Machine learning-based bioimpedance assessment of knee osteoarthritis severity.

This study proposes a multiclass model to classify the severity of knee osteoarthritis (KOA) using bioimpedance measurements. The experimental setup considered three types of measurements using eight electrodes: global impedance with adjacent pattern, global impedance with opposite pattern, and direct impedance measurement, which were taken using an electronic device proposed by authors and based on the Analog Devices AD5933 impedance converter. The study comprised 37 participants, 25 with healthy knees and 13 with three different degrees of KOA. All participants performed 20 repetitions of each of the following five tasks: (i) sitting with the knee bent, (ii) sitting with the knee extended, (iii) sitting and performing successive extensions and flexions of the knee, (iv) standing, and (v) walking. Data from the 15 experimental setups (3 types of measurements×5 exercises) were used to train a multiclass random forest. The training and validation cycle was repeated 100 times using random undersampling. At each of the 100 cycles, 80% of the data were used for training and the rest for testing. The results showed that the proposed approach achieved average sensitivities and specificities of 100% for the four KOA severity grades in the extension, cyclic, and gait tasks. This suggests that the proposed method can serve as a screening tool to determine which individuals should undergo x-rays or magnetic resonance imaging for further evaluation of KOA.

ENDS consumption in students of higher education: Phenomenon on the rise during the COVID-19 pandemic.

INTRODUCTION: The COVID-19 pandemic triggered transformations in the population's lifestyles, including electronic nicotine delivery system (ENDS) consumption. The aim of the study was to determine associations between ENDS consumption habits and lifestyles among higher education students in Bogotá, Colombia. METHODS: This study employed a cross-sectional analytical design, based on a self-administered online survey, conducted in 2021, among students aged 18-59 years. The sample size was 3985 students. Statistical analysis was done through frequency studies, hypothesis testing and a multivariate-penalized logistic regression model (firthlogit), based on the Akaike information criterion (AIC). RESULTS: A total of 3573 students completed the survey, 61.5% were female, 55.3% were young (aged 18-26 years), and 44.6% were adults (aged 27-59 years). The prevalence of ENDS use during the pandemic was 7.3%. Age was negatively associated with ENDS use, as young people had a higher likelihood of using these devices. The likelihood of ENDS use was negative among females (OR=0.38; 95% CI: 0.2-0.5). In contrast, it was positive in students with a history of psychoactive substance abuse and/or dependence (OR=3.59; 95% CI: 1.0-12.0), students who had tried conventional cigarettes (OR=5.12; 95% CI: 3.0-8.5), participants who smoked tobacco during the pandemic (OR=3.15; 95% CI: 2.3-4.2), those who studied virtually (OR=1.52; 95% CI: 1.0-2.3), participants who lived with other ENDS users (OR=3.86; 95% CI: 2.8-5.2) and students with negative perception of impacts on their mental health (OR=1.48; 95% CI: 1.1-1.9). CONCLUSIONS: Being male, aged <26 years, having a history of substance use, having tried conventional cigarettes, pandemic tobacco use, and having lived with other ENDS users, were the main factors associated with pandemic ENDS use. Studying the consumption habits of students in response to lifestyle changes, is fundamental for the formulation of strategies to reduce the development of addictive behaviors, especially in young students during the pandemic.