Personalized stratification of back to work risk amidst COVID-19: A machine learning approach (Preprint)

2020 ◽  
Author(s):  
Carson Lam ◽  
Jacob Calvert ◽  
Gina Barnes ◽  
Emily Pellegrini ◽  
Anna Lynn-Palevsky ◽  
...  
Keyword(s):  
Machine Learning ◽  
High Risk ◽  
Learning Algorithm ◽  
Severe Disease ◽  
High Specificity ◽  
Population Level ◽  
The United States ◽  
Health Condition ◽  
Available P ◽  
Severe Illness

BACKGROUND In the wake of COVID-19, the United States has developed a three stage plan to outline the parameters to determine when states may reopen businesses and ease travel restrictions. The guidelines also identify subpopulations of Americans that should continue to stay at home due to being at high risk for severe disease should they contract COVID-19. These guidelines were based on population level demographics, rather than individual-level risk factors. As such, they may misidentify individuals at high risk for severe illness and who should therefore not return to work until vaccination or widespread serological testing is available. OBJECTIVE This study evaluated a machine learning algorithm for the prediction of serious illness due to COVID-19 using inpatient data collected from electronic health records. METHODS The algorithm was trained to identify patients for whom a diagnosis of COVID-19 was likely to result in hospitalization, and compared against four U.S policy-based criteria: age over 65, having a serious underlying health condition, age over 65 or having a serious underlying health condition, and age over 65 and having a serious underlying health condition. RESULTS This algorithm identified 80% of patients at risk for hospitalization due to COVID-19, versus at most 62% that are identified by government guidelines. The algorithm also achieved a high specificity of 95%, outperforming government guidelines. CONCLUSIONS This algorithm may help to enable a broad reopening of the American economy while ensuring that patients at high risk for serious disease remain home until vaccination and testing become available.

scholarly journals Unsupervised Phenotypic Clustering for Determining Clinical Status in Children with Cystic Fibrosis

2021 ◽  
pp. 2002881
Author(s):  
Nicole Filipow ◽  
Gwyneth Davies ◽  
Eleanor Main ◽  
Neil J. Sebire ◽  
Colin Wallis ◽  
...  
Keyword(s):  
Machine Learning ◽  
Cystic Fibrosis ◽  
Lung Function ◽  
Disease Severity ◽  
Learning Algorithm ◽  
Severe Disease ◽  
Clinical Status ◽  
Oral Antibiotics ◽  
Multisystem Disease ◽  
Street Hospital

BackgroundCystic Fibrosis (CF) is a multisystem disease in which assessing disease severity based on lung function alone may not be appropriate. The aim of the study was to develop a comprehensive machine-learning algorithm to assess clinical status independent of lung function in children.MethodsA comprehensive prospectively collected clinical database (Toronto, Canada) was used to apply unsupervised cluster analysis. The defined clusters were then compared by current and future lung function, risk of future hospitalisation, and risk of future pulmonary exacerbation (PEx) treated with oral antibiotics. A K-Nearest Neighbours (KNN) algorithm was used to prospectively assign clusters. The methods were validated in a paediatric clinical CF dataset from Great Ormond Street Hospital (GOSH).ResultsThe optimal cluster model identified four (A-D) phenotypic clusters based on 12 200 encounters from 530 individuals. Two clusters (A,B) consistent with mild disease were identified with high FEV1, and low risk of both hospitalisation and PEx treated with oral antibiotics. Two clusters (C,D) consistent with severe disease were also identified with low FEV1. Cluster D had the shortest time to both hospitalisation and PEx treated with oral antibiotics. The outcomes were consistent in 3124 encounters from 171 children at GOSH. The KNN cluster allocation error rate was low, at 2.5% (Toronto), and 3.5% (GOSH).ConclusionMachine learning derived phenotypic clusters can predict disease severity independent of lung function and could be used in conjunction with functional measures to predict future disease trajectories in CF patients.

scholarly journals Predicting Venous Thrombosis in Osteoarthritis Using a Machine Learning Algorithm: A Population-Based Cohort Study

2022 ◽  
Vol 12 (1) ◽  
pp. 114
Author(s):  
Chao Lu ◽  
Jiayin Song ◽  
Hui Li ◽  
Wenxing Yu ◽  
Yangquan Hao ◽  
...  
Keyword(s):  
Machine Learning ◽  
Cohort Study ◽  
High Risk ◽  
Venous Thrombosis ◽  
Learning Algorithm ◽  
Population Based ◽  
Joint Disease ◽  
Recursive Feature Elimination ◽  
Machine Learning Algorithm ◽  
Interpretable Machine Learning

Osteoarthritis (OA) is the most common joint disease associated with pain and disability. OA patients are at a high risk for venous thrombosis (VTE). Here, we developed an interpretable machine learning (ML)-based model to predict VTE risk in patients with OA. To establish a prediction model, we used six ML algorithms, of which 35 variables were employed. Recursive feature elimination (RFE) was used to screen the most related clinical variables associated with VTE. SHapley additive exPlanations (SHAP) were applied to interpret the ML mode and determine the importance of the selected features. Overall, 3169 patients with OA (average age: 66.52 ± 7.28 years) were recruited from Xi’an Honghui Hospital. Of these, 352 and 2817 patients were diagnosed with and without VTE, respectively. The XGBoost algorithm showed the best performance. According to the RFE algorithms, 15 variables were retained for further modeling with the XGBoost algorithm. The top three predictors were Kellgren–Lawrence grade, age, and hypertension. Our study showed that the XGBoost model with 15 variables has a high potential to predict VTE risk in patients with OA.

scholarly journals Optimizing antiviral treatment for seasonal influenza in the United States: A Mathematical Modeling Analysis

2020 ◽  
Author(s):  
Matan Yechezkel ◽  
Martial Ndeffo-Mba ◽  
Dan Yamin
Keyword(s):  
United States ◽  
High Risk ◽  
Seasonal Influenza ◽  
Antiviral Treatment ◽  
Social Contact ◽  
Population Level ◽  
The United States ◽  
Transmission Model ◽  
High Risk Patients ◽  
Risk Patients

Seasonal influenza remains a major health burden in the United States. Despite recommendations of early antiviral treatment of high-risk patients, the effective treatment coverage remains very low. We developed an influenza transmission model that incorporates data on infectious viral load, social contact, and healthcare-seeking behavior, to evaluate the population-level impact of increasing antiviral treatment timeliness and coverage among high-risk patients in the US. We found that increasing the rate of early treatment among high-risk patients who received treatment more than 48 hours after symptoms onset, would substantially avert infections and influenza-induced hospitalizations. We found that treatment of the elderly has the highest impact on reducing hospitalizations, whereas treating high-risk individuals aged 5-19 years old has the highest impact on transmission. The population-level impact of increased timeliness and coverage of treatment among high-risk patients was observed regardless of seasonal influenza vaccination coverage and the severity of the influenza season.

scholarly journals 438. Phenotypic Differences Between Distinct Immune Biomarker Clusters During the ‘Hyperinflammatory’ Middle-Phase of COVID-19

2021 ◽  
Vol 8 (Supplement_1) ◽  
pp. S320-S321
Author(s):  
Paul W Blair ◽  
Joost Brandsma ◽  
Nusrat J Epsi ◽  
Stephanie A Richard ◽  
Deborah Striegel ◽  
...  
Keyword(s):  
Machine Learning ◽  
Data Analysis ◽  
Pulmonary Disease ◽  
The United States ◽  
Phase Iii ◽  
Severe Illness ◽  
Stepwise Logistic Regression ◽  
Chronic Pulmonary Disease ◽  
Middle Phase ◽  
Broad Dynamic Range

Abstract Background Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infections peak during an inflammatory ‘middle’ phase and lead to severe illness predominately among those with certain comorbid noncommunicable diseases (NCDs). We used network machine learning to identify inflammation biomarker patterns associated with COVID-19 among those with NCDs. Methods SARS-CoV-2 RT-PCR positive subjects who had specimens available within 15-28 days post-symptom onset were selected from the DoD/USU EPICC COVID-19 cohort study. Plasma levels of 15 inflammation protein biomarkers were measured using a broad dynamic range immunoassay on samples collected from individuals with COVID-19 at 8 military hospitals across the United States. A network machine learning algorithm, topological data analysis (TDA), was performed using results from the ‘hyperinflammatory’ middle phase. Backward selection stepwise logistic regression was used to identify analytes associated with each cluster. NCDs with a significant association (0.05 significance level) across clusters using Fisher’s exact test were further evaluated comparing the NCD frequency in each cluster against all other clusters using a Kruskal-Wallis test. A sensitivity analysis excluding mild disease was also performed. Results The analysis population (n=129, 33.3% female, median 41.3 years of age) included 77 ambulatory, 31 inpatient, 16 ICU-level, and 5 fatal cases. TDA identified 5 unique clusters (Figure 1). Stepwise regression with a Bonferroni-corrected cutoff adjusted for severity identified representative analytes for each cluster (Table 1). The frequency of diabetes (p=0.01), obesity (p< 0.001), and chronic pulmonary disease (p< 0.001) differed among clusters. When restricting to hospitalized patients, obesity (8 of 11), chronic pulmonary disease (6 of 11), and diabetes (6 of 11) were more prevalent in cluster C than all other clusters. Cluster differences in comorbid diseases and severity by cluster. 1A: bar plot of diabetes prevalence; 1B: bar plot of chronic lung disease ; 1C: bar plot of obesity prevalence; 1D: prevalence of steroid treatment ; 1E: Topologic data analysis network with clusters labeled; 1F: Bar plot of ordinal levels of severity. Conclusion Machine learning clustering methods are promising analytical tools for identifying inflammation marker patterns associated with baseline risk factors and severe illness due to COVID-19. These approaches may offer new insights for COVID19 prognosis, therapy, and prevention. Disclosures Simon Pollett, MBBS, Astra Zeneca (Other Financial or Material Support, HJF, in support of USU IDCRP, funded under a CRADA to augment the conduct of an unrelated Phase III COVID-19 vaccine trial sponsored by AstraZeneca as part of USG response (unrelated work))

scholarly journals Smoking and Comorbidities in Covid-19: A Systematic Review

2020 ◽  
Vol 9 (2) ◽  
pp. 117-125
Author(s):  
Andri Nugraha ◽  
Ernawati Ernawati ◽  
Tuti Anggriani Utama ◽  
Santi Rinjani
Keyword(s):  
Systematic Review ◽  
Intensive Care Unit ◽  
Intensive Care ◽  
Respiratory Failure ◽  
High Risk ◽  
Full Text ◽  
Severe Disease ◽  
Severe Illness ◽  
Severe Infections

COVID-19 is highly contagious, causing pneumonia, respiratory failure, death, and becoming a pandemic. Patients with severe infections must be treated in the Intensive Care Unit (ICU) with a ventilator. Ventilator facilities in the ICU are limited; it must take precautions by knowing the characteristics of patients at high risk of severe disease in COVID-19, one of which was smoking or comorbidity. The purpose of this study was to assess the risk of comorbidity and smoking in COVID-19. This study used systematic review by searching for articles from the ScienceDirect and Medline databases with journals published on January 1, 2019 - March 31, 2020. The results of the study showed that there were 12 relevant articles full text in English and were analysed. The conclusion was that patients with COVID-19 who were smoking or had comorbidities were more susceptible to COVID-19 infection, more severe illness, and causing death.

scholarly journals Hospitalized COVID-19 Patients treated with Convalescent Plasma in a Mid-size City in the Midwest

2020 ◽  
Author(s):  
William Hartman ◽  
Aaron S Hess ◽  
Joseph P Connor
Keyword(s):  
Mechanical Ventilation ◽  
Care Center ◽  
Severe Disease ◽  
Tertiary Care ◽  
The United States ◽  
Severe Illness ◽  
Care Needs ◽  
Course Of Disease ◽  
Effective Option ◽  
Life Threatening

AbstractBackgroundSARS-CoV-2 and its associated disease, COVID-19, has infected over seven million people world-wide, including two million people in the United States. While many people recover from the virus uneventfully, a subset of patients will require hospital admission, some with intensive care needs including intubation, and mechanical ventilation. To date there is no cure and no vaccine is available. Passive immunotherapy by the transfusion of convalescent plasma donated by COVID-19 recovered patients might be an effective option to combat the virus, especially if used early in the course of disease. Here we report our experience of using convalescent plasma at a tertiary care center in a mid-size, midwestern city that did not experience an overwhelming patient surge.MethodsHospitalized COVID-19 patients categorized as having Severe or Life-Threatening disease according to the Mayo Clinic Emergency Access Protocol were screened, consented, and treated with convalescent plasma collected from local donors recovered from COVID-19 infection. Clinical data and outcomes were collected retrospectively.Results31 patients were treated, 16 severe patients and 15 life-threatened patients. Overall mortality was 27% (4/31) but only patients with life-threatening disease died. 94% of transfused patients with severe disease avoided escalation to ICU care and mechanical ventilation. 67% of patients with life-threatening disease were able to be extubated. Most transfused patients had a rapid decrease in their respiratory support requirements on or about day 7 following convalescent plasma transfusion.ConclusionOur results demonstrate that convalescent plasma is associated with reducing ventilatory requirements in patients with both severe and life-threatening disease, but appears to be most beneficial when administered early in the course of disease when patients meet the criteria for severe illness.

Determination of Time-to-Failure for Automotive System Components Using Machine Learning

2020 ◽  
Vol 20 (6) ◽  
Author(s):  
John O’Donnell ◽  
Hwan-Sik Yoon
Keyword(s):  
Machine Learning ◽  
Degradation Rate ◽  
Shock Absorber ◽  
Learning Algorithm ◽  
Health Condition ◽  
Performance Degradation ◽  
Remaining Useful Life ◽  
Machine Learning Algorithm ◽  
Time To Failure ◽  
And Performance

Abstract In recent years, there has been a growing interest in the connectivity of vehicles. This connectivity allows for the monitoring and analysis of large amount of sensor data from vehicles during their normal operations. In this paper, an approach is proposed for analyzing such data to determine a vehicle component’s remaining useful life named time-to-failure (TTF). The collected data is first used to determine the type of performance degradation and then to train a regression model to predict the health condition and performance degradation rate of the component using a machine learning algorithm. When new data is collected later for the same component in a different system, the trained model can be used to estimate the time-to-failure of the component based on the predicted health condition and performance degradation rate. To validate the proposed approach, a quarter-car model is simulated, and a machine learning algorithm is applied to determine the time-to-failure of a failing shock absorber. The results show that a tap-delayed nonlinear autoregressive network with exogenous input (NARX) can accurately predict the health condition and degradation rate of the shock absorber and can estimate the component’s time-to-failure. To the best of the authors’ knowledge, this research is the first attempt to determine a component’s time-to-failure using a machine learning algorithm.

scholarly journals Hospitalized COVID-19 patients treated with convalescent plasma in a mid-size city in the Midwest

2020 ◽  
Vol 5 (1) ◽  
Author(s):  
William R. Hartman ◽  
Aaron S. Hess ◽  
Joseph P. Connor
Keyword(s):  
Mechanical Ventilation ◽  
Care Center ◽  
Severe Disease ◽  
Tertiary Care ◽  
The United States ◽  
Severe Illness ◽  
Care Needs ◽  
Course Of Disease ◽  
Effective Option ◽  
Life Threatening

Abstract Background SARS-CoV-2 and its associated disease, COVID-19, has infected over seven million people world-wide, including two million people in the United States. While many people recover from the virus uneventfully, a subset of patients will require hospital admission, some with intensive care needs including intubation, and mechanical ventilation. To date there is no cure and no vaccine is available. Passive immunotherapy by the transfusion of convalescent plasma donated by COVID-19 recovered patients might be an effective option to combat the virus, especially if used early in the course of disease. Here we report our experience of using convalescent plasma at a tertiary care center in a mid-size, midwestern city that did not experience an overwhelming patient surge. Methods Hospitalized COVID-19 patients categorized as having Severe or Life-Threatening disease according to the Mayo Clinic Emergency Access Protocol were screened, consented, and treated with convalescent plasma collected from local donors recovered from COVID-19 infection. Clinical data and outcomes were collected retrospectively. Results 31 patients were treated, 16 severe patients and 15 life-threatened patients. Overall mortality was 27% (4/31) but only patients with life-threatening disease died. 94% of transfused patients with severe disease avoided escalation to ICU care and mechanical ventilation. 67% of patients with life-threatening disease were able to be extubated. Most transfused patients had a rapid decrease in their respiratory support requirements on or about day 7 following convalescent plasma transfusion. Conclusion Our results demonstrate that convalescent plasma is associated with reducing ventilatory requirements in patients with both severe and life-threatening disease, but appears to be most beneficial when administered early in the course of disease when patients meet the criteria for severe illness.

Sign in / Sign up

Export Citation Format

Share Document