Prevalence and Potential Determinants of COVID-19 Vaccine Hesitancy and Resistance in Qatar: Results from a Nationally Representative Survey of Qatari Nationals and Migrants between December 2020 and January 2021.

Global COVID-19 pandemic containment necessitates understanding the risk of hesitance or resistance to vaccine uptake in different populations. The Middle East and North Africa currently lack vital representative vaccine hesitancy data. We conducted the first representative national phone survey among the adult population of Qatar, between December 2020 and January 2021, to estimate the prevalence and identify potential determinants of vaccine willingness: acceptance (strongly agree), resistance (strongly disagree), and hesitance (somewhat agree, neutral, somewhat disagree). Bivariate and multinomial logistic regression models estimated associations between willingness groups and fifteen variables. In the total sample, 42.7% (95% CI: 39.5-46.1) were accepting, 45.2% (95% CI: 41.9-48.4) hesitant, and 12.1% (95% CI: 10.1-14.4) resistant. Vaccine resistant compared with hesistant and accepting groups reported no endorsement source will increase vaccine confidence (58.9% vs. 5.6% vs. 0.2%, respectively). Female gender, Arab ethnicity, migrant status/type, and vaccine side-effects concerns were associated with hesitancy and resistance. COVID-19 related bereavement, infection, and quarantine status were not significantly associated with any willingness group. Absence of or lack of concern about contracting the virus was solely associated with resistance. COVID-19 vaccine resistance, hesitance, and side-effects concerns are high in Qatar's population compared with those globally. Urgent public health engagement should focus on women, Qataris (non-migrants), and those of Arab ethnicity.

Machine Learning Models Reveal the Importance of Clinical Biomarkers for the Diagnosis of Alzheimer's Disease.

Alzheimer's Disease (AD) is a neurodegenerative disease that causes complications with thinking capability, memory and behavior. AD is a major public health problem among the elderly in developed and developing countries. With the growth of AD around the world, there is a need to further expand our understanding of the roles different clinical measurements can have in the diagnosis of AD. In this work, we propose a machine learning-based technique to distinguish control subjects with no cognitive impairments, AD subjects, and subjects with mild cognitive impairment (MCI), often seen as precursors of AD. We utilized several machine learning (ML) techniques and found that Gradient Boosting Decision Trees achieved the highest performance above 84% classification accuracy. Also, we determined the importance of the features (clinical biomarkers) contributing to the proposed multi-class classification system. Further investigation on the biomarkers will pave the way to introduce better treatment plan for AD patients.