A Machine Learning Model Reveals Older Age and Delayed Hospitalization as Predictors of Mortality in Patients with COVID-19

Sarkar, Jit; Chakrabarti, Partha

doi:10.1101/2020.03.25.20043331

Cited by 46 publications

(41 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In some studies, older age was reported as a factor associated with mortality in SARS and MERS (25). The current study confirmed that old age was associated with mortality in patients with COVID-19, which is consistent with the findings of previous studies (22,24,26). In the univariate analysis, underlying diseases such as cardiovascular disease and hypertension were associated with mortality, as was reported similarly by Jordan (24).…”

Section: Discussionsupporting

confidence: 92%

Association of Underlying Diseases and Clinical Characteristics with Mortality in Patients with 2019 Novel Coronavirus in Iran

Zamanian

Foroozanfar

Izadi

et al. 2020

Arch Clin Infect Dis

View full text Add to dashboard Cite

Objectives: The first case of 2019 novel coronavirus disease (COVID-19) was reported in Iran in February 2020. Here, we report the epidemiological and clinical characteristics of patients with COVID-19 and factors associated with mortality in these patients. Methods: A retrospective cohort study was conducted from February 22, 2020, to March 24, 2020, in Golestan Hospital in Kermanshah, Iran. Demographic data including underlying diseases and clinical data including the presenting symptoms, chest computed tomography (CT) scan, reverse transcription polymerase chain reaction (RT-PCR) test results, and outcomes were extracted from electronic medical records. Simple and multiple logistic regression methods were used to explore the factors associated with mortality. Results: Of 245 patients admitted with COVID-19, 155 (63.30%) were male. The mean age of the subjects was 54.68 ± 19.21. Forty-five (18.48%) patients had underlying diseases. Common symptoms were dyspnea (n = 137; 55.9%), cough (n = 93; 38.0%), and fever (n = 78; 31.8%). All patients had pneumonia with abnormal findings on chest CT scan (100%), and RT-PCR test results were positive in 87 (35.50%) patients. Of the total admitted cases, 38 (15.5%) patients died during hospitalization. An old age (OR = 1.09; 95% CI: 1.02 to 1.06), history of heart disease (OR = 5.07; 95% CI: 1.46 to 17.58), hypertension (OR = 5.82; 95% CI: 1.13 to 30.04), smoking (OR = 11.44; 95% CI: 1.01 to 29.53), history of at least one underlying disease (OR = 3.31; 95%CI: 1.54 to 7.09), and symptoms of decreased consciousness at the time of admission (OR = 24.23; 95% CI: 2.62 to 223.39) were associated with mortality. Also, the symptoms of cough (OR = 0.383; 95% CI: 0.17 to 0.88) and fever (OR = 0.278; 95% CI: 0.10 to 0.74) had a negative association with mortality. Conclusions: In the current study, factors including old age, smoking, symptoms of decreased consciousness, and underlying diseases such as heart disease, hypertension, and history of at least one underlying disease were associated with mortality. Factors associated with mortality should be considered so that we can better manage patients with COVID-19.

show abstract

Section: Discussionsupporting

confidence: 92%

Association of Underlying Diseases and Clinical Characteristics with Mortality in Patients with 2019 Novel Coronavirus in Iran

Zamanian

Foroozanfar

Izadi

et al. 2020

Arch Clin Infect Dis

View full text Add to dashboard Cite

show abstract

“…Several clinical predictive models have recently been proposed for COVID-19, for example, for predicting potential COVID-19 diagnoses using data from emergency care admission exams [ 60 ] and chest imaging data [ 61 - 66 ], for predicting COVID-19–related mortality from clinical risk factors [ 67 , 68 ], for predicting which patients will develop acute respiratory distress syndrome from patients’ clinical characteristics [ 69 ], for predicting critical illness in patients with COVID-19 [ 70 , 71 ], and for predicting progression risk in patients with COVID-19 pneumonia [ 72 ]. Siordia [ 73 ] presented a review of epidemiology and clinical features associated with COVID-19, and Wynants et al [ 74 ] performed a critical review that assessed limitations and risk of bias in diagnostic and prognostic models for COVID-19.…”

Section: Discussionmentioning

confidence: 99%

Clinical Predictive Models for COVID-19: Systematic Study

Schwab¹,

Schütte²,

Dietz³

et al. 2020

J Med Internet Res

View full text Add to dashboard Cite

Background COVID-19 is a rapidly emerging respiratory disease caused by SARS-CoV-2. Due to the rapid human-to-human transmission of SARS-CoV-2, many health care systems are at risk of exceeding their health care capacities, in particular in terms of SARS-CoV-2 tests, hospital and intensive care unit (ICU) beds, and mechanical ventilators. Predictive algorithms could potentially ease the strain on health care systems by identifying those who are most likely to receive a positive SARS-CoV-2 test, be hospitalized, or admitted to the ICU. Objective The aim of this study is to develop, study, and evaluate clinical predictive models that estimate, using machine learning and based on routinely collected clinical data, which patients are likely to receive a positive SARS-CoV-2 test or require hospitalization or intensive care. Methods Using a systematic approach to model development and optimization, we trained and compared various types of machine learning models, including logistic regression, neural networks, support vector machines, random forests, and gradient boosting. To evaluate the developed models, we performed a retrospective evaluation on demographic, clinical, and blood analysis data from a cohort of 5644 patients. In addition, we determined which clinical features were predictive to what degree for each of the aforementioned clinical tasks using causal explanations. Results Our experimental results indicate that our predictive models identified patients that test positive for SARS-CoV-2 a priori at a sensitivity of 75% (95% CI 67%-81%) and a specificity of 49% (95% CI 46%-51%), patients who are SARS-CoV-2 positive that require hospitalization with 0.92 area under the receiver operator characteristic curve (AUC; 95% CI 0.81-0.98), and patients who are SARS-CoV-2 positive that require critical care with 0.98 AUC (95% CI 0.95-1.00). Conclusions Our results indicate that predictive models trained on routinely collected clinical data could be used to predict clinical pathways for COVID-19 and, therefore, help inform care and prioritize resources.

show abstract

“…10 Two other studies applied machine learning algorithms to predict mortality in patients with COVID-19, using patient data from Kaggle and China. 11,12 We propose that machine learning algorithms can be used to allocate priorities in receiving the RT-PCR tests in the case of a shortage, and also to help with critical care decisions while the RT-PCR results are being processed (which have been frequently taking more than a week in most places of Brazil). A promising area for future research will also be to analyze the combined performance of the new rapid tests and the machine learning algorithms.…”

Section: Discussionmentioning

confidence: 99%

COVID-19 diagnosis prediction in emergency care patients: a machine learning approach

Batista

et al. 2020

Preprint

114

View full text Add to dashboard Cite

The coronavirus disease pandemic has increased the necessity of immediate clinical decisions and effective usage of healthcare resources. Currently, the most validated diagnosis test for COVID-19 (RT-PCR) is in shortage in most developing countries, which may increase infection rates and delay important preventive measures. The objective of this study was to predict the risk of positive COVID-19 diagnosis with machine learning, using as predictors only results from emergency care admission exams. We collected data from 235 adult patients from the Hospital Israelita Albert Einstein in São Paulo, Brazil, from 17 to 30 of March, 2020, of which 102 (43%) received a positive diagnosis of COVID-19 from RT-PCR tests. Five machine learning algorithms (neural networks, random forests, gradient boosting trees, logistic regression and support vector machines) were trained on a random sample of 70% of the patients, and performance was tested on new unseen data (30%). The best predictive performance was obtained by the support vector machines algorithm (AUC: 0.85; Sensitivity: 0.68; Specificity: 0.85; Brier Score: 0.16). The three most important variables for the predictive performance of the algorithm were the number of lymphocytes, leukocytes and eosinophils, respectively. In conclusion, we found that targeted decisions for receiving COVID-19 tests using only routinely-collected data is a promising new area with the use of machine learning algorithms.

show abstract

A Machine Learning Model Reveals Older Age and Delayed Hospitalization as Predictors of Mortality in Patients with COVID-19

Cited by 46 publications

References 6 publications

Association of Underlying Diseases and Clinical Characteristics with Mortality in Patients with 2019 Novel Coronavirus in Iran

Association of Underlying Diseases and Clinical Characteristics with Mortality in Patients with 2019 Novel Coronavirus in Iran

Clinical Predictive Models for COVID-19: Systematic Study

COVID-19 diagnosis prediction in emergency care patients: a machine learning approach

Contact Info

Product

Resources

About