scholarly journals Predicting critical illness on initial diagnosis of COVID-19 based on easily-obtained clinical variables: development and validation of the PRIORITY model

2021 ◽  
Author(s):  
Miguel Martinez-Lacalzada ◽  
Adrián Viteri-Noël ◽  
Luis Manzano ◽  
Martin Fabregate ◽  
Manuel Rubio-Rivas ◽  
...  
Keyword(s):  
Critical Illness ◽  
Initial Diagnosis ◽  
Clinical Variables ◽  
Development And Validation ◽  
Priority Model

scholarly journals Development and Validation of a Simplified Risk Score for the Prediction of Critical COVID-19 Illness in Newly Diagnosed Patients

2021 ◽  
Author(s):  
Stanislas Werfel ◽  
Carolin E. M. Jakob ◽  
Stefan Borgmann ◽  
Jochen Schneider ◽  
Christoph Spinner ◽  
...  
Keyword(s):  
Critical Illness ◽  
Clinical Decision Making ◽  
Validation Cohort ◽  
Predictive Accuracy ◽  
Clinical Decision ◽  
Increased Risk ◽  
Risk Of Progression ◽  
Risk Of Disease ◽  
Development And Validation

AbstractScores for identifying patients at high risk of progression of the coronavirus disease 2019 (COVID-19), caused by the Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2), are discussed as key instruments for clinical decision-making and patient management during the current pandemic.Here we used the patient data from the multicenter Lean European Open Survey on SARS-CoV-2 - Infected Patients (LEOSS) and applied a technique of variable selection in order to develop a simplified score to identify patients at increased risk of critical illness or death.A total of 1,946 patients, who were tested positive for SARS-CoV-2 were included in the initial analysis. They were split into a derivation and a validation cohort (n=1,297 and 649, respectively). A stability selection among a total of 105 baseline predictors for the combined endpoint of progression to critical phase or COVID-19-related death allowed us to develop a simplified score consisting of five predictors: CRP, Age, clinical disease phase (uncomplicated vs. complicated), serum urea and D-dimer (abbreviated as CAPS-D score). This score showed an AUC of 0.81 (CI95%: 0.77-0.85) in the validation cohort for predicting the combined endpoint within 7 days of diagnosis and 0.81 (CI95%: 0.77-0.85) during the full follow-up. Finally, we used an additional prospective cohort of 682 patients, who were diagnosed largely after the “first wave” of the pandemic to validate predictive accuracy of the score, observing similar results (AUC for an event within 7 days: 0.83, CI95%, 0.78-0.87; for full follow-up: 0.82, CI95%, 0.78-0.86).We thus successfully establish and validate an easily applicable score to calculate the risk of disease progression of COVID-19 to critical illness or death.

Identificación de Variables Clínicas Asociadas al Diagnóstico Correcto e Incorrecto en Enfermedades Respiratorias

2021 ◽  
Author(s):  
◽  
Sinhue Siordia-Millán
Keyword(s):  
Pulmonary Embolism ◽  
Medical Records ◽  
Initial Diagnosis ◽  
Emergency Rooms ◽  
Clinical Variables ◽  
Laboratory Variables ◽  
Data Extracting ◽  
Associative Analysis ◽  
Pneumonia Diagnosis

In emergency rooms, it is common that several patients present symptoms associated with pulmonary diseases as pneumonia and pulmonary embolism, however, their initial diagnosis presents several challenges: a) both share symptoms, b) the lack of imaging studies at the first diagnosis stage and, c) the amount of data resulting from laboratory analysis are vast to be quickly analyzed. Thus, supporting medical staff through the use of computational tools for detecting clinical variables that are significant on the initial diagnosis, is crucial. Hence, a collaboration with the Centro Medico Nacional de Occidente (CMNO) of the Instituto Mexicano del Seguro Social (IMSS) was established to gather, process, and analyze patients' electronic medical records with a pulmonary embolism or pneumonia diagnosis who were admitted through the emergency room. Data extracting and processing of patients’ medical records (PDF) were performed. Thereafter, a statistical and associative analysis (Apriori) was performed looking for the determination of the clinical variables associated with a correct or incorrect prognosis. As a result, during the patient diagnosis several frequently present variables were identified, pointing out those that whose median values were significantly different for both diseases studied here. Finally, some laboratory variables are suggested to be carefully observed while a patient's initial diagnosis is performed.

scholarly journals Development and validation of a knowledge-driven risk calculator for critical illness in COVID-19 patients

2021 ◽  
Vol 39 ◽  
pp. 143-145
Author(s):  
Amos Cahan ◽  
Tamar Gottesman ◽  
Michal Tzuchman Katz ◽  
Roee Masad ◽  
Gal Azulay ◽  
...  
Keyword(s):  
Critical Illness ◽  
Risk Calculator ◽  
Development And Validation

scholarly journals Development and validation of a knowledge-driven risk calculator for critical illness in COVID-19 patients

2020 ◽  
Author(s):  
Amos Cahan ◽  
Tamar Gottesman ◽  
Michal Tzuchman Katz ◽  
Roee Masad ◽  
Gal Azulay ◽  
...  
Keyword(s):  
Risk Assessment ◽  
Intensive Care Unit ◽  
Critical Illness ◽  
Policy Making ◽  
Risk Calculator ◽  
Policy Makers ◽  
Patient Level ◽  
Novel Coronavirus ◽  
Development And Validation ◽  
Inform Decision Making

Facing the rapidly spreading novel coronavirus disease (COVID-19), evidence to inform decision-making at both the clinical and policy-making level is highly needed. Based on the results of a study by Petrilli et al, we have developed a calculator using patient data at admission to predict the risk of critical illness (intensive care unit admission, use of mechanical ventilation, discharge to hospice, or death). We report a retrospective validation of the risk calculator on 145 consecutive patients admitted with COVID-19 to a single hospital in Israel. Of the 18 patients with critical illness, 17 were correctly identified by the model(sensitivity: 94.4%, 95% CI, 72.7% to 99.9%; specificity: 81.9%, 95% CI, 74.1% to 88.2%). Of the 127 patients with non-critical illness, 104 were correctly identified. This, despite considerable differences between the original and validation study populations. Our results show that data from published knowledge can be used to provide reliable, patient level, automated risk assessment, potentially reducing the cognitive burden on physicians and helping policy makers better prepare for future needs.

scholarly journals OASIS +: leveraging machine learning to improve the prognostic accuracy of OASIS severity score for predicting in-hospital mortality

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Yasser EL-Manzalawy ◽  
Mostafa Abbas ◽  
Ian Hoaglund ◽  
Alvaro Ulloa Cerna ◽  
Thomas B. Morland ◽  
...  
Keyword(s):  
Machine Learning ◽  
Critical Illness ◽  
Hospital Mortality ◽  
Scoring Function ◽  
Severity Of Illness ◽  
Predictive Performance ◽  
Additive Models ◽  
Clinical Variables ◽  
Prognostic Accuracy ◽  
Severity Scores

Abstract Background Severity scores assess the acuity of critical illness by penalizing for the deviation of physiologic measurements from normal and aggregating these penalties (also called “weights” or “subscores”) into a final score (or probability) for quantifying the severity of critical illness (or the likelihood of in-hospital mortality). Although these simple additive models are human readable and interpretable, their predictive performance needs to be further improved. Methods We present OASIS +, a variant of the Oxford Acute Severity of Illness Score (OASIS) in which an ensemble of 200 decision trees is used to predict in-hospital mortality based on the 10 same clinical variables in OASIS. Results Using a test set of 9566 admissions extracted from the MIMIC-III database, we show that OASIS + outperforms nine previously developed severity scoring methods (including OASIS) in predicting in-hospital mortality. Furthermore, our results show that the supervised learning algorithms considered in our experiments demonstrated higher predictive performance when trained using the observed clinical variables as opposed to OASIS subscores. Conclusions Our results suggest that there is room for improving the prognostic accuracy of the OASIS severity scores by replacing the simple linear additive scoring function with more sophisticated non-linear machine learning models such as RF and XGB.

18: Measuring Quality-of-Life after Surgery: Development and Validation of the Convalescence and Recovery Evaluation (CARE)

2007 ◽  
Vol 177 (4S) ◽  
pp. 7-7
Author(s):  
Brent K. Hollenbeck ◽  
J. Stuart Wolf ◽  
Rodney L. Dunn ◽  
Martin G. Sanda ◽  
David P. Wood ◽  
...  
Keyword(s):  
Quality Of Life ◽  
Development And Validation
Sign in / Sign up

Export Citation Format

Share Document