COVID-19 and mental disorders in healthcare Personnel: A novel framework to develop Personas from an online survey

A novel data-driven approach for Personas validation in healthcare using self-supervised machine learning

OBJECTIVE

Persona validation is a challenging task, often relying on costly external validation methods. The aim of this study was the development of a novel method for Personas validation based on data already available during their creation.

METHODS

A novel approach based on self-supervised machine learning (SSML) was proposed. A training-test split was performed (80 % - 20 %), with the training set used for Personas development. The obtained labels were used as input for a 5-fold cross-validation grid search, resulting in 5 optimal different models. The "weak" ground truth for the test set was determined using the trained clustering model, and was compared with the prediction obtained by the majority voting of the optimal models. Performance evaluation was conducted by means of weighted accuracy, precision, recall and F1 score.

RESULTS

The proposed method was evaluated on two very different healthcare datasets composed by questionnaires. The former was presented 1070 subjects, resulting in three unbalanced Personas (P0 n = 100; P1 n = 292; P2 n = 464). The latter included 176 subjects with three slightly unbalanced Personas. (P0 n = 58; P1 n = 32; P2 n = 50). The SSML approach resulted capable of correctly differentiating the clusters with high values of weighted accuracy (88.27 % and 94.12 %), precision (87.11 % and 92.83 %), recall (86.92 % and 91.67 %), and F1 score (86.92 % and 91.76 %).

CONCLUSIONS

The proposed method showed high capabilities in generalization beyond the training data, validating the Personas' capability of stratifying the characteristics of target populations. Additionally, this method significantly reduced the costs to validate Personas when compared to other methods in current literature.

ReGen-DTI: A novel generative drug target interaction model for predicting potential drug candidates against SARS-COV2

Covid-19 has caused massive numbers of infections and fatalities globally. In response, there has been a large-scale experimental and computational research effort to study and develop drugs. Towards this, Deep learning techniques are used for the generation of potential novel drug candidates that are proven to be effective against exploring large molecular search spaces. Recent advances in reinforcement learning in conjunction with generative techniques has proven to be a promising field in the area of drug discovery. In this regard, we propose a generative drug discovery approach using reinforcement techniques for sampling novel molecules that bind to the main protease of SARS-COV2. The generative method reported significant validity scores for the generated novel molecules and captured the underlying features of the training molecules. Further, the model is fine-tuned on existing re-purposed molecules which are active towards specific target proteins based on similarity metrics. Upon fine tuning the model generated 92.71% valid, 93.55% unique, and 100% novel molecules. Unlike previous methods which are dependent on docking procedures, we proposed a deep learning based novel drug target interaction (DTI) model to find the binding affinity between candidate molecules and target protease sequence. Finally, the binding affinity of the generated molecules is predicted against the 3CLPro main protease by using the proposed DTI model. Most of the generated molecules have shown binding affinity scores <100 nM (lower the better), which are significantly better compared to the existing commercial drugs including Remdesevir.

Impact of the COVID-19 pandemic on the development of burnout syndrome in healthcare providers: prevalence and predictive factors

BACKGROUND

In Tunisia, the pandemic is still ongoing, resulting in the burnout of healthcare providers.

AIMS

This study aimed to assess the impact of the management of COVID-19 patients on the physical and mental health of healthcare providers, and to identify the independent and predictive variables for the three components of severe burnout: emotional exhaustion, depersonalization, and lack of personal accomplishment at work.

METHODS

It was a cross-sectional survey. Data were collected between February 8, and April 11, 2021. Healthcare providers, who were positive for COVID, completed the questionnaire. The primary endpoint was to assess the degree of burnout in healthcare providers by adopting the original version of the severe Maslach Burnout Inventory: emotional exhaustion (≥30), depersonalization (≥12), and lack of personal accomplishment at work (≤ 33). A descriptive analysis followed by a bi- and multivariate analysis was performed to identify independent and predictive factors for each component of burnout.

RESULTS

700 healthcare providers were audited. Emotional exhaustion was ≥ 30 in 86%, depersonalization was ≥ 12 in 61%, and lack of personal accomplishment at work was ≤ 33 in 69%. Of the 700 healthcare providers, 93% were working at the same time in the COVID units, 85% had not received compensatory rest. Healthcare provider who had been infected by COVID-19 was the only independent predictive variable of severe emotional exhaustion and severe depersonalization. Healthcare provider who had been infected by COVID-19 and did not have a compensatory rest were two independent predictive variables of severe lack of personal accomplishment at work.

CONCLUSION

Healthcare provider who had been infected by COVID-19 was the only predictive variable of severe emotional exhaustion and severe depersonalization. Healthcare provider who had been infected by COVID-19 and did not have a compensatory rest were two independent and predictive variables of severe lack of personal accomplishment at work.

Developing occupational and health susceptibility personas for wastewater personnel in the United States in the age of COVID-19

Compared with the public, wastewater personnel, are at an increased risk of infection and illness from wastewater pathogens due to work-related tasks. Unfortunately, current risk assessment approaches do not consider individual personnel factors (e.g., age and health conditions) that may influence their susceptibility to a health effect. The objective of this study is to establish a baseline level of occupational and health factors among the wastewater personnel population, quantify these factors using a susceptibility evaluation scoring system, and examine relevant susceptibility features using the concept of "Personas." Using survey data from 246 respondents and public health risk data on COVID-19 from the CDC, personnel clustered into three persona groups: "low susceptibility," "high occupational susceptibility," and "high health susceptibility." Results highlight the intersectionality between gender, age, underlying health conditions, job tasks, and level of exposure to wastewater and provide context for incorporating individual variables into risk assessment methodologies with the goal of protecting this essential workforce. PRACTITIONER POINTS: A risk assessment framework that combines health and occupational susceptibility factors was developed for wastewater treatment plant personnel. Wastewater personnel clustered into three persona groups: "low susceptibility," "high occupational susceptibility," and "high health susceptibility." The intersectionality between job related activities and individual health provides a holistic approach to risk assessment for wastewater personnel.

EEG Evaluation of Stress Exposure on Healthcare Workers During COVID-19 Emergency: Not Just an Impression

Psychological distress among healthcare professionals, although already a common condition, was exacerbated by the COVID-19 pandemic. This effect has been generally self-reported or assessed through questionnaires. We aimed to identify potential abnormalities in the electrical activity of the brain of healthcare workers, operating in different roles during the pandemic. Cortical activity, cognitive performances, sleep, and burnout were evaluated two times in 20 COVID-19 frontline operators (FLCO, median age 29.5 years) and 20 operators who worked in COVID-19-free units (CFO, median 32 years): immediately after the outbreak of the pandemic (first session) and almost 6 months later (second session). FLCO showed higher theta relative power over the entire scalp (FLCO = 19.4%; CFO = 13.9%; p = 0.04) and lower peak alpha frequency of electrodes F7 (FLCO = 10.4 Hz; CFO = 10.87 Hz; p = 0.017) and F8 (FLCO = 10.47 Hz; CFO = 10.87 Hz; p = 0.017) in the first session. FLCO parietal interhemispheric coherence of theta (FLCO I = 0.607; FLCO II = 0.478; p = 0.025) and alpha (FLCO I = 0.578; FLCO II = 0.478; p = 0.007) rhythms decreased over time. FLCO also showed lower scores in the global cognitive assessment test (FLCO = 22.72 points; CFO = 25.56; p = 0.006) during the first session. The quantitative evaluation of the cortical activity might therefore reveal early signs of changes secondary to stress exposure in healthcare professionals, suggesting the implementation of measures to prevent serious social and professional consequences.