Search for a Dark-Matter-Induced Cosmic Axion Background with ADMX

We report the first result of a direct search for a cosmic axion background (CaB)-a relativistic background of axions that is not dark matter-performed with the axion haloscope, the Axion Dark Matter eXperiment (ADMX). Conventional haloscope analyses search for a signal with a narrow bandwidth, as predicted for dark matter, whereas the CaB will be broad. We introduce a novel analysis strategy, which searches for a CaB induced daily modulation in the power measured by the haloscope. Using this, we repurpose data collected to search for dark matter to set a limit on the axion photon coupling of a CaB originating from dark matter cascade decay via a mediator in the 800-995 MHz frequency range. We find that the present sensitivity is limited by fluctuations in the cavity readout as the instrument scans across dark matter masses. Nevertheless, we suggest that these challenges can be surmounted using superconducting qubits as single photon counters, and allow ADMX to operate as a telescope searching for axions emerging from the decay of dark matter. The daily modulation analysis technique we introduce can be deployed for various broadband rf signals, such as other forms of a CaB or even high-frequency gravitational waves.

Early prediction of central line associated bloodstream infection using machine learning

BACKGROUND

Central line-associated bloodstream infections (CLABSIs) are associated with significant morbidity, mortality, and increased healthcare costs. Despite the high prevalence of CLABSIs in the U.S., there are currently no tools to stratify a patient's risk of developing an infection as the result of central line placement. To this end, we have developed and validated a machine learning algorithm (MLA) that can predict a patient's likelihood of developing CLABSI using only electronic health record data in order to provide clinical decision support.

METHODS

We created three machine learning models to retrospectively analyze electronic health record data from 27,619 patient encounters. The models were trained and validated using an 80:20 split for the train and test data. Patients designated as having a central line procedure based on International Statistical Classification of Diseases and Related Health Problems 10 codes were included.

RESULTS

XGBoost was the highest performing MLA out of the three models, obtaining an AUROC of 0.762 for CLABSI risk prediction at 48 hours after the recorded time for central line placement.

CONCLUSIONS

Our results demonstrate that MLAs may be effective clinical decision support tools for assessment of CLABSI risk and should be explored further for this purpose.

Predicting pulmonary embolism among hospitalized patients with machine learning algorithms

Background

Objective

Materials and Methods

Results

Conclusions

Prediction of diabetic kidney disease with machine learning algorithms, upon the initial diagnosis of type 2 diabetes mellitus

INTRODUCTION

Diabetic kidney disease (DKD) accounts for the majority of increased risk of mortality for patients with diabetes, and eventually manifests in approximately half of those patients diagnosed with type 2 diabetes mellitus (T2DM). Although increased screening frequency can avoid delayed diagnoses, this is not uniformly implemented. The purpose of this study was to develop and retrospectively validate a machine learning algorithm (MLA) that predicts stages of DKD within 5 years upon diagnosis of T2DM.

RESEARCH DESIGN AND METHODS

Two MLAs were trained to predict stages of DKD severity, and compared with the Centers for Disease Control and Prevention (CDC) risk score to evaluate performance. The models were validated on a hold-out test set as well as an external dataset sourced from separate facilities.

RESULTS

The MLAs outperformed the CDC risk score in both the hold-out test and external datasets. Our algorithms achieved an area under the receiver operating characteristic curve (AUROC) of 0.75 on the hold-out set for prediction of any-stage DKD and an AUROC of over 0.82 for more severe endpoints, compared with the CDC risk score with an AUROC <0.70 on all test sets and endpoints.

CONCLUSION

This retrospective study shows that an MLA can provide timely predictions of DKD among patients with recently diagnosed T2DM.

Early prediction of severe acute pancreatitis using machine learning

BACKGROUND

Acute pancreatitis (AP) is one of the most common causes of gastrointestinal-related hospitalizations in the United States. Severe AP (SAP) is associated with a mortality rate of nearly 30% and is distinguished from milder forms of AP. Risk stratification to identify SAP cases needing inpatient treatment is an important aspect of AP diagnosis.

METHODS

We developed machine learning algorithms to predict which patients presenting with AP would require treatment for SAP. Three models were developed using logistic regression, neural networks, and XGBoost. Models were assessed in terms of area under the receiver operating characteristic (AUROC) and compared to the Harmless Acute Pancreatitis Score (HAPS) and Bedside Index for Severity in Acute Pancreatitis (BISAP) scores for AP risk stratification.

RESULTS

61,894 patients were used to train and test the machine learning models. With an AUROC value of 0.921, the model developed using XGBoost outperformed the logistic regression and neural network-based models. The XGBoost model also achieved a higher AUROC than both HAPS and BISAP for identifying patients who would be diagnosed with SAP.

CONCLUSIONS

Machine learning may be able to improve the accuracy of AP risk stratification methods and allow for more timely treatment and initiation of interventions.

Search for Invisible Axion Dark Matter in the 3.3-4.2 μeV Mass Range

We report the results from a haloscope search for axion dark matter in the 3.3-4.2  μeV mass range. This search excludes the axion-photon coupling predicted by one of the benchmark models of "invisible" axion dark matter, the Kim-Shifman-Vainshtein-Zakharov model. This sensitivity is achieved using a large-volume cavity, a superconducting magnet, an ultra low noise Josephson parametric amplifier, and sub-Kelvin temperatures. The validity of our detection procedure is ensured by injecting and detecting blind synthetic axion signals.

Usability of Electronic Health records in Predicting Short-term falls: Machine learning Applications in Senior Care Facilities (Preprint)

Background

Short-term fall prediction models that use electronic health records (EHRs) may enable the implementation of dynamic care practices that specifically address changes in individualized fall risk within senior care facilities.

Objective

The aim of this study is to implement machine learning (ML) algorithms that use EHR data to predict a 3-month fall risk in residents from a variety of senior care facilities providing different levels of care.

Methods

This retrospective study obtained EHR data (2007-2021) from Juniper Communities’ proprietary database of 2785 individuals primarily residing in skilled nursing facilities, independent living facilities, and assisted living facilities across the United States. We assessed the performance of 3 ML-based fall prediction models and the Juniper Communities’ fall risk assessment. Additional analyses were conducted to examine how changes in the input features, training data sets, and prediction windows affected the performance of these models.

Results

The Extreme Gradient Boosting model exhibited the highest performance, with an area under the receiver operating characteristic curve of 0.846 (95% CI 0.794-0.894), specificity of 0.848, diagnostic odds ratio of 13.40, and sensitivity of 0.706, while achieving the best trade-off in balancing true positive and negative rates. The number of active medications was the most significant feature associated with fall risk, followed by a resident’s number of active diseases and several variables associated with vital signs, including diastolic blood pressure and changes in weight and respiratory rates. The combination of vital signs with traditional risk factors as input features achieved higher prediction accuracy than using either group of features alone.

Conclusions

This study shows that the Extreme Gradient Boosting technique can use a large number of features from EHR data to make short-term fall predictions with a better performance than that of conventional fall risk assessments and other ML models. The integration of routinely collected EHR data, particularly vital signs, into fall prediction models may generate more accurate fall risk surveillance than models without vital signs. Our data support the use of ML models for dynamic, cost-effective, and automated fall predictions in different types of senior care facilities.

Retrospective validation of a machine learning clinical decision support tool for myocardial infarction risk stratification

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.

Personalized stratification of hospitalization risk amidst COVID-19: A machine learning approach

Objective: In the wake of COVID-19, the United States (U.S.) 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 62% 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 to guide vaccine distribution, anticipate hospital resource needs, and assist health care policymakers to make care decisions in a more principled manner.

Semi-supervised deep learning from time series clinical data for acute respiratory distress syndrome prediction: model development and validation study

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 (<97%) to predict the subsequent development of ARDS during the remaining duration of patients’ hospital stay. Model performance was assessed with the area under the receiver operating characteristic curve and area under the precision recall curve of an external hold-out test set.

Results

For the whole data set, the median time between the first peripheral oxygen saturation measurement of <97% and subsequent respiratory failure was 21 hours. The area under the receiver operating characteristic curve for predicting subsequent ARDS development was 0.73 when the model was trained on a labeled data set of 6930 patients, 0.78 when the model was trained on the labeled data set that had been augmented with the unlabeled data set of 16,173 patients by using SSL techniques, and 0.84 when the model was trained on the entire training set of 23,103 labeled patients.

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.

Predicting ventilator-associated pneumonia with machine learning

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.

A machine learning approach to predicting risk of myelodysplastic syndrome

BACKGROUND

Early myelodysplastic syndrome (MDS) diagnosis can allow physicians to provide early treatment, which may delay advancement of MDS and improve quality of life. However, MDS often goes unrecognized and is difficult to distinguish from other disorders. We developed a machine learning algorithm for the prediction of MDS one year prior to clinical diagnosis of the disease.

METHODS

Retrospective analysis was performed on 790,470 patients over the age of 45 seen in the United States between 2007 and 2020. A gradient boosted decision tree model (XGB) was built to predict MDS diagnosis using vital signs, lab results, and demographics from the prior two years of patient data. The XGB model was compared to logistic regression (LR) and artificial neural network (ANN) models. The models did not use blast percentage and cytogenetics information as inputs. Predictions were made one year prior to MDS diagnosis as determined by International Classification of Diseases (ICD) codes, 9th and 10th revisions. Performance was assessed with regard to area under the receiver operating characteristic curve (AUROC).

RESULTS

On a hold-out test set, the XGB model achieved an AUROC value of 0.87 for prediction of MDS one year prior to diagnosis, with a sensitivity of 0.79 and specificity of 0.80. The XGB model was compared against LR and ANN models, which achieved an AUROC of 0.838 and 0.832, respectively.

CONCLUSIONS

Machine learning may allow for early MDS diagnosis MDS and more appropriate treatment administration.

Prediction of short-term mortality in acute heart failure patients using minimal electronic health record data

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.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13040-021-00255-w.

Machine Learning as a Precision-Medicine Approach to Prescribing COVID-19 Pharmacotherapy with Remdesivir or Corticosteroids

Purpose: Coronavirus disease–2019 (COVID-19) continues to be a global threat and remains a significant cause of hospitalizations. Recent clinical guidelines have supported the use of corticosteroids or remdesivir in the treatment of COVID-19. However, uncertainty remains about which patients are most likely to benefit from treatment with either drug; such knowledge is crucial for avoiding preventable adverse effects, minimizing costs, and effectively allocating resources. This study presents a machine-learning system with the capacity to identify patients in whom treatment with a corticosteroid or remdesivir is associated with improved survival time.

Methods: Gradient-boosted decision-tree models used for predicting treatment benefit were trained and tested on data from electronic health records dated between December 18, 2019, and October 18, 2020, from adult patients (age ≥18 years) with COVID-19 in 10 US hospitals. Models were evaluated for performance in identifying patients with longer survival times when treated with a corticosteroid versus remdesivir. Fine and Gray proportional-hazards models were used for identifying significant findings in treated and nontreated patients, in a subset of patients who received supplemental oxygen, and in patients identified by the algorithm. Inverse probability-of-treatment weights were used to adjust for confounding. Models were trained and tested separately for each treatment.

Findings: Data from 2364 patients were included, with men comprising slightly more than 50% of the sample; 893 patients were treated with remdesivir, and 1471 were treated with a corticosteroid. After adjustment for confounding, neither corticosteroids nor remdesivir use was associated with increased survival time in the overall population or in the subpopulation that received supplemental oxygen. However, in the populations identified by the algorithms, both corticosteroids and remdesivir were significantly associated with an increase in survival time, with hazard ratios of 0.56 and 0.40, respectively (both, P = 0.04).

Implications: Machine-learning methods have the capacity to identify hospitalized patients with COVID-19 in whom treatment with a corticosteroid or remdesivir is associated with an increase in survival time. These methods may help to improve patient outcomes and allocate resources during the COVID-19 crisis.

Convolutional Neural Network Model for Intensive Care Unit Acute Kidney Injury Prediction

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.

A Machine Learning Approach to Predict Deep Venous Thrombosis Among Hospitalized Patients

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.

Validation of a machine learning algorithm for early severe sepsis prediction: a retrospective study predicting severe sepsis up to 48 h in advance using a diverse dataset from 461 US hospitals

BACKGROUND

Severe sepsis and septic shock are among the leading causes of death in the United States and sepsis remains one of the most expensive conditions to diagnose and treat. Accurate early diagnosis and treatment can reduce the risk of adverse patient outcomes, but the efficacy of traditional rule-based screening methods is limited. The purpose of this study was to develop and validate a machine learning algorithm (MLA) for severe sepsis prediction up to 48 h before onset using a diverse patient dataset.

METHODS

Retrospective analysis was performed on datasets composed of de-identified electronic health records collected between 2001 and 2017, including 510,497 inpatient and emergency encounters from 461 health centers collected between 2001 and 2015, and 20,647 inpatient and emergency encounters collected in 2017 from a community hospital. MLA performance was compared to commonly used disease severity scoring systems and was evaluated at 0, 4, 6, 12, 24, and 48 h prior to severe sepsis onset.

RESULTS

270,438 patients were included in analysis. At time of onset, the MLA demonstrated an AUROC of 0.931 (95% CI 0.914, 0.948) and a diagnostic odds ratio (DOR) of 53.105 on a testing dataset, exceeding MEWS (0.725, P < .001; DOR 4.358), SOFA (0.716; P < .001; DOR 3.720), and SIRS (0.655; P < .001; DOR 3.290). For prediction 48 h prior to onset, the MLA achieved an AUROC of 0.827 (95% CI 0.806, 0.848) on a testing dataset. On an external validation dataset, the MLA achieved an AUROC of 0.948 (95% CI 0.942, 0.954) at the time of onset, and 0.752 at 48 h prior to onset.

CONCLUSIONS

The MLA accurately predicts severe sepsis onset up to 48 h in advance using only readily available vital signs extracted from the existing patient electronic health records. Relevant implications for clinical practice include improved patient outcomes from early severe sepsis detection and treatment.

A Racially Unbiased, Machine Learning Approach to Prediction of Mortality: Algorithm Development Study

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<.001, respectively).

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.

Mortality prediction model for the triage of COVID-19, pneumonia, and mechanically ventilated ICU patients: A retrospective study

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.

•

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.

0606 Comparative Effectiveness of Sleep Apnea Screening Tools During Inpatient Rehabilitation for Moderate to Severe TBI

Introduction

Recent studies highlight prevalent obstructive sleep apnea after moderate to severe TBI during a time of critical neural repair. The purpose of this study is to determine the diagnostic sensitivity, specificity and comparative effectiveness of traditional sleep apnea screening tools in TBI neurorehabilitation admissions.

Methods

This is a prospective diagnostic comparative effectiveness trial of sleep apnea screening tools (STOPBANG, Berlin, MAPI [Multi-Apnea Prediction Index]) relative Level 1 polysomnography at six TBI Model System Inpatient Rehabilitation Centers. Between 05/2017 and 02/2019, 449 of 896 screened were eligible for the trial with 345 consented (77% consented). Additional screening left 263 eligible for and completing polysomnography with final analyses completed on 248. The primary outcome was the Area Under the Curve (AUC) of screening tools relative to total apnea hypopnea index ≥15 (AHI, moderate to severe apnea) measured at a median of 47 days post-TBI (IQR 29-47).

Results

Participants were primarily young to middle age (AGE IQR 28,40,59), male (81%), white (74%), and had primarily severe TBI (IQR GCS 3,6,14). A subset (26%) had a history of military service. Results revealed that the Berlin high risk score (ROC-AUC=0.63) was inferior to the MAPI (ROC-AUC = 0.7802) (p=.0211, CI: 0.0181, 0.2233) and STOPBANG (ROCAUC = 0.7852) (p=.0006, CI: 0.0629, 0.2302); both of which had comparable AUC (p=.7245, CI: -0.0472, 0.0678). Findings were similar for AHI≥30 (severe apnea); however, no differences across scales was observed at AHI&gt;5. The pattern was similar across TBI severity subgroups except for delirium or post-traumatic amnesia status wherein the MAPI outperformed the Berlin and STOPBANG. Youden’s Index to determine risk yielded lower sensitivities but higher specificities relative to non-TBI samples.

Conclusion

This study is the first to provide clinicians with data to support a choice for which sleep apnea screening tools are more effective during inpatient rehabilitation for moderate to severe TBI (STOPBANG, MAPI vs Berlin) to help reduce comorbidity and possibly improve neurologic outcome.

Support

PCORI (CER-1511-33005), GDHS (W91YTZ-13-C-0015; HT0014-19-C-0004)) for DVBIC, NIDILRR (NSDC Grant # 90DPTB00070, #90DP0084, 90DPTB0013-01-00, 90DPTB0008, 90DPT80004-02).

Effect of a sepsis prediction algorithm on patient mortality, length of stay and readmission: a prospective multicentre clinical outcomes evaluation of real-world patient data from US hospitals

BACKGROUND

Severe 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.

OBJECTIVE

The 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.

DESIGN

Prospective clinical outcomes evaluation.

SETTING

Evaluation 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.

PARTICIPANTS

Analyses 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).

INTERVENTIONS

Machine learning algorithm for severe sepsis prediction.

OUTCOME MEASURES

In-hospital mortality, length of stay and 30-day readmission rates.

RESULTS

Hospitals 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.

CONCLUSIONS

Reductions 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 NUMBER

NCT03960203.

Abstract P3-14-07: Evaluation of the effects of talazoparib on QT interval prolongation

Background: Talazoparib (TAL), an oral poly ADP-ribose polymerase inhibitor, is under investigation in multiple oncologic clinical trials and has been submitted to the US FDA for use in patients (pts) with germline BRCA-mutated, HER2-negative advanced breast cancer.

International Conference on Harmonisation guidance recommends all new drugs be evaluated for effects on cardiac repolarization in a well-controlled clinical study. For drugs for which such evaluation cannot be conducted in healthy volunteers (eg, most anticancer agents), collection of robust corrected QT (QTc) interval data from a dedicated QTc study (hybrid thorough QT/QTc study) in pts is required in the registration dossier. The effect of steady-state (ss) TAL (1 mg once daily) on cardiac repolarization in pts with advanced solid tumors was evaluated in an open-label phase 1 study (NCT03042910).

Methods: Continuous 12-lead electrocardiogram (ECG) recordings were collected at baseline (Day -1); time-matched pharmacokinetic (PK) samples and continuous ECG recordings were obtained on Days 1, 2, and 22 (when TAL concentrations achieved ss). On Day -1, pts had continuous 12-lead ECG recording starting at Time 0 (Day 1 dosing time) for 6 hrs. On Days 1 and 22, ECG recording started 45 min before TAL administration and continued for 6 hrs post dose and blood samples for PK were collected before dose and at 1, 2, 4, and 6 hrs post dose. On Day 2, a 30-min ECG recording and a PK sample were obtained before dose at Time 0.

Continuous ECG recordings were submitted to a central laboratory; triplicate 10-sec ECGs were extracted from a 5-min extraction window beginning 15 min before each PK collection time. ECG measurements were reported via blinded manual adjudication process and included PR interval, QT interval, RR interval, and QRS complex. The QT interval was corrected for effect of heart rate using Fridericia's correction (QTcF) and Bazett's correction (QTcB).

The estimate of change from time-matched baseline and its 2-sided 90% confidence interval (CI) was calculated for each nominal time point using PROC MEANS. Additionally, a prespecified PK/pharmacodynamic (PD) model was used to describe the relationship between plasma TAL concentrations ([TAL]) and QTc. The prespecified linear mixed-effects model included [TAL], time (categorical), and treatment with random pt effects on [TAL] and the intercept. If the upper bounds (UB) of 1-sided 95% CIs of time-matched ΔQTc for all ECG time points were &lt;20 msec and the UB of 1-sided 95% CIs of the predicted ΔQTc at the mean ss maximum [TAL] was &lt;20 msec, the effect of TAL on QTc was not of clinical relevance.

Results: 37 of 38 pts enrolled received TAL and were included in the ECG and PK/PD analyses. No pts had a postbaseline absolute maximum QTcF or QTcB ≥500 msec or ΔQTc ≥60 msec. The UB of the 1-sided 95% CI for the time-matched ΔQTcF and ΔQTcB were &lt;12 msec at all nominal ECG time points. In the PK/PD analysis, the slopes (95% CI) of QTcF-[TAL] and QTcB-[TAL] relationships were -0.14 (-0.78 to 0.50) msec/ng/mL and -0.24 (-0.88 to 0.41) msec/ng/mL, respectively, indicating that TAL did not have a concentration-dependent effect on QTcF or QTcB.

Conclusion: TAL does not have a clinically relevant effect on QTc.

Funding: Medivation LLC, acquired by Pfizer.

Citation Format: Hoffman J, Chakrabarti J, Wainberg ZA, Plotka A, Babu S, Milillo Naraine A, Kanamori D, Moroose R, Nguyen L, Wang D. Evaluation of the effects of talazoparib on QT interval prolongation [abstract]. In: Proceedings of the 2018 San Antonio Breast Cancer Symposium; 2018 Dec 4-8; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2019;79(4 Suppl):Abstract nr P3-14-07.

Machine-Learning-Based Laboratory Developed Test for the Diagnosis of Sepsis in High-Risk Patients

Sepsis, a dysregulated host response to infection, is a major health burden in terms of both mortality and cost. The difficulties clinicians face in diagnosing sepsis, alongside the insufficiencies of diagnostic biomarkers, motivate the present study. This work develops a machine-learning-based sepsis diagnostic for a high-risk patient group, using a geographically and institutionally diverse collection of nearly 500,000 patient health records. Using only a minimal set of clinical variables, our diagnostics outperform common severity scoring systems and sepsis biomarkers and benefit from being available immediately upon ordering.

Pediatric Severe Sepsis Prediction Using Machine Learning

Background: Early detection of pediatric severe sepsis is necessary in order to optimize effective treatment, and new methods are needed to facilitate this early detection. Objective: Can a machine-learning based prediction algorithm using electronic healthcare record (EHR) data predict severe sepsis onset in pediatric populations? Methods: EHR data were collected from a retrospective set of de-identified pediatric inpatient and emergency encounters for patients between 2-17 years of age, drawn from the University of California San Francisco (UCSF) Medical Center, with encounter dates between June 2011 and March 2016. Results: Pediatric patients (n = 9,486) were identified and 101 (1.06%) were labeled with severe sepsis following the pediatric severe sepsis definition of Goldstein et al. (1). In 4-fold cross-validation evaluations, the machine learning algorithm achieved an AUROC of 0.916 for discrimination between severe sepsis and control pediatric patients at the time of onset and AUROC of 0.718 at 4 h before onset. The prediction algorithm significantly outperformed the Pediatric Logistic Organ Dysfunction score (PELOD-2) (p < 0.05) and pediatric Systemic Inflammatory Response Syndrome (SIRS) (p < 0.05) in the prediction of severe sepsis 4 h before onset using cross-validation and pairwise t-tests. Conclusion: This machine learning algorithm has the potential to deliver high-performance severe sepsis detection and prediction through automated monitoring of EHR data for pediatric inpatients, which may enable earlier sepsis recognition and treatment initiation.

Bone density and asymmetry are not related to DDT in House Sparrows: Insights from micro-focus X-ray computed tomography

In organisms, DDT (Dichlorodiphenyltrichloroethane) and its metabolites, DDE (Dichlorodiphenyldichloroethylene) and DDD (Dichlorobischlorophenylethane) are endocrine mimics. They can influence bone density and other bone structural features. This study was conducted on House Sparrows (Passer domesticus) caught from the Free State - and the Limpopo Provinces of South Africa (SA). The sites were chosen based on spraying patterns of DDT for malaria control or non-spraying. The bone mineral densities of the femurs as well as the lengths of the left- and right leg bones were determined using micro-focus X-ray computed tomography (μ-XCT). The concentrations of DDT and its metabolites in the liver were determined with gas-chromatography mass-spectrometry to provide baseline concentrations of DDT in the body, allowing comparison of the various groups of birds. There was no asymmetry between the lengths of the bones of the left- and the right legs. DDT concentrations in the liver did not correlate with bone lengths. In addition, there were no significant differences between the relative densities of the left- and right leg bones with increase of concentrations of DDT. The concentrations of DDT and its metabolites did not have a significant effect on the measured bone parameters of House Sparrows. It is possible that the concentrations of DDT and its metabolites in the environments were too low to be injurious to the birds and/or tolerance to the insecticide has developed in the birds over more than six decades of almost continuous application of DDT.

Observation of Fine Time Structures in the Cosmic Proton and Helium Fluxes with the Alpha Magnetic Spectrometer on the International Space Station

We present the precision measurement from May 2011 to May 2017 (79 Bartels rotations) of the proton fluxes at rigidities from 1 to 60 GV and the helium fluxes from 1.9 to 60 GV based on a total of 1×10^{9} events collected with the Alpha Magnetic Spectrometer aboard the International Space Station. This measurement is in solar cycle 24, which has the solar maximum in April 2014. We observed that, below 40 GV, the proton flux and the helium flux show nearly identical fine structures in both time and relative amplitude. The amplitudes of the flux structures decrease with increasing rigidity and vanish above 40 GV. The amplitudes of the structures are reduced during the time period, which started one year after solar maximum, when the proton and helium fluxes steadily increase. Above ∼3  GV the p/He flux ratio is time independent. We observed that below ∼3  GV the ratio has a long-term decrease coinciding with the period during which the fluxes start to rise.

Abstract P5-21-23: Evaluation of the drug interaction potential of palbociclib and exemestane – Results from the PEARL pharmacokinetic sub-Study

Background: Palbociclib (PAL) is an oral cyclin-dependent kinase (CDK) 4/6 inhibitor that is under investigation in multiple oncologic clinical trials and is currently approved for use in combination with aromatase inhibitors (AIs) or fulvestrant (FUL) in patients with hormone receptor positive (HR+), human epidermal growth factor receptor 2 negative (HER2–) advanced breast cancer (BC).

The PEARL Study is an ongoing international, open label, controlled, randomized Phase 3 study comparing the efficacy and safety of PAL in combination with endocrine therapy (exemestane [EXE] or FUL) versus capecitabine in postmenopausal women with HR+/ HER2– metastatic BC whose disease progressed on AIs. A secondary objective of the study was to evaluate the pharmacokinetics (PK) of PAL (125mg QD, 3 weeks on/1 week off) and EXE (25mg QD, continuously) when coadministered. This is the first study to investigate the drug-drug interaction (DDI) potential of the combination of PAL and the AI EXE.

Methods: Patients (pts) randomized to the PAL+EXE arm of the PEARL Study in seven selected sites had the option of participating in the PK sub-study. Those who enrolled in the PK sub-study received EXE alone in a 7-day lead-in period immediately prior to Cycle 1 Day 1, when both drugs were coadministered on their standard dosing regimens. Sub-study pts were to have 2 pre-dose plasma PK samples drawn at steady-state (ss) during the lead-in period ("EXE Alone") for EXE determination, and 2 ss PK samples drawn for EXE and PAL determination (2 per analyte) during coadministration ("PAL+EXE"). Plasma concentrations of PAL and EXE were measured using validated liquid chromatography-tandem mass spectrometry (LC-MS/MS) methods. The withinpatient mean concentration of the PK samples which met ss acceptance criteria (WPM-Ctrough) for each analyte were generated for each treatment period as the input for DDI analyses.

To assess the effect of coadministration of PAL on EXE PK, the WPM-Ctrough of EXE was compared within patients between the "PAL+EXE" (Test) and "EXE Alone" (Reference) treatment periods using a one-way analysis of variance (ANOVA) model with treatment as a fixed effect and patient as a random effect. To assess the effect of coadministration of EXE on PAL PK, the WPM-Ctrough of PAL was compared between the "PAL+EXE" period (Test) and historical data (Reference) using an ANOVA model. Analysis of covariance (ANCOVA) models were used to assess the impact of demographic differences between analysis populations in covariates known to impact PAL PK on the ANOVA model conclusions.

Results: A total of 26 pts randomized to the PAL+EXE arm were enrolled in the PK sub-study and had PK samples analysed, of which 23 meet ss acceptance criteria. The ratio of the adjusted geometric means for EXE WPM-Ctrough was 106.9% (90%CI: 82.4-138.8), when EXE was administered with PAL, compared with its administration alone. Likewise, the models to assess potential for EXE to perpetrate DDI on PAL PK showed ratios of adjusted geometric means of 102.4% (90%CI: 82.0-127.9) and 111.6% (90%CI: 90.3137.8), when adjusted for covariates.

Conclusion: The PK data indicate a lack of a clinically meaningful DDI between PAL and EXE when the 2 drugs are coadministered.

Sponsor: GEICAM

Citation Format: Martín M, Hoffman J, Ruiz-Borrego M, Muñoz M, Calvo L, Crownover P, García-Sáenz JA, Alba E, Wang D, Thallinger C, Stradella A, Montaño Á, Adamo B, Antolín S, Moreno-Antón F, Falo C, Ruiz V, Martín N, Caballero R, Carrasco E, Gil-Gil M. Evaluation of the drug interaction potential of palbociclib and exemestane – Results from the PEARL pharmacokinetic sub-Study [abstract]. In: Proceedings of the 2017 San Antonio Breast Cancer Symposium; 2017 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2018;78(4 Suppl):Abstract nr P5-21-23.

Observation of the Identical Rigidity Dependence of He, C, and O Cosmic Rays at High Rigidities by the Alpha Magnetic Spectrometer on the International Space Station

We report the observation of new properties of primary cosmic rays He, C, and O measured in the rigidity (momentum/charge) range 2 GV to 3 TV with 90×10^{6} helium, 8.4×10^{6} carbon, and 7.0×10^{6} oxygen nuclei collected by the Alpha Magnetic Spectrometer (AMS) during the first five years of operation. Above 60 GV, these three spectra have identical rigidity dependence. They all deviate from a single power law above 200 GV and harden in an identical way.

Using Transfer Learning for Improved Mortality Prediction in a Data-Scarce Hospital Setting

Algorithm–based clinical decision support (CDS) systems associate patient-derived health data with outcomes of interest, such as in-hospital mortality. However, the quality of such associations often depends on the availability of site-specific training data. Without sufficient quantities of data, the underlying statistical apparatus cannot differentiate useful patterns from noise and, as a result, may underperform. This initial training data burden limits the widespread, out-of-the-box, use of machine learning–based risk scoring systems. In this study, we implement a statistical transfer learning technique, which uses a large “source” data set to drastically reduce the amount of data needed to perform well on a “target” site for which training data are scarce. We test this transfer technique with AutoTriage, a mortality prediction algorithm, on patient charts from the Beth Israel Deaconess Medical Center (the source) and a population of 48 249 adult inpatients from University of California San Francisco Medical Center (the target institution). We find that the amount of training data required to surpass 0.80 area under the receiver operating characteristic (AUROC) on the target set decreases from more than 4000 patients to fewer than 220. This performance is superior to the Modified Early Warning Score (AUROC: 0.76) and corresponds to a decrease in clinical data collection time from approximately 6 months to less than 10 days. Our results highlight the usefulness of transfer learning in the specialization of CDS systems to new hospital sites, without requiring expensive and time-consuming data collection efforts.

Cost and mortality impact of an algorithm-driven sepsis prediction system

AIMS

To compute the financial and mortality impact of InSight, an algorithm-driven biomarker, which forecasts the onset of sepsis with minimal use of electronic health record data.

METHODS

This study compares InSight with existing sepsis screening tools and computes the differential life and cost savings associated with its use in the inpatient setting. To do so, mortality reduction is obtained from an increase in the number of sepsis cases correctly identified by InSight. Early sepsis detection by InSight is also associated with a reduction in length-of-stay, from which cost savings are directly computed.

RESULTS

InSight identifies more true positive cases of severe sepsis, with fewer false alarms, than comparable methods. For an individual ICU with 50 beds, for example, it is determined that InSight annually saves 75 additional lives and reduces sepsis-related costs by $560,000.

LIMITATIONS

InSight performance results are derived from analysis of a single-center cohort. Mortality reduction results rely on a simplified use case, which fixes prediction times at 0, 1, and 2 h before sepsis onset, likely leading to under-estimates of lives saved. The corresponding cost reduction numbers are based on national averages for daily patient length-of-stay cost.

CONCLUSIONS

InSight has the potential to reduce sepsis-related deaths and to lead to substantial cost savings for healthcare facilities.