Towards clinical data-driven eligibility criteria optimization for interventional COVID-19 clinical trials

ObjectiveThis research aims to evaluate the impact of eligibility criteria on recruitment and observable clinical outcomes of COVID-19 clinical trials using electronic health record (EHR) data.Materials and MethodsOn June 18, 2020, we identified frequently used eligibility criteria from all the interventional COVID-19 trials in ClinicalTrials.gov (n = 288), including age, pregnancy, oxygen saturation, alanine/aspartate aminotransferase, platelets, and estimated glomerular filtration rate. We applied the frequently used criteria to the EHR data of COVID-19 patients in Columbia University Irving Medical Center (CUIMC) (March 2020–June 2020) and evaluated their impact on patient accrual and the occurrence of a composite endpoint of mechanical ventilation, tracheostomy, and in-hospital death.ResultsThere were 3251 patients diagnosed with COVID-19 from the CUIMC EHR included in the analysis. The median follow-up period was 10 days (interquartile range 4–28 days). The composite events occurred in 18.1% (n = 587) of the COVID-19 cohort during the follow-up. In a hypothetical trial with common eligibility criteria, 33.6% (690/2051) were eligible among patients with evaluable data and 22.2% (153/690) had the composite event.DiscussionBy adjusting the thresholds of common eligibility criteria based on the characteristics of COVID-19 patients, we could observe more composite events from fewer patients.ConclusionsThis research demonstrated the potential of using the EHR data of COVID-19 patients to inform the selection of eligibility criteria and their thresholds, supporting data-driven optimization of participant selection towards improved statistical power of COVID-19 trials.     

Impact of angiotensin-converting enzyme inhibitors and angiotensin receptor blockers on in-hospital mortality among patients with COVID-19: a systematic review and meta-analysis

INTRODUCTIONThere are concerns that angiotensin-converting enzyme inhibitors (ACEIs) and angiotensin receptor blockers (ARBs) may worsen the outcomes of patients with COVID-19. This systematic review and meta-analysis aimed to study the in-hospital mortality among COVID-19 patients who were on ACEIs/ARBs as compared to those not on ACEIs/ARBs.METHODSWe searched PubMed, EMBASE, clinicaltrials.gov and Google Scholar between 1 January 2020 and 30 May 2020 to identify all studies that evaluated the use of ACEIs/ARBs and reported the in-hospital mortality outcomes of COVID-19 patients. Nine non-randomised studies were eligible for inclusion in the analysis. The primary outcome studied was the in-hospital mortality of COVID-19 patients who were on ACEIs/ARBs compared with those not on ACEIs/ARBs.RESULTSOf the 8,313 patients in the nine studies, 7,622 (91.7%) were from studies with all-comers, while 691 (8.3%) were from studies involving only patients with hypertension. 577 (14.6%) in-hospital deaths were observed out of a total of 3,949 patients with an outcome in the nine studies. Overall, no significant difference was observed in the in-hospital mortality between patients on ACEIs/ARBs and those not on ACEIs/ARBs (odds ratio [OR] 1.06, 95% confidence interval [CI] 0.75–1.50; p = 0.73). Further sensitivity analysis in the hypertension group and the all-comers group showed similar results (OR 0.88, 95% CI 0.58–1.32; p = 0.53 and OR 1.85, 95% CI 1.00–3.43; p = 0.05, respectively).CONCLUSIONWe observed that ACEIs/ARBs had no significant impact on the in-hospital mortality of COVID-19 patients and can be used safely in patients with indications.     

Predicting brain function status changes in critically ill patients via Machine learning

ObjectiveIn intensive care units (ICUs), a patient’s brain function status can shift from a state of acute brain dysfunction (ABD) to one that is ABD-free and vice versa, which is challenging to forecast and, in turn, hampers the allocation of hospital resources. We aim to develop a machine learning model to predict next-day brain function status changes.Materials and MethodsUsing multicenter prospective adult cohorts involving medical and surgical ICU patients from 2 civilian and 3 Veteran Affairs hospitals, we trained and externally validated a light gradient boosting machine to predict brain function status changes. We compared the performances of the boosting model against state-of-the-art models—an ABD predictive model and its variants. We applied Shapley additive explanations to identify influential factors to develop a compact model.ResultsThere were 1026 critically ill patients without evidence of prior major dementia, or structural brain diseases, from whom 12 295 daily transitions (ABD: 5847 days; ABD-free: 6448 days) were observed. The boosting model achieved an area under the receiver-operating characteristic curve (AUROC) of 0.824 (95% confidence interval [CI], 0.821-0.827), compared with the state-of-the-art models of 0.697 (95% CI, 0.693-0.701) with P < .001. Using 13 identified top influential factors, the compact model achieved 99.4% of the boosting model on AUROC. The boosting and the compact models demonstrated high generalizability in external validation by achieving an AUROC of 0.812 (95% CI, 0.812-0.813).ConclusionThe inputs of the compact model are based on several simple questions that clinicians can quickly answer in practice, which demonstrates the model has direct prospective deployment potential into clinical practice, aiding in critical hospital resource allocation.     

Calcium channel blockers improve prognosis of patients with coronavirus disease 2019 and hypertension

Background:Hypertension is considered an important risk factor for the coronavirus disease 2019 (COVID-19). The commonly anti-hypertensive drugs are the renin-angiotensin-aldosterone system (RAAS) inhibitors, calcium channel blockers (CCBs), and beta-blockers. The association between commonly used anti-hypertensive medications and the clinical outcome of COVID-19 patients with hypertension has not been well studied.Methods:We conducted a retrospective cohort study that included all patients admitted with COVID-19 to Huo Shen Shan Hospital and Guanggu District of the Maternal and Child Health Hospital of Hubei Province, Wuhan, China. Clinical and laboratory characteristics were extracted from electronic medical records. Hypertension and anti-hypertensive treatment were confirmed by medical history and clinical records. The primary clinical endpoint was all-cause mortality. Secondary endpoints included the rates of patients in common wards transferred to the intensive care unit and hospital stay duration. Logistic regression was used to explore the risk factors associated with mortality and prognosis. Propensity score matching was used to balance the confounders between different anti-hypertensive treatments. Kaplan-Meier curves were used to compare the cumulative recovery rate. Log-rank tests were performed to test for differences in Kaplan-Meier curves between different groups.Results:Among 4569 hospitalized patients with COVID-19, 31.7% (1449/4569) had a history of hypertension. There were significant differences in mortality rates between hypertensive patients with CCBs (7/359) and those without (21/359) (1.95% vs. 5.85%, risk ratio [RR]: 0.32, 95% confidence interval [CI]: 0.13–0.76, χ² = 7.61, P = 0.0058). After matching for confounders, the mortality rates were similar between the RAAS inhibitor (4/236) and non-RAAS inhibitor (9/236) cohorts (1.69% vs. 3.81%, RR: 0.43, 95% CI: 0.13–1.43, χ² = 1.98, P = 0.1596). Hypertensive patients with beta-blockers (13/340) showed no statistical difference in mortality compared with those without (11/340) (3.82% vs. 3.24%, RR: 1.19, 95% CI: 0.53–2.69, χ² = 0.17, P = 0.6777).Conclusions:In our study, we did not find any positive or negative effects of RAAS inhibitors or beta-blockers in COVID-19 patients with hypertension, while CCBs could improve prognosis.     

Clinical characteristics and in-hospital mortality of COVID-19 adult patients in Saudi Arabia

Objectives:To provide a detailed study of demographic, baseline comorbidities, clinical features, and outcome for Coronavirus disease 2019 (COVID-19) patients.Methods:A record-based case-series study conducted from March 23 to June 15, 2020 in King Saud Medical City, Riyadh, Saudi Arabia. Demographic data, clinical presentation, laboratory investigations, complications, and in-hospital outcome of COVID-19 patients collected with analysis of the clinical characteristics for survivors and deceased.Results:A total of 768 patients were included. The mean age was 46.36±13.7 years and 76.7% were men. Approximately 96.3% reported more than one comorbidity; diabetes mellitus was the most frequent (46.4%). Fever (84.5%), cough (82.3%), and shortness of breath (79.8%) were the main presenting symptoms. During the follow-up, pneumonia reported in 68.6%, acute respiratory distress syndrome in 32.7%, septic shock in 20.7%, respiratory failure in 20.3%, and acute kidney injury in 19.3%. Approximately 45.8% of enrolled patients required intensive care unit admission. Lung disease (odd ratio [OR]=3.862 with 95% confident interval [CI] (2.455-6.074), obesity (OR=3.732, CI=2.511-5.546), smoking (OR=2.991, CI=2.072-4.317), chronic kidney disease (OR=2.296. CI=1.497-3.521), and diabetes mellitus (OR=2.291, CI=1.714-3.063) are predictors of ICU admission. Fatality ratio was 89/2084 (4.27%). Men were more prevalent in dead group.Conclusion:Coronavirus disease 2019 places a huge burden on healthcare facilities, particularly in patients with comorbidity. Coronavirus disease 2019 patients who are obese and smokers with history of diabetes mellitus have a high risk of death.     

Higher neonatal morbidity after routine early hospital discharge: Are we sending newborns home too early?

BACKGROUND: A growing body of evidence suggests that the trend toward earlier discharge may affect newborn morbidity. The authors assessed how hospital readmission rates were affected by a clinical guideline aimed at discharging newborns from hospital 24 hours after birth. METHOD: A retrospective before-after cohort study was conducted involving 7009 infants born by uncomplicated vaginal delivery at a large level II hospital in Toronto between Dec. 31, 1993, and Sept. 29, 1997. The primary outcome was a comparison of the rate of hospital readmission among newborns before (5936 infants) and after (1073 infants) the early-discharge policy was implemented (Apr. 1, 1997). The causes for readmission were secondary outcomes. RESULTS: Before the early-discharge guideline was implemented, the mean length of stay declined from 2.25 days (95% confidence interval [CI] 2.18-2.32) to 1.88 days (95% CI 1.84-1.92) (p < 0.001). After implementation there was a further decline, to 1.62 days (95% CI 1.56-1.67) (p < 0.001). A total of 126 infants (11.7%) in the early-discharge cohort required readmission by 1 month, as compared with 396 infants (6.7%) in the preguideline cohort (odds ratio 1.86, 95% CI 1.51-2.30). The main reason for early readmission was neonatal jaundice, with a higher rate among infants in the early-discharge cohort than among those in the preguideline cohort (8.6% v. 3.1%; odds ratio 2.96, 95% CI 2.29-3.84). INTERPRETATION: Decreases in newborn length of stay may result in substantial increases in morbidity. Careful consideration is needed to establish whether a reduction in length of stay to less than 24 to 36 hours is harmful to babies.     

Serum neutrophil gelatinase-associated lipocalin concentrations are significantly associated with the severity of COVID-19 in pregnant patients

Objectives:To evaluate serum neutrophil gelatinase-associated lipocalin (NGAL) concentrations of pregnant women complicated with coronavirus disease 2019 (COVID-19) and investigate its diagnostic value for the severity of COVID-19.Methods:Of the 46 pregnant women with COVID-19 included in the study, we further classified these women into 2 subgroups: the non-severe COVID-19 group (n=25) and the severe COVID-19 group (n=21).Results:Neutrophil gelatinase-associated lipocalin plasma concentrations were significantly higher in pregnant women complicated with severe COVID-19 (90 [53.1-207.7] ng/ml) compared to those from pregnant women with non-severe COVID-19 (51.8 [39.6-70.3] ng/ml) and healthy pregnant women (44.3 [32.2-54.1] ng/ml, p<0.001). Also, at a cutoff value of 72 ng/ml, NGAL predicted severe COVID-19 with a sensitivity rate of 57% and a specificity rate of 84%. Serum NGAL level (adjusted hazard ratio [aHR]=1.020, 95% confidence interval [CI]= [1.006-1.035], p=0.007), and D-dimer level (aHR=2.371, 95% CI= [1.085-5.181], p=0.030) were the variables that were revealed to be significantly associated with the disease severity.Conclusion:We demonstrated that NGAL was highly associated with COVID-19 severity. We consider that NGAL might be a useful biomarker to diagnose the disease severity in patients with COVID-19.     

Machine learning for initial insulin estimation in hospitalized patients

ObjectiveThe study sought to determine whether machine learning can predict initial inpatient total daily dose (TDD) of insulin from electronic health records more accurately than existing guideline-based dosing recommendations.Materials and MethodsUsing electronic health records from a tertiary academic center between 2008 and 2020 of 16,848 inpatients receiving subcutaneous insulin who achieved target blood glucose control of 100-180 mg/dL on a calendar day, we trained an ensemble machine learning algorithm consisting of regularized regression, random forest, and gradient boosted tree models for 2-stage TDD prediction. We evaluated the ability to predict patients requiring more than 6 units TDD and their point-value TDDs to achieve target glucose control.ResultsThe method achieves an area under the receiver-operating characteristic curve of 0.85 (95% confidence interval [CI], 0.84-0.87) and area under the precision-recall curve of 0.65 (95% CI, 0.64-0.67) for classifying patients who require more than 6 units TDD. For patients requiring more than 6 units TDD, the mean absolute percent error in dose prediction based on standard clinical calculators using patient weight is in the range of 136%-329%, while the regression model based on weight improves to 60% (95% CI, 57%-63%), and the full ensemble model further improves to 51% (95% CI, 48%-54%).DiscussionOwingto the narrow therapeutic window and wide individual variability, insulin dosing requires adaptive and predictive approaches that can be supported through data-driven analytic tools.ConclusionsMachine learning approaches based on readily available electronic medical records can discriminate which inpatients will require more than 6 units TDD and estimate individual doses more accurately than standard guidelines and practices.     

Risk factor for 31-day unplanned readmission to hospital in patients with pulmonary tuberculosis in China

Objectives:To evaluate risk factors associated with 31-day unplanned readmission(s) for pulmonary tuberculosis (TB) in China.Methods:This retrospective study enrolled patients (age, >14 years) with pulmonary TB who experienced 31-day unplanned readmissions to a specialized hospital for TB between January 2018 and December 2019. For each confirmed readmission, 2 control subjects were randomly selected from among patients with pulmonary TB but did not experience an unplanned readmission within 31 days.Results:A total of 402 pulmonary TB patients (5.9%) experienced unplanned readmission within 31 days after discharge. In univariate analysis, readmission was associated with gender, age, insurance coverage, residing in a rural area, active smoking, chronic obstructive pulmonary disease (COPD), drug-induced hepatitis, and leaving hospital against medical advice. The final logistic regression model revealed that higher risks for unplanned readmissions were associated with male gender (odds ratio [OR] 1.44, [95% confidence interval (CI) : 1.06-1.95]), age >65 years (OR 2.94, 95%CI: 2.03-4.27), rural residence (OR 8.86, 95%CI: 6.61-11.87), active smoking (OR 2.15, 95% CI 1.37-3.40), COPD (OR 2.77, 95%CI: 1.59-4.81), and leaving hospital against physician advice (OR 4.11, 95%CI: 1.43-11.83). The median time to 31-day unplanned readmission was 24 days. Major reasons for unplanned readmission included fever, exacerbation of dyspnea, and hemoptysis.Conclusion:Unplanned readmission for pulmonary TB within 31 days of discharge was higher among older males residing in rural areas, active smokers, and those leaving hospital against medical advice.     

Comorbidities and severity of coronavirus disease 2019 patients

Objectives:To determine the association between comorbidities and the severity of the disease among COVID-19 patients.Methods:We searched the Cochrane, Medline, Trip, and EMBASE databases from 2019. The review included all available studies of COVID-19 patients published in the English language and studied the clinical characteristics, comorbidities, and disease outcomes from the beginning of the pandemic. Two authors extracted studies characteristics and the risk of bias. Odds ratio (OR) was used to analyze the data with 95% confidence interval (CI).Results:The review included 1,885 COVID-19 patients from 7 observational studies with some degree of bias risk and substantial heterogeneity. A significant association was recorded between COVID-19 severity and the following variables: male (OR= 1.60, 95%CI= 1.05 - 2.43); current smoker (OR=2.06, 95%CI= 1.08 - 3.94); and the presence of comorbidities including hypertension (OR=2.05, 95%CI= 1.56 - 2.70), diabetes (OR=2.46, 95%CI= 1.53 - 3.96), coronary heart disease (OR=4.10, 95%CI= 2.36 - 7.12), chronic kidney disease (OR=4.06, 95%CI= 1.45 - 11.35), and cancer (OR=2.28, 95%CI= 1.08 - 4.81).Conclusions:Comorbidities among COVID-19 patients may contribute to increasing their susceptibility to severe illness. The identification of these potential risk factors could help reduce mortality by identifying patients with poor prognosis at an early stage.     

Predicting hospitalization of COVID-19 positive patients using clinician-guided machine learning methods

ObjectivesThe coronavirus disease 2019 (COVID-19) is a resource-intensive global pandemic. It is important for healthcare systems to identify high-risk COVID-19-positive patients who need timely health care. This study was conducted to predict the hospitalization of older adults who have tested positive for COVID-19.MethodsWe screened all patients with COVID test records from 11 Mass General Brigham hospitals to identify the study population. A total of 1495 patients with age 65 and above from the outpatient setting were included in the final cohort, among which 459 patients were hospitalized. We conducted a clinician-guided, 3-stage feature selection, and phenotyping process using iterative combinations of literature review, clinician expert opinion, and electronic healthcare record data exploration. A list of 44 features, including temporal features, was generated from this process and used for model training. Four machine learning prediction models were developed, including regularized logistic regression, support vector machine, random forest, and neural network.ResultsAll 4 models achieved area under the receiver operating characteristic curve (AUC) greater than 0.80. Random forest achieved the best predictive performance (AUC = 0.83). Albumin, an index for nutritional status, was found to have the strongest association with hospitalization among COVID positive older adults.ConclusionsIn this study, we developed 4 machine learning models for predicting general hospitalization among COVID positive older adults. We identified important clinical factors associated with hospitalization and observed temporal patterns in our study cohort. Our modeling pipeline and algorithm could potentially be used to facilitate more accurate and efficient decision support for triaging COVID positive patients.     

Comparative effectiveness and safety of 32 pharmacological interventions recommended by guidelines for coronavirus disease 2019: a systematic review and network meta-analysis combining 66 trials

Background:The global pandemic coronavirus disease 2019 (COVID-19) has become a major public health problem and presents an unprecedented challenge. However, no specific drugs were currently proven. This study aimed to evaluate the comparative efficacy and safety of pharmacological interventions in patients with COVID-19.Methods:Medline, Embase, the Cochrane Library, and clinicaltrials.gov were searched for randomized controlled trials (RCTs) in patients infected with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)/SARS-CoV. Random-effects network meta-analysis within the Bayesian framework was performed, followed by the Grading of Recommendations Assessment, Development, and Evaluation system assessing the quality of evidence. The primary outcome of interest includes mortality, cure, viral negative conversion, and overall adverse events (OAEs). Odds ratio (OR) with 95% confidence interval (CI) was calculated as the measure of effect size.Results:Sixty-six RCTs with 19,095 patients were included, involving standard of care (SOC), eight different antiviral agents, six different antibiotics, high and low dose chloroquine (CQ_HD, CQ_LD), traditional Chinese medicine (TCM), corticosteroids (COR), and other treatments. Compared with SOC, a significant reduction of mortality was observed for TCM (OR = 0.34, 95% CI: 0.20–0.56, moderate quality) and COR (OR = 0.84, 95% CI: 0.75–0.96, low quality) with improved cure rate (OR = 2.16, 95% CI: 1.60–2.91, low quality for TCM; OR = 1.17, 95% CI: 1.05–1.30, low quality for COR). However, an increased risk of mortality was found for CQ_HD vs. SOC (OR = 3.20, 95% CI: 1.18–8.73, low quality). TCM was associated with decreased risk of OAE (OR = 0.52, 95% CI: 0.38–0.70, very low quality) but CQ_HD (OR = 2.51, 95% CI: 1.20–5.24) and interferons (IFN) (OR = 2.69, 95% CI: 1.02–7.08) vs. SOC with very low quality were associated with an increased risk.Conclusions:COR and TCM may reduce mortality and increase cure rate with no increased risk of OAEs compared with standard care. CQ_HD might increase the risk of mortality. CQ, IFN, and other antiviral agents could increase the risk of OAEs. The current evidence is generally uncertain with low-quality and further high-quality trials are needed.     

Prevalence of COVID-19 antibodies among operating room and critical care staff at a tertiary teaching hospital: A cross-sectional study

Objectives:To identify the prevalence of COVID-19 antibodies among operating room and critical care staff.Methods:In this cross-sectional study, we recruited 319 Healthcare workers employed in the operation theater and intensive care unit of King Abdulaziz University Hospital (KAUH), a tertiary teaching hospital in Jeddah, Saudi Arabia between August 9, 2020 and November 2, 2020. All participants completed a 20-item questionnaire on demographic data and COVID-19 risk factors and provided blood samples. Antibody testing was performed using an in-house enzyme immunoassay and microneutralization test.Results:Of the 319 participants, 39 had detectable COVID-19 antibodies. Five of them had never experienced any symptoms suggestive of COVID-19, and only 19 were previously diagnosed with COVID-19. The odds of developing COVID-19 or having corresponding antibodies increased if participants experienced COVID-19 symptoms (odds ratio [OR], 3.1; 95% confidence interval [CI], 1.2-7.5) or reported contact with an infected family member (OR, 5.3; 95% CI, 2.5-11.2). Disease acquisition was not associated with employment in the ICU and involvement in the intubation of or close contact with COVID-19 patients. Of the 19 previously diagnosed participants, 6 did not possess any detectable COVID-19 antibodies.Conclusions:Healthcare workers may have undiagnosed COVID-19, and those previously infected may not have long-lasting immunity. Therefore, hospitals must continue to uphold strict infection control during the COVID-19 pandemic.     

Respiratory support status from EHR data for adult population: classification,heuristics, and usage in predictive modeling

ObjectiveRespiratory support status is critical in understanding patient status, but electronic health record data are often scattered, incomplete, and contradictory. Further, there has been limited work on standardizing representations for respiratory support. The objective of this work was to (1) propose a practical terminology system for respiratory support methods; (2) develop (meta-)heuristics for constructing respiratory support episodes; and (3) evaluate the utility of respiratory support information for mortality prediction.Materials and MethodsAll analyses were performed using electronic health record data of COVID-19-tested, emergency department-admit, adult patients at a large, Midwestern healthcare system between March 1, 2020 and April 1, 2021. Logistic regression and XGBoost models were trained with and without respiratory support information, and performance metrics were compared. Importance of respiratory-support-based features was explored using absolute coefficient values for logistic regression and SHapley Additive exPlanations values for the XGBoost model.ResultsThe proposed terminology system for respiratory support methods is as follows: Low-Flow Oxygen Therapy (LFOT), High-Flow Oxygen Therapy (HFOT), Non-Invasive Mechanical Ventilation (NIMV), Invasive Mechanical Ventilation (IMV), and ExtraCorporeal Membrane Oxygenation (ECMO). The addition of respiratory support information significantly improved mortality prediction (logistic regression area under receiver operating characteristic curve, median [IQR] from 0.855 [0.852—0.855] to 0.881 [0.876—0.884]; area under precision recall curve from 0.262 [0.245—0.268] to 0.319 [0.313—0.325], both P < 0.01). The proposed generalizable, interpretable, and episodic representation had commensurate performance compared to alternate representations despite loss of granularity. Respiratory support features were among the most important in both models.ConclusionRespiratory support information is critical in understanding patient status and can facilitate downstream analyses.     

Routine laboratory parameters predict serious outcome as well as length of hospital stay in COVID-19

Objectives:To validate C-reactive protein (CRP), red cell distribution width (RDW), and neutrophil lymphocyte ratio (NLR) for both serious outcomes and length of hospital stay (LOS) among hospitalized coronavirus disease-19 (COVID-19) patients.Methods:Laboratory data of adult COVID-19 patients (n=74) was collected in this retrospective cohort. Logistic regression was employed for risk factor evaluation and receiver operating curve was used for comparison of these risk factors for the prediction of serious outcome. Multiple regression was applied to determine the association between routine analytes and LOS.Results:Higher levels of CRP (3 times), white blood cells (20%), and neutrophil counts (40%) were seen in the serious category. Odds ratio for CRP for the serious outcome was 1.052 (p=0.007) and RDW for the serious outcome was 1.218 (p=0.040) in unadjusted model and odds ratio for CRP for the serious outcome was 1.048 (p=0.024) and for RDW 1.286 (p=0.023) in adjusted model. In a multivariate regression analysis for the LOS of the unadjusted models consisting of NLR, monocyte lymphocyte ratio (MLR) and platelet lymphocyte ratio (PLR), the beta coefficients (BC) for the CRP were 0.006 (NLR), 0.005 (MLR) and 0.006 (PLR), whereas -0.029 (NLR), -0.034 (MLR) and -0.027 (PLR) were BCs for mean corpuscular hemoglobin concentration (MCHC). Additionally, in adjusted models, the BCs for MCHC were -0.044 (NLR), -0.047 (MLR) and -0.043 (PLR). However, the CRP was consistent with 0.004 (BC) in all models.Conclusion:We observed that CRP is a better predictor than RDW and NLR for serious outcome among COVID-19 patients. Besides, CRP was positively, whereas MCHC was negatively associated with LOS.     

Clinical and epidemiological characteristics of COVID-19 mortality in Saudi Arabia

Objectives:To analyze the clinical and epidemiological characteristics for 224 of in-hospital coronavirus disease 2019 (COVID-19) mortality cases. This study’s clinical implications provide insight into the significant death indicators among COVID-19 patients and the outbreak burden on the healthcare system in the Kingdom of Saudi Arabia (KSA).Methods:A multi-center retrospective cross-sectional study conducted among all COVID-19 mortality cases admitted to 15 Armed Forces hospitals across KSA, from March to July 2020. Demographic data, clinical presentations, laboratory investigations, and complications of COVID-19 mortality cases were collected and analyzed.Results:The mean age was 69.66±14.68 years, and 142 (63.4%) of the cases were male. Overall, 30% of the COVID-19 mortalities occurred in the first 24 hours of hospital admission, while 50% occurred on day 10. The most prevalent comorbidities were diabetes mellitus (DM, 73.7%), followed by hypertension (HTN, 69.6%). Logistic regression for risk factors in all mortality cases revealed that direct mortality cases from COVID-19 were more likely to develop acute respiratory distress syndrome (odds ratio [OR]: 1.75, confidence intervel [CI: 0.89-3.43]; p=0.102) and acute kidney injury (OR: 1.01, CI: [0.54-1.90]; p=0.960).Conclusion:Aging, male gender and the high prevalence of the underlying diseases such as, DM and HTN were a significant death indicators among COVID-19 mortality cases in KSA. Increases in serum ferritin, procalcitonin, C-reactive protein (CRP), and D-dimer levels can be used as indicators of disease progression.     

The emerging role of clinical informatics fellows in service learning during the COVID-19 pandemic

ObjectiveThe study sought to describe the contributions of clinical informatics (CI) fellows to their institutions’ coronavirus disease 2019 (COVID-19) response.Materials and MethodsWe designed a survey to capture key domains of health informatics and perceptions regarding fellows’ application of their CI skills. We also conducted detailed interviews with select fellows and described their specific projects in a brief case series.ResultsForty-one of the 99 CI fellows responded to our survey. Seventy-five percent agreed that they were “able to apply clinical informatics training and interest to the COVID-19 response.” The most common project types were telemedicine (63%), reporting and analytics (49%), and electronic health record builds and governance (32%). Telehealth projects included training providers on existing telehealth tools, building entirely new virtual clinics for video triage of COVID-19 patients, and pioneering workflows and implementation of brand-new emergency department and inpatient video visit types. Analytics projects included reports and dashboards for institutional leadership, as well as developing digital contact tracing tools. For electronic health record builds, fellows directly contributed to note templates with embedded screening and testing guidance, adding COVID-19 tests to order sets, and validating clinical triage workflows.DiscussionFellows were engaged in projects that span the breadth of the CI specialty and were able to make system-wide contributions in line with their educational milestones.ConclusionsCI fellows contributed meaningfully and rapidly to their institutions’ response to the COVID-19 pandemic.     

Complete blood cells count abnormalities in COVID-19 patients and their prognostic significance: Single center study in Makkah,Saudi Arabia

Objectives:To evaluate the role of different peripheral blood count parameters as a cheap and rapid test in determination of coronavirus disease -19 (COVID-19) severity and patients’ outcome.Methods:The data of 462 confirmed COVID-19 patients who attended at the Security Force Hospital, Makkah, Saudi Arabia, from October 2020 to March 2021 was retrospectively reviewed and C. Patients with viral infection and respiratory diseases other than COVID-19 were excluded from the study. Complete blood count parameters were compared in accordance with the severity of the clinical presentation, age, and disease outcome.Results:A total of 277 (60%) were male and 185 (40%) female. Clinically, 32 (6.9%) had severe illness and 430 (93.1%) showed moderate clinical disease. Organ failure occurred in 2.8% of the patients. There was significant leucocytosis, neutrophilia, lymphopenia, high neutrophil-lymphocyte (N/L) ratio, and anemia in patients with severe COVID-19 diseases as well as in non-survivors’ cases (p<0.001). Similarly, the inflammatory markers (C-reactive protein [CRP] and serum ferritin) were significantly elevated in the above-mentioned 2 groups (p<0.001). Significant decrease of the platelets count was detectable in clinically severe cases and non-survivors (p<0.01). Older age (>60 years) was associated with high leucocyte, neutrophil count, lymphopenia, anemia, organ failure, and poor outcome.Conclusion:Leucocytosis, neutrophilia, lymphopenia, and high N/L ratio together with elevated serum level of ferritin and CRP are eminent features of COVID-19 severity. The inclusion of these parameters in the regimens for patients’ categorization on admission will enable early effective intervention and proper decision making during clinical case management.     

基于机器学习算法的新型冠状病毒肺炎患者院内结局预测

目的 利用机器学习算法构建新型冠状病毒肺炎(COVID-19)患者临床结局的预测模型,并探索结局相关因子.方法 收集2020年2月5日至4月15日武汉市火神山医院及华中科技大学同济医学院附属同济医院光谷院区收治的COVID-19患者的临床指标与结局(院内死亡和院内接受气管插管治疗),利用人工神经网络(ANN)、朴素贝叶斯、logistic回归、随机森林4种机器学习算法构建患者临床结局的预测模型.结果 共纳入4804例COVID-19患者,其中发生院内死亡100例(2.08％)、接受气管插管治疗87例(1.81％).与院内死亡相关性最强的变量为白细胞计数、白蛋白、钙离子、血尿素氮、心肌型肌酸激酶同工酶和年龄,与院内接受气管插管治疗相关性最强的变量为白细胞计数、淋巴细胞绝对值、超敏CRP、总胆红素、钙离子和年龄,分别利用以上变量、基于4种机器学习算法构建院内死亡和院内接受气管插管治疗预测模型.4种预测模型中,相较于基于ANN、logistic回归、随机森林算法构建的模型[预测院内死亡的AUC值(95％CI)分别为0.938(0.882～0.993)、0.926(0.865～0.987)、0.867(0.780～0.954),预测院内接受气管插管治疗的AUC值(95％CI)分别为0.932(0.814～0.980)、0.935(0.817～0.981)、0.936(0.921～0.972)],基于朴素贝叶斯算法构建的模型在预测COVID-19患者院内死亡(AUC=0.952,95％CI 0.925～0.979)和接受气管插管治疗(AUC=0.948,95％CI 0.896～0.965)方面性能均最佳.结论 4种机器学习算法在预测COVID-19患者临床结局方面性能良好,其中以基于朴素贝叶斯算法构建的预测模型最佳.白细胞计数、白蛋白、钙离子、血尿素氮、心肌型肌酸激酶同工酶和年龄可以用来预测COVID-19患者院内死亡,白细胞计数、淋巴细胞绝对值、超敏CRP、总胆红素、钙离子和年龄可以用来预测患者院内是否接受气管插管治疗.