Foundations for fairness in digital health apps.

Digital mental health applications promise scalable and cost-effective solutions to mitigate the gap between the demand and supply of mental healthcare services. However, very little attention is paid on differential impact and potential discrimination in digital mental health services with respect to different sensitive user groups (e.g., race, age, gender, ethnicity, socio-economic status) as the extant literature as well as the market lack the corresponding evidence. In this paper, we outline a 7-step model to assess algorithmic discrimination in digital mental health services, focusing on algorithmic bias assessment and differential impact. We conduct a pilot analysis with 610 users of the model applied on a digital wellbeing service called Foundations that incorporates a rich set of 150 proposed activities designed to increase wellbeing and reduce stress. We further apply the 7-step model on the evaluation of two algorithms that could extend the current service: monitoring step-up model, and a popularity-based activities recommender system. This study applies an algorithmic fairness analysis framework for digital mental health and explores differences in the outcome metrics for the interventions, monitoring model, and recommender engine for the users of different age, gender, type of work, country of residence, employment status and monthly income. Systematic Review Registration: The study with main hypotheses is registered at: https://osf.io/hvtf8.

Techniques for Oxygenation and Ventilation in Coronavirus Disease 2019.

This paper discusses mechanisms of hypoxemia and interventions to oxygenate critically ill patients with COVID-19 which range from nasal cannula to noninvasive and mechanical ventilation. Noninvasive ventilation includes continuous positive airway pressure ventilation (CPAP) and high-flow nasal cannula (HFNC) with or without proning. The evidence for each of these modalities is discussed and thereafter, when to transition to mechanical ventilation (MV). Various techniques of MV, again with and without proning, and rescue strategies which would include extra corporeal membrane oxygenation (ECMO) when it is available and permissive hypoxemia where it is not, are discussed.

Improved COVID-19 outcomes in a large non-invasive respiratory support cohort despite emergence of the alpha variant.

INTRODUCTION: Respiratory high-dependency units (rHDUs) are used to manage respiratory failure in COVID-19 outside of the intensive care unit (ICU). The alpha variant of COVID-19 has been linked to increased rates of mortality and admission to ICU; however, its impact on a rHDU population is not known. We aimed to compare rHDU outcomes between the two main UK waves of COVID-19 infection and evaluate the impact of the alpha variant on second wave outcomes. METHODS: We conducted a single-centre, retrospective analysis of all patients with a diagnosis of COVID-19 admitted to the rHDU of our teaching hospital for respiratory support during the first and second main UK waves. RESULTS: In total, 348 patients were admitted to rHDU. In the second wave, mortality (26.7% s vs 50.7% first wave, χ2=14.7, df=1, p=0.0001) and intubation rates in those eligible (24.3% s vs 58.8% first wave, χ2=17.3, df=2, p=0.0002) were improved compared with the first wave. In the second wave, the alpha variant had no effect on mortality (OR 1.18, 95% CI 0.60 to 2.32, p=0.64). Continuous positive airway pressure (CPAP) (89.5%) and awake proning (85.6%) were used in most patients in the second wave. DISCUSSION: Our single-centre experience shows that rHDU mortality and intubation rates have improved over time in spite of the emergence of the alpha variant. Our data support the use of CPAP and awake proning, although improvements in outcome are likely to be multifactorial.