ABSTRACT
BackgroundIn a pandemic, it is important for clinicians to stratify patients and decide who receives limited medical resources. In this study, we used automated machine learning (autoML) to develop and compare between multiple machine learning (ML) models that predict the chance of patient survival from COVID-19 infection and identified the best-performing model. In addition, we investigated which biomarkers are the most influential in generating an accurate model. We believe an ML model such as this could be a useful tool for clinicians stratifying hospitalized SARS-CoV-2 patients. MethodsThe data was retrospectively collected from Clinical Looking Glass (CLG) on all patients testing positive for COVID-19 through a nasopharyngeal specimen by real-time RT-PCR and admitted between 3/1/2020-7/3/2020 (4376 patients) at our institution. We collected 47 biomarkers from each patient within 36 hours before or after the index time: RT-PCR positivity, and tracked whether a patient survived or not for one month following this time. We utilized the autoML from H2O.ai, an open source package for R language. The autoML generated 20 ML models and ranked them by area under the precision-recall curve (AUCPR) on the test set. We selected the best model (model_var_47) and chose a threshold probability that maximized F2 score to make a binary classifier: dead or alive. Subsequently, we ranked the relative importance of variables that generated model_var_47 and chose the 10 most influential variables. Next, we reran the autoML with these 10 variables and likewise selected the model with the best AUCPR on the test set (model_var_10). Again, threshold probability that maximized F2 score for model_var_10 was chosen to make a binary classifier. We calculated and compared the sensitivity, specificity, and positive predicate value (PPV) for model_var_10 and model_var_47. ResultsThe best model that autoML generated using all 47 variables was the stacked ensemble model of all models (AUCPR = 0.836). The most influential variables were: systolic and diastolic blood pressure, age, respiratory rate, pulse oximetry, blood urea nitrogen, lactate dehydrogenase, d-dimer, troponin, and glucose. When the autoML was retrained with these 10 most important variables, it did not significantly affect the performance (AUCPR= 0.828). For the binary classifiers, sensitivity, specificity, and PPV of model_var_47 was 83.6%, 87.7%, and 69.8% respectively, while for model_var_10 they were 90.9%, 71.1%, and 51.8% respectively. ConclusionsBy using autoML, we developed high-performing models that predict patient mortality from COVID-19 infection. In addition, we identified the most important biomarkers correlated with mortality. This ML model can be used as a decision supporting tool for medical practitioners to efficiently triage COVID-19 infected patients. From our literature review, this will be the largest COVID-19 patient cohort to train ML models and the first to utilize autoML. The COVID-19 survival calculator based on this study can be found at https://www.tsubomitech.com/.
ABSTRACT
ImportanceCOVID-19 has caused a worldwide illness and New York has become the epicenter of COVID-19 in the United States. Currently Bronx has the highest prevalence per capita in New York. ObjectiveTo investigate the coagulopathic presentation of COVID and its natural course and to investigate whether hematologic and coagulation parameters can be used to assess illness severity and death. DesignRetrospective case study of positive COVID inpatients between 3/20/2020-3/31/2020. SettingMontefiore Health System main hospital, Moses, a large tertiary care center in the Bronx. ParticipantsAdult inpatients with positive COVID tests hospitalized at MHS. Exposure (for observational studies)Datasets of participants were queried for physiological, demographic (age, sex, socioeconomic status and self-reported race and/or ethnicity) and laboratory data. Main Outcome and MeasuresRelationship and predictive value of measured parameters to mortality and illness severity. ResultsOf the 217 in this case review, 70 died during hospitalization while 147 were discharged home. Only the admission PT and first D-Dimer could very significantly differentiate those who were discharged alive and those who died. Logistic regression analysis shows increased odds ratio for mortality by first D-Dimer within 48 hrs. of admission. The optimal cut-point for the initial D-Dimer to predict mortality was found to be 1.65 g/mL ConclusionsWe describe here a comprehensive assessment of hematologic and coagulation parameters in COVID and examine the relationship of these to mortality. We demonstrate that both initial and maximum D-Dimer values are biomarkers that can be used for survival assessments.
