Machine learning predictive system based upon radiodensitometric distributions from mid-thigh CT images

Correlation between trunk function improvement and recovery of activities of daily living after stroke in older adult patients

OBJECTIVES

To examine the impact of improved trunk function on activities of daily living in stroke patients using the Functional Independence Measure (FIM).

METHODS

This retrospective observational study was conducted on patients aged ≥ 65 years who had cerebral infarction. Patients were divided into a group with improved trunk function and a group without trunk function improvement based on the difference between the calculated Functional Assessment for Control of Trunk (FACT) gain at discharge and admission.

RESULTS

Of the 218 patients (mean age, 79.5 ± 7.9 years; 56.9% were men) included, 110 patients had improved FACT scores. Multiple linear regression analysis revealed that the group with improved FACT scores had higher FIM gain (coefficient = 7.562, 95% confidence interval = 3.870-11.253, P < 0.001). Multivariate logistic regression showed that the factors associated with FACT score improvement were the Mini Nutritional Assessment Short-Form score at admission, National Institutes of Health Stroke Scale score at admission, FACT score at admission, length of hospital stay, and period of rehabilitation.

DISCUSSIONS

Improvement in trunk function suggests a positive correlation with the recovery of activities of daily living in patients with cerebral infarction. This relationship should be further validated through prospective observational studies.

Development of soft tissue asymmetry indicators to characterize aging and functional mobility

Introduction: The aging population poses significant challenges to healthcare systems globally, necessitating a comprehensive understanding of age-related changes affecting physical function. Age-related functional decline highlights the urgency of understanding how tissue composition changes impact mobility, independence, and quality of life in older adults. Previous research has emphasized the influence of muscle quality, but the role of tissue composition asymmetry across various tissue types remains understudied. This work develops asymmetry indicators based on muscle, connective and fat tissue extracted from cross-sectional CT scans, and shows their interplay with BMI and lower extremity function among community-dwelling older adults. Methods: We used data from 3157 older adults from 71 to 98 years of age (mean: 80.06). Tissue composition asymmetry was defined by the differences between the right and left sides using CT scans and the non-Linear Trimodal Regression Analysis (NTRA) parameters. Functional mobility was measured through a 6-meter gait (Normal-GAIT and Fast-GAIT) and the Timed Up and Go (TUG) performance test. Statistical analysis included paired t-tests, polynomial fitting curves, and regression analysis to uncover relationships between tissue asymmetry, age, and functional mobility. Results: Findings revealed an increase in tissue composition asymmetry with age. Notably, muscle and connective tissue width asymmetry showed significant variation across age groups. BMI classifications and gait tasks also influenced tissue asymmetry. The Fast-GAIT task demonstrated a substantial separation in tissue asymmetry between normal and slow groups, whereas the Normal-GAIT and the TUG task did not exhibit such distinction. Muscle quality, as reflected by asymmetry indicators, appears crucial in understanding age-related changes in muscle function, while fat and connective tissue play roles in body composition and mobility. Discussion: Our study emphasizes the importance of tissue asymmetry indicators in understanding how muscle function changes with age in older individuals, demonstrating their role as risk factor and their potential employment in clinical assessment. We also identified the influence of fat and connective tissue on body composition and functional mobility. Incorporating the NTRA technology into clinical evaluations could enable personalized interventions for older adults, promoting healthier aging and maintaining physical function.

Association between serum soluble α-klotho and bone mineral density (BMD) in middle-aged and older adults in the United States: a population-based cross-sectional study

BACKGROUND

Osteoporosis is a degenerative disease defined by low bone mineral density, has a high prevalence, and causes fractures at multiple sites throughout the body, greatly affecting the quality of patients. α-Klotho is an endocrine factor involved in the regulation of various metabolic processes in humans, and its role in bone metabolism has attracted widespread attention. The relationship between α-klotho and bone mineral density has not been uniformly recognized, and no large-scale correlation analysis has been conducted in the middle-aged and elderly population.

OBJECTIVE

To determine the relationship between α-klotho and bone mineral density in middle-aged and elderly people.

METHODS

Population data of 3120 individuals aged 40-79 years were obtained from the NHANES database for the period 2011-2016. Regression analysis was performed using a general linear model with serum α-klotho as the independent variable and total bone mineral density, thoracic bone mineral density, lumbar bone mineral density, pelvic bone mineral density, and trunk bone mineral density as the dependent variables, respectively. The generalized additive model was also used for smoothing curve fitting and threshold effect analysis.

RESULTS

Serum α-klotho was positively correlated with total bone mineral density at lg (Klotho) < 2.97 and with thoracic bone mineral density at lg (Klotho) > 2.69 (β = 0.05, p = 0.0006), and negatively correlated (β = -0.27, p = 0.0341) with lumbar bone mineral density at lg (Klotho) < 2.69. It also positively correlated with trunk bone mineral density (β = 0.027, p = 0.03657) and had no segmental effect but did not correlate with pelvic bone mineral density. The positive association of serum α-klotho with those aged 40-49 years, female, non-Hispanic White, and without hypertension was clearer. In the population with diabetes, a significantly positive association between total (β = 0.15, p = 0.01), thoracic (β = 0.23, p = 0.0404), and lumbar (β = 0.22, p = 0.0424) bone mineral density and α-klotho was observed.

CONCLUSIONS

α-Klotho has different relationships with total, thoracic, lumbar, and trunk bone mineral density. Among them, the positive correlation between α-klotho and trunk bone mineral density is more valuable for predicting osteoporosis. The significant effect of α-klotho on bone mineral density in diabetes patients suggests its potential as a predictive marker of diabetes progression.

Effects of transcranial direct current stimulation on lower limb function, balance and quality of life after stroke: a systematic review and meta-analysis

OBJECTIVE

This systematic review with meta-analysis aimed to evaluate the effectiveness of tDCS on lower limb function, balance and quality of life in stroke patients.

METHODS

The search included PubMed, CENTRAL, PEDro, Web of Science, SCOPUS, PsycINFO Ovid, CINAHL EBSCO, EMBASE, ScienceDirect, reference lists of relevant reviews, clinical trials registries and academic google, in June and July 2021. Randomized controlled trials were selected, which present the effect of tDCS on lower limb motor function recovery in stroke patients, comparing any type of active tDCS versus sham; parallel or crossover study design; adult patients; stimulation on the primary motor cortex; articles published in any language; without restriction of publication period.

RESULTS

Nineteen studies were included. The treatment with active tDCS did not improve motor function (Chi2 = 32,87, I2 = 76%, SMD = 0,36 e 95% CI -0,18-0,90). Subgroup analyzes showed a significant effect favorable to tDCS, in relation to motor function, in the acute and subacute post stroke phases. However, the quality of evidence for this outcome was very low. Regarding balance outcome, a meta-analysis showed a significant difference in favor of active tDCS, but the quality of the evidence was considered very low. As for the quality of life outcome, no statistically significant difference was found in favor of tDCS.

DISCUSSION

There is a lack of evidence in recommending the use of tDCS in isolation in the treatment of patients after stroke, aiming at improving motor function, balance and quality of life. However, it is possible that tDCS can be beneficial when associated with other therapies or interventions.

Evaluating the Asymmetry of Muscle Activation and Strength in Paralympic Powerlifting Athletes

BACKGROUND

Strength training is a complex task, as it requires a combination of many variables. In paralympic powerlifting (PP) asymmetries for the evaluation of activation, and static force indicators have been increasingly studied.

OBJECTIVE

To investigate the asymmetries in the strength and muscle activation indicators, before and after a training session of PP athletes.

METHODOLOGY

Twelve elite athletes from the PP participated in the study, and asymmetry was evaluated through surface electromyography (sEMG) and static strength indicators. Evaluations were made before and after a protocol of five series of five repetitions (5 × 5), with 80% of 1-Maximum Repetition (1RM).

RESULTS

In the pectoral muscles, there were differences in the non-dominant limbs between the before and after in the sEMG. There were differences in the pectoralis muscle in the non-dominant limb between moments before (110.75 ± 59.52%) and after (130.53 ± 98.48%, p < 0.001), and there was no difference in triceps activation. In the Maximum Isometric Strength (MIF), there was a difference in the non-dominant limb between before (710.36 ± 129.36) and after (620.27 ± 69.73; p < 0.030). There was a difference before in the dominant (626.89 ± 120.16; 95% CI 550.55-703.24) and non-dominant (710.36 ± 129.36; p = 0.011) limbs. There was no difference in time to MIF.

CONCLUSION

PP athletes showed small levels of asymmetry before and after training, and adaptation to training tends to promote fewer asymmetries.

Methods for automated delineation and assessment of EMG responses evoked by peripheral nerve stimulation in diagnostic and closed-loop therapeutic applications

Objective.Surface electromyography measurements of the Hoffmann (H-) reflex are essential in a wide range of neuroscientific and clinical applications. One promising emerging therapeutic application is H-reflex operant conditioning, whereby a person is trained to modulate the H-reflex, with generalized beneficial effects on sensorimotor function in chronic neuromuscular disorders. Both traditional diagnostic and novel realtime therapeutic applications rely on accurate definitions of the H-reflex and M-wave temporal bounds, which currently depend on expert case-by-case judgment. The current study automates such judgments.Approach.Our novel wavelet-based algorithm automatically determines temporal extent and amplitude of the human soleus H-reflex and M-wave. In each of 20 participants, the algorithm was trained on data from a preliminary 3 or 4 min recruitment-curve measurement. Output was evaluated on parametric fits to subsequent sessions' recruitment curves (92 curves across all participants) and on the conditioning protocol's subsequent baseline trials (∼1200 per participant) performed nearHmax. Results were compared against the original temporal bounds estimated at the time, and against retrospective estimates made by an expert 6 years later.Main results.Automatic bounds agreed well with manual estimates: 95% lay within ±2.5 ms. The resulting H-reflex magnitude estimates showed excellent agreement (97.5% average across participants) between automatic and retrospective bounds regarding which trials would be considered successful for operant conditioning. Recruitment-curve parameters also agreed well between automatic and manual methods: 95% of the automatic estimates of the current required to elicitHmaxfell within±1.4%of the retrospective estimate; for the 'threshold' current that produced an M-wave 10% of maximum, this value was±3.5%.Significance.Such dependable automation of M-wave and H-reflex definition should make both established and emerging H-reflex protocols considerably less vulnerable to inter-personnel variability and human error, increasing translational potential.

Assessment of Therapeutic Potential of a Dual AAV Approach for Duchenne Muscular Dystrophy

Duchenne muscular dystrophy (DMD) is a yet incurable rare genetic disease that affects the skeletal and cardiac muscles, leading to progressive muscle wasting and premature death. DMD is caused by the lack of dystrophin, a muscle protein essential for the biochemical support and integrity of muscle fibers. Gene replacement strategies for Duchenne muscular dystrophy (DMD) employing the adeno-associated virus (AAV) face the challenge imposed by the limited packaging capacity of AAV, only allowing the accommodation of a short version of dystrophin (µDys) that is still far removed from correcting human disease. The need to develop strategies leading to the expression of a best performing dystrophin variant led to only few studies reporting on the use of dual vectors, but none reported on a method to assess in vivo transgene reconstitution efficiency, the degree of which directly affects the use of safe AAV dosing. We report here on the generation of a dual AAV vector approach for the expression of a larger dystrophin version (quasidystrophin) based on homologous recombination, and the development of a methodology employing a strategic droplet digital PCR design, to determine the recombination efficiency as well as the occurrence of unwanted concatemerization events or aberrant expression from the single vectors. We demonstrated that, upon systemic delivery in the dystrophic D2.B10-Dmd^mdx/J (DBA2mdx) mice, our dual AAV approach led to high transgene reconstitution efficiency and negligible Inverted Terminal Repeats (ITR)-dependent concatemerization, with consequent remarkable protein restoration in muscles and improvement of muscle pathology. This evidence supports the suitability of our system for gene therapy application and the potential of this methodology to assess and improve the feasibility for therapeutic translation of multiple vector approaches.

Accumulation of Dystrophin-Positive Muscle Fibers and Improvement of Neuromuscular Junctions in mdx Mouse Muscles after Bone Marrow Transplantation under Different Conditions

Duchenne muscular dystrophy (DMD) is a severe muscular disorder caused by mutations in the dystrophin gene. It leads to respiratory and cardiac failure and premature death at a young age. Although recent studies have greatly deepened the understanding of the primary and secondary pathogenetic mechanisms of DMD, an effective treatment remains elusive. In recent decades, stem cells have emerged as a novel therapeutic product for a variety of diseases. In this study, we investigated nonmyeloablative bone marrow cell (BMC) transplantation as a method of cell therapy for DMD in an mdx mouse model. By using BMC transplantation from GFP-positive mice, we confirmed that BMCs participate in the muscle restoration of mdx mice. We analyzed both syngeneic and allogeneic BMC transplantation under different conditions. Our data indicated that 3 Gy X-ray irradiation with subsequent BMC transplantation improved dystrophin synthesis and the structure of striated muscle fibers (SMFs) in mdx mice as well as decreasing the death rate of SMFs. In addition, we observed the normalization of neuromuscular junctions (NMJs) in mdx mice after nonmyeloablative BMC transplantation. In conclusion, we demonstrated that nonmyeloablative BMC transplantation could be considered a method for DMD treatment.

Machine Learning Approaches with Textural Features to Calculate Breast Density on Mammography

BACKGROUND

breast cancer (BC) is the world's most prevalent cancer in the female population, with 2.3 million new cases diagnosed worldwide in 2020. The great efforts made to set screening campaigns, early detection programs, and increasingly targeted treatments led to significant improvement in patients' survival. The Full-Field Digital Mammograph (FFDM) is considered the gold standard method for the early diagnosis of BC. From several previous studies, it has emerged that breast density (BD) is a risk factor in the development of BC, affecting the periodicity of screening plans present today at an international level.

OBJECTIVE

in this study, the focus is the development of mammographic image processing techniques that allow the extraction of indicators derived from textural patterns of the mammary parenchyma indicative of BD risk factors.

METHODS

a total of 168 patients were enrolled in the internal training and test set while a total of 51 patients were enrolled to compose the external validation cohort. Different Machine Learning (ML) techniques have been employed to classify breasts based on the values of the tissue density. Textural features were extracted only from breast parenchyma with which to train classifiers, thanks to the aid of ML algorithms.

RESULTS

the accuracy of different tested classifiers varied between 74.15% and 93.55%. The best results were reached by a Support Vector Machine (accuracy of 93.55% and a percentage of true positives and negatives equal to TPP = 94.44% and TNP = 92.31%). The best accuracy was not influenced by the choice of the features selection approach. Considering the external validation cohort, the SVM, as the best classifier with the 7 features selected by a wrapper method, showed an accuracy of 0.95, a sensitivity of 0.96, and a specificity of 0.90.

CONCLUSIONS

our preliminary results showed that the Radiomics analysis and ML approach allow us to objectively identify BD.

Excessive Sagittal Slope of the Tibia Component during Kinematic Alignment-Safety and Functionality at a Minimum 2-Year Follow-Up

The aim of this study was to assess the safety and functional outcomes of excessive sagittal alignment in the unrestricted kinematic alignment technique for total knee arthroplasty (TKA). A retrospective, single-center study was conducted between 2018 and 2020, including patients undergoing primary TKA with a minimum 2-year follow-up. EOS imaging conducted before and after surgery was reviewed for overall alignment, and a number of measurements were taken, including sagittal tibial slope and other tibia and femur component positioning. Patients were interviewed and asked to fill out several questionnaires including a visual analog scale, the Oxford Knee Score, and the Knee Injury and Osteoarthritis Outcome Score. Overall, 225 patients (66.7%) had a sagittal tibial slope angle above 5° (excessive) and 112 (33.3%) patients had an angle under 5° (moderate). A significant improvement in pain and function scores was observed in both groups following the surgery (p < 0.001). There were no significant differences between the moderate and excessive groups in the average VAS, OKS or the various subtypes of the KOOS score. However, there was a slight but significant difference in the number of patients achieving MCID in KOOS symptoms. There were no cases of early failure or loosening. Unrestricted KA and the excessive sagittal alignment of the tibial component seem to be reliable and safe in terms of restoring daily function and alleviating pain after a minimum of 2 years following the surgery.

A Therapeutic Strategy for Lower Motor Neuron Disease and Injury Integrating Neural Stem Cell Transplantation and Functional Electrical Stimulation in a Rat Model

Promising treatments for upper motor neuron disease are emerging in which motor function is restored by brain–computer interfaces and functional electrical stimulation. At present, such technologies and procedures are not applicable to lower motor neuron disease. We propose a novel therapeutic strategy for lower motor neuron disease and injury integrating neural stem cell transplantation with our new functional electrical stimulation control system. In a rat sciatic nerve transection model, we transplanted embryonic spinal neural stem cells into the distal stump of the peripheral nerve to reinnervate denervated muscle, and subsequently demonstrated that highly responsive limb movement similar to that of a healthy limb could be attained with a wirelessly powered two-channel neurostimulator that we developed. This unique technology, which can reinnervate and precisely move previously denervated muscles that were unresponsive to electrical stimulation, contributes to improving the condition of patients suffering from intractable diseases of paralysis and traumatic injury.

Using Machine Learning to Identify Intravenous Contrast Phases on Computed Tomography

PURPOSE

The purpose of the present work is to demonstrate the application of machine learning (ML) techniques to automatically identify the presence and physiologic phase of intravenous (IV) contrast in Computed Tomography (CT) scans of the Chest, Abdomen and Pelvis.

MATERIALS AND METHODS

Training, testing and validation data were acquired from a dataset of 82,690 chest and abdomen CT examinations performed at 17 different institutions. Free text in DICOM metadata was utilized as weak labels for semi-supervised classification training. Contrast phase identification was approached as a classification task, using a 12-layer CNN and ResNet18 with four contrast-phase output. The model was reformulated to fit a regression task aimed to predict actual seconds from time of IV contrast administration to series image acquisition. Finally, transfer learning was used to optimize the model to predict contrast presence on CT Chest.

RESULTS

By training based on labels inferred from noisy, free text DICOM information, contrast phase was predicted with 93.3% test accuracy (95% CI: 89.3%, 96.6%) . Regression analysis resulted in delineation of early vs late arterial phases and a nephrogenic phase in between the portal venous and delayed excretory phase. Transfer learning applied to Chest CT achieved an AUROC of 0.776 (95% CI: 0.721, 0.832) directly using the model trained for abdomen CT and 0.999 (95% CI: 0.998, 1.000) by fine-tuning.

CONCLUSIONS

The presence and phase of contrast on CT examinations of the Abdomen-pelvis accurately and automatically be ascertained by a machine learning algorithm. Transfer learning applied to CT Chest achieves high precision with as little as 100 labeled samples.

Trauma of Peripheral Innervation Impairs Content of Epidermal Langerhans Cells

Langerhans cells represent the first immune cells that sense the entry of external molecules and microorganisms at the epithelial level in the skin. In this pilot case-study, we evaluated Langerhans cells density and progression of epidermal atrophy in permanent spinal cord injury (SCI) patients suffering with either lower motor neuron lesions (LMNSCI) or upper motor neuron lesions (UMNSCI), both submitted to surface electrical stimulation. Skin biopsies harvested from both legs were analyzed before and after 2 years of home-based Functional Electrical Stimulation for denervated degenerating muscles (DDM) delivered at home (h-bFES) by large anatomically shaped surface electrodes placed on the skin of the anterior thigh in the cases of LMNSCI patients or by neuromuscular electrical stimulation (NMES) for innervated muscles in the cases of UMNSCI persons. Using quantitative histology, we analyzed epidermal thickness and flattening and content of Langerhans cells. Linear regression analyses show that epidermal atrophy worsens with increasing years of LMNSCI and that 2 years of skin electrostimulation reverses skin changes, producing a significant recovery of epidermis thickness, but not changes in Langerhans cells density. In UMNSCI, we did not observe any statistically significant changes of the epidermis and of its content of Langerhans cells, but while the epidermal thickness is similar to that of first year-LMNSCI, the content of Langerhans cells is almost twice, suggesting that the LMNSCI induces an early decrease of immunoprotection that lasts at least 10 years. All together, these are original clinically relevant results suggesting a possible immuno-repression in epidermis of the permanently denervated patients.

Bidimensional and Tridimensional Poincaré Maps in Cardiology: A Multiclass Machine Learning Study

Heart rate is a nonstationary signal and its variation may contain indicators of current disease or warnings about impending cardiac diseases. Hence, heart rate variation analysis has become a noninvasive tool to further study the activities of the autonomic nervous system. In this scenario, the Poincaré plot analysis has proven to be a valuable tool to support cardiac diseases diagnosis. The study’s aim is a preliminary exploration of the feasibility of machine learning to classify subjects belonging to five cardiac states (healthy, hypertension, myocardial infarction, congestive heart failure and heart transplanted) using ten unconventional quantitative parameters extracted from bidimensional and three-dimensional Poincaré maps. Knime Analytic Platform was used to implement several machine learning algorithms: Gradient Boosting, Adaptive Boosting, k-Nearest Neighbor and Naïve Bayes. Accuracy, sensitivity and specificity were computed to assess the performances of the predictive models using the leave-one-out cross-validation. The Synthetic Minority Oversampling technique was previously performed for data augmentation considering the small size of the dataset and the number of features. A feature importance, ranked on the basis of the Information Gain values, was computed. Preliminarily, a univariate statistical analysis was performed through one-way Kruskal Wallis plus post-hoc for all the features. Machine learning analysis achieved interesting results in terms of evaluation metrics, such as demonstrated by Adaptive Boosting and k-Nearest Neighbor (accuracies greater than 90%). Gradient Boosting and k-Nearest Neighbor reached even 100% score in sensitivity and specificity, respectively. The most important features according to information gain are in line with the results obtained from the statistical analysis confirming their predictive power. The study shows the proposed combination of unconventional features extracted from Poincaré maps and well-known machine learning algorithms represents a valuable approach to automatically classify patients with different cardiac diseases. Future investigations on enriched datasets will further confirm the potential application of this methodology in diagnostic.

Length-dependent changes of lower limb muscle morphology in Chronic Inflammatory Demyelinating Polyneuropathy assessed with magnetic resonance imaging

The objective of the present study was to assess muscle quantity of the thigh and leg in patients with chronic inflammatory demyelinating polyneuropathy (CIDP) compared to age and sex matched controls in exploring length-dependent changes of innervated muscles. In five people with CIDP and seven controls, magnetic resonance imaging was used to assess muscle morphology of the four parts of the quadriceps and medial hamstring muscles. Findings were compared to the triceps surae from a subset of participants. The CIDP group had less contractile tissue in the quadriceps (11.5%, P<0.05), hamstrings (15.6%, P<0.05) and triceps surae (35.9%, P<0.05) compared to controls. Additionally, CIDP had less contractile tissue (18.7%) in the triceps surae compared to the hamstrings (P<0.05). Muscle quantity in the quadriceps and hamstrings in CIDP was less than controls, but differences were greater for the distal triceps surae. These findings support a length-dependent affect of CIDP on limb musculature composition.

Muscle Oxygenation Level Might Trigger the Regulation of Capillary Venous Blood Filling during Fatiguing Isometric Muscle Actions

The regulation of oxygen and blood supply during isometric muscle actions is still unclear. Recently, two behavioral types of oxygen saturation (SvO2) and relative hemoglobin amount (rHb) in venous microvessels were described during a fatiguing holding isometric muscle action (HIMA) (type I: nearly parallel behavior of SvO2 and rHb; type II: partly inverse behavior). The study aimed to ascertain an explanation of these two regulative behaviors. Twelve subjects performed one fatiguing HIMA trial with each arm by weight holding at 60% of the maximal voluntary isometric contraction (MVIC) in a 90° elbow flexion. Six subjects additionally executed one fatiguing PIMA trial by pulling on an immovable resistance with 60% of the MVIC with each side and same position. Both regulative types mentioned were found during HIMA (I: n = 7, II: n = 17) and PIMA (I: n = 3, II: n = 9). During the fatiguing measurements, rHb decreased initially and started to increase in type II at an average SvO2-level of 58.75 ± 2.14%. In type I, SvO2 never reached that specific value during loading. This might indicate the existence of a threshold around 59% which seems to trigger the increase in rHb and could explain the two behavioral types. An approach is discussed to meet the apparent incompatibility of an increased capillary blood filling (rHb) despite high intramuscular pressures which were found by other research groups during isometric muscle actions.

Comparing the Prognostic Value of Stress Myocardial Perfusion Imaging by Conventional and Cadmium-Zinc Telluride Single-Photon Emission Computed Tomography through a Machine Learning Approach

We compared the prognostic value of myocardial perfusion imaging (MPI) by conventional- (C-) single-photon emission computed tomography (SPECT) and cadmium-zinc-telluride- (CZT-) SPECT in a cohort of patients with suspected or known coronary artery disease (CAD) using machine learning (ML) algorithms. A total of 453 consecutive patients underwent stress MPI by both C-SPECT and CZT-SPECT. The outcome was a composite end point of all-cause death, cardiac death, nonfatal myocardial infarction, or coronary revascularization procedures whichever occurred first. ML analysis performed through the implementation of random forest (RF) and k-nearest neighbors (KNN) algorithms proved that CZT-SPECT has greater accuracy than C-SPECT in detecting CAD. For both algorithms, the sensitivity of CZT-SPECT (96% for RF and 60% for KNN) was greater than that of C-SPECT (88% for RF and 53% for KNN). A preliminary univariate analysis was performed through Mann-Whitney tests separately on the features of each camera in order to understand which ones could distinguish patients who will experience an adverse event from those who will not. Then, a machine learning analysis was performed by using Matlab (v. 2019b). Tree, KNN, support vector machine (SVM), Naïve Bayes, and RF were implemented twice: first, the analysis was performed on the as-is dataset; then, since the dataset was imbalanced (patients experiencing an adverse event were lower than the others), the analysis was performed again after balancing the classes through the Synthetic Minority Oversampling Technique. According to KNN and SVM with and without balancing the classes, the accuracy (p value = 0.02 and p value = 0.01) and recall (p value = 0.001 and p value = 0.03) of the CZT-SPECT were greater than those obtained by C-SPECT in a statistically significant way. ML approach showed that although the prognostic value of stress MPI by C-SPECT and CZT-SPECT is comparable, CZT-SPECT seems to have higher accuracy and recall.

Using machine learning to reduce unnecessary rehospitalization of cardiovascular patients in Saudi Arabia

OBJECTIVES

Patient readmission is a costly and preventable burden on healthcare systems. The main objective of this study was to develop a machine-learning classification model to identify cardiovascular patients with a high risk of readmission.

METHODS

Inpatient data were collected from 48 Ministry of Health hospitals (MOH) in Saudi Arabia from 2016 to 2019. Cardiovascular disease (CVD)-related diagnoses were defined as congestive heart failure (HF), ischemic heart disease (IHD), cardiac arrhythmias (CA), and valvular diseases (VD). Hospitalization days, daily hospitalization price, and the price of each basic and medical service provided were used to calculate the healthcare utilization cost. We employed a Python machine-learning model to identify all-cause 30-day CVD-related readmissions using the International Classification of Diseases, Revision 10 classification system (ICD10) as the gold standard. Demographics, comorbidities, and healthcare utilization were used as the independent variables.

RESULTS

From 2016 to 2019, we identified 403,032 hospitalized patients from 48 hospitals in 13 administrative regions of Saudi Arabia. Out of these patients, 17,461 had a history of hospital admission for cardiovascular reasons. The total direct cost of overall hospitalizations was 1.6 B international dollars (I$) with an average of I$ 3,156 per hospitalization, whereas CVD-related readmission costs were estimated to be I$ 14.9 M, with an average of I$ 7,600 per readmission. Finally, an empirical approach was followed to test several algorithms to identify patients at high risk of readmission. The comparison indicated that the decision-tree algorithm correctly classified 2,336 instances (926 readmitted and 1,410 not readmitted) and showed a higher F1 score than other models (64%), with a recall of 71% and precision of 57%.

CONCLUSION

This study identified IHD as the most prevalent CVD, and hypertension and diabetes were found to be the most common comorbidities among hospitalized CVD patients. Compared to general encounters, readmission encounters were nearly two times higher on average among the study population. Furthermore, we concluded that a machine-learning model can be used to identify CVD patients at a high risk of readmission. Further research is required to develop more accurate models based on clinical notes and laboratory results.

The relationship between extracellular water-to-body water ratio and sarcopenia according to the newly revised Asian Working Group for Sarcopenia: 2019 Consensus Update

OBJECTIVE

The purpose of this study was to evaluate the association between sarcopenia and extracellular water-to-total body water ratio (ECW/TBW), one of the results of bioimpedance that can be easily measured in communities, following the recent revision of the Asian Working Group for Sarcopenia.

METHODS

This study data were extracted from the baseline data of Namgaram-2. Among the surveyed subjects, 885 persons aged 60 years or older were selected as study subjects. All surveys were conducted on a one-on-one interview basis; blood tests, physical function evaluations (hand grip strength, short physical performance battery; SPPB), and dual-energy X-ray absorptiometry (DEXA) and bioimpedance were also conducted. The Asian Working Group's revised definition of sarcopenia was applied. ECW/TBW was one of the results of bioimpedance this study.

RESULTS

A high ECW/TBW was 1.63 times higher in the low grip strength group than in the robust group (P = 0.017) and was 2.13 times higher in the low SPPB group compared to the robust group (P < 0.001). ECW/TBW higher than 0.391 was 2.17 times more likely to occur in sarcopenic patients compared to the robust group (P < 0.001). In addition, ECW/TBW lower than 0.391 was 3.65 times more likely to occur in severely sarcopenic patients compared to the robust group (P = 0.002).

CONCLUSION

The ECW/TBW may be one of the valid research tools to evaluate the strength and physical performance of the elderly. In addition, it is expected to be one of the effective indicators for tracking physical function under newly revised sarcopenia criteria.

Testing soft tissue radiodensity parameters interplay with age and self-reported physical activity

Aging well is directly associated to a healthy lifestyle. The focus of this paper is to relate individual wellness with medical image features. Non-linear trimodal regression analysis (NTRA) is a novel method that models the radiodensitometric distributions of x-ray computed tomography (CT) cross-sections. It generates 11 patient-specific parameters that describe the quality and quantity of muscle, fat, and connective tissues. In this research, the relationship of these 11 NTRA parameters with age, physical activity, and lifestyle is investigated in the 3,157 elderly volunteers AGES-I dataset. First, univariate statistical analyses were performed, and subjects were grouped by age and self-reported past (youth–midlife) and present (within 12 months of the survey) physical activity to ascertain which parameters were the most influential. Then, machine learning (ML) analyses were conducted to classify patients using NTRA parameters as input features for three ML algorithms. ML is also used to classify a Lifestyle index using the age groups. This classification analysis yielded robust results with the lifestyle index underlying the relevant differences of the soft tissues between age groups, especially in fat and connective tissue. Univariate statistical models suggested that NTRA parameters may be susceptible to age and differences between past and present physical activity levels. Moreover, for both age and physical activity, lean muscle parameters expressed more significant variation than fat and connective tissues.

Skeletal muscle weakness in older adults home-restricted due to COVID-19 pandemic: a role for full-body in-bed gym and functional electrical stimulation

Persons suffering with systemic neuromuscular disorders or chronic organ failures, spend less time for daily physical activity, aggravating their mobility impairments. From 2020, patients at risk are also older adults, who, though negative for the SARS-Cov-2 infection, suffer with a fatigue syndrome due to home restriction/quarantine. Besides eventual psycological managements, it could be useful to offer to these patients a rehabilitation workouts easy to learn and to independently repeat at home (Full-Body In-Bed Gym). Inspired by the proven capability to recover skeletal muscle contractility and strength by home-based volitional exercises and functional electrical stimulation (FES), we suggest for this fatigue syndrome a 10–20 min long daily routine of easy and safe physical exercises that may recover from muscle weakness the main 400 skeletal muscles used for every-day activities. Leg muscles could be trained also by an adjunctive neuro-muscular electrical stimulation (NMES) in frail old persons. Many of the exercises could be performed in bed (Full-Body in-Bed Gym), thus hospitalized patients can learn this light training before leaving the hospital. Full-Body in-Bed Gym is, indeed, an extension of well-established cardiovascular-ventilation rehabilitation training performed by patients after heavy surgery. Blood pressure readings, monitored before and after daily routine of Full-Body in-Bed Gym, demonstrate a transient decrease in peripheral resistance due to increased blood flow to major body muscles. Continued regularly, Full-Body in-Bed Gym may help maintaining independence of frail people, including those suffering with the fatigue syndrome related to the restrictions/quarantine imposed to the general population during the COVID-19 pandemic.

Healthy Aging Within an Image: Using Muscle Radiodensitometry and Lifestyle Factors to Predict Diabetes and Hypertension

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.

To contrast and reverse skeletal muscle weakness by Full-Body In-Bed Gym in chronic COVID-19 pandemic syndrome

Mobility-impaired persons, either very old or younger but suffering with systemic neuromuscular disorders or chronic organ failures, spend small amounts of time for daily physical activity, contributing to aggravate their poor mobility by resting muscle atrophy. Sooner or later the limitations to their mobility enforce them to bed and to more frequent hospitalizations. We include among these patients at risk those who are negative for the SARS-COV-2 infection, but suffering with COVID-19 pandemic syndrome. Beside managements of psychological symptoms, it is mandatory to offer to the last group physical rehabilitation approaches easy to learn and self-managed at home. Inspired by the proven capability to recover skeletal muscle contractility and strength by home-based volitional exercises and functional electrical stimulation, we suggest also for chronic COVID-19 pandemic syndrome a 10-20 min long daily routine of easy and safe physical exercises that can activate, and recover from weakness, the main 400 skeletal muscles used for every-day mobility activities. Persons can do many of them in bed (Full-Body in-Bed Gym), and hospitalized patients can learn this light training before leaving the hospital. It is, indeed, an extension of well-established cardiovascular-respiratory rehabilitation training performed after heavy surgical interventions. Blood pressure readings, monitored before and after daily routine, demonstrate a transient decrease in peripheral resistance due to increased blood flow of many muscles. Continued regularly, Full-Body in-Bed Gym may help maintaining independence of frail people, including those suffering with the COVID-19 pandemic syndrome.

To contrast and reverse skeletal muscle weakness by Full-Body In-Bed Gym in chronic COVID-19 pandemic syndrome

Mobility-impaired persons, either very old or younger but suffering with systemic neuromuscular disorders or chronic organ failures, spend small amounts of time for daily physical activity, contributing to aggravate their poor mobility by resting muscle atrophy. Sooner or later the limitations to their mobility enforce them to bed and to more frequent hospitalizations. We include among these patients at risk those who are negative for the SARS-COV-2 infection, but suffering with COVID-19 pandemic syndrome. Beside managements of psychological symptoms, it is mandatory to offer to the last group physical rehabilitation approaches easy to learn and self-managed at home. Inspired by the proven capability to recover skeletal muscle contractility and strength by home-based volitional exercises and functional electrical stimulation, we suggest also for chronic COVID-19 pandemic syndrome a 10–20 min long daily routine of easy and safe physical exercises that can activate, and recover from weakness, the main 400 skeletal muscles used for every-day mobility activities. Persons can do many of them in bed (Full-Body in-Bed Gym), and hospitalized patients can learn this light training before leaving the hospital. It is, indeed, an extension of well-established cardiovascular-respiratory rehabilitation training performed after heavy surgical interventions. Blood pressure readings, monitored before and after daily routine, demonstrate a transient decrease in peripheral resistance due to increased blood flow of many muscles. Continued regularly, Full-Body in-Bed Gym may help maintaining independence of frail people, including those suffering with the COVID-19 pandemic syndrome.

Texture Features of Proton Density Fat Fraction Maps from Chemical Shift Encoding-Based MRI Predict Paraspinal Muscle Strength

Texture analysis (TA) has shown promise as a surrogate marker for tissue structure, based on conventional and quantitative MRI sequences. Chemical-shift-encoding-based MRI (CSE-MRI)-derived proton density fat fraction (PDFF) of paraspinal muscles has been associated with various medical conditions including lumbar back pain (LBP) and neuromuscular diseases (NMD). Its application has been shown to improve the prediction of paraspinal muscle strength beyond muscle volume. Since mean PDFF values do not fully reflect muscle tissue structure, the purpose of our study was to investigate PDFF-based TA of paraspinal muscles as a predictor of muscle strength, as compared to mean PDFF. We performed 3T-MRI of the lumbar spine in 26 healthy subjects (age = 30 ± 6 years; 15 females) using a six-echo 3D spoiled gradient echo sequence for chemical-shift-encoding-based water–fat separation. Erector spinae (ES) and psoas (PS) muscles were segmented bilaterally from level L2–L5 to extract mean PDFF and texture features. Muscle flexion and extension strength was measured with an isokinetic dynamometer. Out of the eleven texture features extracted for each muscle, Kurtosis(global) of ES showed the highest significant correlation (r = 0.59, p = 0.001) with extension strength and Variance(global) of PS showed the highest significant correlation (r = 0.63, p = 0.001) with flexion strength. Using multivariate linear regression models, Kurtosis(global) of ES and BMI were identified as significant predictors of extension strength (R²_adj = 0.42; p < 0.001), and Variance(global) and Skewness(global) of PS were identified as significant predictors of flexion strength (R²_adj = 0.59; p = 0.001), while mean PDFF was not identified as a significant predictor. TA of CSE-MRI-based PDFF maps improves the prediction of paraspinal muscle strength beyond mean PDFF, potentially reflecting the ability to quantify the pattern of muscular fat infiltration. In the future, this may help to improve the pathophysiological understanding, diagnosis, monitoring and treatment evaluation of diseases with paraspinal muscle involvement, e.g., NMD and LBP.

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

Stroke is among the leading causes of death and disability worldwide. Approximately 20–25% of stroke survivors present severe disability, which is associated with increased mortality risk. Prognostication is inherent in the process of clinical decision-making. Machine learning (ML) methods have gained increasing popularity in the setting of biomedical research. The aim of this study was twofold: assessing the performance of ML tree-based algorithms for predicting three-year mortality model in 1207 stroke patients with severe disability who completed rehabilitation and comparing the performance of ML algorithms to that of a standard logistic regression. The logistic regression model achieved an area under the Receiver Operating Characteristics curve (AUC) of 0.745 and was well calibrated. At the optimal risk threshold, the model had an accuracy of 75.7%, a positive predictive value (PPV) of 33.9%, and a negative predictive value (NPV) of 91.0%. The ML algorithm outperformed the logistic regression model through the implementation of synthetic minority oversampling technique and the Random Forests, achieving an AUC of 0.928 and an accuracy of 86.3%. The PPV was 84.6% and the NPV 87.5%. This study introduced a step forward in the creation of standardisable tools for predicting health outcomes in individuals affected by stroke.

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

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.

Three dimensional bone mineral density changes in the femur over 1 year in primary total hip arthroplasty patients

BACKGROUND

The aim of the study was to compare the bone mineral density changes between unmatched patients undergoing total hip arthroplasty receiving uncemented and cemented type of implants. Previous studies have used DEXA or a two dimensional analysis to estimate the bone quality following total joint replacement, whereas this study presents the changes in three dimensions.

METHODS

Fifty subjects both male and females receiving both cemented and uncemented type of implant were recruited. Two CT scans were taken of each subject, the first at 24 h post surgery and the second one 1 year after surgery. The scans were calibrated using a phantom converting the Hounsfield units to bone mineral density values in g/cm³. The two scans were registered together using anatomical landmarks and resliced to compare the two femurs in the identical frame of reference. The bone density gain and loss was calculated by comparing density values between the two sets of scans.

FINDINGS

The results showed that most of the bone loss was located around the Lesser Trochanter and some bone density gain at the distal tip of the implant. The three dimensional density changes occur differently between individuals and the study showed no correlation of bone loss with age.

INTERPRETATION

The bone loss occurred mostly at the proximal femur, which is in agreement with previously presented studies. By carrying out three dimensional analysis on the bone gain and loss on the femur, it is possible to identify the patients that are showing high degree of bone loss.

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

Spinal cord injury (SCI) produces muscle wasting that is especially severe after complete and permanent damage of lower motor neurons, as can occur in complete conus and cauda equina syndrome. Even in this worst-case scenario, mass and function of permanently denervated quadriceps muscle can be rescued by surface functional electrical stimulation using a purpose designed home-based rehabilitation strategy. Early diagnostics is a key factor in the long-term success of this management. Function of quadriceps muscle was quantitated by force measurements. Muscle gross cross-sections were evaluated by quantitative color computed tomography (CT) and muscle and skin biopsies by quantitative histology, electron microscopy, and immunohistochemistry. Two years of treatment that started earlier than 5 years from SCI produced: (a) an increase in cross-sectional area of stimulated muscles; (b) an increase in muscle fiber mean diameter; (c) improvements in ultrastructural organization; and (d) increased force output during electrical stimulation. Improvements are extended to hamstring muscles and skin. Indeed, the cushioning effect provided by recovered tissues is a major clinical benefit. It is our hope that new trials start soon, providing patients the benefits they need.