Application of C5.0 Algorithm for the Assessment of Perceived Stress in Healthcare Professionals Attending COVID-19.

Coronavirus disease (COVID-19) represents one of the greatest challenges to public health in modern history. As the disease continues to spread globally, medical and allied healthcare professionals have become one of the most affected sectors. Stress and anxiety are indirect effects of the COVID-19 pandemic. Therefore, it is paramount to understand and categorize their perceived levels of stress, as it can be a detonating factor leading to mental illness. Here, we propose a computer-based method to better understand stress in healthcare workers facing COVID-19 at the beginning of the pandemic. We based our study on a representative sample of healthcare professionals attending to COVID-19 patients in the northeast region of Mexico, at the beginning of the pandemic. We used a machine learning classification algorithm to obtain a visualization model to analyze perceived stress. The C5.0 decision tree algorithm was used to study datasets. We carried out an initial preprocessing statistical analysis for a group of 101 participants. We performed chi-square tests for all questions, individually, in order to validate stress level calculation (p < 0.05) and a calculated Cronbach's alpha of 0.94 and McDonald's omega of 0.95, demonstrating good internal consistency in the dataset. The obtained model failed to classify only 6 out of the 101, missing two cases for mild, three for moderate and one for severe (accuracy of 94.1%). We performed statistical correlation analysis to ensure integrity of the method. In addition, based on the decision tree model, we concluded that severe stress cases can be related mostly to high levels of xenophobia and compulsive stress. Thus, showing that applied machine learning algorithms represent valuable tools in the assessment of perceived stress, which can potentially be adapted to other areas of the medical field.

Determinants of COVID-19 Vaccine Hesitancy: A Cross-Sectional Study on a Mexican Population Using an Online Questionnaire (COV-AHQ).

Mexico has become one of the most highly affected countries by coronavirus disease 2019 (COVID-19) pandemic in Latin America. Therefore, efficient vaccination programs are needed to address COVID-19 pandemic. Although recent advances around the world have made it possible to develop vaccines in record time, there has been increasing fear and misinformation around the vaccines. Hence, understanding vaccine hesitancy is imperative for modeling successful vaccination strategies. In this study, we analyzed the attitude and perceptions toward COVID-19 vaccination, in a Mexican population (n = 1,512), using the proposed COVID-19 Vaccine Acceptance and Hesitancy Questionnaire (COV-AHQ) (Cronbach's alpha > 0.8), which evaluates a mild perception of danger and contamination with respect to COVID-19, a moderate perception of xenophobia generated throughout COVID-19 quarantine, fear of adverse effects of COVID-19 vaccination, and hesitancy of parent toward vaccination of children; furthermore, a section including sociodemographic variables was included. According to the results of this study, the statistical correlation analysis of the general vaccination posture seems to correlate significantly (p < 0.05) with a mild perception of danger and contamination with respect to COVID-19, a moderate perception of xenophobia generated throughout COVID-19 quarantine, hesitancy of parent toward vaccination of children, willingness to get COVID-19 vaccine, previous influenza vaccination, perception of the vaccine that could help the economy of country, occupation, gender, age, and participants actively researching COVID-19 vaccine information. An in-depth analysis assisted by binary logistic regression concluded that the young adult population around ages 18-34 years are the most likely to get vaccinated. This posture seems to be highly influenced by a mild perception of danger and contamination with respect to COVID-19, a moderate perception of xenophobia generated throughout COVID-19 quarantine, fear of adverse effects of COVID-19 vaccination, and hesitancy of parents toward vaccination of children. While their own personal religious beliefs and economic status, the level of education does not seem to have an effect on the willingness to get vaccinated neither did having a previous COVID-19 diagnosis or even knowing someone with a positive COVID-19 diagnosis. Health authorities and policymakers could use the results of this study to aid in modeling vaccination programs and strategies and identify population groups with high vaccine hesitancy prevalence and assess significant public health issues.

Topological Data Analysis for Eye Fundus Image Quality Assessment.

The objective of this work is to perform image quality assessment (IQA) of eye fundus images in the context of digital fundoscopy with topological data analysis (TDA) and machine learning methods. Eye health remains inaccessible for a large amount of the global population. Digital tools that automize the eye exam could be used to address this issue. IQA is a fundamental step in digital fundoscopy for clinical applications; it is one of the first steps in the preprocessing stages of computer-aided diagnosis (CAD) systems using eye fundus images. Images from the EyePACS dataset were used, and quality labels from previous works in the literature were selected. Cubical complexes were used to represent the images; the grayscale version was, then, used to calculate a persistent homology on the simplex and represented with persistence diagrams. Then, 30 vectorized topological descriptors were calculated from each image and used as input to a classification algorithm. Six different algorithms were tested for this study (SVM, decision tree, k-NN, random forest, logistic regression (LoGit), MLP). LoGit was selected and used for the classification of all images, given the low computational cost it carries. Performance results on the validation subset showed a global accuracy of 0.932, precision of 0.912 for label "quality" and 0.952 for label "no quality", recall of 0.932 for label "quality" and 0.912 for label "no quality", AUC of 0.980, F1 score of 0.932, and a Matthews correlation coefficient of 0.864. This work offers evidence for the use of topological methods for the process of quality assessment of eye fundus images, where a relatively small vector of characteristics (30 in this case) can enclose enough information for an algorithm to yield classification results useful in the clinical settings of a digital fundoscopy pipeline for CAD.

Teaching Anxiety, Stress and Resilience During the COVID-19 Pandemic: Evaluating the Vulnerability of Academic Professionals in Mexico Through the Adapted COVID-19 Stress Scales.

To mitigate the COVID-19 infection, many world governments endorsed the cessation of non-essential activities, such as the school attendance, forcing a shift of the teaching model to the virtual classroom. From this shift, several changes in the teaching paradigm derived, in addition to the COVID-19 pandemic, which could have an impact in academic professional's mental health. In the present work we show the application of a modified version of the adapted COVID-19 stress scales (ACSS) which also included teaching anxiety and preparedness, and resilience for academic professionals in Mexico. These scales were applied during the unprecedented transformation of the education system undergone in the COVID-19 quarantine. Most of the studied variables: gender, age, academic degree, household occupants, having a disease, teaching level, teaching mode, work hours, resilience, teaching anxiety and preparedness, and fear of being an asymptomatic patient (FOBAP), showed significant statistical correlation between each other (p < 0.050) and to the 6 areas of the ACSS (danger, contamination, social economical, xenophobia, traumatic stress, and compulsive checking). Our results further showed that the perceived stress and anxiety fell into the category of Absent to Mild, with only the danger section of the ACSS falling into the Moderate category. Finally, the resilience generated throughout the quarantine was very high, which seems to be a predictor of adaptation the academic professional has undergone to cope with stress.

Dataset of the adapted COVID stress scales for healthcare professionals of the northeast region of Mexico.

The dataset presented examines the levels of stress persisting in healthcare professionals of the Northeast region of Mexico. Using an online platform to obtain data, a survey was developed and distributed through electronic means during a 6-week period covering July and August 2020, considered one of the periods with the highest reported COVID cases in Mexico. Our survey looked at six major stress developing areas: danger, fear of contamination, social economic consequences, xenophobia, compulsive checking and reassurance seeking, and traumatic stress; we added an extra question to assess fear of being an asymptomatic patient. The data was statistically analyzed looking for correlations and dependencies. Thus, helping in policy and decision-making processes to assist and manage stress in healthcare professionals.

Parent's Perspective towards Child COVID-19 Vaccination: An Online Cross-Sectional Study in Mexico.

COVID-19 vaccination programs continue in child populations. Thus, parents' attitude towards COVID-19 vaccination of their children is crucial for these strategies to succeed. The present study derives from the application of an online COVID-19 Vaccine Acceptance & Hesitancy Questionnaire (COV-AHQ) in which we measure parent's hesitancy towards children's vaccination (section 4 of the COV-AHQ) and other significant factors. A logistic regression analysis with backward stepwise method was used to quantify the associations between factors and parent's hesitancy. According to the correlation analysis, the most representative factors predicting vaccine hesitancy/acceptance were positive attitude towards vaccination, parents believing that the COVID-19 vaccine will enhance the economic situation of the country, parents actively researching information, having the willingness to obtain the COVID-19 vaccine themselves, and the possibility of their children developing adverse effects. Our findings also showed that parents are highly interested in having their children vaccinated. Nonetheless, parents expressed high levels of concern involving their children in developing adverse effects from the vaccine. In addition, obtaining influenza immunization prompted interest in obtaining the COVID-19 vaccine, and younger-aged parents are much more concerned with having their children vaccinated. Therefore, in order to ensure successful vaccination programs, policymakers and health authorities should design strategies to gain confidence and provide security amongst the population, including giving continuous information about the benefits of vaccination and presenting the frequency of side effects to bring parents on board with vaccinating their children.