Auditory-verbal memory function of women during the menstruation and ovulation periods

Background and Aim: Auditory-verbal mem­ory (AVM) is the ability to learn, retain, and recall syllables and words. Memory has a strong relationship with the nervous and endocrine systems in humans. Changes in estrogen levels occur naturally at short (menstrual period) and long (pregnancy, menopause, and maturity) peri­ods. Changes in estrogen levels are likely to affect memory function. This study aimed to evaluate the effects of hormone fluctuations on the AVM of women. Methods: This cross-sectional study with a pretest/posttest design was conducted on 25 women aged 40−49 years with normal hearing and normal menstrual cycles of 28 ± 4 days, who were selected using a convenience sampling method. They were evaluated using two Persian versions of Rey Auditory-Verbal Learning Test (RAVLT). This test was performed twice and at two different menstrual periods (2-5 and 14−16 days). Results: A significant correlation was observed between the mean of total recall score, recall score after interference, and delayed recall score at two different periods (p < 0.01). The scores of women in three areas on days 14−16 of the menstrual cycle were higher than on days 2−5. Conclusion: Women’s RAVLT scores on days 14−16 of the menstrual cycle are higher than on days 2−5, indicating the effect of hormonal fluc­tuations on their AVM function. Therefore, it is necessary to consider the changes in women’s AVM in different days of the menstrual cycle. Keywords: Auditory-verbal working memory; Rey learning test; menstrual cycle

Factors influencing client recall of contraceptive counseling at community-based distribution events in Kinshasa, Democratic Republic of the Congo

Background Clients must recall information from contraceptive counseling sessions to properly use their chosen method. Client recall in community-based settings is challenging given the public nature of these events and the presence of many potential distractions. Understanding the factors that influence client recall during community-based distribution events can guide future training of providers to improve proper use of contraceptive methods and client satisfaction. Methods This cross-sectional study employed a convenience sample of 957 women ages 15–49 old who sought contraceptive services from community-based contraceptive distribution events in Kinshasa, Democratic Republic of the Congo, known as Lelo PF. Recall scores were developed by matching direct observations with client exit interviews. The association between recall and client characteristics, provider characteristics and an index for the quality of the provider-client interaction were tested using multivariate linear regression. Results The average recall score was 67.6%. Recall scores were higher among clients who accepted methods with simpler administration procedures, such as CycleBeads (81.3%), compared to methods requiring more medically advanced administration procedures, such as DMPA-SC (56.6%) and Implanon-NXT (62.1%). This relationship held even after controlling for amount of information each client received. Status as a first-time user was associated with a 5.8 percentage point decrease in recall score (p = 0.002). Time since the provider’s initial family planning training and clients’ perception of the provider-client interaction were associated with higher client recall scores. Conclusion Results of this study suggest that to improve client recall at Lelo PF events, future provider training should focus on how to deliver clear, specific information to clients, making sure clients feel at ease during the counseling session, and treating clients with respect. First-time family planning users and clients who select methods with more medically advanced administration procedures may require extra attention during the consultation to ensure they are able understand and remember the information. Results suggest that providers who have been offering services longer may be more effective in conveying information in a way that clients can remember. Program managers should consider requesting input from experienced providers to improve training sessions.

Lowered cognitive function and the risk of the first events of cardiovascular diseases: findings from a cohort study in Lithuania

Background The purpose of this prospective cohort study was to examine whether the level of cognitive function at the baseline expressed as a cognitive function composite score and score of specific domains predict the risk of first cardiovascular disease (CVD) events in middle-aged and older populations. Methods Seven thousand eighty-seven participants, men and women aged 45–72 years, were assessed in the baseline survey of the Health Alcohol Psychosocial Factors in Eastern Europe (HAPIEE) study in 2006–2008 in the city of Kaunas, Lithuania. During 10 years of follow-up, the risk of first non-fatal events of CVD and death from CVD (excluding those participants with a documented history of CVD and/or ischemic heart disease (IHD) diagnosed at the baseline survey) was evaluated. Cox proportional hazards regression models were applied to examine how cognitive function predicts the first events of CVD. Results During the follow-up, there were 156 deaths from CVD (49 women and 107 men) and 464 first non-fatal CVD events (195 women and 269 men) registered. The total number of first CVD events was 620 (11.5%). After adjustment for sociodemographic factors, biological and lifestyle risk factors and illnesses, a decrease per 1 standard deviation in different cognitive function scores significantly increased the risk of a first event of CVD (immediate verbal recall score - by 17% in men and 32% in women; delayed verbal recall score – by 17% in men and 24% in women; and a composite score of cognitive function – by 15% in men and 29% in women). Kaplan-Meier survival curves for the probability of a first cardiovascular event according to the categories of a composite score of cognitive function, revealed that a lowered cognitive function predicts a higher probability of the events compared to normal cognitive function (p < 0.05). Conclusions The findings of this follow-up study suggest that men and women with lower cognitive functions have an increased risk for a first event of CVD compared to participants with a higher level of cognitive functions.

A reconstruction error-based framework for label noise detection

Label noise is an important data quality issue that negatively impacts machine learning algorithms. For example, label noise has been shown to increase the number of instances required to train effective predictive models. It has also been shown to increase model complexity and decrease model interpretability. In addition, label noise can cause the classification results of a learner to be poor. In this paper, we detect label noise with three unsupervised learners, namely $$\textit{principal component analysis} \hbox { (PCA)}$$ principal component analysis (PCA) , $$\textit{independent component analysis} \hbox { (ICA)}$$ independent component analysis (ICA) , and autoencoders. We evaluate these three learners on a credit card fraud dataset using multiple noise levels, and then compare results to the traditional Tomek links noise filter. Our binary classification approach, which considers label noise instances as anomalies, uniquely uses reconstruction errors for noisy data in order to identify and filter label noise. For detecting noisy instances, we discovered that the autoencoder algorithm was the top performer (highest recall score of 0.90), while Tomek links performed the worst (highest recall score of 0.62).

Association Between Dietary Theobromine and Cognitive Function in a Representative Elderly American Population: A Cross-Sectional Study

Background: Despite reports on neuroprotective effects of dietary theobromine intake, whether dietary theobromine can exert beneficial effects on cognitive function is unclear. We aimed to investigate the association between dietary theobromine and cognitive function in old American population.Methods: We collected data from the 2011-2012 and 2013-2014 cycles of the National Health and Nutrition Examination Survey, a cross-sectional survey. Daily dietary theobromine was treated as a continuous variable and a log transform. Cognitive function was measured by four tests: Consortium to Establish a Registry for Alzheimer's Disease (CERAD) Word Learning tests, CERAD delayed recall test, animal fluency test, and digit symbol substitution test (DSST). We conducted linear regression analyses and subgroup analyses to study the association between theobromine intake and cognitive performance. Basic characteristics, lifestyle factors, disease history, and nutritional intake were adjusted in these models.Results: A total of 2,845 participants were included in this study. Daily theobromine intake was not significantly different between the 2011-2012 and 2013-2014 cycles. The CERAD-immediate and delayed recall scores were significantly different between these two cycles, but not the animal fluency score or digital symbol score. The daily dietary theobromine intake in log form was positively associated with immediate recall score (β, 95% CI, P: 0.661, 0.222-1.101, <0.01), delayed recall score (β, 95% CI, P: 0.232, 0.016-0.449, 0.04), and DSST score (β, 95% CI, P: 1.395, 0.140-2.649, 0.03) in the fully adjusted model, but not with the animal fluency score (β, 95% CI: 0.001, -0.122-0.907, 0.13). Sensitive analyses showed that L-theobromine intake was linearly associated with cognitive performance.Conclusions: Daily theobromine intake was associated with cognitive performance in a large national representative population. However, further research is needed in order to corroborate our findings.

A-03 SCAT5 Cognitive Screening Normative Data and Reliable Change Indices

Objective This study provides normative data on the SCAT5 Cognitive Screening, establishes test-retest reliability, and creates clinically relevant cut points for low performance. Method The multisport baseline sample was composed of 727 uninjured college athletes (52% female) at a Division I university who were administered the SCAT5 before the 2017–2018 season. Descriptive statistics, including base rates of low performance, were calculated for SCAT5 indices. Repeat baseline testing was completed by 325 athletes (48% female) at 1 year (days M = 352.56;SD = 56.03) who were included in the test-retest reliability and practice effect analyses. Reliable change indices were calculated. Results Descriptive statistics for SCAT5 were computed for both baselines (Baseline 1: SAC total M = 35.15,SD = 4.93; immediate recall total M = 20.01,SD = 3.46; delayed recall total M = 6.43,SD = 1.75). A difference in descriptive statistics and practice effects by sex on the SCAT5 Cognitive Screening has been demonstrated (Bailey, Meyer, Tangen et al., under review). For female athletes, the 1st administration cutoff scores for abnormal performance (&lt;10th%ile) included SAC total score = 33, immediate recall score = 18, and delayed recall score = 6. For male athletes, the 1st administration cutoff scores for abnormal performance (&lt;10th%ile) included SAC total score = 30, immediate recall score = 17, and delayed recall score = 5. Test-retest reliability of the SAC was similar to previous versions but varied by sex. Reliable change indices (RCI) were created with cut points for significant change. Conclusions The present study provides clinically relevant normative data for the SCAT5 Cognitive Screening. Cut points for low performance on both reliable chance indices (RCIs) and normative performance reflected meaningful sex differences that could influence clinical interpretation.

A Machine Learning–Based Model to Predict Acute Traumatic Coagulopathy in Trauma Patients Upon Emergency Hospitalization

Acute traumatic coagulopathy (ATC) is an extremely common but silent murderer; this condition presents early after trauma and impacts approximately 30% of severely injured patients who are admitted to emergency departments (EDs). Given that conventional coagulation indicators usually require more than 1 hour after admission to yield results—a limitation that frequently prevents the ability for clinicians to make appropriate interventions during the optimal therapeutic window—it is clearly of vital importance to develop prediction models that can rapidly identify ATC; such models would also facilitate ancillary resource management and clinical decision support. Using the critical care Emergency Rescue Database and further collected data in ED, a total of 1385 patients were analyzed and cases with initial international normalized ratio (INR) values >1.5 upon admission to the ED met the defined diagnostic criteria for ATC; nontraumatic conditions with potentially disordered coagulation systems were excluded. A total of 818 individuals were collected from Emergency Rescue Database as derivation cohorts, then were split 7:3 into training and test data sets. A Pearson correlation matrix was used to initially identify likely key clinical features associated with ATC, and analysis of data distributions was undertaken prior to the selection of suitable modeling tools. Both machine learning (random forest) and traditional logistic regression were deployed for prediction modeling of ATC. After the model was built, another 587 patients were further collected in ED as validation cohorts. The ATC prediction models incorporated red blood cell count, Shock Index, base excess, lactate, diastolic blood pressure, and potential of hydrogen. Of 818 trauma patients filtered from the database, 747 (91.3%) patients did not present ATC (INR ≤ 1.5) and 71 (8.7%) patients had ATC (INR > 1.5) upon admission to the ED. Compared to the logistic regression model, the model based on the random forest algorithm showed better accuracy (94.0%, 95% confidence interval [CI]: 0.922-0.954 to 93.5%, 95% CI: 0.916-0.95), precision (93.3%, 95% CI: 0.914-0.948 to 93.1%, 95% CI: 0.912-0.946), F1 score (93.4%, 95% CI: 0.915-0.949 to 92%, 95% CI: 0.9-0.937), and recall score (94.0%, 95% CI: 0.922-0.954 to 93.5%, 95% CI: 0.916-0.95) but yielded lower area under the receiver operating characteristic curve (AU-ROC) (0.810, 95% CI: 0.673-0.918 to 0.849, 95% CI: 0.732-0.944) for predicting ATC in the trauma patients. The result is similar in the validation cohort. The values for classification accuracy, precision, F1 score, and recall score of random forest model were 0.916, 0.907, 0.901, and 0.917, while the AU-ROC was 0.830. The values for classification accuracy, precision, F1 score, and recall score of logistic regression model were 0.905, 0.887, 0.883, and 0.905, while the AU-ROC was 0.858. We developed and validated a prediction model based on objective and rapidly accessible clinical data that very confidently identify trauma patients at risk for ATC upon their arrival to the ED. Beyond highlighting the value of ED initial laboratory tests and vital signs when used in combination with data analysis and modeling, our study illustrates a practical method that should greatly facilitates both warning and guided target intervention for ATC.

SUMMARIZING INDONESIAN NEWS ARTICLES USING GRAPH CONVOLUTIONAL NETWORK

Multi-document summarization transforms a set of related documents into one concise summary. Existing Indonesian news articles summarizations do not take relationships between sentences into account and heavily depends on Indonesian language tools and resources. In this paper, we employ Graph Convolutional Network (GCN) which accepts word embedding sequence and sentence relationship graph as input for Indonesian news articles summarization. Our system is comprised of four main components, which are preprocess, graph construction, sentence scoring, and sentence selection components. Sentence scoring component is a neural network that uses Recurrent Neural Network (RNN) and GCN to produce the scores of all sentences. We use three different representation types for the sentence relationship graph. Sentence selection component then generates summary with two different techniques, which are by greedily choosing sentences with the highest scores and by using Maximum Marginal Relevance (MMR) technique. The evaluation shows that GCN summarizer with Personalized Discourse Graph (PDG) graph representation system achieves the best results with average ROUGE-2 recall score of 0.370 for 100-word summary and 0.378 for 200-word summary. Sentence selection using greedy technique gives better results for generating 100-word summary, while MMR performs better for generating 200-word summary.

Thermal Comfort-Based Personalized Models with Non-Intrusive Sensing Technique in Office Buildings

Heating, ventilation and air-conditioning (HVAC) systems play a key role in shaping the built environment. However, centralized HVAC systems cannot guarantee the provision of a comfortable thermal environment for everyone. Therefore, a personalized HVAC system that aims to adapt thermal preferences has drawn much more attention. Meanwhile, occupant-related factors like skin temperature have not had standardized measurement methods. Therefore, this paper proposes to use infrared thermography to develop individual thermal models to predict thermal sensations using three different feature sets with the random forest (RF) and support vector machine (SVM). The results have shown the correlation coefficients between clothing surface temperature and thermal sensation are 11% and 3% higher than those between skin temperature and thermal sensation of two subjects, respectively. With cross-validation, SVM with a linear kernel and penalty number of 1, as well as RF with 50 trees and the maximum tree depth of 3 were selected as the model configurations. As a result, the model trained with the feature set, consisting of indoor air temperature, relative humidity, skin temperature and clothing surface temperature, and with linear kernel SVM has achieved 100% recall score on test data of female subjects and 95% recall score on that of male subjects.