Information Technology Solutions, Challenges, and Suggestions for Tackling the COVID-19 Pandemic.

Summary Background A subset of patients with severe COVID-19 develop a hyperinflammatory syndrome, which might contribute to morbidity and mortality. This study explores a specific phenotype of COVID-19-associated hyperinflammation (COV-HI), and its associations with escalation of respiratory support and survival. Methods In this retrospective cohort study, we enrolled consecutive inpatients (aged ≥18 years) admitted to University College London Hospitals and Newcastle upon Tyne Hospitals in the UK with PCR-confirmed COVID-19 during the first wave of community-acquired infection. Demographic data, laboratory tests, and clinical status were recorded from the day of admission until death or discharge, with a minimum follow-up time of 28 days. We defined COV-HI as a C-reactive protein concentration greater than 150 mg/L or doubling within 24 h from greater than 50 mg/L, or a ferritin concentration greater than 1500 μg/L. Respiratory support was categorised as oxygen only, non-invasive ventilation, and intubation. Initial and repeated measures of hyperinflammation were evaluated in relation to the next-day risk of death or need for escalation of respiratory support (as a combined endpoint), using a multi-level logistic regression model. Findings We included 269 patients admitted to one of the study hospitals between March 1 and March 31, 2020, among whom 178 (66%) were eligible for escalation of respiratory support and 91 (34%) patients were not eligible. Of the whole cohort, 90 (33%) patients met the COV-HI criteria at admission. Despite having a younger median age and lower median Charlson Comorbidity Index scores, a higher proportion of patients with COV-HI on admission died during follow-up (36 [40%] of 90 patients) compared with the patients without COV-HI on admission (46 [26%] of 179). Among the 178 patients who were eligible for full respiratory support, 65 (37%) met the definition for COV-HI at admission, and 67 (74%) of the 90 patients whose respiratory care was escalated met the criteria by the day of escalation. Meeting the COV-HI criteria was significantly associated with the risk of next-day escalation of respiratory support or death (hazard ratio 2·24 [95% CI 1·62–2·87]) after adjustment for age, sex, and comorbidity. Interpretation Associations between elevated inflammatory markers, escalation of respiratory support, and survival in people with COVID-19 indicate the existence of a high-risk inflammatory phenotype. COV-HI might be useful to stratify patient groups in trial design. Funding None.

COVID-19-associated hyperinflammation and escalation of patient care: a retrospective longitudinal cohort study.

Background: COVID-19 has infected millions of people worldwide and is responsible for several hundred thousand fatalities. The COVID-19 pandemic has necessitated thoughtful resource allocation and early identification of high-risk patients. However, effective methods to meet these needs are lacking.
Objective: The aims of this study were to analyze the electronic health records (EHRs) of patients who tested positive for COVID-19 and were admitted to hospitals in the Mount Sinai Health System in New York City; to develop machine learning models for making predictions about the hospital course of the patients over clinically meaningful time horizons based on patient characteristics at admission; and to assess the performance of these models at multiple hospitals and time points.
Methods: We used Extreme Gradient Boosting (XGBoost) and baseline comparator models to predict in-hospital mortality and critical events at time windows of 3, 5, 7, and 10 days from admission. Our study population included harmonized EHR data from five hospitals in New York City for 4098 COVID-19–positive patients admitted from March 15 to May 22, 2020. The models were first trained on patients from a single hospital (n=1514) before or on May 1, externally validated on patients from four other hospitals (n=2201) before or on May 1, and prospectively validated on all patients after May 1 (n=383). Finally, we established model interpretability to identify and rank variables that drive model predictions.
Results: Upon cross-validation, the XGBoost classifier outperformed baseline models, with an area under the receiver operating characteristic curve (AUC-ROC) for mortality of 0.89 at 3 days, 0.85 at 5 and 7 days, and 0.84 at 10 days. XGBoost also performed well for critical event prediction, with an AUC-ROC of 0.80 at 3 days, 0.79 at 5 days, 0.80 at 7 days, and 0.81 at 10 days. In external validation, XGBoost achieved an AUC-ROC of 0.88 at 3 days, 0.86 at 5 days, 0.86 at 7 days, and 0.84 at 10 days for mortality prediction. Similarly, the unimputed XGBoost model achieved an AUC-ROC of 0.78 at 3 days, 0.79 at 5 days, 0.80 at 7 days, and 0.81 at 10 days. Trends in performance on prospective validation sets were similar. At 7 days, acute kidney injury on admission, elevated LDH, tachypnea, and hyperglycemia were the strongest drivers of critical event prediction, while higher age, anion gap, and C-reactive protein were the strongest drivers of mortality prediction.
Conclusions: We externally and prospectively trained and validated machine learning models for mortality and critical events for patients with COVID-19 at different time horizons. These models identified at-risk patients and uncovered underlying relationships that predicted outcomes.

/pdf/machine-learning-to-predict-mortality-and-critical-events-in-2wm6m1ads7.pdf

Machine Learning to Predict Mortality and Critical Events in a Cohort of Patients With COVID-19 in New York City: Model Development and Validation.

Colloquially known as coronavirus, the Severe Acute Respiratory Syndrome CoronaVirus 2 (SARS-CoV-2), that causes CoronaVirus Disease 2019 (COVID-19), has become a matter of grave concern for every country around the world. The rapid growth of the pandemic has wreaked havoc and prompted the need for immediate reactions to curb the effects. To manage the problems, many research in a variety of area of science have started studying the issue. Artificial Intelligence is among the area of science that has found great applications in tackling the problem in many aspects. Here, we perform an overview on the applications of AI in a variety of fields including diagnosis of the disease via different types of tests and symptoms, monitoring patients, identifying severity of a patient, processing covid-19 related imaging tests, epidemiology, pharmaceutical studies, etc. The aim of this paper is to perform a comprehensive survey on the applications of AI in battling against the difficulties the outbreak has caused. Thus we cover every way that AI approaches have been employed and to cover all the research until the writing of this paper. We try organize the works in a way that overall picture is comprehensible. Such a picture, although full of details, is very helpful in understand where AI sits in current pandemonium. We also tried to conclude the paper with ideas on how the problems can be tackled in a better way and provide some suggestions for future works.

/pdf/applications-of-artificial-intelligence-in-battling-against-18cfgukc2t.pdf

Applications of artificial intelligence in battling against covid-19: A literature review.

The SARS-COV-2 pandemic has put pressure on intensive care units, so that identifying predictors of disease severity is a priority. We collect 58 clinical and biological variables, and chest CT scan data, from 1003 coronavirus-infected patients from two French hospitals. We train a deep learning model based on CT scans to predict severity. We then construct the multimodal AI-severity score that includes 5 clinical and biological variables (age, sex, oxygenation, urea, platelet) in addition to the deep learning model. We show that neural network analysis of CT-scans brings unique prognosis information, although it is correlated with other markers of severity (oxygenation, LDH, and CRP) explaining the measurable but limited 0.03 increase of AUC obtained when adding CT-scan information to clinical variables. Here, we show that when comparing AI-severity with 11 existing severity scores, we find significantly improved prognosis performance; AI-severity can therefore rapidly become a reference scoring approach.

/pdf/integrating-deep-learning-ct-scan-model-biological-and-wxnpvda04j.pdf

Integrating deep learning CT-scan model, biological and clinical variables to predict severity of COVID-19 patients.

The sudden deterioration of patients with novel coronavirus disease 2019 (COVID-19) into critical illness is of major concern. It is imperative to identify these patients early. We show that a deep learning-based survival model can predict the risk of COVID-19 patients developing critical illness based on clinical characteristics at admission. We develop this model using a cohort of 1590 patients from 575 medical centers, with internal validation performance of concordance index 0.894 We further validate the model on three separate cohorts from Wuhan, Hubei and Guangdong provinces consisting of 1393 patients with concordance indexes of 0.890, 0.852 and 0.967 respectively. This model is used to create an online calculation tool designed for patient triage at admission to identify patients at risk of severe illness, ensuring that patients at greatest risk of severe illness receive appropriate care as early as possible and allow for effective allocation of health resources.

/pdf/early-triage-of-critically-ill-covid-19-patients-using-deep-4nch8kd6vt.pdf

Early triage of critically ill COVID-19 patients using deep learning

/pdf/addendum-early-triage-of-critically-ill-covid-19-patients-1j1u7qu1j2.pdf

Addendum: Early triage of critically ill COVID-19 patients using deep learning.

Aniridia is an autosomal dominant disorder characterized by the complete or partial loss of the iris and is almost associated with mutations in the paired box gene 6 (PAX6). We examined three generations of a Chinese family with congenital aniridia and observed genetic defects. Exons of PAX6 from 12 family members were amplified by polymerase chain reaction, sequenced, and compared with reference sequences in NCBI reference sequence database (http://www.ncbi.nlm.nih.gov/nuccore/ NG_008679.1?from=5001&to=38170&report=genbank). A rare mutation c.2T>A (M1K) in exon 4 of PAX6 was identified in all affected family members but not in unaffected family members. Our results suggest that the c.2T>A (M1K) mutation may be responsible for the pathogenesis of congenital aniridia in this family. To our knowledge, this is the first report of the M1K mutation in PAX6 in a Chinese family with this disease and the second report worldwide.

/pdf/a-rare-pax6-mutation-in-a-chinese-family-with-congenital-2xmbugq6pq.pdf

Ligong Lu

Papers

Early triage of critically ill COVID-19 patients using deep learning

Addendum: Early triage of critically ill COVID-19 patients using deep learning.

A rare PAX6 mutation in a Chinese family with congenital aniridia.