Evolution of Clinical Phenotypes of COVID-19 Patients During Intensive Care Treatment: An Unsupervised Machine Learning Analysis.

BACKGROUND: Identification of clinical phenotypes in critically ill COVID-19 patients could improve understanding of the disease heterogeneity and enable prognostic and predictive enrichment. However, previous attempts did not take into account temporal dynamics with high granularity. By including the dimension of time, we aim to gain further insights into the heterogeneity of COVID-19. METHODS: We used granular data from 3202 adult COVID patients in the Dutch Data Warehouse that were admitted to one of 25 Dutch ICUs between February 2020 and March 2021. Parameters including demographics, clinical observations, medications, laboratory values, vital signs, and data from life support devices were selected. Twenty-one datasets were created that each covered 24 h of ICU data for each day of ICU treatment. Clinical phenotypes in each dataset were identified by performing cluster analyses. Both evolution of the clinical phenotypes over time and patient allocation to these clusters over time were tracked. RESULTS: The final patient cohort consisted of 2438 COVID-19 patients with a ICU mortality outcome. Forty-one parameters were chosen for cluster analysis. On admission, both a mild and a severe clinical phenotype were found. After day 4, the severe phenotype split into an intermediate and a severe phenotype for 11 consecutive days. Heterogeneity between phenotypes appears to be driven by inflammation and dead space ventilation. During the 21-day period, only 8.2% and 4.6% of patients in the initial mild and severe clusters remained assigned to the same phenotype respectively. The clinical phenotype half-life was between 5 and 6 days for the mild and severe phenotypes, and about 3 days for the medium severe phenotype. CONCLUSIONS: Patients typically do not remain in the same cluster throughout intensive care treatment. This may have important implications for prognostic or predictive enrichment. Prominent dissimilarities between clinical phenotypes are predominantly driven by inflammation and dead space ventilation.

Preparedness of Primary Care Centers for COVID-19 epidemic in Aseer region, KSA.

Objective: The objective of this study is to assesses the preparedness of primary care centers (PHCs) in Aseer region, KSA, for the coronavirus disease 2019 (COVID-19) pandemic. Methods: This survey was conducted during April 2020 in PHCs. The questionnaire was developed by the investigators and sent via e-mail to health care providers of primary health care centers (PHCCs). The questionnaire consisted of five parts to assesses readiness of PHCs, knowledge, attitude, and practice of health care providers (HCPs) concerning the COVID-19 pandemic. Data entry and analysis were managed by SPSS version 20. Results: Three hundred and seventy-one HCPs participated in this study. Most of them were males (58%), doctors or nurses (81%). Almost all PHCCs have adequate infection control resources, with some shortage in sterilization rooms. Most of participants received on-job training (85%) and had good knowledge about COVID-19. Attitudes of participants showed variation toward COVID-19; 74% were afraid to be infected, 54% were afraid to care for infected patients, 58% were ready for vaccination, and 80% thought that COVID-19 has a huge negative impact on the health care system. Compliance with preventive measures ranged from 66% for keeping social distance to 90% for using personal protective equipment. Most of the participants had positive contributions regarding health education of individuals and communities using different methods including the new social media (80%). Conclusion: This study revealed that PHCCs in Aseer region were well equipped and HCPs were well prepared to deal with the COVID-19 pandemic. There are some shortage in a few items of infection control at PHCCs and gaps in knowledge and practice among HCPs which need continuous assessment and monitoring to overcome such barriers.

INCIDENCE, RISK FACTORS, AND OUTCOME OF SUSPECTED CENTRAL VENOUS CATHETER-RELATED INFECTIONS IN CRITICALLY ILL COVID-19 PATIENTS: A MULTICENTER RETROSPECTIVE COHORT STUDY.

ABSTRACT: Background: Aims of this study were to investigate the prevalence and incidence of catheter-related infection, identify risk factors, and determine the relation of catheter-related infection with mortality in critically ill COVID-19 patients. Methods: This was a retrospective cohort study of central venous catheters (CVCs) in critically ill COVID-19 patients. Eligible CVC insertions required an indwelling time of at least 48 hours and were identified using a full-admission electronic health record database. Risk factors were identified using logistic regression. Differences in survival rates at day 28 of follow-up were assessed using a log-rank test and proportional hazard model. Results: In 538 patients, a total of 914 CVCs were included. Prevalence and incidence of suspected catheter-related infection were 7.9% and 9.4 infections per 1,000 catheter indwelling days, respectively. Prone ventilation for more than 5 days was associated with increased risk of suspected catheter-related infection; odds ratio, 5.05 (95% confidence interval 2.12-11.0). Risk of death was significantly higher in patients with suspected catheter-related infection (hazard ratio, 1.78; 95% confidence interval, 1.25-2.53). Conclusions: This study shows that in critically ill patients with COVID-19, prevalence and incidence of suspected catheter-related infection are high, prone ventilation is a risk factor, and mortality is higher in case of catheter-related infection.

COVID-19 vaccine acceptance and associated factors among people living with HIV in the Middle East and North Africa region.

Background: Identifying coronavirus disease 2019 (COVID-19) vaccine acceptance and associated factors among people living with HIV (PLHIV) in the Middle East and North Africa region is important to meet the need for broad-scale vaccination against COVID-19. Objectives: To investigate the COVID-19 vaccine acceptance rate and factors among PLHIV in the Middle East and North Africa region. Method: An online cross-sectional survey was conducted among PLHIV currently living in Egypt, Tunisia and Saudi Arabia between March 2021 and August 2021. Results: Of the 540 respondents, 19.3% reported already being vaccinated against COVID-19 (n = 104), 32.0% responded 'definitely yes' (n = 173), and 13.3% responded 'probably yes' (n = 72) for intention to receive a COVID-19 vaccine, with an overall COVID-19 vaccine acceptance rate of 64.6% among PLHIV in the region. The most significant predictors of COVID-19 vaccine acceptance included feeling less worried about COVID-19 transmission post-vaccination (221.0% higher odds), and believing the disease is vaccine-preventable (160.0% higher odds). Reported barriers to COVID-19 vaccine acceptance include concerns about vaccine effectiveness and belief that HIV medications protect against COVID-19 transmission, living in a rural area and reporting less-frequent engagement with HIV care. Nine out of 10 participants reported that the chances of them getting COVID-19 vaccine would increase if given adequate information and if their doctor recommended it. Conclusion: Findings of the study can help researchers, health officials, and other health system actors understand the predictors and barriers to COVID-19 vaccine acceptance reported by PLHIV. This understanding could inform the future planning of interventions tailored to PLHIV.

Predicting responders to prone positioning in mechanically ventilated patients with COVID-19 using machine learning.

BACKGROUND: For mechanically ventilated critically ill COVID-19 patients, prone positioning has quickly become an important treatment strategy, however, prone positioning is labor intensive and comes with potential adverse effects. Therefore, identifying which critically ill intubated COVID-19 patients will benefit may help allocate labor resources. METHODS: From the multi-center Dutch Data Warehouse of COVID-19 ICU patients from 25 hospitals, we selected all 3619 episodes of prone positioning in 1142 invasively mechanically ventilated patients. We excluded episodes longer than 24 h. Berlin ARDS criteria were not formally documented. We used supervised machine learning algorithms Logistic Regression, Random Forest, Naive Bayes, K-Nearest Neighbors, Support Vector Machine and Extreme Gradient Boosting on readily available and clinically relevant features to predict success of prone positioning after 4 h (window of 1 to 7 h) based on various possible outcomes. These outcomes were defined as improvements of at least 10% in PaO2/FiO2 ratio, ventilatory ratio, respiratory system compliance, or mechanical power. Separate models were created for each of these outcomes. Re-supination within 4 h after pronation was labeled as failure. We also developed models using a 20 mmHg improvement cut-off for PaO2/FiO2 ratio and using a combined outcome parameter. For all models, we evaluated feature importance expressed as contribution to predictive performance based on their relative ranking. RESULTS: The median duration of prone episodes was 17 h (11-20, median and IQR, N = 2632). Despite extensive modeling using a plethora of machine learning techniques and a large number of potentially clinically relevant features, discrimination between responders and non-responders remained poor with an area under the receiver operator characteristic curve of 0.62 for PaO2/FiO2 ratio using Logistic Regression, Random Forest and XGBoost. Feature importance was inconsistent between models for different outcomes. Notably, not even being a previous responder to prone positioning, or PEEP-levels before prone positioning, provided any meaningful contribution to predicting a successful next proning episode. CONCLUSIONS: In mechanically ventilated COVID-19 patients, predicting the success of prone positioning using clinically relevant and readily available parameters from electronic health records is currently not feasible. Given the current evidence base, a liberal approach to proning in all patients with severe COVID-19 ARDS is therefore justified and in particular regardless of previous results of proning.

Assess and validate predictive performance of models for in-hospital mortality in COVID-19 patients: A retrospective cohort study in the Netherlands comparing the value of registry data with high-granular electronic health records.

PURPOSE: To assess, validate and compare the predictive performance of models for in-hospital mortality of COVID-19 patients admitted to the intensive care unit (ICU) over two different waves of infections. Our models were built with high-granular Electronic Health Records (EHR) data versus less-granular registry data. METHODS: Observational study of all COVID-19 patients admitted to 19 Dutch ICUs participating in both the national quality registry National Intensive Care Evaluation (NICE) and the EHR-based Dutch Data Warehouse (hereafter EHR). Multiple models were developed on data from the first 24 h of ICU admissions from February to June 2020 (first COVID-19 wave) and validated on prospective patients admitted to the same ICUs between July and December 2020 (second COVID-19 wave). We assessed model discrimination, calibration, and the degree of relatedness between development and validation population. Coefficients were used to identify relevant risk factors. RESULTS: A total of 1533 patients from the EHR and 1563 from the registry were included. With high granular EHR data, the average AUROC was 0.69 (standard deviation of 0.05) for the internal validation, and the AUROC was 0.75 for the temporal validation. The registry model achieved an average AUROC of 0.76 (standard deviation of 0.05) in the internal validation and 0.77 in the temporal validation. In the EHR data, age, and respiratory-system related variables were the most important risk factors identified. In the NICE registry data, age and chronic respiratory insufficiency were the most important risk factors. CONCLUSION: In our study, prognostic models built on less-granular but readily-available registry data had similar performance to models built on high-granular EHR data and showed similar transportability to a prospective COVID-19 population. Future research is needed to verify whether this finding can be confirmed for upcoming waves.

Cheese Intake Exhibits an Alteration of Glycolipid Profile and Impacts on Non-Alcoholic Fatty Liver in Bahraini Older Adults.

Background: Metabolic syndrome (MetS) is a multifactorial condition characterized by a complex interrelation between genetic and environmental factors that heighten the risk of cardiovascular diseases and all-cause mortality. It is hypothesized that diet may play an important role in the regulation of metabolic syndrome factors and influence the process. Therefore, the main objective of this study was to investigate the specific dietary patterns associated with metabolic syndrome markers and quantify the possible effects of dietary patterns among Bahrain older adults. Methods: This is a cross-sectional study that included 151 Bahraini patients diagnosed with MetS, 89 (58.7%) were females and 62 (41.3%) males. Results: The prevalence of Non-Alcoholic Fatty Liver was 89%. Statistically significant correlations were found between dairy products with low fat and SBP (r = 0.182, p < 0.001) body mass index (BMI) (r = -0.195; p < -0.01). Higher chicken consumption was associated with reduction of BMI (r = -0.273; p < -0.01). A higher consumption of ricotta and cheddar cheese (high in fat) was associated with higher levels of triglycerides (p < 0.01). Higher frequent consumption of rice (basmati) was associated with lower glucose levels (r = -0.200; p < -0.01). Fatty liver has been associated with high consumption of cream cheese (p < 0.01). Conclusion: In older Bahraini adults with metabolic syndrome, higher frequency of food consumption of full-fat cheese was linked with a derangement of lipid profile and Non-Alcoholic Fatty Liver. Positive effects on BMI have been recorded with higher-frequency consumption of basmati rice and chicken.

The Impact of COVID-19 on Physical (In)Activity Behavior in 10 Arab Countries.

Insufficient physical activity is considered a strong risk factor associated with non-communicable diseases. This study aimed to assess the impact of COVID-19 on physical (in)activity behavior in 10 Arab countries before and during the lockdown. A cross-sectional study using a validated online survey was launched originally in 38 different countries. The Eastern Mediterranean regional data related to the 10 Arabic countries that participated in the survey were selected for analysis in this study. A total of 12,433 participants were included in this analysis. The mean age of the participants was 30.3 (SD, 11.7) years. Descriptive and regression analyses were conducted to examine the associations between physical activity levels and the participants' sociodemographic characteristics, watching TV, screen time, and computer usage. Physical activity levels decreased significantly during the lockdown. Participants' country of origin, gender, and education were associated with physical activity before and during the lockdown (p < 0.050). Older age, watching TV, and using computers had a negative effect on physical activity before and during the lockdown (p < 0.050). Strategies to improve physical activity and minimize sedentary behavior should be implemented, as well as to reduce unhealthy levels of inactive time, especially during times of crisis. Further research on the influence of a lack of physical activity on overall health status, as well as on the COVID-19 disease effect is recommended.

Revisiting Middle East Respiratory Coronavirus (MERS-CoV) Outbreak Chest Radiographic Initial Findings, Temporal Progression, and Correlation to Outcomes: A Multicenter Study.

Objectives Accounts of initial and follow-up chest X-rays (CXRs) of the Middle East respiratory coronavirus (MERS-CoV) patients, and correlation with outcomes, are sparse. We retrospectively evaluated MERS-CoV CXRs initial findings, temporal progression, and outcomes correlation. Materials and methods Fifty-three real-time reverse-transcriptase-polymerase chain reaction (rRT-PCR)-confirmed MERS-CoV patients with CXRs were retrospectively identified from November 2013 to October 2014. Initial and follow-up CXR imaging findings and distribution were evaluated over 75 days. Findings were correlated with outcomes. Results Twenty-two of 53 (42%) initial CXRs were normal. In 31 (68%) abnormal initial CXRs, 15 (48%) showed bilateral non-diffuse involvement, 16 (52%) had ground-glass opacities (GGO), and 13 (42%) had peripheral distribution. On follow-up CXRs, mixed airspace opacities prevailed, seen in 16 (73%) of 22 patients 21-30 days after the initial CXRs. Bilateral non-diffuse involvement was the commonest finding throughout follow-up, affecting 16 (59%) of 27 patients 11-20 days after the initial CXRs. Bilateral diffuse involvement was seen in five (63%) of eight patients 31-40 days after the initial CXRs. A bilateral diffuse CXR pattern had an odds ratio for mortality of 13 (95% CI=2-78) on worst and 18 (95% CI=3-119) on final CXRs (P-value <0.05). Conclusion Initially, normal CXRs are common in MERS-CoV patients. Peripherally located ground-glass and mixed opacities are common on initial and follow-up imaging. The risk of mortality is higher when bilateral diffuse radiographic abnormalities are detected.

Effect of COVID-19 Pandemic on Neonatal Sepsis.

BACKGROUND: There is a sudden rise in infectious diseases, with special concern to the most recent SARS-CoV 2 outbreak. A retrospective study was conducted to study the effect of this outbreak on neonatal sepsis as a global issue that poses a challenge for pediatric management and to identify its risk factors, microbial profile, and mortality rate at King Faisal Medical Complex, Taif, KSA, a COVID-19-tertiary care segregation hospital. METHODS: This research included 111 neonates with a culture-proven diagnosis of neonatal sepsis (4 and 62 cases during 2019 and 2020, respectively). RESULTS: During 2019 early onset sepsis (EOS) occurred in 6/49 (12.2%) while in 2020 22/62 (35.5%), and during 2019 late onset sepsis (LOS) occurred in 43/49 (87.7%) while in 2020 40/62 (64.5%). Premature rupture of membrane was the major neonatal risk factor for EOS during 2019 and 2020 with proportions of 4 (66.7%), 20 (90.9%); respectively. As regards LOS, the peripherally inserted central catheters and peripheral lines were the top neonatal risk factors. In the two-year outbreak, the most prevalent causative organism for EOS neonates was Escherichia coli and for LOS neonates it was Klebsiella. There was non-significant change in the mortality rate of neonatal sepsis between 2019 and 2020. However, the mortality rate was higher in EOS 9/22 (40.9%) in 2020 in comparison to 2/6 (33.3%) in 2019. CONCLUSIONS: Neonatal sepsis remains a major health problem causing serious morbidity and mortality, and health care policy makers have to implement EOS preventive measures.

Evolution of Clinical Phenotypes of COVID-19 Patients During Intensive Care Treatment: An Unsupervised Machine Learning Analysis (preprint)

Background: Identification of distinct clinical phenotypes in critically ill COVID-19 patients could improve understanding of the disease heterogeneity and enable prognostic and predictive enrichment facilitating more personalized treatment. However, previous attempts did not take into account temporal dynamics of the disease. By including the dimension of time, we aim to gain further insights into the heterogeneity of COVID-19.Methods: We used highly granular data from 3202 adult critically ill COVID patients in the multicenter Dutch Data Warehouse that were admitted to one of 25 Dutch ICUs between February 2020 and March 2021. Parameters including demographics, clinical observations, medications, laboratory values, vital signs, and data from life support devices were selected based on relevance and availability. Twenty-one consecutive datasets were created that each covered 24 hours of ICU data for each day of ICU treatment up until day 21. After aggregation and multiple imputation of the temporal data, clinical phenotypes in each dataset were identified by performing multiple cluster analyses. Clinical phenotypes were identified by aggregating values from all patients per cluster. Both evolution of the clinical phenotypes over time and patient allocation to these clusters over time were tracked.Results: The final patient cohort consisted of 2438 critically ill COVID-19 patients with a registered ICU mortality outcome. Forty-one parameters were chosen for the cluster analysis. On admission, both a mild and a more severe clinical phenotype were found. After day 4, the severe phenotype split into an intermediate and a severe phenotype for 11 consecutive days. Heterogeneity between phenotypes appears to be strongly driven by inflammation and dead space ventilation. During the 21-day period only 8.2% and 4.6% of patients in the initial mild and severe clusters remained assigned to the same phenotype respectively. The clinical phenotype half-life was between 5 and 6 days for the mild and severe phenotypes, and about 3 days for the medium severe phenotype.Conclusions: Patients typically do not remain in the same cluster throughout intensive care treatment. This may have important implications for prognostic or predictive enrichment. Prominent dissimilarities between clinical phenotypes are predominantly driven by inflammation and dead space ventilation.

Predictors for extubation failure in COVID-19 patients using a machine learning approach.

INTRODUCTION: Determining 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. METHODS: We 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. RESULTS: A 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. CONCLUSION: The 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.