Toward characterizing cardiovascular fitness using machine learning based on unobtrusive data.

Cardiopulmonary exercise testing (CPET) is a non-invasive approach to measure the maximum oxygen uptake ([Formula: see text]), which is an index to assess cardiovascular fitness (CF). However, CPET is not available to all populations and cannot be obtained continuously. Thus, wearable sensors are associated with machine learning (ML) algorithms to investigate CF. Therefore, this study aimed to predict CF by using ML algorithms using data obtained by wearable technologies. For this purpose, 43 volunteers with different levels of aerobic power, who wore a wearable device to collect unobtrusive data for 7 days, were evaluated by CPET. Eleven inputs (sex, age, weight, height, and body mass index, breathing rate, minute ventilation, total hip acceleration, walking cadence, heart rate, and tidal volume) were used to predict the [Formula: see text] by support vector regression (SVR). Afterward, the SHapley Additive exPlanations (SHAP) method was used to explain their results. SVR was able to predict the CF, and the SHAP method showed that the inputs related to hemodynamic and anthropometric domains were the most important ones to predict the CF. Therefore, we conclude that the cardiovascular fitness can be predicted by wearable technologies associated with machine learning during unsupervised activities of daily living.

Effects of Physical Exercise on Left Ventricular Function in Type 2 Diabetes Mellitus: A Systematic Review

Abstract Background The incidence of diabetes mellitus in younger adults is rising over the years. The diabetic population has an increased risk of developing heart failure, and diabetic individuals with heart failure have four times greater mortality rate. Studies results about exercise effect on left ventricular function in type 2 diabetes mellitus are heterogenous. Objective This review aimed to analyze the effects of physical exercise on left ventricular dysfunction in type 2 diabetes mellitus (T2DM). Methods Only randomized clinical trials with humans published in English were included. Inclusion criteria were studies with type 2 diabetes patients, physical exercise, control group and left ventricular function. Exclusion criteria were studies with animals, children, teenagers, elderly individuals and athletes, presence of diet intervention, and patients with type 1 diabetes, cancer, cardiac, pulmonary, or neurological diseases. Electronic databases PubMed, Web of Science, Cochrane, and Scopus were last searched in September 2021. Risk of bias was assessed by the Physiotherapy Evidence Database (PEDro) scale. Results Five studies were included, representing 314 diabetic individuals submitted to resistance and aerobic exercise training. Of the variables analyzed, physical exercise improved peak torsion (PTo), global longitudinal strain, global strain rate (GSR), time to peak untwist rate (PUTR), early diastolic filling rate (EDFR) and peak early diastolic strain rate (PEDSR). Conclusion To our knowledge, this is the first systematic review on the effects of exercise on left ventricular function in T2DM including only randomized clinical trials with humans. Physical exercise seems to improve systolic and diastolic strain, twist, and torsion. High intensity exercise was reported to be superior to moderate intensity exercise in one study. This review was limited by the small number of studies and their heterogeneity regarding exercise protocols, follow-up period, exercise supervision and left ventricular function variables analyzed. This review was registered in PROSPERO (CRD42021234964).

Improvement of Sympathovagal Balance by Regular Exercise May Counteract the Ageing Process. A Study by the Analysis of QT Variability.

QT interval (QT) variability analysis provides pathophysiological and prognostic information utilized in cardiac and non-cardiac diseases, complementary to those obtained from the analysis of heart period (HP) variability. An increased QT variability has been associated to a higher risk for cardiac events and poorest prognosis. Autonomic cardiovascular adaptation to internal and external challenges, such those occurring in athletes exposed to high levels of physical stress and in ageing could also be deepen by analyzing QT variability, searching for early prognostic signatures. The aim of the study was to analyze the QT variability and cardiac control complexity in a group of middle-aged half-marathon runners at baseline (B) and at a 10-year follow-up (FU). We found that the overall QT variability decreased at FU, despite the inescapable increase in age (52.3 ± 8.0 years at FU). This change was accompanied by an increase of the HP variability complexity without changes of the QT variability complexity. Of notice, over the years, the group of athletes maintained their regular physical activity by switching to a moderate intensity rather than strenuous. In conclusion, regular and moderate exercise over the years was beneficial for this group of athletes, as reflected by the decreased overall QT variability that is known to be associated to lower cardiovascular risk. The concomitant enhanced cardiac control complexity also suggests a trend opposite to what usually occurs with ageing, resulting in a more flexible cardiac control, typical of younger people.

Cardiovascular responses to low-intensity isometric handgrip exercise in coronary artery disease: effects of posture.

BACKGROUND: Coronary artery disease (CAD) lead to cardiovascular autonomic control disfunctions that can worsen exercise and/or posture adjustments. OBJECTIVES: To verify the cardiovascular responses to low-intensity isometric handgrip exercise performed in different postures in CAD patients. This study tested the hypothesis that the posture influences the cardiovascular responses during isometric handgrip exercise and that the presence of CAD leads to greater cardiovascular stress during this type of exercise. METHODS: We investigated cardiovascular responses to isometric handgrip exercise in 15 CAD patients (CADG) and 15 health matched-control (CG). The subjects performed isometric handgrip exercise at 30% of maximum voluntary contraction until exhaustion in SUPINE, SITTING and STANDING positions. Systolic arterial pressure, diastolic arterial pressure, mean blood pressure, heart rate, peripheral vascular resistance, cardiac output, stroke volume and double product were measured during rest (baseline), exercise (peak value) and recovery in the 1st minute (REC1). Delta PB (ΔPB, peak minus baseline) and PR1 (ΔPR1, peak minus REC1) were calculated. RESULTS: Higher ΔPB and ΔPR1 of systolic and mean arterial pressure and double product were observed in STANDING when compared to SITTING and/or SUPINE. CADG showed higher ΔPB of systolic and mean arterial pressure in all postures and higher ΔPR1 of strove volume in the SITTING. CONCLUSION: We concluded that the posture during isometric handgrip exercise influences the cardiovascular responses with STANDING leading to higher cardiovascular stress. CAD promoted higher arterial pressure responses however these responses were physiological and expected due to the presence of disease and type of exercise.

Cardiovascular Variability Analysis and Baroreflex Estimation in Patients with Type 2 Diabetes in Absence of Any Manifest Neuropathy.

INTRODUCTION: Indexes derived from spontaneous heart period (HP) and systolic arterial pressure (SAP) fluctuations can detect autonomic dysfunction in individuals with type 2 diabetes mellitus (DM) associated to cardiovascular autonomic neuropathy (CAN) or other neuropathies. It is unknown whether HP and SAP variability indexes are sensitive enough to detect the autonomic dysfunction in DM patients without CAN and other neuropathies. METHODS: We evaluated 68 males aged between 40 and 65 years. The group was composed by DM type 2 DM with no manifest neuropathy (n = 34) and healthy (H) subjects (n = 34). The protocol consisted of 15 minutes of recording of HP and SAP variabilities at rest in supine position (REST) and after active standing (STAND). The HP power in the high frequency band (HF, from 0.15 to 0.5 Hz), the SAP power in the low frequency band (LF, from 0.04 to 0.15 Hz) and BRS estimated via spectral approach and sequence method were computed. RESULTS: The HF power of HP was lower in DM patients than in H subjects, while the two groups exhibited comparable HF power of HP during STAND. The LF power of SAP was similar in DM and H groups at REST and increased during STAND in both groups. BRSs estimated in the HF band and via baroreflex sequence method were lower in DM than in H and they decreased further during STAND in both populations. CONCLUSION: Results suggest that vagal control of heart rate and cardiac baroreflex control was impaired in type 2 DM, while sympathetic control directed to vessels, sympathetic and baroreflex response to STAND were preserved. Cardiovascular variability indexes are sensitive enough to typify the early, peculiar signs of autonomic dysfunction in type-2 DM patients well before CAN becomes manifest.

Resposta aguda de variáveis clínicas e funcionais em exercício máximo de contração concêntrica versus excêntrica / Acute response of clinical and functional variables in maximal exercise from contraction concentric versus eccentric / Respuesta aguda de las variables clínicas y funcionales de la contracción concéntrica máxima de ejercicio en comparación con excéntrica

O objetivo do estudo foi analisar e comparar as respostas agudas de variáveis clínicas e funcionais, após uma sessão de exercício de força máxima de contração concêntrica versus excêntrica. Foram avaliados 46 indivíduos do sexo masculino, divididos aleatoriamente em dois grupos, conforme o tipo de exercício. Na comparação entre os grupos não houve diferenças significativas. Porém, na análise de cada grupo observou-se aumento da sensação de dor (EVA) e da percepção de esforço (escala de Borg) e incrementos nas medidas da circunferência da coxa (grupo excêntrico: 10% [p<0,001], 20% [p<0,001] e 30% [p<0,05]; grupo concêntrico: 40% [p<0,01]). Para o algômetro, apenas o grupo concêntrico apresentou menor limiar (p<0,01). Pode-se inferir que estímulos controlados até 100% não são agressivos e limitantes e futuros estudos podem incluir análises de marcadores de lesão.

The aim of the study was to analyze and compare the acute responses of clinical and functional variables after a maximum force exercise of eccentric versus concentric contraction. We evaluated 46 male subjects were randomly divided into two groups according to the type of exercise. Comparing the groups no significant differences, but the analysis of each group, there was an increased sensation of pain (VAS), perceived exertion (Borg scale) and increases in measures of thigh circumference (eccentric group: 10% (p<0.001) 20% (p<0.001) 30% (p<0.05) and concentric to the group: measured with 40% p<0.01) for the algometer, only concentric group showed lower threshold (p<0.01). It can be inferred that stimuli controlled up to 100% are not aggressive and limiting, and future studies may include analysis of injury markers.

El objetivo del estudio fue analizar y comparar las respuestas agudas de las variables clínica y funcional después de un ejercicio de fuerza máxima de contracción excéntrica frente concéntrica. Se evaluaron 46 sujetos masculinos, divididos aleatoriamente en dos grupos, de acuerdo con el tipo de ejercicio. La comparación de los grupos no hubo diferencias significativas, pero el análisis de cada grupo, se produjo un aumento de la sensación de dolor (VAS), el esfuerzo percibido (escala de Borg) y el aumento de las medidas de la circunferencia del muslo (grupo excéntrico: 10% (p<0,001) 20% (p<0,001) 30% (p<0,05) y concéntrico con el grupo: medido con 40% p<0,01) para algómetro, sólo el grupo concéntrico tuvo umbral inferior (p<0,01). Se puede inferir que los estímulos controlados hasta el 100% no son agresivos y limitante, y los estudios futuros pueden incluir análisis de marcadores de lesión.