Dataset Information

Identifying Predictors of Psychological Distress During COVID-19: A Machine Learning Approach.

ABSTRACT: Scientific understanding about the psychological impact of the COVID-19 global pandemic is in its nascent stage. Prior research suggests that demographic factors, such as gender and age, are associated with greater distress during a global health crisis. Less is known about how emotion regulation impacts levels of distress during a pandemic. The present study aimed to identify predictors of psychological distress during the COVID-19 pandemic. Participants (N = 2,787) provided demographics, history of adverse childhood experiences, current coping strategies (use of implicit and explicit emotion regulation), and current psychological distress. The overall prevalence of clinical levels of anxiety, depression, and post-traumatic stress was higher than the prevalence outside a pandemic and was higher than rates reported among healthcare workers and survivors of severe acute respiratory syndrome. Younger participants (<45 years), women, and non-binary individuals reported higher prevalence of symptoms across all measures of distress. A random forest machine learning algorithm was used to identify the strongest predictors of distress. Regression trees were developed to identify individuals at greater risk for anxiety, depression, and post-traumatic stress. Somatization and less reliance on adaptive defense mechanisms were associated with greater distress. These findings highlight the importance of assessing individuals' physical experiences of psychological distress and emotion regulation strategies to help mental health providers tailor assessments and treatment during a global health crisis.

SUBMITTER: Prout TA

PROVIDER: S-EPMC7682196 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Identifying Predictors of Psychological Distress During COVID-19: A Machine Learning Approach.

Prout Tracy A TA Zilcha-Mano Sigal S Aafjes-van Doorn Katie K Békés Vera V Christman-Cohen Isabelle I Whistler Kathryn K Kui Thomas T Di Giuseppe Mariagrazia M

Frontiers in psychology 20201105

Scientific understanding about the psychological impact of the COVID-19 global pandemic is in its nascent stage. Prior research suggests that demographic factors, such as gender and age, are associated with greater distress during a global health crisis. Less is known about how emotion regulation impacts levels of distress during a pandemic. The present study aimed to identify predictors of psychological distress during the COVID-19 pandemic. Participants (<i>N</i> = 2,787) provided demographics ...[more]

PMID: 33240178

Similar Datasets

Project description:BackgroundEndometriosis is a multifaceted chronic pain condition that can have a negative impact on mental health. Patients suffering from chronic pain may face an additional psychological burden during adversity, such as the COVID-19 pandemic. The main aim of this research was to evaluate the prevalence of self-reported depression and anxiety, the influence of demographic, endometriosis-specific, pandemic-specific factors, and resilience on mental health outcomes of patients with endometriosis.MethodsAn online survey was conducted through patient support groups of women suffering from endometriosis during the first wave of the COVID-19 pandemic. The PHQ-4 questionnaire, which combines two items of the Patient Health Questionnaire for Depression (PHQ-2) and two items from the Generalized Anxiety Disorder Scale (GAD-2) was used to assess self-reported mental health. The Brief Resilience Score (BRS) was employed to evaluate resilience. Independent risk and protective factors for mental health were investigated by multivariate logistic regression analyses.ResultsThe PHQ-4 questionnaire was completed by 274 respondents. More than 40% reached depression (PHQ-2) and anxiety (GAD-2) scores of ≥3, and more than 20% achieved PHQ-2 and GAD-2 scores of ≥5. High resilience was found to be a reliable and strong independent protector for the probability of developing adverse psychological outcomes: OR 0.295, p < 0.001 for developing generalized anxiety disorder (GAD-2 ≥ 3), and OR 0.467, p < 0.001 for having major depression (PHQ-2 ≥ 3).ConclusionsPain-induced disability is an independent risk factor for developing major depression and anxiety, while resilience was identified as a potential protective parameter in terms of positive psychological outcomes in women with endometriosis. The results of this study may help to identify women at risk for adverse mental health outcomes and should encourage healthcare practitioners to establish strategies for the reduction of negative psychological and psychiatric impacts on patients with endometriosis.

Project description:IntroductionDetermining the optimal timing for extubation can be challenging in the intensive care. In this study, we aim to identify predictors for extubation failure in critically ill patients with COVID-19.MethodsWe used highly granular data from 3464 adult critically ill COVID patients in the multicenter Dutch Data Warehouse, including demographics, clinical observations, medications, fluid balance, laboratory values, vital signs, and data from life support devices. All intubated patients with at least one extubation attempt were eligible for analysis. Transferred patients, patients admitted for less than 24 h, and patients still admitted at the time of data extraction were excluded. Potential predictors were selected by a team of intensive care physicians. The primary and secondary outcomes were extubation without reintubation or death within the next 7 days and within 48 h, respectively. We trained and validated multiple machine learning algorithms using fivefold nested cross-validation. Predictor importance was estimated using Shapley additive explanations, while cutoff values for the relative probability of failed extubation were estimated through partial dependence plots.ResultsA total of 883 patients were included in the model derivation. The reintubation rate was 13.4% within 48 h and 18.9% at day 7, with a mortality rate of 0.6% and 1.0% respectively. The grandient-boost model performed best (area under the curve of 0.70) and was used to calculate predictor importance. Ventilatory characteristics and settings were the most important predictors. More specifically, a controlled mode duration longer than 4 days, a last fraction of inspired oxygen higher than 35%, a mean tidal volume per kg ideal body weight above 8 ml/kg in the day before extubation, and a shorter duration in assisted mode (< 2 days) compared to their median values. Additionally, a higher C-reactive protein and leukocyte count, a lower thrombocyte count, a lower Glasgow coma scale and a lower body mass index compared to their medians were associated with extubation failure.ConclusionThe most important predictors for extubation failure in critically ill COVID-19 patients include ventilatory settings, inflammatory parameters, neurological status, and body mass index. These predictors should therefore be routinely captured in electronic health records.

Project description:BackgroundResearch gaps refer to unanswered questions in the existing body of knowledge, either due to a lack of studies or inconclusive results. Research gaps are essential starting points and motivation in scientific research. Traditional methods for identifying research gaps, such as literature reviews and expert opinions, can be time consuming, labor intensive, and prone to bias. They may also fall short when dealing with rapidly evolving or time-sensitive subjects. Thus, innovative scalable approaches are needed to identify research gaps, systematically assess the literature, and prioritize areas for further study in the topic of interest.ObjectiveIn this paper, we propose a machine learning-based approach for identifying research gaps through the analysis of scientific literature. We used the COVID-19 pandemic as a case study.MethodsWe conducted an analysis to identify research gaps in COVID-19 literature using the COVID-19 Open Research (CORD-19) data set, which comprises 1,121,433 papers related to the COVID-19 pandemic. Our approach is based on the BERTopic topic modeling technique, which leverages transformers and class-based term frequency-inverse document frequency to create dense clusters allowing for easily interpretable topics. Our BERTopic-based approach involves 3 stages: embedding documents, clustering documents (dimension reduction and clustering), and representing topics (generating candidates and maximizing candidate relevance).ResultsAfter applying the study selection criteria, we included 33,206 abstracts in the analysis of this study. The final list of research gaps identified 21 different areas, which were grouped into 6 principal topics. These topics were: "virus of COVID-19," "risk factors of COVID-19," "prevention of COVID-19," "treatment of COVID-19," "health care delivery during COVID-19," "and impact of COVID-19." The most prominent topic, observed in over half of the analyzed studies, was "the impact of COVID-19."ConclusionsThe proposed machine learning-based approach has the potential to identify research gaps in scientific literature. This study is not intended to replace individual literature research within a selected topic. Instead, it can serve as a guide to formulate precise literature search queries in specific areas associated with research questions that previous publications have earmarked for future exploration. Future research should leverage an up-to-date list of studies that are retrieved from the most common databases in the target area. When feasible, full texts or, at minimum, discussion sections should be analyzed rather than limiting their analysis to abstracts. Furthermore, future studies could evaluate more efficient modeling algorithms, especially those combining topic modeling with statistical uncertainty quantification, such as conformal prediction.

Project description:BackgroundDuring major pandemics such as COVID-19, the fear of being infected, uncertain prognoses, and the imposition of restrictions may result in greater odds of emotional and psychological distress. Hence, the present study examines the predictors of psychological distress during the COVID-19 pandemic in Canada, and how they differ by gender.MethodsData of 2,756 adults aged 18 years and above from a cross-sectional online survey conducted between July and October 2020 was used for this study. A multivariable logistic regression analysis was carried out. The results were presented as adjusted odds ratio (aOR) with their respective confidence interval (CI).ResultsLower odds of psychological distress were found among males compared to females and among individuals aged 45-64 or 65-84 years compared to those aged 18-44. The odds of psychological distress decreased with a rise in income, with individuals whose annual income was greater than or equal to $100,000 being less likely to experience psychological distress compared to those whose income was less than $20,000. The odds of psychological distress were higher among residents of Ontario compared to residents of Quebec. Similarly, the odds of psychological distress were higher among individuals who reported experiencing COVID-19 symptoms compared to those who did not report any COVID-19 symptoms. The disaggregated results by gender showed that age, province, and self-reported COVID-19 symptoms had significant associations with psychological distress in both males and females, but these effects were more pronounced among females compared to males. In addition, income was negatively associated with psychological distress for both males and females, with this effect being stronger among males.ConclusionFive exposure variables (gender, age, province, experiencing COVID-19 symptoms, and total annual income in 2019) significantly predicted the likelihood of reporting psychological distress during the COVID-19 pandemic in Canada. Clearly, there is an imminent need to provide mental health support services to vulnerable groups. Additionally, interventions and policies aimed at combating psychological distress during pandemics such as COVID-19 should be gender specific.

Dataset Information

Identifying Predictors of Psychological Distress During COVID-19: A Machine Learning Approach.

Publications

Identifying Predictors of Psychological Distress During COVID-19: A Machine Learning Approach.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets