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.

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 Despite the limitations in the use of cycle threshold (CT) values for individual patient care, population distributions of CT values may be useful indicators of local outbreaks. Objective We aimed to conduct an exploratory analysis of potential correlations between the population distribution of cycle threshold (CT) values and COVID-19 dynamics, which were operationalized as percent positivity, transmission rate (Rt), and COVID-19 hospitalization count. Methods In total, 148,410 specimens collected between September 15, 2020, and January 11, 2021, from the greater El Paso area were processed in the Dascena COVID-19 Laboratory. The daily median CT value, daily Rt, daily count of COVID-19 hospitalizations, daily change in percent positivity, and rolling averages of these features were plotted over time. Two-way scatterplots and linear regression were used to evaluate possible associations between daily median CT values and outbreak measures. Cross-correlation plots were used to determine whether a time delay existed between changes in daily median CT values and measures of community disease dynamics. Results Daily median CT values negatively correlated with the daily Rt values (P Conclusions This study adds to the literature by analyzing samples collected from an entire geographical area and contextualizing the results with other research investigating population CT values.

BACKGROUND Despite the limitations in the use of cycle threshold (CT) values for individual patient care, population distributions of CT values may be useful indicators of local outbreaks. OBJECTIVE We aimed to conduct an exploratory analysis of potential correlations between the population distribution of cycle threshold (CT) values and COVID-19 dynamics, which were operationalized as percent positivity, transmission rate (Rt), and COVID-19 hospitalization count. METHODS In total, 148,410 specimens collected between September 15, 2020, and January 11, 2021, from the greater El Paso area were processed in the Dascena COVID-19 Laboratory. The daily median CT value, daily Rt, daily count of COVID-19 hospitalizations, daily change in percent positivity, and rolling averages of these features were plotted over time. Two-way scatterplots and linear regression were used to evaluate possible associations between daily median CT values and outbreak measures. Cross-correlation plots were used to determine whether a time delay existed between changes in daily median CT values and measures of community disease dynamics. RESULTS Daily median CT values negatively correlated with the daily Rt values (PPPP CONCLUSIONS This study adds to the literature by analyzing samples collected from an entire geographical area and contextualizing the results with other research investigating population CT values.

IntroductionDespite limitations on the use of cycle threshold (CT) values for individual patient care, population distributions of CT values may be useful indicators of local outbreaks.MethodsSpecimens from the greater El Paso area were processed in the Dascena COVID-19 Laboratory. Daily median CT value, daily transmission rate R(t), daily count of COVID-19 hospitalizations, daily change in percent positivity, and rolling averages of these features were plotted over time. Two-way scatterplots and linear regression evaluated possible associations between daily median CT and outbreak measures. Cross-correlation plots determined whether a time delay existed between changes in the daily median CT value and measure of community disease dynamics.ResultsDaily median CT was negatively correlated with the daily R(t), the daily COVID-19 hospitalization count (with a time delay), and the daily change in percent positivity among testing samples. Despite visual trends suggesting time delays in the plots for median CT and outbreak measures, a statistically significant delay was only detected between changes in median CT and COVID-19 hospitalization count.ConclusionsThis study adds to the literature by analyzing samples collected from an entire geographical area, and contextualizing the results with other research investigating population CT values.

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.

Ventilator-associated pneumonia (VAP) is the most common and fatal nosocomial infection in intensive care units (ICUs). Existing methods for identifying VAP display low accuracy, and their use may delay antimicrobial therapy. VAP diagnostics derived from machine learning (ML) methods that utilize electronic health record (EHR) data have not yet been explored. The objective of this study is to compare the performance of a variety of ML models trained to predict whether VAP will be diagnosed during the patient stay. A retrospective study examined data from 6126 adult ICU encounters lasting at least 48 hours following the initiation of mechanical ventilation. The gold standard was the presence of a diagnostic code for VAP. Five different ML models were trained to predict VAP 48 hours after initiation of mechanical ventilation. Model performance was evaluated with regard to the area under the receiver operating characteristic (AUROC) curve on a 20% hold-out test set. Feature importance was measured in terms of Shapley values. The highest performing model achieved an AUROC value of 0.854. The most important features for the best-performing model were the length of time on mechanical ventilation, the presence of antibiotics, sputum test frequency, and the most recent Glasgow Coma Scale assessment. Supervised ML using patient EHR data is promising for VAP diagnosis and warrants further validation. This tool has the potential to aid the timely diagnosis of VAP.

Objective Ventilator-associated pneumonia (VAP) is the most common and fatal nosocomial infection in intensive care units (ICUs). Existing methods for identifying VAP display low accuracy, and their use may delay antimicrobial therapy. ​VAP diagnostics derived from machine learning methods that utilize electronic health record data have not yet been explored. The objective of this study is to compare the performance of a variety of machine learning models trained to predict whether VAP will be diagnosed during the patient stay.Methods A retrospective study examined data from 6,129 adult ICU encounters lasting at least 48 hours following the initiation of mechanical ventilation. The gold standard was the presence of a diagnostic code for VAP. Five different machine learning models were trained to predict VAP 48 hours after initiation of mechanical ventilation. Model performance was evaluated with regard to area under the receiver operating characteristic curve (AUROC) on a 10% hold-out test set. Feature importance was measured in terms of Shapley values.Results The highest performing model achieved an AUROC value of 0.827. The most important features for the best-performing model were the length of time on mechanical ventilation, presence of antibiotics, sputum test frequency, and most recent Glasgow Coma Scale assessment.Discussion Supervised machine learning using patient electronic health record data is promising for VAP diagnosis and warrants further validation. Conclusion This tool has the potential to aid the timely diagnosis of VAP.

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.

Nitrogen fixation, the biological conversion of N_2 to NH_3, is critical to alleviating nitrogen limitation in many marine ecosystems. To date, few measurements exist of N_2 fixation in deep‐sea sediments. Here, we conducted > 400 bottle incubations with sediments from methane seeps, whale falls and background sites off the western coast of the United States from 600 to 2893 m water depth to investigate the potential rates, spatial distribution and biological mediators of benthic N_2 fixation. We found that N2 fixation was widespread, yet heterogeneously distributed with sediment depth at all sites. In some locations, rates exceeded previous measurements by > 10×, and provided up to 30% of the community anabolic growth requirement for nitrogen. Diazotrophic activity appeared to be inhibited by pore water ammonium: N_2 fixation was only observed if incubation ammonium concentrations were ≤ 25 μM, and experimental additions of ammonium reduced diazotrophy. In seep sediments, N_2 fixation was dependent on CH_4 and coincident with sulphate reduction, consistent with previous work showing diazotrophy by microorganisms mediating sulphate‐coupled methane oxidation. However, the pattern of diazotrophy was different in whale‐fall and associated reference sediments, where it was largely unaffected by CH_4, suggesting catabolically different diazotrophs at these sites.

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.

Neural crest cells are multipotent progenitors that dynamically interpret diverse microenvironments to migrate significant distances as a loosely associated collective and contribute to many tissues in the developing vertebrate embryo. Uncovering details of neural crest migration has helped to inform a general understanding of collective cell migration, including that which occurs during cancer metastasis. Here, we discuss several commonalities and differences of neural crest and cancer cell migration and behavior. First, we focus on some of the molecular pathways required for the initial specification and potency of neural crest cells and the roles of many of these pathways in cancer progression. We also describe epithelial-to-mesenchymal transition, which plays a critical role in initiating both neural crest migration and cancer metastasis. Finally, we evaluate studies that demonstrate myriad forms of cell-cell and cell-environment communication during neural crest and cancer collective migration to highlight the remarkable similarities in their molecular and cell biological regulation.

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.

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.

To measure single cell microbial activity and substrate utilization patterns in environmental systems, we employ a new technique using stable isotope labeling of microbial populations with heavy water (a passive tracer) and ¹⁵N ammonium in combination with multi-isotope imaging mass spectrometry. We demonstrate simultaneous NanoSIMS analysis of hydrogen, carbon and nitrogen at high spatial and mass resolution, and report calibration data linking single cell isotopic compositions to the corresponding bulk isotopic equivalents for Pseudomonas aeruginosa and Staphylococcus aureus. Our results show that heavy water is capable of quantifying in situ single cell microbial activities ranging from generational time scales of minutes to years, with only light isotopic incorporation (~0.1 atom % ²H). Applying this approach to study the rates of fatty acid biosynthesis by single cells of S. aureus growing at different rates in chemostat culture (~6 hours, 1 day and 2 week generation times), we observe the greatest anabolic activity diversity in the slowest growing populations. By using heavy water to constrain cellular growth activity, we can further infer the relative contributions of ammonium vs. amino acid assimilation to the cellular nitrogen pool. The approach described here can be applied to disentangle individual cell activities even in nutritionally complex environments.

Diverse associations between methanotrophic archaea (ANME) and sulfate-reducing bacterial groups (SRB) often co-occur in marine methane seeps; however, the ecophysiology of these different symbiotic associations has not been examined. Here, we applied a combination of molecular, geochemical and Fluorescence in situ hybridization (FISH) coupled to nanoscale secondary ion mass spectrometry (FISH-NanoSIMS) analyses of in situ seep sediments and methane-amended sediment incubations from diverse locations (Eel River Basin, Hydrate Ridge and Costa Rican Margin seeps) to investigate the distribution and physiology of a newly identified subgroup of the Desulfobulbaceae (seepDBB) found in consortia with ANME-2c archaea, and compared these with the more commonly observed associations between the same ANME partner and the Desulfobacteraceae (DSS). FISH analyses revealed aggregates of seepDBB cells in association with ANME-2 from both environmental samples and laboratory incubations that are distinct in their structure relative to co-occurring ANME/DSS consortia. ANME/seepDBB aggregates were most abundant in shallow sediment depths below sulfide-oxidizing microbial mats. Depth profiles of ANME/seepDBB aggregate abundance revealed a positive correlation with elevated porewater nitrate relative to ANME/DSS aggregates in all seep sites examined. This relationship with nitrate was supported by sediment microcosm experiments, in which the abundance of ANME/seepDBB was greater in nitrate-amended incubations relative to the unamended control. FISH-NanoSIMS additionally revealed significantly higher (15)N-nitrate incorporation levels in individual aggregates of ANME/seepDBB relative to ANME/DSS aggregates from the same incubation. These combined results suggest that nitrate is a geochemical effector of ANME/seepDBB aggregate distribution, and provides a unique niche for these consortia through their utilization of a greater range of nitrogen substrates than the ANME/DSS.

Terrestrial mud volcanoes (TMVs) represent geochemically diverse habitats with varying sulfur sources and yet sulfur cycling in these environments remains largely unexplored. Here we characterized the sulfur-metabolizing microorganisms and activity in four TMVs in Azerbaijan. A combination of geochemical analyses, biological rate measurements and molecular diversity surveys (targeting metabolic genes aprA and dsrA and SSU ribosomal RNA) supported the presence of active sulfur-oxidizing and sulfate-reducing guilds in all four TMVs across a range of physiochemical conditions, with diversity of these guilds being unique to each TMV. The TMVs varied in potential sulfate reduction rates (SRR) by up to four orders of magnitude with highest SRR observed in sediments where in situ sulfate concentrations were highest. Maximum temperatures at which SRR were measured was 60°C in two TMVs. Corresponding with these trends in SRR, members of the potentially thermophilic, spore-forming, Desulfotomaculum were detected in these TMVs by targeted 16S rRNA analysis. Additional sulfate-reducing bacterial lineages included members of the Desulfobacteraceae and Desulfobulbaceae detected by aprA and dsrA analyses and likely contributing to the mesophilic SRR measured. Phylotypes affiliated with sulfide-oxidizing Gamma- and Betaproteobacteria were abundant in aprA libraries from low sulfate TMVs, while the highest sulfate TMV harboured 16S rRNA phylotypes associated with sulfur-oxidizing Epsilonproteobacteria. Altogether, the biogeochemical and microbiological data indicate these unique terrestrial habitats support diverse active sulfur-cycling microorganisms reflecting the in situ geochemical environment.

To measure single-cell microbial activity and substrate utilization patterns in environmental systems, we employ a new technique using stable isotope labelling of microbial populations with heavy water (a passive tracer) and (15) N ammonium in combination with multi-isotope imaging mass spectrometry. We demonstrate simultaneous NanoSIMS analysis of hydrogen, carbon and nitrogen at high spatial and mass resolution, and report calibration data linking single-cell isotopic compositions to the corresponding bulk isotopic equivalents for Pseudomonas aeruginosa and Staphylococcus aureus. Our results show that heavy water is capable of quantifying in situ single-cell microbial activities ranging from generational time scales of minutes to years, with only light isotopic incorporation (∼0.1 atom % (2) H). Applying this approach to study the rates of fatty acid biosynthesis by single cells of S. aureus growing at different rates in chemostat culture (∼6 h, 1 day and 2 week generation times), we observe the greatest anabolic activity diversity in the slowest growing populations. By using heavy water to constrain cellular growth activity, we can further infer the relative contributions of ammonium versus amino acid assimilation to the cellular nitrogen pool. The approach described here can be applied to disentangle individual cell activities even in nutritionally complex environments.

Magneto-FISH, in combination with metagenomic techniques, explores the middle ground between single-cell analysis and complex community characterization in bulk samples to better understand microbial partnerships and their roles in ecosystems. The Magneto-FISH method combines the selectivity of catalyzed reporter deposition-fluorescence in situ hybridization (CARD-FISH) with immunomagnetic capture to provide targeted molecular and metagenomic analysis of co-associated microorganisms in the environment. This method was originally developed by Pernthaler et al. (Pernthaler et al., 2008; PernthalerOrphan, 2010). It led to the discovery of new bacterial groups associated with anaerobic methane-oxidizing (ANME-2) archaea in methane seeps, as well as provided insight into their physiological potential using metagenomics. Here, we demonstrate the utility of this method for capturing aggregated consortia using a series of nested oligonucleotide probes of differing specificity designed to target either the ANME archaea or their Deltaproteobacteria partner, combined with 16S rRNA and mcrA analysis. This chapter outlines a modified Magneto-FISH protocol for large- and small-volume samples and evaluates the strengths and limitations of this method predominantly focusing on (1) the relationship between FISH probe specificity and sample selectivity, (2) means of improving DNA yield from paraformaldehyde-fixed samples, and (3) suggestions for adapting the Magneto-FISH method for other microbial systems, including potential for single-cell recovery.

In this work we use metabolomics and ^(13)C-labeling data to refine central metabolic pathways for methane utilization in Methylosinus trichosporium OB3b, a model alphaproteobacterial methanotrophic bacterium. We demonstrate here that similar to non-methane utilizing methylotrophic alphaproteobacteria the core metabolism of the microbe is represented by several tightly connected metabolic cycles, such as the serine pathway, the ethylmalonyl-CoA (EMC) pathway, and the citric acid (TCA) cycle. Both in silico estimations and stable isotope labeling experiments combined with single cell (NanoSIMS) and bulk biomass analyses indicate that a significantly larger portion of the cell carbon (over 60%) is derived from CO_2 in this methanotroph. Our ^(13) C-labeling studies revealed an unusual topology of the assimilatory network in which phosph(enol) pyruvate/pyruvate interconversions are key metabolic switches. A set of additional pathways for carbon fixation are identified and discussed.

Magneto-FISH, in combination with metagenomic techniques, explores the middle ground between single-cell analysis and complex community characterization in bulk samples to better understand microbial partnerships and their roles in ecosystems. The Magneto-FISH method combines the selectivity of catalyzed reporter deposition– fluorescence in situ hybridization (CARD–FISH) with immunomagnetic capture to provide targeted molecular and metagenomic analysis of co-associated microorganisms in the environment. This method was originally developed by Pernthaler et al. (Pernthaler et al., 2008; Pernthaler & Orphan, 2010). It led to the discovery of new bacterial groups associated with anaerobic methane-oxidizing (ANME-2) archaea in methane seeps, as well as provided insight into their physiological potential using metagenomics. Here, we demonstrate the utility of this method for capturing aggregated consortia using a series of nested oligonucleotide probes of differing specificity designed to target either the ANME archaea or their Deltaproteobacteria partner, combined with 16S rRNA and mcrA analysis. This chapter outlines a modified Magneto-FISH protocol for largeand small-volume samples and evaluates the strengths and limitations of this method predominantly focusing on (1) the relationship between FISH probe specificity and sample selectivity, (2) means of improving DNA yield from paraformaldehyde-fixed samples, and (3) suggestions for adapting the Magneto-FISH method for other microbial systems, including potential for single-cell recovery.