Search

Introduction Posteroanterior chest X-rays (CXRs) are recommended over computed tomography scans for COVID-19 diagnosis, as CXRs can be obtained with relatively low risk of facility contamination. The objective of this study was to assess seven configurations of six convolutional deep neural network architectures for classification of CXRs as COVID-19 positive or negative. Methods The primary dataset consisted of 294 COVID-19 positive and 294 COVID-19 negative CXRs, the latter comprising roughly equally many pneumonia, emphysema, fibrosis, and healthy images. We used six common convolutional neural network architectures, VGG16, DenseNet121, DenseNet201, MobileNet, NasNetMobile and InceptionV3. We studied six models (one for each architecture) which were pre-trained on a vast repository of generic (non-CXR) images, as well as a seventh, a DenseNet121 model which was pre-trained on a repository of CXR images. For each model, we replaced the output layers with custom fully connected layers for the task of binary classification of images as COVID-19 positive or negative. Performance metrics were calculated on a hold-out test set with CXRs from patients who were not included in the training/validation set. Results When pre-trained on generic images, the VGG16, DenseNet121, DenseNet201, MobileNet, NasNetMobile, and InceptionV3 architectures respectively produced hold-out test set areas under the receiver operating characteristic (AUROCs) of 0.98, 0.95, 0.97, 0.95, 0.99, and 0.96 for the COVID-19 classification of CXRs. The X-ray pre-trained DenseNet121 model, in comparison, had a test set AUROC of 0.87. Discussion Common convolutional neural network architectures with parameters pre-trained on generic images yield high-performance and well-calibrated COVID-19 CXR classification.

Diagnosis and appropriate intervention for myocardial infarction (MI) are time‐sensitive but rely on clinical measures that can be progressive and initially inconclusive, underscoring the need for an accurate and early predictor of MI to support diagnostic and clinical management decisions. The objective of this study was to develop a machine learning algorithm (MLA) to predict MI diagnosis based on electronic health record data (EHR) readily available during Emergency Department assessment. An MLA was developed using retrospective patient data. The MLA used patient data as they became available in the first 3 h of care to predict MI diagnosis (defined by International Classification of Diseases, 10th revision code) at any time during the encounter. The MLA obtained an area under the receiver operating characteristic curve of 0.87, sensitivity of 87% and specificity of 70%, outperforming the comparator scoring systems TIMI and GRACE on all metrics. An MLA can synthesize complex EHR data to serve as a clinically relevant risk stratification tool for MI.

Coronavirus disease 2019 (COVID-19) is caused by infection of the coronavirus severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) with typical respiratory symptoms. SARS-CoV-2 invades not only the respiratory system, but also other organs expressing the cell surface receptor angiotensin converting enzyme 2. In particular, the digestive system is a susceptible target of SARS-CoV-2. Gastrointestinal symptoms of COVID-19 include anorexia, nausea, vomiting, diarrhea, abdominal pain, and liver damage. Patients with digestive damage have a greater chance of progressing to severe or critical illness, a poorer prognosis, and a higher risk of death. This paper aims to summarize the digestive system symptoms of COVID-19 and discuss fecal-oral contagion of SARS-CoV-2. It also describes the characteristics of inflammatory bowel disease patients with SARS-CoV-2 infection and discusses precautions for preventing SARS-CoV-2 infection during gastrointestinal endoscopy procedures. Improved attention to digestive system abnormalities and gastrointestinal symptoms of COVID-19 patients may aid health care providers in the process of clinical diagnosis, treatment, and epidemic prevention and control.

Background Acute heart failure (AHF) is associated with significant morbidity and mortality. Effective patient risk stratification is essential to guiding hospitalization decisions and the clinical management of AHF. Clinical decision support systems can be used to improve predictions of mortality made in emergency care settings for the purpose of AHF risk stratification. In this study, several models for the prediction of seven-day mortality among AHF patients were developed by applying machine learning techniques to retrospective patient data from 236,275 total emergency department (ED) encounters, 1881 of which were considered positive for AHF and were used for model training and testing. The models used varying subsets of age, sex, vital signs, and laboratory values. Model performance was compared to the Emergency Heart Failure Mortality Risk Grade (EHMRG) model, a commonly used system for prediction of seven-day mortality in the ED with similar (or, in some cases, more extensive) inputs. Model performance was assessed in terms of area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity. Results When trained and tested on a large academic dataset, the best-performing model and EHMRG demonstrated test set AUROCs of 0.84 and 0.78, respectively, for prediction of seven-day mortality. Given only measurements of respiratory rate, temperature, mean arterial pressure, and FiO2, one model produced a test set AUROC of 0.83. Neither a logistic regression comparator nor a simple decision tree outperformed EHMRG. Conclusions A model using only the measurements of four clinical variables outperforms EHMRG in the prediction of seven-day mortality in AHF. With these inputs, the model could not be replaced by logistic regression or reduced to a simple decision tree without significant performance loss. In ED settings, this minimal-input risk stratification tool may assist clinicians in making critical decisions about patient disposition by providing early and accurate insights into individual patient’s risk profiles.

PurposeAcute respiratory distress syndrome (ARDS) is a serious respiratory condition with high mortality and associated morbidity. The objective of this study is to develop and evaluate a novel application of gradient boosted tree models trained on patient health record data for the early prediction of ARDS.Materials and Methods9919 patient encounters were retrospectively analyzed from the Medical Information Mart for Intensive Care III (MIMIC-III) data base. XGBoost gradient boosted tree models for early ARDS prediction were created using routinely collected clinical variables and numerical representations of radiology reports as inputs. XGBoost models were iteratively trained and validated using 10-fold cross validation.ResultsOn a hold-out test set, algorithm classifiers attained area under the receiver operating characteristic curve (AUROC) values of 0.905, 0.827, 0.810, and 0.790 when tested for the prediction of ARDS at 0-, 12-, 24-, and 48-hour windows prior to onset, respectively.ConclusionSupervised machine learning predictions may help predict patients with ARDS up to 48 hours prior to onset.

Rationale Prediction of patients at risk for mortality can help triage patients and assist in resource allocation. Objectives Develop and evaluate a machine learning-based algorithm which accurately predicts mortality in COVID-19, pneumonia, and mechanically ventilated patients. Methods Retrospective study of 53,001 total ICU patients, including 9166 patients with pneumonia and 25,895 mechanically ventilated patients, performed on the MIMIC dataset. An additional retrospective analysis was performed on a community hospital dataset containing 114 patients positive for SARS-COV-2 by PCR test. The outcome of interest was in-hospital patient mortality. Results When trained and tested on the MIMIC dataset, the XGBoost predictor obtained area under the receiver operating characteristic (AUROC) values of 0.82, 0.81, 0.77, and 0.75 for mortality prediction on mechanically ventilated patients at 12-, 24-, 48-, and 72- hour windows, respectively, and AUROCs of 0.87, 0.78, 0.77, and 0.734 for mortality prediction on pneumonia patients at 12-, 24-, 48-, and 72- hour windows, respectively. The predictor outperformed the qSOFA, MEWS and CURB-65 risk scores at all prediction windows. When tested on the community hospital dataset, the predictor obtained AUROCs of 0.91, 0.90, 0.86, and 0.87 for mortality prediction on COVID-19 patients at 12-, 24-, 48-, and 72- hour windows, respectively, outperforming the qSOFA, MEWS and CURB-65 risk scores at all prediction windows. Conclusions This machine learning-based algorithm is a useful predictive tool for anticipating patient mortality at clinically useful timepoints, and is capable of accurate mortality prediction for mechanically ventilated patients as well as those diagnosed with pneumonia and COVID-19., Highlights • Mortality predictions have not previously been evaluated for COVID-19 patients. • Machine learning may be a useful predictive tool for anticipating patient mortality. • Prediction can be estimated at clinically useful windows up to 72 h in advance.

Background: Machine learning methods have been developed to predict the likelihood of a given event or classify patients into two or more diagnostic categories. Digital twin models, which forecast entire trajectories of patient health data, have potential applications in clinical trials and patient management. Methods: In this study, we apply a digital twin model based on a variational autoencoder to a population of patients who went on to experience an ischemic stroke. The digital twin’s ability to model patient clinical features was assessed with regard to its ability to forecast clinical measurement trajectories leading up to the onset of the acute medical event and beyond using International Classification of Diseases (ICD) codes for ischemic stroke and lab values as inputs. Results: The simulated patient trajectories were virtually indistinguishable from real patient data, with similar feature means, standard deviations, inter-feature correlations, and covariance structures on a withheld test set. A logistic regression adversary model was unable to distinguish between the real and simulated data area under the receiver operating characteristic (ROC) curve (AUCadversary = 0.51). Conclusion: Through accurate projection of patient trajectories, this model may help inform clinical decision making or provide virtual control arms for efficient clinical trials.

Interventions to better prevent or manage Clostridioides difficile infection (CDI) may significantly reduce morbidity, mortality, and healthcare spending.We present a retrospective study using electronic health record data from over 700 United States hospitals. A subset of hospitals was used to develop machine learning algorithms (MLAs); the remaining hospitals served as an external test set. Three MLAs were evaluated: gradient-boosted decision trees (XGBoost), Deep Long Short Term Memory neural network, and one-dimensional convolutional neural network. MLA performance was evaluated with area under the receiver operating characteristic curve (AUROC), sensitivity, specificity, diagnostic odds ratios and likelihood ratios.The development dataset contained 13,664,840 inpatient encounters with 80,046 CDI encounters; the external dataset contained 1,149,088 inpatient encounters with 7,107 CDI encounters. The highest AUROCs were achieved for XGB, Deep Long Short Term Memory neural network, and one-dimensional convolutional neural network via abstaining from use of specialized training techniques, resampling in isolation, and resampling and output bias in combination, respectively. XGBoost achieved the highest AUROC.MLAs can predict future CDI in hospitalized patients using just 6 hours of data. In clinical practice, a machine-learning based tool may support prophylactic measures, earlier diagnosis, and more timely implementation of infection control measures.

BACKGROUND A high number of patients who are hospitalized with COVID-19 develop acute respiratory distress syndrome (ARDS). OBJECTIVE In response to the need for clinical decision support tools to help manage the next pandemic during the early stages (ie, when limited labeled data are present), we developed machine learning algorithms that use semisupervised learning (SSL) techniques to predict ARDS development in general and COVID-19 populations based on limited labeled data. METHODS SSL techniques were applied to 29,127 encounters with patients who were admitted to 7 US hospitals from May 1, 2019, to May 1, 2021. A recurrent neural network that used a time series of electronic health record data was applied to data that were collected when a patient’s peripheral oxygen saturation level fell below the normal range ( RESULTS For the whole data set, the median time between the first peripheral oxygen saturation measurement of CONCLUSIONS In the context of using time-series inpatient data and a careful model training design, unlabeled data can be used to improve the performance of machine learning models when labeled data for predicting ARDS development are scarce or expensive.

ObjectiveThe objective of this study is to quantify the relationship between acute kidney injury (AKI) and alcohol use disorder (AUD), in terms of disease burden, mortality burden and disease progression.MethodsWe used the University of California, San Francisco Medical Center in San Francisco, CA (UCSF) and Medical Information Mart for Intensive Care (MIMIC-III) databases to quantify AKI disease and mortality burden as well as AKI disease progression in the AUD and non-AUD subpopulations. We used the MIMIC-III dataset to compare two different methods of encoding AKI: ICD-9 codes, and the 2012 Kidney Disease: Improving Global Outcomes scheme (KDIGO). In addition to the AUD subpopulation (defined by AUD-related ICD-9 codes), we also present analysis for the hepatorenal syndrome (HRS) and alcohol-related cirrhosis subpopulations identified via ICD-9 coding.ResultsIn both the ICD-9 and KDIGO encodings of AKI, the AUD subpopulation had a higher prevalence of AKI (ICD-9: 48.59% vs. 29.99% AKI in the non-AUD subpopulations; KDIGO: 39.84% vs. 27.99%) in the MIMIC-III dataset. In the UCSF dataset, the AUD subpopulation also had a higher prevalence of AKI than the non-AUD subpopulation (ICD-9: 48.60% vs. 8.45%). The mortality rate of the subpopulation with both AKI and an AUD-related condition (AUD, HRS, or alcohol-related cirrhosis) was consistently higher than that of the subpopulation with only AKI in both datasets after adjusting for disease severity using two methods of severity estimation in the MIMIC-III dataset. Disease progression rates were similar for AUD and non-AUD subpopulations.ConclusionsOur work using the UCSF multi-ward academic hospital data and the MIMIC-III ICU dataset shows that the AUD patient subpopulation had a higher number of AKI patients than the non-AUD subpopulation, and that patients with both AKI and either AUD, HRS, or alcohol-related cirrhosis were shown to have higher rates of mortality than the non-AUD subpopulation with AKI.Trial RegistrationNot applicable.

Introduction: Acute heart failure (AHF) syndromes are associated with significant morbidity, mortality, and hemodynamic complications. Patients at risk of AHF are likely to experience rehospitalization or death post-discharge. AHF patient risk stratification remains an unmet need. Hypothesis: Gradient boosted machine learning can be used to predict likelihood of AHF diagnosis, enabling identification of at-risk patients. Methods: A gradient boosted machine learning algorithm was developed on retrospective data from 236,275 total emergency department patients, 807 of whom experienced AHF and were prescribed a vasodilator during their stay. A model was developed using age, sex, and six vital signs (systolic and diastolic blood pressure, heart rate, respiratory rate, peripheral oxygen saturation, and temperature). A second model used these demographics, vitals, and laboratory data (troponin, bicarbonate, and O2 saturation) as available to predict AHF diagnosis, as defined by ICD code and prescription of beta-blocker and angiotensin converting enzyme (ACE) inhibitor vasodilators. Model performance was assessed with regard to area under the receiver operating characteristic (AUROC). Results: The algorithm obtained AUROCs of 0.860 and 0.767 for prediction of AHF diagnosis and prescription of vasodilator at discharge with and without laboratory data, respectively (Figure 1). Predictions from the vitals only model were made an average of 38.5 hours prior to AHF diagnosis. Predictions from the model which included labs were made an average of 34 hours prior to AHF diagnosis. Conclusion: Machine learning is a useful method for predicting AHF diagnosis. Patient risk stratification enabled by the tool may serve to reduce duration of hospital stay for patients at low risk of developing AHF. Identification of high risk patient populations may also allow for earlier diagnosis and treatment, preventing development of chronic heart failure and other sequelae of AHF.

Therapeutic agents for the novel coronavirus disease 2019 (COVID-19) have been proposed, but evidence supporting their use is limited. A machine learning algorithm was developed in order to identify a subpopulation of COVID-19 patients for whom hydroxychloroquine was associated with improved survival, this population might be relevant for study in a clinical trial. A pragmatic trial was conducted at six United States hospitals. We enrolled COVID-19 patients that were admitted between 10 March and 4 June 2020. Treatment was not randomized. The study endpoint was mortality, discharge was a competing event. Hazard ratios were obtained on the entire population, and on the subpopulation indicated by the algorithm as suitable for treatment. A total of 290 patients were enrolled. In the subpopulation that was identified by the algorithm, hydroxychloroquine was associated with a statistically significant (p = 0.011) increase in survival (adjusted hazard ratio 0.29, 95% confidence interval (CI) 0.11&ndash, 0.75). Adjusted survival among the algorithm indicated patients was 82.6% in the treated arm and 51.2% in the arm not treated. No association between treatment and mortality was observed in the general population. A 31% increase in survival at the end of the study was observed in a population of COVID-19 patients that were identified by a machine learning algorithm as having a better outcome with hydroxychloroquine treatment. Precision medicine approaches may be useful in identifying a subpopulation of COVID-19 patients more likely to be proven to benefit from hydroxychloroquine treatment in a clinical trial.

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., SCOPUS: ar.j, info:eu-repo/semantics/published

Introduction Acute kidney injury (AKI) is common among hospitalized patients and has a significant impact on morbidity and mortality. Although early prediction of AKI has the potential to reduce adverse patient outcomes, it remains a difficult condition to predict and diagnose. The purpose of this study was to evaluate the ability of a machine learning algorithm to predict for AKI as defined by Kidney Disease: Improving Global Outcomes (KDIGO) stage 2 or 3 up to 48 hours in advance of onset using convolutional neural networks (CNNs) and patient electronic health record (EHR) data. Methods A CNN prediction system was developed to use EHR data gathered during patients’ stays to predict AKI up to 48 hours before onset. A total of 12,347 patient encounters were retrospectively analyzed from the Medical Information Mart for Intensive Care III (MIMIC-III) database. An XGBoost AKI prediction model and the sequential organ failure assessment (SOFA) scoring system were used as comparators. The outcome was AKI onset. The model was trained on routinely collected patient EHR data. Measurements included area under the receiver operating characteristic (AUROC) curve, positive predictive value (PPV), and a battery of additional performance metrics for advance prediction of AKI onset. Results On a hold-out test set, the algorithm attained an AUROC of 0.86 and PPV of 0.24, relative to a cohort AKI prevalence of 7.62%, for long-horizon AKI prediction at a 48-hour window before onset. Conclusion A CNN machine learning-based AKI prediction model outperforms XGBoost and the SOFA scoring system, revealing superior performance in predicting AKI 48 hours before onset, without reliance on serum creatinine (SCr) measurements., Graphical abstract

BACKGROUND Racial disparities in health care are well documented in the United States. As machine learning methods become more common in health care settings, it is important to ensure that these methods do not contribute to racial disparities through biased predictions or differential accuracy across racial groups. OBJECTIVE The goal of the research was to assess a machine learning algorithm intentionally developed to minimize bias in in-hospital mortality predictions between white and nonwhite patient groups. METHODS Bias was minimized through preprocessing of algorithm training data. We performed a retrospective analysis of electronic health record data from patients admitted to the intensive care unit (ICU) at a large academic health center between 2001 and 2012, drawing data from the Medical Information Mart for Intensive Care–III database. Patients were included if they had at least 10 hours of available measurements after ICU admission, had at least one of every measurement used for model prediction, and had recorded race/ethnicity data. Bias was assessed through the equal opportunity difference. Model performance in terms of bias and accuracy was compared with the Modified Early Warning Score (MEWS), the Simplified Acute Physiology Score II (SAPS II), and the Acute Physiologic Assessment and Chronic Health Evaluation (APACHE). RESULTS The machine learning algorithm was found to be more accurate than all comparators, with a higher sensitivity, specificity, and area under the receiver operating characteristic. The machine learning algorithm was found to be unbiased (equal opportunity difference 0.016, P=.20). APACHE was also found to be unbiased (equal opportunity difference 0.019, P=.11), while SAPS II and MEWS were found to have significant bias (equal opportunity difference 0.038, P=.006 and equal opportunity difference 0.074, P CONCLUSIONS This study indicates there may be significant racial bias in commonly used severity scoring systems and that machine learning algorithms may reduce bias while improving on the accuracy of these methods.

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.

Rationale and objectivesAcute kidney injury (AKI) is common among hospitalized patients and has a significant impact on morbidity and mortality. While early prediction of AKI has the potential to reduce adverse patient outcomes, it remains a difficult condition to predict and diagnose. The purpose of this study was to evaluate the ability of a machine learning algorithm to predict for AKI KDIGO Stage 2 or 3 up to 72 hours in advance of onset using convolutional recurrent neural nets (CNN) and patient Electronic Health Record (EHR) data.MethodsA CNN prediction system was developed to continuously and automatically monitor for incipient AKI. 7122 patient encounters were retrospectively analyzed from the Medical Information Mart for Intensive Care III (MIMIC-III) database.New Predictors and Established PredictorsNew predictor - CNN machine learning-based AKI prediction model. Established predictors - XGBoost AKI prediction model and the Sequential Organ Failure Assessment (SOFA) scoring system.OutcomesAKI onset.Analytical ApproachThe model was trained on routinely-collected patient EHR data. Measurements included Area Under the Receiver Operating Characteristic (AUROC) curve, positive predictive value (PPV), and a battery of additional performance metrics for 72 hour advance prediction of AKI onset.ResultsOn a hold-out test set, the algorithm attained an AUROC of 0.85 and PPV of 0.25, relative to a cohort AKI prevalence of 5.21%, for long-horizon AKI prediction at a 72-hour window prior to onset.ConclusionsA CNN machine learning-based AKI prediction model outperforms XGBoost and the SOFA scoring system, demonstrating superior performance in predicting acute kidney injury 72 hours prior to onset, without reliance on changes in serum creatinine.

Background A high number of patients who are hospitalized with COVID-19 develop acute respiratory distress syndrome (ARDS). Objective In response to the need for clinical decision support tools to help manage the next pandemic during the early stages (ie, when limited labeled data are present), we developed machine learning algorithms that use semisupervised learning (SSL) techniques to predict ARDS development in general and COVID-19 populations based on limited labeled data. Methods SSL techniques were applied to 29,127 encounters with patients who were admitted to 7 US hospitals from May 1, 2019, to May 1, 2021. A recurrent neural network that used a time series of electronic health record data was applied to data that were collected when a patient’s peripheral oxygen saturation level fell below the normal range ( Results For the whole data set, the median time between the first peripheral oxygen saturation measurement of Conclusions In the context of using time-series inpatient data and a careful model training design, unlabeled data can be used to improve the performance of machine learning models when labeled data for predicting ARDS development are scarce or expensive.

Objective: In the wake of COVID-19, the United States 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 deemed to be 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 may therefore be of limited use in decisions surrounding resource allocation to vulnerable populations. The objective of this study was to evaluate a machine learning algorithm for 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% as identified by government guidelines. The algorithm also achieved a high specificity of 95%, outperforming government guidelines. Conclusions: This algorithm may identify individuals likely to require hospitalization should they contract COVID-19. This information may be useful in guiding vaccine distribution, in anticipating hospital resource needs, and in assisting health care policymakers to make care decisions in a more principled manner.

Background: The objective of this study was to develop and evaluate a machine learning-based algorithm which accurately predicts mortality in COVID-19, pneumonia, and mechanically ventilated patients. Methods: A retrospective study of 53,001 total ICU patients, including 9,166 patients with pneumonia and 25,895 mechanically ventilated patients, was performed on the MIMIC dataset. An additional retrospective analysis was performed on a community hospital dataset containing 114 patients positive for SARS-COV-2 by PCR test. The outcome of interest was in-hospital patient mortality. Findings: W hen trained and tested on the MIMIC dataset, the XGBoost predictor obtained AUROCs of 0.88, 0.86, 0.81, and 0.78 for mortality prediction on mechanically ventilated patients at 12-, 24-, 48-, and 72- hour windows, respectively, and AUROCs of 0.86, 0.82, 0.79, and 0.75 for mortality prediction on pneumonia patients at 12-, 24-, 48-, and 72- hour windows, respectively. The predictor outperformed the qSOFA risk score at all prediction windows. When tested on the community hospital dataset, the predictor obtained AUROCs of 0.934, 0.927, 0.916, and 0.916 for mortality prediction on COVID-19 PCR positive patients at 12-, 24-, 48-, and 72- hour windows, respectively, outperforming the qSOFA risk score at all prediction windows. Interpretation: This machine learning-based algorithm is a useful predictive tool for anticipating patient mortality at clinically useful windows of 12, 24, 48, and 72 hours in advance, and is capable of accurate mortality prediction for mechanically ventilated patients as well as those diagnosed with pneumonia and COVID-19. Trial Registration : This study has been registered on ClinicalTrials.gov under study number NCT 04358510. Funding Statement: N/A Declaration of Interests: All authors who have affiliations listed with Dascena (Oakland, California, USA) are employees or contractors of Dascena. All other authors declare no conflicts of interest Ethics Approval Statement: Studies performed on the de-identified data constitute non-human subject studies, and therefore, our study did not require Institutional Review Board approval.

Background: Identifying patient characteristics associated with poor outcomes is vital to minimizing death due to COVID-19. Identification of features that predict mortality may improve triage and management of COVID-19 patients. Methods: A machine learning algorithm was applied to retrospective patient data to identify features correlated with mortality. Four populations were analyzed: 221 COVID-19 patients admitted to general isolated wards or ICU in Wuhan, China between January and February 2020; 230 COVID-19 inpatients admitted across four U.S. hospitals between January and April 2020; 99,224 inpatients admitted to a U.S. hospital; and 8,492 inpatients admitted to a U.S. hospital with viral infections other than SARS-CoV-2. Findings: Features associated with predicted mortality varied across populations. Among Chinese COVID-19 patients, creatinine was the top predictor of mortality, but was not among the most important features for the U.S. COVID-19 patients. Blood pressure was a more important predictor for U.S COVID-19 patients than for the U.S. viral or general hospitalized populations. Interpretation: The SARS-CoV-2 virus may affect different patient populations in different ways. This may be due to differences in treatment practice across populations, or to evolution of SARS-Cov-2 itself over time. The finding that creatinine was an important predictor only in the Chinese COVID-19 population may indicate that kidney-related complications due to SARS-CoV-2 are becoming less severe. Blood pressure was found to be an important feature in the U.S. COVID-19 population, suggesting an increased importance of cardiac and thrombotic complications of COVID-19. Funding Statement: None. Declaration of Interests: All authors who have affiliations listed with Dascena (Oakland, California, USA) are employees or contractors of Dascena. Ethics Approval Statement: All patient data was maintained in compliance with the Health Insurance Portability and Accountability Act (HIPAA). This study has been determined by the Pearl Institutional Review Board to be Exempt according to FDA 21 CFR 56.104 and 45CFR46.104(b)(4): (4) Secondary Research Uses of Data or Specimens under study number 20-DASC-119.

In order to evaluate mortality predictions based on boosted trees, this retrospective study uses electronic medical record data from three academic health centers for inpatients 18 years or older with at least one observation of each vital sign. Predictions were made 12, 24, and 48 hours before death. Models fit to training data from each institution were evaluated using hold-out test data from the same institution, and from the other institutions. Gradient-boosted trees (GBT) were compared to regularized logistic regression (LR) predictions, support vector machine (SVM) predictions, quick Sepsis-Related Organ Failure Assessment (qSOFA), and Modified Early Warning Score (MEWS) using area under the receiver operating characteristic curve (AUROC). For training and testing GBT on data from the same institution, the average AUROCs were 0.96, 0.95, and 0.94 across institutional test sets for 12-, 24-, and 48-hour predictions, respectively. When trained and tested on data from different hospitals, GBT AUROCs achieved up to 0.98, 0.96, and 0.96, for 12-, 24-, and 48-hour predictions, respectively. Average AUROC for 48-hour predictions for LR, SVM, MEWS, and qSOFA were 0.85, 0.79, 0.86 and 0.82, respectively. GBT predictions may help identify patients who would benefit from increased clinical care.

BackgroundSevere sepsis and septic shock are among the leading causes of death in the USA. While early prediction of severe sepsis can reduce adverse patient outcomes, sepsis remains one of the most expensive conditions to diagnose and treat.ObjectiveThe purpose of this study was to evaluate the effect of a machine learning algorithm for severe sepsis prediction on in-hospital mortality, hospital length of stay and 30-day readmission.DesignProspective clinical outcomes evaluation.SettingEvaluation was performed on a multiyear, multicentre clinical data set of real-world data containing 75 147 patient encounters from nine hospitals across the continental USA, ranging from community hospitals to large academic medical centres.ParticipantsAnalyses were performed for 17 758 adult patients who met two or more systemic inflammatory response syndrome criteria at any point during their stay (‘sepsis-related’ patients).InterventionsMachine learning algorithm for severe sepsis prediction.Outcome measuresIn-hospital mortality, length of stay and 30-day readmission rates.ResultsHospitals saw an average 39.5% reduction of in-hospital mortality, a 32.3% reduction in hospital length of stay and a 22.7% reduction in 30-day readmission rate for sepsis-related patient stays when using the machine learning algorithm in clinical outcomes analysis.ConclusionsReductions of in-hospital mortality, hospital length of stay and 30-day readmissions were observed in real-world clinical use of the machine learning-based algorithm. The predictive algorithm may be successfully used to improve sepsis-related outcomes in live clinical settings.Trial registration numberNCT03960203

Deep venous thrombosis (DVT) is associated with significant morbidity, mortality, and increased healthcare costs. Standard scoring systems for DVT risk stratification often provide insufficient stratification of hospitalized patients and are unable to accurately predict which inpatients are most likely to present with DVT. There is a continued need for tools which can predict DVT in hospitalized patients. We performed a retrospective study on a database collected from a large academic hospital, comprised of 99,237 total general ward or ICU patients, 2,378 of whom experienced a DVT during their hospital stay. Gradient boosted machine learning algorithms were developed to predict a patient’s risk of developing DVT at 12- and 24-hour windows prior to onset. The primary outcome of interest was diagnosis of in-hospital DVT. The machine learning predictors obtained AUROCs of 0.83 and 0.85 for DVT risk prediction on hospitalized patients at 12- and 24-hour windows, respectively. At both 12 and 24 hours before DVT onset, the most important features for prediction of DVT were cancer history, VTE history, and internal normalized ratio (INR). Improved risk stratification may prevent unnecessary invasive testing in patients for whom DVT cannot be ruled out using existing methods. Improved risk stratification may also allow for more targeted use of prophylactic anticoagulants, as well as earlier diagnosis and treatment, preventing the development of pulmonary emboli and other sequelae of DVT.

Background Racial disparities in health care are well documented in the United States. As machine learning methods become more common in health care settings, it is important to ensure that these methods do not contribute to racial disparities through biased predictions or differential accuracy across racial groups. Objective The goal of the research was to assess a machine learning algorithm intentionally developed to minimize bias in in-hospital mortality predictions between white and nonwhite patient groups. Methods Bias was minimized through preprocessing of algorithm training data. We performed a retrospective analysis of electronic health record data from patients admitted to the intensive care unit (ICU) at a large academic health center between 2001 and 2012, drawing data from the Medical Information Mart for Intensive Care–III database. Patients were included if they had at least 10 hours of available measurements after ICU admission, had at least one of every measurement used for model prediction, and had recorded race/ethnicity data. Bias was assessed through the equal opportunity difference. Model performance in terms of bias and accuracy was compared with the Modified Early Warning Score (MEWS), the Simplified Acute Physiology Score II (SAPS II), and the Acute Physiologic Assessment and Chronic Health Evaluation (APACHE). Results The machine learning algorithm was found to be more accurate than all comparators, with a higher sensitivity, specificity, and area under the receiver operating characteristic. The machine learning algorithm was found to be unbiased (equal opportunity difference 0.016, P=.20). APACHE was also found to be unbiased (equal opportunity difference 0.019, P=.11), while SAPS II and MEWS were found to have significant bias (equal opportunity difference 0.038, P=.006 and equal opportunity difference 0.074, P Conclusions This study indicates there may be significant racial bias in commonly used severity scoring systems and that machine learning algorithms may reduce bias while improving on the accuracy of these methods.