Classification of Parkinson's disease severity using gait stance signals in a spatiotemporal deep learning classifier.

Parkinson's disease (PD) is a degenerative nervous system disorder involving motor disturbances. Motor alterations affect the gait according to the progression of PD and can be used by experts in movement disorders to rate the severity of the disease. However, this rating depends on the expertise of the clinical specialist. Therefore, the diagnosis may be inaccurate, particularly in the early stages of PD where abnormal gait patterns can result from normal aging or other medical conditions. Consequently, several classification systems have been developed to enhance PD diagnosis. In this paper, a PD gait severity classification algorithm was developed using vertical ground reaction force (VGRF) signals. The VGRF records used are from a public database that includes 93 PD patients and 72 healthy controls adults. The work presented here focuses on modeling each foot's gait stance phase signals using a modified convolutional long deep neural network (CLDNN) architecture. Subsequently, the results of each model are combined to predict PD severity. The classifier performance was evaluated using ten-fold cross-validation. The best-weighted accuracies obtained were 99.296(0.128)% and 99.343(0.182)%, with the Hoehn-Yahr and UPDRS scales, respectively, outperforming previous results presented in the literature. The classifier proposed here can effectively differentiate gait patterns of different PD severity levels based on gait signals of the stance phase.

AI-Enhanced Analysis Reveals Impact of Maternal Diabetes on Subcutaneous Fat Mass in Fetuses without Growth Alterations.

Pregnant women with diabetes often present impaired fetal growth, which is less common if maternal diabetes is well-controlled. However, developing strategies to estimate fetal body composition beyond fetal growth that could better predict metabolic complications later in life is essential. This study aimed to evaluate subcutaneous fat tissue (femur and humerus) in fetuses with normal growth among pregnant women with well-controlled diabetes using a reproducible 3D-ultrasound tool and offline TUI (Tomographic Ultrasound Imaging) analysis. Additionally, three artificial intelligence classifier models were trained and validated to assess the clinical utility of the fetal subcutaneous fat measurement. A significantly larger subcutaneous fat area was found in three-femur and two-humerus selected segments of fetuses from women with diabetes compared to the healthy pregnant control group. The full classifier model that includes subcutaneous fat measure, gestational age, fetal weight, fetal abdominal circumference, maternal body mass index, and fetal weight percentile as variables, showed the best performance, with a detection rate of 70%, considering a false positive rate of 10%, and a positive predictive value of 82%. These findings provide valuable insights into the impact of maternal diabetes on fetal subcutaneous fat tissue as a variable independent of fetal growth.

Recurrence quantification analysis during a mental calculation task.

The identification of brain dynamical changes under different cognitive conditions with noninvasive techniques such as electroencephalography (EEG) is relevant for the understanding of their underlying neural mechanisms. The comprehension of these mechanisms has applications in the early diagnosis of neurological disorders and asynchronous brain computer interfaces. In both cases, there are no reported features that could describe intersubject and intra subject dynamics behavior accurately enough to be applied on a daily basis. The present work proposes the use of three nonlinear features (recurrence rate, determinism, and recurrence times) extracted from recurrence quantification analysis (RQA) to describe central and parietal EEG power series complexity in continuous alternating episodes of mental calculation and rest state. Our results demonstrate a consistent mean directional change of determinism, recurrence rate, and recurrence times between conditions. Increasing values of determinism and recurrence rate were present from the rest state to mental calculation, whereas recurrence times showed the opposite pattern. The analyzed features in the present study showed statistically significant changes between rest and mental calculation states in both individual and population analysis. In general, our study described mental calculation EEG power series as less complex systems in comparison to the rest state. Moreover, ANOVA showed stability of RQA features along time.

Development and validation of anthropometric-based fat-mass prediction equations using air displacement plethysmography in Mexican infants.

BACKGROUND/OBJECTIVES: Fat-mass (FM) assessment since birth using valid methodologies is crucial since excessive adiposity represents a risk factor for adverse metabolic outcomes. AIM: To develop infant FM prediction equations using anthropometry and validate them against air-displacement plethysmography (ADP). SUBJECTS/METHODS: Clinical, anthropometric (weight, length, body-mass index -BMI-, circumferences, and skinfolds), and FM (ADP) data were collected from healthy-term infants at 1 (n = 133), 3 (n = 105), and 6 (n = 101) months enrolled in the OBESO perinatal cohort (Mexico City). FM prediction models were developed in 3 steps: 1) Variable Selection (LASSO regression), 2) Model behavior evaluation (12-fold cross-validation, using Theil-Sen regressions), and 3) Final model evaluation (Bland-Altman plots, Deming regression). RESULTS: Relevant variables in the FM prediction models included BMI, circumferences (waist, thigh, and calf), and skinfolds (waist, triceps, subscapular, thigh, and calf). The R2 of each model was 1 M: 0.54, 3 M: 0.69, 6 M: 0.63. Predicted FM showed high correlation values (r ≥ 0.73, p < 0.001) with FM measured with ADP. There were no significant differences between predicted vs measured FM (1 M: 0.62 vs 0.6; 3 M: 1.2 vs 1.35; 6 M: 1.65 vs 1.76 kg; p > 0.05). Bias were: 1 M -0.021 (95%CI: -0.050 to 0.008), 3 M: 0.014 (95%CI: 0.090-0.195), 6 M: 0.108 (95%CI: 0.046-0.169). CONCLUSION: Anthropometry-based prediction equations are inexpensive and represent a more accessible method to estimate body composition. The proposed equations are useful for evaluating FM in Mexican infants.

Multimodal Early Birth Weight Prediction Using Multiple Kernel Learning.

In this work, a novel multimodal learning approach for early prediction of birth weight is presented. Fetal weight is one of the most relevant indicators in the assessment of fetal health status. The aim is to predict early birth weight using multimodal maternal-fetal variables from the first trimester of gestation (Anthropometric data, as well as metrics obtained from Fetal Biometry, Doppler and Maternal Ultrasound). The proposed methodology starts with the optimal selection of a subset of multimodal features using an ensemble-based approach of feature selectors. Subsequently, the selected variables feed the nonparametric Multiple Kernel Learning regression algorithm. At this stage, a set of kernels is selected and weighted to maximize performance in birth weight prediction. The proposed methodology is validated and compared with other computational learning algorithms reported in the state of the art. The obtained results (absolute error of 234 g) suggest that the proposed methodology can be useful as a tool for the early evaluation and monitoring of fetal health status through indicators such as birth weight.

Ultra-Processed Food Consumption during Pregnancy and Its Association with Maternal Oxidative Stress Markers.

Ultra-processed food (UPF) consumption during gestation may lead to increased oxidative stress (OS) and could affect pregnancy outcomes. This study aims to evaluate the association of UPF consumption during pregnancy with circulating levels of OS markers. Diet was assessed (average of three assessments) in 119 pregnant women enrolled in the OBESO perinatal cohort (Mexico), obtaining quantitative data and the percentage of energy that UPFs (NOVA) contributed to the total diet. Sociodemographic, clinical (pregestational body-mass index and gestational weight gain) and lifestyle data were collected. Maternal circulating levels of OS markers (malondialdehyde (MDA), protein carbonylation (PC), and total antioxidant capacity (TAC)) were determined at the third trimester of pregnancy. Adjusted linear regression models were performed to analyze the association between UPFs and OS markers. UPFs represented 27.99% of the total energy intake. Women with a lower UPF consumption (<75 percentile°) presented a higher intake of fiber, ω-3, ω-6, and a lower ω-6/3 ratio. Linear regression models showed that UPFs were inversely associated with TAC and MDA. Fiber intake was associated with PC. UPF intake during pregnancy may result in an increase in oxidative stress. When providing nutrition care, limiting or avoiding UPFs may be an intervention strategy that could promote a better antioxidant capacity in the body.

Scenario Screen: A Dynamic and Context Dependent P300 Stimulator Screen Aimed at Wheelchair Navigation Control.

P300 spellers have been widely modified to implement nonspelling tasks. In this work, we propose a "scenario" stimulation screen that is a P300 speller variation to command a wheelchair. Our approach utilized a stimulation screen with an image background (scenario snapshot for a wheelchair) and stimulation markers arranged asymmetrically over relevant landmarks, such as suitable paths, doors, windows, and wall signs. Other scenario stimulation screen features were green/blue stimulation marker color scheme, variable Interstimulus Interval, single marker stimulus mode, and optimized stimulus sequence generator. Eighteen able-bodied subjects participated in the experiment; 78% had no experience in BCI usage. A waveform feature analysis and a Mann-Whitney U test performed over the pairs of target and nontarget coherent averages confirmed that 94% of the subjects elicit P300 (p < .005) on this modified stimulator. Least Absolute Shrinkage and Selection Operator optimization and Linear Discriminant Analysis were utilized for the automatic detection of P300. For evaluation with unseen data, target detection was computed (median sensitivity = 1.00 (0.78-1.00)), together with nontarget discrimination (median specificity = 1.00 (0.98-1.00)). The scenario screen adequately elicits P300 and seems suitable for commanding a wheelchair even when users have no previous experience on the BCI spelling task.