Evaluating a Widely Implemented Proprietary Deterioration Index Model Among Hospitalized COVID-19 Patients

Singh, Karandeep; Valley, Thomas S.; Tang, Shengpu; Li, Benjamin Y.; Kamran, Fahad; Sjoding, Michael W.; Wiens, Jenna; Ötleş, Erkin; Donnelly, John P.; Wei, Melissa Y.; McBride, Jonathon P; Cao, Jie; Penoza, Carleen; Ayanian, John Z.; Nallamothu, Brahmajee K.

doi:10.1101/2020.04.24.20079012

Cited by 35 publications

(53 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There is therefore potential ambiguity about how the algorithm may perform in novel clinical settings or for detecting more rapid patient deterioration. Singh et al [ 33 ] evaluated the Epic Deterioration Index (EDI) prospectively in a population of 174 COVID-19 patients, assessing its performance for a composite outcome of requirement of ICU care, initiation of mechanical ventilation, or in-hospital death. While the EDI showed moderate discrimination for the COVID-19 with a maximum AUC of 0.76, the authors again do not examine ventilation as an individual outcome.…”

Section: Discussionmentioning

confidence: 99%

Prediction of respiratory decompensation in Covid-19 patients using machine learning: The READY trial

Burdick

Lam

Mataraso

et al. 2020

Computers in Biology and Medicine

132

View full text Add to dashboard Cite

Background Currently, physicians are limited in their ability to provide an accurate prognosis for COVID-19 positive patients. Existing scoring systems have been ineffective for identifying patient decompensation. Machine learning (ML) may offer an alternative strategy. A prospectively validated method to predict the need for ventilation in COVID-19 patients is essential to help triage patients, allocate resources, and prevent emergency intubations and their associated risks. Methods In a multicenter clinical trial, we evaluated the performance of a machine learning algorithm for prediction of invasive mechanical ventilation of COVID-19 patients within 24 h of an initial encounter. We enrolled patients with a COVID-19 diagnosis who were admitted to five United States health systems between March 24 and May 4, 2020. Results 197 patients were enrolled in the REspirAtory Decompensation and model for the triage of covid-19 patients: a prospective studY (READY) clinical trial. The algorithm had a higher diagnostic odds ratio (DOR, 12.58) for predicting ventilation than a comparator early warning system, the Modified Early Warning Score (MEWS). The algorithm also achieved significantly higher sensitivity (0.90) than MEWS, which achieved a sensitivity of 0.78, while maintaining a higher specificity (p < 0.05). Conclusions In the first clinical trial of a machine learning algorithm for ventilation needs among COVID-19 patients, the algorithm demonstrated accurate prediction of the need for mechanical ventilation within 24 h. This algorithm may help care teams effectively triage patients and allocate resources. Further, the algorithm is capable of accurately identifying 16% more patients than a widely used scoring system while minimizing false positive results.

show abstract

Section: Discussionmentioning

confidence: 99%

Prediction of respiratory decompensation in Covid-19 patients using machine learning: The READY trial

Burdick

Lam

Mataraso

et al. 2020

Computers in Biology and Medicine

132

View full text Add to dashboard Cite

show abstract

“…Major differences in sampling: due to differences in the age of the patients (which we will address next); or due to exclusively including patients diagnosed by chest CT [34] (which is more sensitive than plain radiography); or excluding patients who already present in a severe condition [35][36][37][38] (because their objective is to study the progression from non-severe to severe); or limiting follow-up to a short period which does not allow to reach the outcome of interest to a signi cant proportion of included patients, [39,40] and therefore rising signi cant risk of selection bias that will be later discussed.…”

Section: Discussionmentioning

confidence: 99%

Prognosis of COVID-19 Pneumonia Can Be Early Predicted Combining Age-Adjusted Charlson Comorbidity Index, CRB Score and Baseline Oxygen Saturation.

Nuevo-Ortega

Reina-Artacho

Dominguez-Moreno

et al. 2021

Preprint

View full text Add to dashboard Cite

Background: In potentially severe diseases in general and COVID-19 in particular, it is vital to early identify those patients who are going to develop complications. The last update of a recent living systematic review dedicated to predictive models in COVID-19,[1] critically appraises 145 models, 8 of them focused on prediction of severe disease and 23 on mortality. Unfortunately, in all 145 models, they found a risk of bias significant enough to finally "not recommend any for clinical use". Authors suggest concentrating on avoiding biases in sampling and prioritising the study of already identified predictive factors, rather than the identification of new ones that are often dependent on the database. Our objective is to develop a model to predict which patients with COVID-19 pneumonia are at high risk of developing severe illness or dying, using basic and validated clinical tools.Methods: prospective cohort of consecutive patients admitted in a teaching hospital during the “first wave” of the COVID-19 pandemic. Follow-up to discharge from hospital. Multiple logistic regression selecting variables according to clinical and statistical criteria. Results: 404 consecutive patients were evaluated, 392 (97%) completed follow-up. Mean age was 61 years; 59% were men. The median burden of comorbidity was 2 points in the Age-adjusted Charlson Comorbidity Index, CRB was abnormal in 18% of patients and basal oxygen saturation on admission lower than 90% in 18%. A model composed of Age-adjusted Charlson Comorbidity Index, CRB score and basal oxygen saturation can predict unfavorable evolution or death with an area under the ROC curve of 0.85 (95% CI: 0.80-0.89), and 0.90 (95% CI: 0.86 to 0.94), respectively.Conclusion: prognosis of COVID-19 pneumonia can be predicted in the out-of-hospital environment using two classic prognostic scales and a pocket pulse oximeter.

show abstract

“…There is a number of studies investigating severity [6][7][8][9][10][11][12] and mortality [8,[13][14][15][16] neutrophil and lymphocyte count, D-dimer, AST and GFR) mortality-prediction models were developed.…”

Section: Discussionmentioning

confidence: 99%

“…predictors in COVID-19 infection. Some of the studies reported that they developed scores or models for the prediction of disease severity[6][7][8][9][10][11][12]. Shi et al de ned a host risk score consisting of three parameters (age, sex, hypertension) and reported an increase in severe infection risk with the increasing score point (from 0 to 3)[12].…”

mentioning

confidence: 99%

Ankara City Hospital COVID-19 Severity Score (ACCSES):A Calculation Tool in the Prediction of Severe Illness Requiring Intensive Care Follow-up

Güner¹,

Kayaaslan²,

Hasanoğlu³

et al. 2020

Preprint

View full text Add to dashboard Cite

Aim: The aim of this study is to develop and explain an easy-to-use severity score calculation tool to predict severe COVID-19 cases that would need intensive care unit (ICU) follow-up.Material method: The study was carried out in patients with laboratory-confirmed COVID-19 hospitalized in Ankara City Hospital between March 15, 2020, and June 15, 2020. The outcome was severe illness that required ICU follow-up. Univariate and binary logistic regression were used to create a prediction model by using potential predictive parameters obtained on the day of hospitalization. Youden’s J index was calculated with receiver-operator characteristic curves analysis in order to evaluate cut-off points, and predicted probability was calculated. The accuracy of the prediction model was tested by calculating the area under curve (AUC). Results: Of the total of 1022 patients, 152 had a severe illness and required ICU follow-up. Among 68 variables, 20 parameters met the potential predictive factor condition for severe illness and were included in the development process for ANKARA CITY HOSPITAL COVID-19 SEVERITY SCORE (ACCSES). The ACCSES calculation tool was created by the final 9 parameters (sex, oxygen saturation, hemoglobin, platelet count, glomerular filtration rate, aspartate transaminase, procalcitonin, ferritin, and D-dimer). AUC was 0.96 (95% CI, 0.95-0.98).Conclusion: We developed a simple, accessible, easy to use calculation tool, ACCSES, with good distinctive power for a severe illness that required ICU follow-up. The clinician can easily predict the course of COVID-19 and decide the procedure and facility of further follow-up simply using available clinical and laboratory values of patients upon admission.

show abstract

Evaluating a Widely Implemented Proprietary Deterioration Index Model Among Hospitalized COVID-19 Patients

Cited by 35 publications

References 12 publications

Prediction of respiratory decompensation in Covid-19 patients using machine learning: The READY trial

Prediction of respiratory decompensation in Covid-19 patients using machine learning: The READY trial

Prognosis of COVID-19 Pneumonia Can Be Early Predicted Combining Age-Adjusted Charlson Comorbidity Index, CRB Score and Baseline Oxygen Saturation.

Ankara City Hospital COVID-19 Severity Score (ACCSES):A Calculation Tool in the Prediction of Severe Illness Requiring Intensive Care Follow-up

Contact Info

Product

Resources

About