Origins of Racial and Ethnic Bias in Pulmonary Technologies.

Understanding how biases originate in medical technologies and developing safeguards to identify, mitigate, and remove their harms are essential to ensuring equal performance in all individuals. Drawing upon examples from pulmonary medicine, this article describes how bias can be introduced in the physical aspects of the technology design, via unrepresentative data, or by conflation of biological with social determinants of health. It then can be perpetuated by inadequate evaluation and regulatory standards. Research demonstrates that pulse oximeters perform differently depending on patient race and ethnicity. Pulmonary function testing and algorithms used to predict healthcare needs are two additional examples of medical technologies with racial and ethnic biases that may perpetuate health disparities.

External Validation and Comparison of a General Ward Deterioration Index Between Diversely Different Health Systems.

OBJECTIVES: Implementing a predictive analytic model in a new clinical environment is fraught with challenges. Dataset shifts such as differences in clinical practice, new data acquisition devices, or changes in the electronic health record (EHR) implementation mean that the input data seen by a model can differ significantly from the data it was trained on. Validating models at multiple institutions is therefore critical. Here, using retrospective data, we demonstrate how Predicting Intensive Care Transfers and other UnfoReseen Events (PICTURE), a deterioration index developed at a single academic medical center, generalizes to a second institution with significantly different patient population. DESIGN: PICTURE is a deterioration index designed for the general ward, which uses structured EHR data such as laboratory values and vital signs. SETTING: The general wards of two large hospitals, one an academic medical center and the other a community hospital. SUBJECTS: The model has previously been trained and validated on a cohort of 165,018 general ward encounters from a large academic medical center. Here, we apply this model to 11,083 encounters from a separate community hospital. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: The hospitals were found to have significant differences in missingness rates (> 5% difference in 9/52 features), deterioration rate (4.5% vs 2.5%), and racial makeup (20% non-White vs 49% non-White). Despite these differences, PICTURE's performance was consistent (area under the receiver operating characteristic curve [AUROC], 0.870; 95% CI, 0.861-0.878), area under the precision-recall curve (AUPRC, 0.298; 95% CI, 0.275-0.320) at the first hospital; AUROC 0.875 (0.851-0.902), AUPRC 0.339 (0.281-0.398) at the second. AUPRC was standardized to a 2.5% event rate. PICTURE also outperformed both the Epic Deterioration Index and the National Early Warning Score at both institutions. CONCLUSIONS: Important differences were observed between the two institutions, including data availability and demographic makeup. PICTURE was able to identify general ward patients at risk of deterioration at both hospitals with consistent performance (AUROC and AUPRC) and compared favorably to existing metrics.

Multi-center atrial fibrillation electrocardiogram (ECG) classification using Fourier space convolutional neural networks (FD-CNN) and transfer learning.

There has been a proliferation of machine learning (ML) electrocardiogram (ECG) classification algorithms reaching >85% accuracy for various cardiac pathologies. Despite the high accuracy at individual institutions, challenges remain when it comes to multi-center deployment. Transfer learning (TL) is a technique in which a model trained for a specific task is repurposed for another related task, in this case ECG ML model trained at one institution is fine-tuned to be utilized to classify ECGs at another institution. Models trained at one institution, however, might not be generalizable for accurate classification when deployed broadly due to differences in type, time, and sampling rate of traditional ECG acquisition. In this study, we evaluate the performance of time domain (TD) and frequency domain (FD) convolutional neural network (CNN) classification models in an inter-institutional scenario leveraging three different publicly available datasets. The larger PTB-XL ECG dataset was used to initially train TD and FD CNN models for atrial fibrillation (AFIB) classification. The models were then tested on two different data sets, Lobachevsky University Electrocardiography Database (LUDB) and Korea University Medical Center database (KURIAS). The FD model was able to retain most of its performance (>0.81 F1-score), whereas TD was highly affected (<0.53 F1-score) by the dataset variations, even with TL applied. The FD CNN showed superior robustness to cross-institutional variability and has potential for widespread application with no compromise to ECG classification performance.

Fourier space approach for convolutional neural network (CNN) electrocardiogram (ECG) classification: A proof-of-concept study.

There has been a proliferation of machine learning (ML) electrocardiogram (ECG) classification algorithms reaching > 85% accuracy for various cardiac pathologies. Although the accuracy within institutions might be high, models trained at one institution might not be generalizable enough for accurate detection when deployed in other institutions due to differences in type of signal acquisition, sampling frequency, time of acquisition, device noise characteristics and number of leads. In this proof-of-concept study, we leverage the publicly available PTB-XL dataset to investigate the use of time-domain (TD) and frequency-domain (FD) convolutional neural networks (CNN) to detect myocardial infarction (MI), ST/T-wave changes (STTC), atrial fibrillation (AFIB) and sinus arrhythmia (SARRH). To simulate interinstitutional deployment, the TD and FD implementations were also compared on adapted test sets using different sampling frequencies 50 Hz, 100 Hz and 250 Hz, and acquisition times of 5 s and 10s at 100 Hz sampling frequency from the training dataset. When tested on the original sampling frequency and duration, the FD approach showed comparable results to TD for MI (0.92 FD - 0.93 TD AUROC) and STTC (0.94 FD - 0.95 TD AUROC), and better performance for AFIB (0.99 FD - 0.86 TD AUROC) and SARRH (0.91 FD - 0.65 TD AUROC). Although both methods were robust to changes in sampling frequency, changes in acquisition time were detrimental to the TD MI and STTC AUROCs, at 0.72 and 0.58 respectively. Alternatively, the FD approach was able to maintain the same level of performance, and, therefore, showed better potential for interinstitutional deployment.

Tracking Peripheral Artery Motion and Vascular Resistance With a Multimodal Wearable Sensor Under Pressure Perturbations.

The status of peripheral arteries is known to be a key physiological indicator of the body's response to both acute and chronic medical conditions. In this paper, peripheral artery deformation is tracked by wearable photoplethysmograph (PPG) and piezo-electric (polyvinylidene difluoride, PVDF) sensors, under pressure-varying cuff. A simple mechanical model for the local artery and intervening tissue captures broad features present in the PPG and PVDF signals on multiple swine subjects, with respect to varying cuff pressure. These behaviors provide insight into the robustness of cardiovascular property identification by noninvasive wearable sensing. This is found to help refine noninvasive blood pressure measurements and estimation of systemic vascular resistance (SVR) using selected features of sensor amplitude versus applied pressure.

Detection of Low Cardiac Index using a Polyvinylidene Fluoride-Based Wearable Ring and Convolutional Neural Networks.

This study investigated the use of a wearable ring made of polyvinylidene fluoride film to identify a low cardiac index (≤2 L/min). The waveform generated by the ring contains patterns that may be indicative of low blood pressure and/or high vascular resistance, both of which are markers of a low cardiac index. In particular, the waveform contains reflection waves whose timing and amplitude are correlated with pulse travel time and vascular resistance, respectively. Hence, the pattern of the waveform is expected to vary in response to changes in blood pressure and vascular resistance. By analyzing the morphology of the waveform, our aim was to create a tool to identify patients with low cardiac index. This was done using a convolutional neural network which was trained on data from animal models. The model was then tested on waveforms that were collected from patients undergoing pulmonary artery catheterization. The results indicate high accuracy in classifying patients with a low cardiac index, achieving an area under the receiver operating characteristics and precision-recall curves of 0.88 and 0.71, respectively.

Demonstrating the consequences of learning missingness patterns in early warning systems for preventative health care: A novel simulation and solution.

When using tree-based methods to develop predictive analytics and early warning systems for preventive healthcare, it is important to use an appropriate imputation method to prevent learning the missingness pattern. To demonstrate this, we developed a novel simulation that generated synthetic electronic health record data using a variational autoencoder with a custom loss function, which took into account the high missing rate of electronic health data. We showed that when tree-based methods learn missingness patterns (correlated with adverse events) in electronic health record data, this leads to decreased performance if the system is used in a new setting that has different missingness patterns. Performance is worst in this scenario when the missing rate between those with and without an adverse event is the greatest. We found that randomized and Bayesian regression imputation methods mitigate the issue of learning the missingness pattern for tree-based methods. We used this information to build a novel early warning system for predicting patient deterioration in general wards and telemetry units: PICTURE (Predicting Intensive Care Transfers and other UnfoReseen Events). To develop, tune, and test PICTURE, we used labs and vital signs from electronic health records of adult patients over four years (n = 133,089 encounters). We analyzed primary outcomes of unplanned intensive care unit transfer, emergency vasoactive medication administration, cardiac arrest, and death. We compared PICTURE with existing early warning systems and logistic regression at multiple levels of granularity. When analyzing PICTURE on the testing set using all observations within a hospital encounter (event rate = 3.4%), PICTURE had an area under the receiver operating characteristic curve (AUROC) of 0.83 and an adjusted (event rate = 4%) area under the precision-recall curve (AUPR) of 0.27, while the next best tested method-regularized logistic regression-had an AUROC of 0.80 and an adjusted AUPR of 0.22. To ensure system interpretability, we applied a state-of-the-art prediction explainer that provided a ranked list of features contributing most to the prediction. Though it is currently difficult to compare machine learning-based early warning systems, a rudimentary comparison with published scores demonstrated that PICTURE is on par with state-of-the-art machine learning systems. To facilitate more robust comparisons and development of early warning systems in the future, we have released our variational autoencoder's code and weights so researchers can (a) test their models on data similar to our institution and (b) make their own synthetic datasets.

Learning Using Concave and Convex Kernels: Applications in Predicting Quality of Sleep and Level of Fatigue in Fibromyalgia.

Fibromyalgia is a medical condition characterized by widespread muscle pain and tenderness and is often accompanied by fatigue and alteration in sleep, mood, and memory. Poor sleep quality and fatigue, as prominent characteristics of fibromyalgia, have a direct impact on patient behavior and quality of life. As such, the detection of extreme cases of sleep quality and fatigue level is a prerequisite for any intervention that can improve sleep quality and reduce fatigue level for people with fibromyalgia and enhance their daytime functionality. In this study, we propose a new supervised machine learning method called Learning Using Concave and Convex Kernels (LUCCK). This method employs similarity functions whose convexity or concavity can be configured so as to determine a model for each feature separately, and then uses this information to reweight the importance of each feature proportionally during classification. The data used for this study was collected from patients with fibromyalgia and consisted of blood volume pulse (BVP), 3-axis accelerometer, temperature, and electrodermal activity (EDA), recorded by an Empatica E4 wristband over the courses of several days, as well as a self-reported survey. Experiments on this dataset demonstrate that the proposed machine learning method outperforms conventional machine learning approaches in detecting extreme cases of poor sleep and fatigue in people with fibromyalgia.

Intrastate Variation in Treatment and Outcomes of Out-of-Hospital Cardiac Arrest.

OBJECTIVE: Our objective was to analyze and compare out-of-hospital cardiac arrest (OHCA) system of care performance and outcomes at the Medical Control Authority (MCA) level in the state of Michigan. We hypothesized that clinically and statistically significant variations in treatment and outcomes of OHCA exists within a single U.S. state. METHODS: We performed a retrospective, observational study of all non-traumatic EMS-treated OHCA from the state of Michigan CARES registry for 2014-2015. Geocoding of the OHCA incident address was used to assign records to individual MCAs. MCA-based demographics, arrest characteristics, system of care performance and outcomes were quantified and compared. Associations between demographics, system of care parameters, and outcomes were examined at the MCA level. RESULTS: A total of 8,115 records with complete data were available for analysis. Eleven MCAs met study inclusion criteria of >100 cases, producing a final sample size of 7,788 records (96%). Statistically significant variations in survival to hospital discharge ranged from 4.5% to 15% (p < 0.001) (Adjusted odds ratio [AOR] range 0.6-2.0) and survival with good neurologic outcome 2.7-12.5% (p < 0.001; AOR range 0.5-2.2,) were observed across MCAs. Bystander CPR ranged from 32% to 53% (p < 0.001) and bystander AED application ranged from 3.5% 11.5% (p < 0.05). Of patients admitted to the hospital alive, 29-68% received targeted temperature management. In hospital mortality ranged from 53.1% to 73.9% (p < 0.05). CONCLUSION: Significant intrastate variability in OHCA system of care performance and outcomes currently exist and are similar to what has been previously reported across North America almost a decade ago. This degree of variability highlights the opportunity to optimize modifiable factors within local systems of care to improve OHCA outcomes.

The physiological determinants of symptom burden in cirrhosis with ascites.

BACKGROUND & AIMS: Paracentesis is commonly used to manage patient discomfort due to ascites. The relationship between ascites pressure, ascites volume, and patient discomfort has not been elucidated. METHODS: We prospectively enrolled adult patients with non-malignant ascites undergoing outpatient therapeutic paracenteses from 2021 to 2024 at a tertiary care hospital. Patients completed a validated symptom questionnaire (ASI-7, maximum score 35) before, immediately after, and 1 week after paracentesis. An open-ended manometer was used to measure ascites pressure at the beginning and end of paracentesis. Mixed effect linear regression was performed to evaluate the relationships between patient characteristics, pressure, volume, and symptoms. RESULTS: One hundred and fifty paracentesis procedures among 48 unique patients with an average Model for End Stage Liver Disease-Sodium 3.0 of 16.7 were included. An average of 6.5 L was drained, which reduced abdominal pressure from a mean of 13.7 to 6.0 cm H2O (10.1 to 4.4 mmHg, p < 0.001) and mean symptom score from 22.6 to 6.5 (p < 0.001). Regression models identified that symptoms and abdominal pressure linearly correlated above a pressure of 6 cm H2O or ASI-7 score of 16 (p < 0.01). Taller patients required about 670 ml additional drainage per inch above the cohort mean height (5'8″) to achieve the same symptom relief. CONCLUSIONS: Pressure measured at the bedside can be used to explore changes in abdominal pressure during paracentesis. Pressure, volume, and patient level factors such as height contribute to patient symptoms but cannot fully explain discomfort associated with ascites and relief after paracentesis.

Collaborative strategies for deploying artificial intelligence to complement physician diagnoses of acute respiratory distress syndrome.

There is a growing gap between studies describing the capabilities of artificial intelligence (AI) diagnostic systems using deep learning versus efforts to investigate how or when to integrate AI systems into a real-world clinical practice to support physicians and improve diagnosis. To address this gap, we investigate four potential strategies for AI model deployment and physician collaboration to determine their potential impact on diagnostic accuracy. As a case study, we examine an AI model trained to identify findings of the acute respiratory distress syndrome (ARDS) on chest X-ray images. While this model outperforms physicians at identifying findings of ARDS, there are several reasons why fully automated ARDS detection may not be optimal nor feasible in practice. Among several collaboration strategies tested, we find that if the AI model first reviews the chest X-ray and defers to a physician if it is uncertain, this strategy achieves a higher diagnostic accuracy (0.869, 95% CI 0.835-0.903) compared to a strategy where a physician reviews a chest X-ray first and defers to an AI model if uncertain (0.824, 95% CI 0.781-0.862), or strategies where the physician reviews the chest X-ray alone (0.808, 95% CI 0.767-0.85) or the AI model reviews the chest X-ray alone (0.847, 95% CI 0.806-0.887). If the AI model reviews a chest X-ray first, this allows the AI system to make decisions for up to 79% of cases, letting physicians focus on the most challenging subsets of chest X-rays.

A Comprehensive Comparison of Six Publicly Available Algorithms for Localization of QRS Complex on Electrocardiograph.

The QRS complex is the most prominent feature of the electrocardiogram (ECG) that is used as a marker to identify the cardiac cycles. Identification of QRS complex locations enables arrhythmia detection and heart rate variability estimation. Therefore, accurate and consistent localization of the QRS complex is an important component of automated ECG analysis which is necessary for the early detection of cardiovascular diseases. This study evaluates the performance of six popular publicly available QRS complex detection methods on a large dataset of over half a million ECGs in a diverse population of patients. We found that a deep-learning method that won first place in the 2019 Chinese physiological challenge (CPSC-1) outperforms the remaining five QRS complex detection methods with an F1 score of 98.8% and an absolute sdRR error of 5.5 ms. We also examined the stratified performance of the studied methods on various cardiac conditions. All six methods had a lower performance in the detection of QRS complexes in ECG signals of patients with pacemakers, complete atrioventricular block, or indeterminate cardiac axis. We also concluded that, in the presence of different cardiac conditions, CPSC-1 is more robust than Pan-Tompkins which is the most popular model for QRS complex detection. We expect that this study can potentially serve as a guide for researchers on the appropriate QRS detection method for their target applications.Clinical Relevance-This study highlights the overall performance of publicly available QRS detection algorithms in a large dataset of diverse patients. We showed that there are specific cardiac conditions that are associated with the poor performance of QRS detection algorithms and may adversely influence the performance of algorithms that rely on accurate and reliable QRS detection.

Automated Gas Chromatography Peak Alignment: A Deep Learning Approach using Greedy Optimization and Simulation.

The clinical significance of volatile organic compounds (VOC) in detecting diseases has been established over the past decades. Gas chromatography (GC) devices enable the measurement of these VOCs. Chromatographic peak alignment is one of the important yet challenging steps in analyzing chromatogram signals. Traditional semi-automated alignment algorithms require manual intervention by an operator which is slow, expensive and inconsistent. A pipeline is proposed to train a deep-learning model from artificial chromatograms simulated from a small, annotated dataset, and a postprocessing step based on greedy optimization to align the signals.Clinical Relevance- Breath VOCs have been shown to have a significant diagnostic power for various diseases including asthma, acute respiratory distress syndrome and COVID-19. Automatic analysis of chromatograms can lead to improvements in the diagnosis and management of such diseases.

Portable Breath-Based Volatile Organic Compound Monitoring for the Detection of COVID-19 During the Circulation of the SARS-CoV-2 Delta Variant and the Transition to the SARS-CoV-2 Omicron Variant.

Importance: Breath analysis has been explored as a noninvasive means to detect COVID-19. However, the impact of emerging variants of SARS-CoV-2, such as Omicron, on the exhaled breath profile and diagnostic accuracy of breath analysis is unknown. Objective: To evaluate the diagnostic accuracies of breath analysis on detecting patients with COVID-19 when the SARS-CoV-2 Delta and Omicron variants were most prevalent. Design, Setting, and Participants: This diagnostic study included a cohort of patients who had positive and negative test results for COVID-19 using reverse transcriptase polymerase chain reaction between April 2021 and May 2022, which covers the period when the Delta variant was overtaken by Omicron as the major variant. Patients were enrolled through intensive care units and the emergency department at the University of Michigan Health System. Patient breath was analyzed with portable gas chromatography. Main Outcomes and Measures: Different sets of VOC biomarkers were identified that distinguished between COVID-19 (SARS-CoV-2 Delta and Omicron variants) and non-COVID-19 illness. Results: Overall, 205 breath samples from 167 adult patients were analyzed. A total of 77 patients (mean [SD] age, 58.5 [16.1] years; 41 [53.2%] male patients; 13 [16.9%] Black and 59 [76.6%] White patients) had COVID-19, and 91 patients (mean [SD] age, 54.3 [17.1] years; 43 [47.3%] male patients; 11 [12.1%] Black and 76 [83.5%] White patients) had non-COVID-19 illness. Several patients were analyzed over multiple days. Among 94 positive samples, 41 samples were from patients in 2021 infected with the Delta or other variants, and 53 samples were from patients in 2022 infected with the Omicron variant, based on the State of Michigan and US Centers for Disease Control and Prevention surveillance data. Four VOC biomarkers were found to distinguish between COVID-19 (Delta and other 2021 variants) and non-COVID-19 illness with an accuracy of 94.7%. However, accuracy dropped substantially to 82.1% when these biomarkers were applied to the Omicron variant. Four new VOC biomarkers were found to distinguish the Omicron variant and non-COVID-19 illness (accuracy, 90.9%). Breath analysis distinguished Omicron from the earlier variants with an accuracy of 91.5% and COVID-19 (all SARS-CoV-2 variants) vs non-COVID-19 illness with 90.2% accuracy. Conclusions and Relevance: The findings of this diagnostic study suggest that breath analysis has promise for COVID-19 detection. However, similar to rapid antigen testing, the emergence of new variants poses diagnostic challenges. The results of this study warrant additional evaluation on how to overcome these challenges to use breath analysis to improve the diagnosis and care of patients.

Issues in the automated classification of multilead ecgs using heterogeneous labels and populations.

Objective.The standard twelve-lead electrocardiogram (ECG) is a widely used tool for monitoring cardiac function and diagnosing cardiac disorders. The development of smaller, lower-cost, and easier-to-use ECG devices may improve access to cardiac care in lower-resource environments, but the diagnostic potential of these devices is unclear. This work explores these issues through a public competition: the 2021 PhysioNet Challenge. In addition, we explore the potential for performance boosting through a meta-learning approach.Approach.We sourced 131,149 twelve-lead ECG recordings from ten international sources. We posted 88,253 annotated recordings as public training data and withheld the remaining recordings as hidden validation and test data. We challenged teams to submit containerized, open-source algorithms for diagnosing cardiac abnormalities using various ECG lead combinations, including the code for training their algorithms. We designed and scored the algorithms using an evaluation metric that captures the risks of different misdiagnoses for 30 conditions. After the Challenge, we implemented a semi-consensus voting model on all working algorithms.Main results.A total of 68 teams submitted 1,056 algorithms during the Challenge, providing a variety of automated approaches from both academia and industry. The performance differences across the different lead combinations were smaller than the performance differences across the different test databases, showing that generalizability posed a larger challenge to the algorithms than the choice of ECG leads. A voting model improved performance by 3.5%.Significance.The use of different ECG lead combinations allowed us to assess the diagnostic potential of reduced-lead ECG recordings, and the use of different data sources allowed us to assess the generalizability of the algorithms to diverse institutions and populations. The submission of working, open-source code for both training and testing and the use of a novel evaluation metric improved the reproducibility, generalizability, and applicability of the research conducted during the Challenge.

Redox Potential Correlates with Changes in Metabolite Concentrations Attributable to Pathways Active in Oxidative Stress Response in Swine Traumatic Shock.

INTRODUCTION: Oxidation-reduction (redox) reactions, and the redox potential (RP) that must be maintained for proper cell function, lie at the heart of physiologic processes in critical illness. Imbalance in RP reflects systemic oxidative stress, and whole blood RP measures have been shown to correlate with oxygen debt level over time in swine traumatic shock. We hypothesize that RP measures reflect changing concentrations of metabolites involved in oxidative stress. To test this hypothesis, we compared blood and urine RP with concentrations of multiple metabolites in a swine traumatic shock model to identify meaningful RP-metabolite relationships. METHODS: Seven swine were subjected to traumatic shock. Mixed venous (MV) RP, urine RP, and concurrent MV and urine metabolite concentrations were assessed at baseline, max O 2 Debt (80 mL/kg), end resuscitation, and 2 h post-resuscitation. RP was measured at collection via open circuit potential using nanoporous gold electrodes with Ag/AgCl reference and a ParstatMC potentiostat. Metabolite concentrations were measured by quantitative 1 H-NMR spectroscopy. MV and urine RP were compared with time-matched metabolites across all swine. LASSO regression with leave-one-out cross validation was used to determine meaningful RP/metabolite relationships. Metabolites had to maintain magnitude and direction of coefficients across 6 or more swine to be considered as having a meaningful relationship. KEGG IDs of these metabolites were uploaded into Metscape for pathway identification and evaluation for physiologic function. RESULTS: Meaningful metabolite relationships (and mean coefficients across cross-validation folds) with MV RP included: choline (-6.27), ATP (-4.39), glycine (5.93), ADP (1.84), glucose (15.96), formate (-13.09), pyruvate (6.18), and taurine (-7.18). Relationships with urine RP were: betaine (4.81), urea (4.14), glycine (-2.97), taurine (10.32), 3-hydroxyisobutyrate (-7.67), N-phenylacetylglycine, PAG (-14.52), hippurate (12.89), and formate (-5.89). These meaningful metabolites were found to scavenge extracellular peroxide (pyruvate), inhibit ROS and activate cellular antioxidant defense (taurine), act as indicators of antioxidant mobilization against oxidative stress (glycine + PAG), and reflect renal hydroxyl radical trapping (hippurate), among other activities. CONCLUSIONS: Real-time RP measures demonstrate significant relationships with metabolites attributable to metabolic pathways involved in systemic responses to oxidative stress, as well as those involved in these processes. These data support RP measures as a feasible, biologically relevant marker of oxidative stress. As a direct measure of redox state, RP may be a useful biomarker and clinical tool in guiding diagnosis and therapy in states of increased oxidative stress and may offer value as a marker for organ injury in these states as well.

Predicting Intensive Care Transfers and Other Unforeseen Events: Analytic Model Validation Study and Comparison to Existing Methods.

BACKGROUND: COVID-19 has led to an unprecedented strain on health care facilities across the United States. Accurately identifying patients at an increased risk of deterioration may help hospitals manage their resources while improving the quality of patient care. Here, we present the results of an analytical model, Predicting Intensive Care Transfers and Other Unforeseen Events (PICTURE), to identify patients at high risk for imminent intensive care unit transfer, respiratory failure, or death, with the intention to improve the prediction of deterioration due to COVID-19. OBJECTIVE: This study aims to validate the PICTURE model's ability to predict unexpected deterioration in general ward and COVID-19 patients, and to compare its performance with the Epic Deterioration Index (EDI), an existing model that has recently been assessed for use in patients with COVID-19. METHODS: The PICTURE model was trained and validated on a cohort of hospitalized non-COVID-19 patients using electronic health record data from 2014 to 2018. It was then applied to two holdout test sets: non-COVID-19 patients from 2019 and patients testing positive for COVID-19 in 2020. PICTURE results were aligned to EDI and NEWS scores for head-to-head comparison via area under the receiver operating characteristic curve (AUROC) and area under the precision-recall curve. We compared the models' ability to predict an adverse event (defined as intensive care unit transfer, mechanical ventilation use, or death). Shapley values were used to provide explanations for PICTURE predictions. RESULTS: In non-COVID-19 general ward patients, PICTURE achieved an AUROC of 0.819 (95% CI 0.805-0.834) per observation, compared to the EDI's AUROC of 0.763 (95% CI 0.746-0.781; n=21,740; P<.001). In patients testing positive for COVID-19, PICTURE again outperformed the EDI with an AUROC of 0.849 (95% CI 0.820-0.878) compared to the EDI's AUROC of 0.803 (95% CI 0.772-0.838; n=607; P<.001). The most important variables influencing PICTURE predictions in the COVID-19 cohort were a rapid respiratory rate, a high level of oxygen support, low oxygen saturation, and impaired mental status (Glasgow Coma Scale). CONCLUSIONS: The PICTURE model is more accurate in predicting adverse patient outcomes for both general ward patients and COVID-19 positive patients in our cohorts compared to the EDI. The ability to consistently anticipate these events may be especially valuable when considering potential incipient waves of COVID-19 infections. The generalizability of the model will require testing in other health care systems for validation.

Deep learning to detect acute respiratory distress syndrome on chest radiographs: a retrospective study with external validation.

BACKGROUND: Acute respiratory distress syndrome (ARDS) is a common, but under-recognised, critical illness syndrome associated with high mortality. An important factor in its under-recognition is the variability in chest radiograph interpretation for ARDS. We sought to train a deep convolutional neural network (CNN) to detect ARDS findings on chest radiographs. METHODS: CNNs were pretrained on 595 506 radiographs from two centres to identify common chest findings (eg, opacity and effusion), and then trained on 8072 radiographs annotated for ARDS by multiple physicians using various transfer learning approaches. The best performing CNN was tested on chest radiographs in an internal and external cohort, including a subset reviewed by six physicians, including a chest radiologist and physicians trained in intensive care medicine. Chest radiograph data were acquired from four US hospitals. FINDINGS: In an internal test set of 1560 chest radiographs from 455 patients with acute hypoxaemic respiratory failure, a CNN could detect ARDS with an area under the receiver operator characteristics curve (AUROC) of 0·92 (95% CI 0·89-0·94). In the subgroup of 413 images reviewed by at least six physicians, its AUROC was 0·93 (95% CI 0·88-0·96), sensitivity 83·0% (95% CI 74·0-91·1), and specificity 88·3% (95% CI 83·1-92·8). Among images with zero of six ARDS annotations (n=155), the median CNN probability was 11%, with six (4%) assigned a probability above 50%. Among images with six of six ARDS annotations (n=27), the median CNN probability was 91%, with two (7%) assigned a probability below 50%. In an external cohort of 958 chest radiographs from 431 patients with sepsis, the AUROC was 0·88 (95% CI 0·85-0·91). When radiographs annotated as equivocal were excluded, the AUROC was 0·93 (0·92-0·95). INTERPRETATION: A CNN can be trained to achieve expert physician-level performance in ARDS detection on chest radiographs. Further research is needed to evaluate the use of these algorithms to support real-time identification of ARDS patients to ensure fidelity with evidence-based care or to support ongoing ARDS research. FUNDING: National Institutes of Health, Department of Defense, and Department of Veterans Affairs.

Preprocessing Sequence Coverage Data for More Precise Detection of Copy Number Variations.

Copy number variation (CNV) is a type of genomic/genetic variation that plays an important role in phenotypic diversity, evolution, and disease susceptibility. Next generation sequencing (NGS) technologies have created an opportunity for more accurate detection of CNVs with higher resolution. However, efficient and precise detection of CNVs remains challenging due to high levels of noise and biases, data heterogeneity, and the "big data" nature of NGS data. Sequence coverage (readcount) data are mostly used for detecting CNVs, specially for whole exome sequencing data. Readcount data are contaminated with several types of biases and noise that hinder accurate detection of CNVs. In this work, we introduce a novel preprocessing pipeline for reducing noise and biases to improve the detection accuracy of CNVs in heterogeneous NGS data, such as cancer whole exome sequencing data. We have employed several normalization methods to reduce readcount's biases that are due to GC content of reads, read alignment problems, and sample impurity. We have also developed a novel efficient and effective smoothing approach based on Taut String to reduce noise and increase CNV detection power. Using simulated and real data we showed that employing the proposed preprocessing pipeline significantly improves the accuracy of CNV detection.

Noise Detection in Electrocardiography Signal for Robust Heart Rate Variability Analysis: A Deep Learning Approach.

Heart rate variability (HRV) analysis is widely used to assess the sympathetic and parasympathetic tones. However, the quality of the derived HRV features is heavily dependent on the accuracy of QRS detection. Noisy electrocardiography (ECG) signals, such as those measured by wearable ECG patches, can lead to inaccuracies in the QRS detection and significantly impair the HRV analysis. Hence, it is critical to employ noise detection algorithms to identify the corrupted segments of the ECG signal and discard them from the analysis. This paper proposes a convolutional neural network to distinguish between usable and unusable ECG segments where usability is defined based on the accuracy of QRS detection. The results indicate that the proposed method has significantly lower error rates compared to both the baseline method (HRV analysis on the noisy signals) and a noise detection method based on four ECG signal quality indices and a support vector machines classifier.