A MACHINE LEARNING MODEL DERIVED FROM ANALYSIS OF TIME-COURSE GENE-EXPRESSION DATASETS REVEALS TEMPORALLY STABLE GENE MARKERS PREDICTIVE OF SEPSIS MORTALITY.

ABSTRACT: Sepsis is associated with significant mortality and morbidity among critically ill patients admitted to intensive care units and represents a major health challenge globally. Given the significant clinical and biological heterogeneity among patients and the dynamic nature of the host immune response, identifying those at high risk of poor outcomes remains a critical challenge. Here, we performed secondary analysis of publicly available time-series gene-expression datasets from peripheral blood of patients admitted to the intensive care unit to elucidate temporally stable gene-expression markers between sepsis survivors and nonsurvivors. Using a limited set of genes that were determined to be temporally stable, we derived a dynamical model using a Support Vector Machine classifier to accurately predict the mortality of sepsis patients. Our model had robust performance in a test dataset, where patients' transcriptome was sampled at alternate time points, with an area under the curve of 0.89 (95% CI, 0.82-0.96) upon 5-fold cross-validation. We also identified 7 potential biomarkers of sepsis mortality (STAT5A, CX3CR1, LCP1, SNRPG, RPS27L, LSM5, SHCBP1) that require future validation. Pending prospective testing, our model may be used to identify sepsis patients with high risk of mortality accounting for the dynamic nature of the disease and with potential therapeutic implications.

HIRA: Heart Rate Interval based Rapid Alert score to characterize autonomic dysfunction among patients with sepsis-related acute respiratory failure (ARF).

Objective. To examine whether heart rate interval based rapid alert (HIRA) score derived from a combination model of heart rate variability (HRV) and modified early warning score (MEWS) is a surrogate for the detection of acute respiratory failure (ARF) in critically ill sepsis patients.Approach. Retrospective HRV analysis of sepsis patients admitted to Emory healthcare intensive care unit (ICU) was performed between sepsis-related ARF and sepsis controls without ARF. HRV measures such as time domain, frequency domain, and nonlinear measures were analyzed up to 24 h after patient admission, 1 h before the onset of ARF, and a random event time in the sepsis controls. Statistical significance was computed by the Wilcoxon Rank Sum test. Machine learning algorithms such as eXtreme Gradient Boosting and logistic regression were developed to validate the HIRA score model. The performance of HIRA and early warning score models were evaluated using the area under the receiver operating characteristic (AUROC).Main Results. A total of 89 (ICU) patients with sepsis were included in this retrospective cohort study, of whom 31 (34%) developed sepsis-related ARF and 58 (65%) were sepsis controls without ARF. Time-domain HRV for Electrocardiogram (ECG) Beat-to-Beat RR intervals strongly distinguished ARF patients from controls. HRV measures for nonlinear and frequency domains were significantly altered (p< 0.05) among ARF compared to controls. The HIRA score AUC: 0.93; 95% confidence interval (CI): 0.88-0.98) showed a higher predictive ability to detect ARF when compared to MEWS (AUC: 0.71; 95% CI: 0.50-0.90).Significance. HRV was significantly impaired across patients who developed ARF when compared to controls. The HIRA score uses non-invasively derived HRV and may be used to inform diagnostic and therapeutic decisions regarding the severity of sepsis and earlier identification of the need for mechanical ventilation.

Overt and Occult Hypoxemia in Patients Hospitalized With COVID-19.

Progressive hypoxemia is the predominant mode of deterioration in COVID-19. Among hypoxemia measures, the ratio of the Pao2 to the Fio2 (P/F ratio) has optimal construct validity but poor availability because it requires arterial blood sampling. Pulse oximetry reports oxygenation continuously (ratio of the Spo2 to the Fio2 [S/F ratio]), but it is affected by skin color and occult hypoxemia can occur in Black patients. Oxygen dissociation curves allow noninvasive estimation of P/F ratios (ePFRs) but remain unproven. OBJECTIVES: Measure overt and occult hypoxemia using ePFR. DESIGN SETTING AND PARTICIPANTS: We retrospectively studied COVID-19 hospital encounters (n = 5,319) at two academic centers (University of Virginia [UVA] and Emory University). MAIN OUTCOMES AND MEASURES: We measured primary outcomes (death or ICU transfer within 24 hr), ePFR, conventional hypoxemia measures, baseline predictors (age, sex, race, comorbidity), and acute predictors (National Early Warning Score [NEWS] and Sequential Organ Failure Assessment [SOFA]). We updated predictors every 15 minutes. We assessed predictive validity using adjusted odds ratios (AORs) and area under the receiver operating characteristic curves (AUROCs). We quantified disparities (Black vs non-Black) in empirical cumulative distributions using the Kolmogorov-Smirnov (K-S) two-sample test. RESULTS: Overt hypoxemia (low ePFR) predicted bad outcomes (AOR for a 100-point ePFR drop: 2.7 [UVA]; 1.7 [Emory]; p < 0.01) with better discrimination (AUROC: 0.76 [UVA]; 0.71 [Emory]) than NEWS (0.70 [both sites]) or SOFA (0.68 [UVA]; 0.65 [Emory]) and similar to S/F ratio (0.76 [UVA]; 0.70 [Emory]). We found racial differences consistent with occult hypoxemia. Black patients had better apparent oxygenation (K-S distance: 0.17 [both sites]; p < 0.01) but, for comparable ePFRs, worse outcomes than other patients (AOR: 2.2 [UVA]; 1.2 [Emory]; p < 0.01). CONCLUSIONS AND RELEVANCE: The ePFR was a valid measure of overt hypoxemia. In COVID-19, it may outperform multi-organ dysfunction models. By accounting for biased oximetry as well as clinicians' real-time responses to it (supplemental oxygen adjustment), ePFRs may reveal racial disparities attributable to occult hypoxemia.

A Delphi Process to Identify Relevant Outcomes That May Be Associated With a Predictive Analytic Tool to Detect Hemodynamic Deterioration in the Intensive Care Unit.

Background The critical care literature has seen an increase in the development and validation of tools using artificial intelligence for early detection of patient events or disease onset in the intensive care unit (ICU). The hemodynamic stability index (HSI) was found to have an AUC of 0.82 in predicting the need for hemodynamic intervention in the ICU. Future studies using this tool may benefit from targeting those outcomes that are more relevant to clinicians and most achievable. Methods A three-round Delphi study was conducted with a panel of 10 critical care physicians and three nurses in the United States to identify outcomes that may be most relevant and achievable with the HSI when evaluated for use in the ICU. To achieve criteria for relevance, at least 65% of panelists had to rate an outcome as a 4 or 5 on a 5-point scale. Results Nineteen of 24 outcomes that may be associated with the HSI achieved consensus for relevance. The Kemeny-Young approach was used to develop a matrix depicting the distribution of outcomes considering both relevance and achievability. "Reduces time spent in hemodynamic instability" and "reduces times to recognition of hemodynamic instability" were the highest-ranking outcomes considering both relevance and achievability. Conclusion This Delphi study was a feasible method to identify relevant outcomes that may be associated with an appropriate predictive analytic tool in the ICU. These findings can provide insight to researchers looking to study such tools to impact outcomes relevant to critical care practitioners. Future studies should test these tools in the ICU that target the most clinically relevant and achievable outcomes, such as time spent hemodynamically unstable or time until actionable nursing assessment or treatment.

Serial Measurements of Protein Biomarkers in Sepsis-Induced Acute Respiratory Distress Syndrome.

The role of early, serial measurements of protein biomarkers in sepsis-induced acute respiratory distress syndrome (ARDS) is not clear. OBJECTIVES: To determine the differences in soluble receptor for advanced glycation end-products (sRAGEs), angiopoietin-2, and surfactant protein-D (SP-D) levels and their changes over time between sepsis patients with and without ARDS. DESIGN SETTING AND PARTICIPANTS: Prospective observational cohort study of adult patients admitted to the medical ICU at Grady Memorial Hospital within 72 hours of sepsis diagnosis. MAIN OUTCOMES AND MEASURES: Plasma sRAGE, angiopoietin-2, and SP-D levels were measured for 3 consecutive days after enrollment. The primary outcome was ARDS development, and the secondary outcome of 28-day mortality. The biomarker levels and their changes over time were compared between ARDS and non-ARDS patients and between nonsurvivors and survivors. RESULTS: We enrolled 111 patients, and 21 patients (18.9%) developed ARDS. The three biomarker levels were not significantly different between ARDS and non-ARDS patients on all 3 days of measurement. Nonsurvivors had higher levels of all three biomarkers than did survivors on multiple days. The changes of the biomarker levels over time were not different between the outcome groups. Logistic regression analyses showed association between day 1 SP-D level and mortality (odds ratio, 1.52; 95% CI, 1.03-2.24; p = 0.03), and generalized estimating equation analyses showed association between angiopoietin-2 levels and mortality (estimate 0.0002; se 0.0001; p = 0.04). CONCLUSIONS AND RELEVANCE: Among critically ill patients with sepsis, sRAGE, angiopoietin-2, and SP-D levels were not significantly different between ARDS and non-ARDS patients but were higher in nonsurvivors compared with survivors. The trend toward higher levels of sRAGE and SP-D, but not of angiopoietin-2, in ARDS patients may indicate the importance of epithelial injury in sepsis-induced ARDS. Changes of the biomarker levels over time were not different between the outcome groups.

Overt and occult hypoxemia in patients hospitalized with novel coronavirus disease 2019.

Background: Progressive hypoxemia is the predominant mode of deterioration in COVID-19. Among hypoxemia measures, the ratio of the partial pressure of arterial oxygen to the fraction of inspired oxygen (P/F ratio) has optimal construct validity but poor availability because it requires arterial blood sampling. Pulse oximetry reports oxygenation continuously, but occult hypoxemia can occur in Black patients because the technique is affected by skin color. Oxygen dissociation curves allow non-invasive estimation of P/F ratios (ePFR) but this approach remains unproven. Research Question: Can ePFRs measure overt and occult hypoxemia? Study Design and methods: We retrospectively studied COVID-19 hospital encounters (n=5319) at two academic centers (University of Virginia [UVA] and Emory University). We measured primary outcomes (death or ICU transfer within 24 hours), ePFR, conventional hypoxemia measures, baseline predictors (age, sex, race, comorbidity), and acute predictors (National Early Warning Score (NEWS) and Sepsis-3). We updated predictors every 15 minutes. We assessed predictive validity using adjusted odds ratios (AOR) and area under receiver operating characteristics curves (AUROC). We quantified disparities (Black vs non-Black) in empirical cumulative distributions using the Kolmogorov-Smirnov (K-S) two-sample test. Results: Overt hypoxemia (low ePFR) predicted bad outcomes (AOR for a 100-point ePFR drop: 2.7 [UVA]; 1.7 [Emory]; p<0.01) with better discrimination (AUROC: 0.76 [UVA]; 0.71 [Emory]) than NEWS (AUROC: 0.70 [UVA]; 0.70 [Emory]) or Sepsis-3 (AUROC: 0.68 [UVA]; 0.65 [Emory]). We found racial differences consistent with occult hypoxemia. Black patients had better apparent oxygenation (K-S distance: 0.17 [both sites]; p<0.01) but, for comparable ePFRs, worse outcomes than other patients (AOR: 2.2 [UVA]; 1.2 [Emory], p<0.01). Interpretation: The ePFR was a valid measure of overt hypoxemia. In COVID-19, it may outperform multi-organ dysfunction models like NEWS and Sepsis-3. By accounting for biased oximetry as well as clinicians’ real-time responses to it (supplemental oxygen adjustment), ePFRs may enable statistical modelling of racial disparities in outcomes attributable to occult hypoxemia.

Leveraging clinical data across healthcare institutions for continual learning of predictive risk models.

The inherent flexibility of machine learning-based clinical predictive models to learn from episodes of patient care at a new institution (site-specific training) comes at the cost of performance degradation when applied to external patient cohorts. To exploit the full potential of cross-institutional clinical big data, machine learning systems must gain the ability to transfer their knowledge across institutional boundaries and learn from new episodes of patient care without forgetting previously learned patterns. In this work, we developed a privacy-preserving learning algorithm named WUPERR (Weight Uncertainty Propagation and Episodic Representation Replay) and validated the algorithm in the context of early prediction of sepsis using data from over 104,000 patients across four distinct healthcare systems. We tested the hypothesis, that the proposed continual learning algorithm can maintain higher predictive performance than competing methods on previous cohorts once it has been trained on a new patient cohort. In the sepsis prediction task, after incremental training of a deep learning model across four hospital systems (namely hospitals H-A, H-B, H-C, and H-D), WUPERR maintained the highest positive predictive value across the first three hospitals compared to a baseline transfer learning approach (H-A: 39.27% vs. 31.27%, H-B: 25.34% vs. 22.34%, H-C: 30.33% vs. 28.33%). The proposed approach has the potential to construct more generalizable models that can learn from cross-institutional clinical big data in a privacy-preserving manner.

Coronavirus Disease 2019 Temperature Trajectories Correlate With Hyperinflammatory and Hypercoagulable Subphenotypes.

OBJECTIVES: Body temperature trajectories of infected patients are associated with specific immune profiles and survival. We determined the association between temperature trajectories and distinct manifestations of coronavirus disease 2019. DESIGN: Retrospective observational study. SETTING: Four hospitals within an academic healthcare system from March 2020 to February 2021. PATIENTS: All adult patients hospitalized with coronavirus disease 2019. INTERVENTIONS: Using a validated group-based trajectory model, we classified patients into four previously defined temperature trajectory subphenotypes using oral temperature measurements from the first 72 hours of hospitalization. Clinical characteristics, biomarkers, and outcomes were compared between subphenotypes. MEASUREMENTS AND MAIN RESULTS: The 5,903 hospitalized coronavirus disease 2019 patients were classified into four subphenotypes: hyperthermic slow resolvers (n = 1,452, 25%), hyperthermic fast resolvers (1,469, 25%), normothermics (2,126, 36%), and hypothermics (856, 15%). Hypothermics had abnormal coagulation markers, with the highest d-dimer and fibrin monomers (p < 0.001) and the highest prevalence of cerebrovascular accidents (10%, p = 0.001). The prevalence of venous thromboembolism was significantly different between subphenotypes (p = 0.005), with the highest rate in hypothermics (8.5%) and lowest in hyperthermic slow resolvers (5.1%). Hyperthermic slow resolvers had abnormal inflammatory markers, with the highest C-reactive protein, ferritin, and interleukin-6 (p < 0.001). Hyperthermic slow resolvers had increased odds of mechanical ventilation, vasopressors, and 30-day inpatient mortality (odds ratio, 1.58; 95% CI, 1.13-2.19) compared with hyperthermic fast resolvers. Over the course of the pandemic, we observed a drastic decrease in the prevalence of hyperthermic slow resolvers, from representing 53% of admissions in March 2020 to less than 15% by 2021. We found that dexamethasone use was associated with significant reduction in probability of hyperthermic slow resolvers membership (27% reduction; 95% CI, 23-31%; p < 0.001). CONCLUSIONS: Hypothermics had abnormal coagulation markers, suggesting a hypercoagulable subphenotype. Hyperthermic slow resolvers had elevated inflammatory markers and the highest odds of mortality, suggesting a hyperinflammatory subphenotype. Future work should investigate whether temperature subphenotypes benefit from targeted antithrombotic and anti-inflammatory strategies.

Analysis of Discrepancies Between Pulse Oximetry and Arterial Oxygen Saturation Measurements by Race and Ethnicity and Association With Organ Dysfunction and Mortality.

Importance: Discrepancies in oxygen saturation measured by pulse oximetry (Spo2), when compared with arterial oxygen saturation (Sao2) measured by arterial blood gas (ABG), may differentially affect patients according to race and ethnicity. However, the association of these disparities with health outcomes is unknown. Objective: To examine racial and ethnic discrepancies between Sao2 and Spo2 measures and their associations with clinical outcomes. Design, Setting, and Participants: This multicenter, retrospective, cross-sectional study included 3 publicly available electronic health record (EHR) databases (ie, the Electronic Intensive Care Unit-Clinical Research Database and Medical Information Mart for Intensive Care III and IV) as well as Emory Healthcare (2014-2021) and Grady Memorial (2014-2020) databases, spanning 215 hospitals and 382 ICUs. From 141 600 hospital encounters with recorded ABG measurements, 87 971 participants with first ABG measurements and an Spo2 of at least 88% within 5 minutes before the ABG test were included. Exposures: Patients with hidden hypoxemia (ie, Spo2 ≥88% but Sao2 <88%). Main Outcomes and Measures: Outcomes, stratified by race and ethnicity, were Sao2 for each Spo2, hidden hypoxemia prevalence, initial demographic characteristics (age, sex), clinical outcomes (in-hospital mortality, length of stay), organ dysfunction by scores (Sequential Organ Failure Assessment [SOFA]), and laboratory values (lactate and creatinine levels) before and 24 hours after the ABG measurement. Results: The first Spo2-Sao2 pairs from 87 971 patient encounters (27 713 [42.9%] women; mean [SE] age, 62.2 [17.0] years; 1919 [2.3%] Asian patients; 26 032 [29.6%] Black patients; 2397 [2.7%] Hispanic patients, and 57 632 [65.5%] White patients) were analyzed, with 4859 (5.5%) having hidden hypoxemia. Hidden hypoxemia was observed in all subgroups with varying incidence (Black: 1785 [6.8%]; Hispanic: 160 [6.0%]; Asian: 92 [4.8%]; White: 2822 [4.9%]) and was associated with greater organ dysfunction 24 hours after the ABG measurement, as evidenced by higher mean (SE) SOFA scores (7.2 [0.1] vs 6.29 [0.02]) and higher in-hospital mortality (eg, among Black patients: 369 [21.1%] vs 3557 [15.0%]; P < .001). Furthermore, patients with hidden hypoxemia had higher mean (SE) lactate levels before (3.15 [0.09] mg/dL vs 2.66 [0.02] mg/dL) and 24 hours after (2.83 [0.14] mg/dL vs 2.27 [0.02] mg/dL) the ABG test, with less lactate clearance (-0.54 [0.12] mg/dL vs -0.79 [0.03] mg/dL). Conclusions and Relevance: In this study, there was greater variability in oxygen saturation levels for a given Spo2 level in patients who self-identified as Black, followed by Hispanic, Asian, and White. Patients with and without hidden hypoxemia were demographically and clinically similar at baseline ABG measurement by SOFA scores, but those with hidden hypoxemia subsequently experienced higher organ dysfunction scores and higher in-hospital mortality.

eARDS: A multi-center validation of an interpretable machine learning algorithm of early onset Acute Respiratory Distress Syndrome (ARDS) among critically ill adults with COVID-19.

We present an interpretable machine learning algorithm called 'eARDS' for predicting ARDS in an ICU population comprising COVID-19 patients, up to 12-hours before satisfying the Berlin clinical criteria. The analysis was conducted on data collected from the Intensive care units (ICU) at Emory Healthcare, Atlanta, GA and University of Tennessee Health Science Center, Memphis, TN and the Cerner® Health Facts Deidentified Database, a multi-site COVID-19 EMR database. The participants in the analysis consisted of adults over 18 years of age. Clinical data from 35,804 patients who developed ARDS and controls were used to generate predictive models that identify risk for ARDS onset up to 12-hours before satisfying the Berlin criteria. We identified salient features from the electronic medical record that predicted respiratory failure among this population. The machine learning algorithm which provided the best performance exhibited AUROC of 0.89 (95% CI = 0.88-0.90), sensitivity of 0.77 (95% CI = 0.75-0.78), specificity 0.85 (95% CI = 085-0.86). Validation performance across two separate health systems (comprising 899 COVID-19 patients) exhibited AUROC of 0.82 (0.81-0.83) and 0.89 (0.87, 0.90). Important features for prediction of ARDS included minimum oxygen saturation (SpO2), standard deviation of the systolic blood pressure (SBP), O2 flow, and maximum respiratory rate over an observational window of 16-hours. Analyzing the performance of the model across various cohorts indicates that the model performed best among a younger age group (18-40) (AUROC = 0.93 [0.92-0.94]), compared to an older age group (80+) (AUROC = 0.81 [0.81-0.82]). The model performance was comparable on both male and female groups, but performed significantly better on the severe ARDS group compared to the mild and moderate groups. The eARDS system demonstrated robust performance for predicting COVID19 patients who developed ARDS at least 12-hours before the Berlin clinical criteria, across two independent health systems.

A Locally Optimized Data-Driven Tool to Predict Sepsis-Associated Vasopressor Use in the ICU.

OBJECTIVES: To train a model to predict vasopressor use in ICU patients with sepsis and optimize external performance across hospital systems using domain adaptation, a transfer learning approach. DESIGN: Observational cohort study. SETTING: Two academic medical centers from January 2014 to June 2017. PATIENTS: Data were analyzed from 14,512 patients (9,423 at the development site and 5,089 at the validation site) who were admitted to an ICU and met Center for Medicare and Medicaid Services definition of severe sepsis either before or during the ICU stay. Patients were excluded if they never developed sepsis, if the ICU length of stay was less than 8 hours or more than 20 days or if they developed shock up to the first 4 hours of ICU admission. MEASUREMENTS AND MAIN RESULTS: Forty retrospectively collected features from the electronic medical records of adult ICU patients at the development site (four hospitals) were used as inputs for a neural network Weibull-Cox survival model to derive a prediction tool for future need of vasopressors. Domain adaptation updated parameters to optimize model performance in the validation site (two hospitals), a different healthcare system over 2,000 miles away. The cohorts at both sites were randomly split into training and testing sets (80% and 20%, respectively). When applied to the test set in the development site, the model predicted vasopressor use 4-24 hours in advance with an area under the receiver operator characteristic curve, specificity, and positive predictive value ranging from 0.80 to 0.81, 56.2% to 61.8%, and 5.6% to 12.1%, respectively. Domain adaptation improved performance of the model to predict vasopressor use within 4 hours at the validation site (area under the receiver operator characteristic curve 0.81 [CI, 0.80-0.81] from 0.77 [CI, 0.76-0.77], p < 0.01; specificity 59.7% [CI, 58.9-62.5%] from 49.9% [CI, 49.5-50.7%], p < 0.01; positive predictive value 8.9% [CI, 8.5-9.4%] from 7.3 [7.1-7.4%], p < 0.01). CONCLUSIONS: Domain adaptation improved performance of a model predicting sepsis-associated vasopressor use during external validation.

Prediction of Acute Respiratory Failure Requiring Advanced Respiratory Support in Advance of Interventions and Treatment: A Multivariable Prediction Model From Electronic Medical Record Data.

BACKGROUND: Acute respiratory failure occurs frequently in hospitalized patients and often begins outside the ICU, associated with increased length of stay, cost, and mortality. Delays in decompensation recognition are associated with worse outcomes. OBJECTIVES: The objective of this study is to predict acute respiratory failure requiring any advanced respiratory support (including noninvasive ventilation). With the advent of the coronavirus disease pandemic, concern regarding acute respiratory failure has increased. DERIVATION COHORT: All admission encounters from January 2014 to June 2017 from three hospitals in the Emory Healthcare network (82,699). VALIDATION COHORT: External validation cohort: all admission encounters from January 2014 to June 2017 from a fourth hospital in the Emory Healthcare network (40,143). Temporal validation cohort: all admission encounters from February to April 2020 from four hospitals in the Emory Healthcare network coronavirus disease tested (2,564) and coronavirus disease positive (389). PREDICTION MODEL: All admission encounters had vital signs, laboratory, and demographic data extracted. Exclusion criteria included invasive mechanical ventilation started within the operating room or advanced respiratory support within the first 8 hours of admission. Encounters were discretized into hour intervals from 8 hours after admission to discharge or advanced respiratory support initiation and binary labeled for advanced respiratory support. Prediction of Acute Respiratory Failure requiring advanced respiratory support in Advance of Interventions and Treatment, our eXtreme Gradient Boosting-based algorithm, was compared against Modified Early Warning Score. RESULTS: Prediction of Acute Respiratory Failure requiring advanced respiratory support in Advance of Interventions and Treatment had significantly better discrimination than Modified Early Warning Score (area under the receiver operating characteristic curve 0.85 vs 0.57 [test], 0.84 vs 0.61 [external validation]). Prediction of Acute Respiratory Failure requiring advanced respiratory support in Advance of Interventions and Treatment maintained a positive predictive value (0.31-0.21) similar to that of Modified Early Warning Score greater than 4 (0.29-0.25) while identifying 6.62 (validation) to 9.58 (test) times more true positives. Furthermore, Prediction of Acute Respiratory Failure requiring advanced respiratory support in Advance of Interventions and Treatment performed more effectively in temporal validation (area under the receiver operating characteristic curve 0.86 [coronavirus disease tested], 0.93 [coronavirus disease positive]), while achieving identifying 4.25-4.51× more true positives. CONCLUSIONS: Prediction of Acute Respiratory Failure requiring advanced respiratory support in Advance of Interventions and Treatment is more effective than Modified Early Warning Score in predicting respiratory failure requiring advanced respiratory support at external validation and in coronavirus disease 2019 patients. Silent prospective validation necessary before local deployment.

Predicting Progression to Septic Shock in the Emergency Department Using an Externally Generalizable Machine-Learning Algorithm.

STUDY OBJECTIVE: Machine-learning algorithms allow improved prediction of sepsis syndromes in the emergency department (ED), using data from electronic medical records. Transfer learning, a new subfield of machine learning, allows generalizability of an algorithm across clinical sites. We aim to validate the Artificial Intelligence Sepsis Expert for the prediction of delayed septic shock in a cohort of patients treated in the ED and demonstrate the feasibility of transfer learning to improve external validity at a second site. METHODS: This was an observational cohort study using data from greater than 180,000 patients from 2 academic medical centers between 2014 and 2019, using multiple definitions of sepsis. The Artificial Intelligence Sepsis Expert algorithm was trained with 40 input variables at the development site to predict delayed septic shock (occurring greater than 4 hours after ED triage) at various prediction windows. We then validated the algorithm at a second site, using transfer learning to demonstrate generalizability of the algorithm. RESULTS: We identified 9,354 patients with severe sepsis, of whom 723 developed septic shock at least 4 hours after triage. The Artificial Intelligence Sepsis Expert algorithm demonstrated excellent area under the receiver operating characteristic curve (>0.8) at 8 and 12 hours for the prediction of delayed septic shock. Transfer learning significantly improved the test characteristics of the Artificial Intelligence Sepsis Expert algorithm and yielded comparable performance at the validation site. CONCLUSION: The Artificial Intelligence Sepsis Expert algorithm accurately predicted the development of delayed septic shock. The use of transfer learning allowed significantly improved external validity and generalizability at a second site. Future prospective studies are indicated to evaluate the clinical utility of this model.

Major publications in the critical care pharmacotherapy literature: 2019.

PURPOSE: To summarize selected meta-analyses and trials related to critical care pharmacotherapy published in 2019. MATERIALS AND METHODS: The Critical Care Pharmacotherapy Literature Update (CCPLU) Group screened 36 journals monthly for impactful articles and reviewed 113 articles during 2019 according to Grading of Recommendations, Assessment, Development, and Evaluations (GRADE) criteria. RESULTS: Articles with a 1A grade, including three clinical practice guidelines, six meta-analyses, and five original research trials are reviewed here from those included in the monthly CCPLU. Clinical practice guidelines on the use of polymyxins and antiarrhythmic drugs in cardiac arrest as well as meta-analyses on antipsychotic use in delirium, stress ulcer prophylaxis (SUP), and vasoactive medications in septic shock and cardiac arrest were summarized. Original research trials evaluated delirium, sedation, neuromuscular blockade, SUP, anticoagulation reversal, and hemostasis. CONCLUSION: This clinical review and expert opinion provides summary and perspectives of clinical practice impact on influential critical care pharmacotherapy publications in 2019.

Predicting progression to septic shock in the emergency department using an externally generalizable machine learning algorithm.

OBJECTIVE: Machine-learning (ML) algorithms allow for improved prediction of sepsis syndromes in the ED using data from electronic medical records. Transfer learning, a new subfield of ML, allows for generalizability of an algorithm across clinical sites. We aimed to validate the Artificial Intelligence Sepsis Expert (AISE) for the prediction of delayed septic shock in a cohort of patients treated in the ED and demonstrate the feasibility of transfer learning to improve external validity at a second site. METHODS: Observational cohort study utilizing data from over 180,000 patients from two academic medical centers between 2014 and 2019 using multiple definitions of sepsis. The AISE algorithm was trained using 40 input variables at the development site to predict delayed septic shock (occurring greater than 4 hours after ED triage) at varying prediction windows. We then validated the AISE algorithm at a second site using transfer learning to demonstrate generalizability of the algorithm. RESULTS: We identified 9354 patients with severe sepsis of which 723 developed septic shock at least 4 hours after triage. The AISE algorithm demonstrated excellent area under the receiver operating curve (>0.8) at 8 and 12 hours for the prediction of delayed septic shock. Transfer learning significantly improved the test characteristics of the AISE algorithm and yielded comparable performance at the validation site. CONCLUSIONS: The AISE algorithm accurately predicted the development of delayed septic shock. The use of transfer learning allowed for significantly improved external validity and generalizability at a second site. Future prospective studies are indicated to evaluate the clinical utility of this model.

Fluid Response Evaluation in Sepsis Hypotension and Shock: A Randomized Clinical Trial.

BACKGROUND: Fluid and vasopressor management in septic shock remains controversial. In this randomized controlled trial, we evaluated the efficacy of dynamic measures (stroke volume change during passive leg raise) to guide resuscitation and improve patient outcome. RESEARCH QUESTION: Will resuscitation that is guided by dynamic assessments of fluid responsiveness in patients with septic shock improve patient outcomes? STUDY DESIGN AND METHODS: We conducted a prospective, multicenter, randomized clinical trial at 13 hospitals in the United States and United Kingdom. Patients presented to EDs with sepsis that was associated hypotension and anticipated ICU admission. Intervention arm patients were assessed for fluid responsiveness before clinically driven fluid bolus or increase in vasopressors occurred. The protocol included reassessment and therapy as indicated by the passive leg raise result. The control arm received usual care. The primary clinical outcome was positive fluid balance at 72 hours or ICU discharge, whichever occurred first. RESULTS: In modified intent-to-treat analysis that included 83 intervention and 41 usual care eligible patients, fluid balance at 72 hours or ICU discharge was significantly lower (-1.37 L favoring the intervention arm; 0.65 ± 2.85 L intervention arm vs 2.02 ± 3.44 L usual care arm; P = .021. Fewer patients required renal replacement therapy (5.1% vs 17.5%; P = .04) or mechanical ventilation (17.7% vs 34.1%; P = .04) in the intervention arm compared with usual care. In the all-randomized intent-to-treat population (102 intervention, 48 usual care), there were no significant differences in safety signals. INTERPRETATION: Physiologically informed fluid and vasopressor resuscitation with the use of the passive leg raise-induced stroke volume change to guide management of septic shock is safe and demonstrated lower net fluid balance and reductions in the risk of renal and respiratory failure. Dynamic assessments to guide fluid administration may improve outcomes for patients with septic shock compared with usual care. CLINICAL TRIAL REGISTRATION: NCT02837731.

Machine Learning Methods to Predict Acute Respiratory Failure and Acute Respiratory Distress Syndrome.

Acute respiratory failure (ARF) is a common problem in medicine that utilizes significant healthcare resources and is associated with high morbidity and mortality. Classification of acute respiratory failure is complicated, and it is often determined by the level of mechanical support that is required, or the discrepancy between oxygen supply and uptake. These phenotypes make acute respiratory failure a continuum of syndromes, rather than one homogenous disease process. Early recognition of the risk factors for new or worsening acute respiratory failure may prevent that process from occurring. Predictive analytical methods using machine learning leverage clinical data to provide an early warning for impending acute respiratory failure or its sequelae. The aims of this review are to summarize the current literature on ARF prediction, to describe accepted procedures and common machine learning tools for predictive tasks through the lens of ARF prediction, and to demonstrate the challenges and potential solutions for ARF prediction that can improve patient outcomes.

Increasing Cardiovascular Data Sampling Frequency and Referencing It to Baseline Improve Hemorrhage Detection.

We hypothesize that knowledge of a stable personalized baseline state and increased data sampling frequency would markedly improve the ability to detect progressive hypovolemia during hemorrhage earlier and with a lower false positive rate than when using less granular data. DESIGN: Prospective temporal challenge. SETTING: Large animal research laboratory, University Medical Center. SUBJECTS: Fifty-one anesthetized Yorkshire pigs. INTERVENTIONS: Pigs were instrumented with arterial, pulmonary arterial, and central venous catheters and allowed to stabilize for 30 minutes then bled at a constant rate of either 5 mL·min-1 (n = 13) or 20 (n = 38) until mean arterial pressure decreased to 40 or 30 mm Hg in the 5 and 20 mL·min-1 pigs, respectively. MEASUREMENTS AND MAIN RESULTS: Data during the stabilization period served as baseline. Hemodynamic variables collected at 250 Hz were used to create predictive models of "bleeding" using featurized beat-to-beat and waveform data and compared with models using mean unfeaturized hemodynamic variables averaged over 1-minute as simple hemodynamic metrics using random forest classifiers to identify bleeding with or without baseline data. The robustness of the prediction was evaluated in a leave-one-pig-out cross-validation. Predictive performance of models was compared by their activity monitoring operating characteristic and receiver operating characteristic profiles. Primary hemodynamic threshold data poorly identified bleed onset unless very stable initial baseline reference data were available. When referenced to baseline, bleed detection at a false positive rates of 10-2 with time to detect 80% of pigs bleeding was similar for simple hemodynamic metrics, beat-to-beat, and waveform at about 3-4 minutes. Whereas when universally baselined, increasing sampling frequency reduced latency of bleed detection from 10 to 8 to 6 minutes, for simple hemodynamic metrics, beat-to-beat, and waveform, respectively. Some informative features differed between simple hemodynamic metrics, beat-to-beat, and waveform models. CONCLUSIONS: Knowledge of personal stable baseline data allows for early detection of new-onset bleeding, whereas if no personal baseline exists increasing sampling frequency of hemodynamic monitoring data improves bleeding detection earlier and with lower false positive rate.