decision-making process and provide clinicians with information regarding the follow up of patients.

Osteoarthritis (OA) is a common joint disease affecting people worldwide, notably impacting quality of life due to joint pain and functional limitations. This study explores the potential of radiomics — quantitative image analysis combined with machine learning — to enhance knee OA diagnosis. Using a multimodal dataset of MRI and CT scans from 138 knees, radiomic features were extracted from cartilage segments. Machine learning algorithms were employed to classify degenerated and healthy knees based on radiomic features. Feature selection, guided by correlation and importance analyses, revealed texture and shape-related features as key predictors. Robustness analysis, assessing feature stability across segmentation variations, further refined feature selection. Results demonstrate high accuracy in knee OA classification using radiomics, showcasing its potential for early disease detection and personalized treatment approaches. This work contributes to advancing OA assessment and is part of the European SINPAIN project aimed at developing new OA therapies.

The variability in patient outcome and propensity for surgical complications in total hip replacement (THR) necessitates the development of a comprehensive, quantitative methodology for prescribing the optimal type of prosthetic stem: cemented or cementless. The objective of the research presented herein was to describe a novel approach to this problem as a first step towards creating a patient-specific, presurgical application for determining the optimal prosthesis procedure. Finite element analysis (FEA) and bone mineral density (BMD) calculations were performed with ten voluntary primary THR patients to estimate the status of their operative femurs before surgery. A compilation model of the press-fitting procedure was generated to define a fracture risk index (FRI) from incurred forces on the periprosthetic femoral head. Comparing these values to patient age, sex, and gender elicited a high degree of variability between patients grouped by implant procedure, reinforcing the notion that age and gender alone are poor indicators for prescribing prosthesis type. Additionally, correlating FRI and BMD measurements indicated that at least two of the ten patients may have received nonideal implants. This investigation highlights the utility of our model as a foundation for presurgical software applications to assist orthopedic surgeons with selecting THR prostheses.

Muscle degeneration has been consistently identified as an independent risk factor for high mortality in both aging populations and individuals suffering from neuromuscular pathology or injury. While there is much extant literature on its quantification and correlation to comorbidities, a quantitative gold standard for analyses in this regard remains undefined. Herein, we hypothesize that rigorously quantifying entire radiodensitometric distributions elicits more muscle quality information than average values reported in extant methods. This study reports the development and utility of a nonlinear trimodal regression analysis method utilized on radiodensitometric distributions of upper leg muscles from CT scans of a healthy young adult, a healthy elderly subject, and a spinal cord injury patient. The method was then employed with a THA cohort to assess pre- and postsurgical differences in their healthy and operative legs. Results from the initial representative models elicited high degrees of correlation to HU distributions, and regression parameters highlighted physiologically evident differences between subjects. Furthermore, results from the THA cohort echoed physiological justification and indicated significant improvements in muscle quality in both legs following surgery. Altogether, these results highlight the utility of novel parameters from entire HU distributions that could provide insight into the optimal quantification of muscle degeneration.