Assessing Risk of Health Outcomes From Brain Activity in Sleep: A Retrospective Cohort Study.

Background and Objectives: Patterns of electrical activity in the brain (EEG) during sleep are sensitive to various health conditions even at subclinical stages. The objective of this study was to estimate sleep EEG-predicted incidence of future neurologic, cardiovascular, psychiatric, and mortality outcomes. Methods: This is a retrospective cohort study with 2 data sets. The Massachusetts General Hospital (MGH) sleep data set is a clinic-based cohort, used for model development. The Sleep Heart Health Study (SHHS) is a community-based cohort, used as the external validation cohort. Exposure is good, average, or poor sleep defined by quartiles of sleep EEG-predicted risk. The outcomes include ischemic stroke, intracranial hemorrhage, mild cognitive impairment, dementia, atrial fibrillation, myocardial infarction, type 2 diabetes, hypertension, bipolar disorder, depression, and mortality. Diagnoses were based on diagnosis codes, brain imaging reports, medications, cognitive scores, and hospital records. We used the Cox survival model with death as the competing risk. Results: There were 8673 participants from MGH and 5650 from SHHS. For all outcomes, the model-predicted 10-year risk was within the 95% confidence interval of the ground truth, indicating good prediction performance. When comparing participants with poor, average, and good sleep, except for atrial fibrillation, all other 10-year risk ratios were significant. The model-predicted 10-year risk ratio closely matched the observed event rate in the external validation cohort. Discussion: The incidence of health outcomes can be predicted by brain activity during sleep. The findings strengthen the concept of sleep as an accessible biological window into unfavorable brain and general health outcomes.

Linking brain structure, cognition, and sleep: insights from clinical data.

STUDY OBJECTIVES: To use relatively noisy routinely collected clinical data (brain magnetic resonance imaging (MRI) data, clinical polysomnography (PSG) recordings, and neuropsychological testing), to investigate hypothesis-driven and data-driven relationships between brain physiology, structure, and cognition. METHODS: We analyzed data from patients with clinical PSG, brain MRI, and neuropsychological evaluations. SynthSeg, a neural network-based tool, provided high-quality segmentations despite noise. A priori hypotheses explored associations between brain function (measured by PSG) and brain structure (measured by MRI). Associations with cognitive scores and dementia status were studied. An exploratory data-driven approach investigated age-structure-physiology-cognition links. RESULTS: Six hundred and twenty-three patients with sleep PSG and brain MRI data were included in this study; 160 with cognitive evaluations. Three hundred and forty-two participants (55%) were female, and age interquartile range was 52 to 69 years. Thirty-six individuals were diagnosed with dementia, 71 with mild cognitive impairment, and 326 with major depression. One hundred and fifteen individuals were evaluated for insomnia and 138 participants had an apnea-hypopnea index equal to or greater than 15. Total PSG delta power correlated positively with frontal lobe/thalamic volumes, and sleep spindle density with thalamic volume. rapid eye movement (REM) duration and amygdala volume were positively associated with cognition. Patients with dementia showed significant differences in five brain structure volumes. REM duration, spindle, and slow-oscillation features had strong associations with cognition and brain structure volumes. PSG and MRI features in combination predicted chronological age (R2 = 0.67) and cognition (R2 = 0.40). CONCLUSIONS: Routine clinical data holds extended value in understanding and even clinically using brain-sleep-cognition relationships.

Decoding information about cognitive health from the brainwaves of sleep.

Sleep electroencephalogram (EEG) signals likely encode brain health information that may identify individuals at high risk for age-related brain diseases. Here, we evaluate the correlation of a previously proposed brain age biomarker, the "brain age index" (BAI), with cognitive test scores and use machine learning to develop and validate a series of new sleep EEG-based indices, termed "sleep cognitive indices" (SCIs), that are directly optimized to correlate with specific cognitive scores. Three overarching cognitive processes were examined: total, fluid (a measure of cognitive processes involved in reasoning-based problem solving and susceptible to aging and neuropathology), and crystallized cognition (a measure of cognitive processes involved in applying acquired knowledge toward problem-solving). We show that SCI decoded information about total cognition (Pearson's r = 0.37) and fluid cognition (Pearson's r = 0.56), while BAI correlated only with crystallized cognition (Pearson's r = - 0.25). Overall, these sleep EEG-derived biomarkers may provide accessible and clinically meaningful indicators of neurocognitive health.

Sound and light levels in intensive care units in a large urban hospital in the United States.

Intensive care units (ICUs) may disrupt sleep. Quantitative ICU studies of concurrent and continuous sound and light levels and timings remain sparse in part due to the lack of ICU equipment that monitors sound and light. Here, we describe sound and light levels across three adult ICUs in a large urban United States tertiary care hospital using a novel sensor. The novel sound and light sensor is composed of a Gravity Sound Level Meter for sound level measurements and an Adafruit TSL2561 digital luminosity sensor for light levels. Sound and light levels were continuously monitored in the room of 136 patients (mean age = 67.0 (8.7) years, 44.9% female) enrolled in the Investigation of Sleep in the Intensive Care Unit study (ICU-SLEEP; Clinicaltrials.gov: #NCT03355053), at the Massachusetts General Hospital. The hours of available sound and light data ranged from 24.0 to 72.2 hours. Average sound and light levels oscillated throughout the day and night. On average, the loudest hour was 17:00 and the quietest hour was 02:00. Average light levels were brightest at 09:00 and dimmest at 04:00. For all participants, average nightly sound levels exceeded the WHO guideline of < 35 decibels. Similarly, mean nightly light levels varied across participants (minimum: 1.00 lux, maximum: 577.05 lux). Sound and light events were more frequent between 08:00 and 20:00 than between 20:00 and 08:00 and were largely similar on weekdays and weekend days. Peaks in distinct alarm frequencies (Alarm 1) occurred at 01:00, 06:00, and at 20:00. Alarms at other frequencies (Alarm 2) were relatively consistent throughout the day and night, with a small peak at 20:00. In conclusion, we present a sound and light data collection method and results from a cohort of critically ill patients, demonstrating excess sound and light levels across multiple ICUs in a large tertiary care hospital in the United States. ClinicalTrials.gov, #NCT03355053. Registered 28 November 2017, https://clinicaltrials.gov/ct2/show/NCT03355053.

Sample Size Analysis for Machine Learning Clinical Validation Studies.

BACKGROUND: Before integrating new machine learning (ML) into clinical practice, algorithms must undergo validation. Validation studies require sample size estimates. Unlike hypothesis testing studies seeking a p-value, the goal of validating predictive models is obtaining estimates of model performance. There is no standard tool for determining sample size estimates for clinical validation studies for machine learning models. METHODS: Our open-source method, Sample Size Analysis for Machine Learning (SSAML) was described and was tested in three previously published models: brain age to predict mortality (Cox Proportional Hazard), COVID hospitalization risk prediction (ordinal regression), and seizure risk forecasting (deep learning). RESULTS: Minimum sample sizes were obtained in each dataset using standardized criteria. DISCUSSION: SSAML provides a formal expectation of precision and accuracy at a desired confidence level. SSAML is open-source and agnostic to data type and ML model. It can be used for clinical validation studies of ML models.

Sleep staging in the ICU with heart rate variability and breathing signals. An exploratory cross-sectional study using deep neural networks.

Introduction: To measure sleep in the intensive care unit (ICU), full polysomnography is impractical, while activity monitoring and subjective assessments are severely confounded. However, sleep is an intensely networked state, and reflected in numerous signals. Here, we explore the feasibility of estimating conventional sleep indices in the ICU with heart rate variability (HRV) and respiration signals using artificial intelligence methods Methods: We used deep learning models to stage sleep with HRV (through electrocardiogram) and respiratory effort (through a wearable belt) signals in critically ill adult patients admitted to surgical and medical ICUs, and in age and sex-matched sleep laboratory patients Results: We studied 102 adult patients in the ICU across multiple days and nights, and 220 patients in a clinical sleep laboratory. We found that sleep stages predicted by HRV- and breathing-based models showed agreement in 60% of the ICU data and in 81% of the sleep laboratory data. In the ICU, deep NREM (N2 + N3) proportion of total sleep duration was reduced (ICU 39%, sleep laboratory 57%, p < 0.01), REM proportion showed heavy-tailed distribution, and the number of wake transitions per hour of sleep (median 3.6) was comparable to sleep laboratory patients with sleep-disordered breathing (median 3.9). Sleep in the ICU was also fragmented, with 38% of sleep occurring during daytime hours. Finally, patients in the ICU showed faster and less variable breathing patterns compared to sleep laboratory patients Conclusion: The cardiovascular and respiratory networks encode sleep state information, which, together with artificial intelligence methods, can be utilized to measure sleep state in the ICU.

The sleep and wake electroencephalogram over the lifespan.

Both sleep and wake encephalograms (EEG) change over the lifespan. While prior studies have characterized age-related changes in the EEG, the datasets span a particular age group, or focused on sleep and wake macrostructure rather than the microstructure. Here, we present sex-stratified data from 3372 community-based or clinic-based otherwise neurologically and psychiatrically healthy participants ranging from 11 days to 80 years of age. We estimate age norms for key sleep and wake EEG parameters including absolute and relative powers in delta, theta, alpha, and sigma bands, as well as sleep spindle density, amplitude, duration, and frequency. To illustrate the potential use of the reference measures developed herein, we compare them to sleep EEG recordings from age-matched participants with Alzheimer's disease, severe sleep apnea, depression, osteoarthritis, and osteoporosis. Although the partially clinical nature of the datasets may bias the findings towards less normal and hence may underestimate pathology in practice, age-based EEG reference values enable objective screening of deviations from healthy aging among individuals with a variety of disorders that affect brain health.

High prevalence of sleep-disordered breathing in the intensive care unit - a cross-sectional study.

PURPOSE: Sleep-disordered breathing may be induced by, exacerbate, or complicate recovery from critical illness. Disordered breathing during sleep, which itself is often fragmented, can go unrecognized in the intensive care unit (ICU). The objective of this study was to investigate the prevalence, severity, and risk factors of sleep-disordered breathing in ICU patients using a single respiratory belt and oxygen saturation signals. METHODS: Patients in three ICUs at Massachusetts General Hospital wore a thoracic respiratory effort belt as part of a clinical trial for up to 7 days and nights. Using a previously developed machine learning algorithm, we processed respiratory and oximetry signals to measure the 3% apnea-hypopnea index (AHI) and estimate AH-specific hypoxic burden and periodic breathing. We trained models to predict AHI categories for 12-h segments from risk factors, including admission variables and bio-signals data, available at the start of these segments. RESULTS: Of 129 patients, 68% had an AHI ≥ 5; 40% an AHI > 15, and 19% had an AHI > 30 while critically ill. Median [interquartile range] hypoxic burden was 2.8 [0.5, 9.8] at night and 4.2 [1.0, 13.7] %min/h during the day. Of patients with AHI ≥ 5, 26% had periodic breathing. Performance of predicting AHI-categories from risk factors was poor. CONCLUSIONS: Sleep-disordered breathing and sleep apnea events while in the ICU are common and are associated with substantial burden of hypoxia and periodic breathing. Detection is feasible using limited bio-signals, such as respiratory effort and SpO2 signals, while risk factors were insufficient to predict AHI severity.

Dementia detection from brain activity during sleep.

STUDY OBJECTIVES: Dementia is a growing cause of disability and loss of independence in the elderly, yet remains largely underdiagnosed. Early detection and classification of dementia can help close this diagnostic gap and improve management of disease progression. Altered oscillations in brain activity during sleep are an early feature of neurodegenerative diseases and be used to identify those on the verge of cognitive decline. METHODS: Our observational cross-sectional study used a clinical dataset of 10 784 polysomnography from 8044 participants. Sleep macro- and micro-structural features were extracted from the electroencephalogram (EEG). Microstructural features were engineered from spectral band powers, EEG coherence, spindle, and slow oscillations. Participants were classified as dementia (DEM), mild cognitive impairment (MCI), or cognitively normal (CN) based on clinical diagnosis, Montreal Cognitive Assessment, Mini-Mental State Exam scores, clinical dementia rating, and prescribed medications. We trained logistic regression, support vector machine, and random forest models to classify patients into DEM, MCI, and CN groups. RESULTS: For discriminating DEM versus CN, the best model achieved an area under receiver operating characteristic curve (AUROC) of 0.78 and area under precision-recall curve (AUPRC) of 0.22. For discriminating MCI versus CN, the best model achieved an AUROC of 0.73 and AUPRC of 0.18. For discriminating DEM or MCI versus CN, the best model achieved an AUROC of 0.76 and AUPRC of 0.32. CONCLUSIONS: Our dementia classification algorithms show promise for incorporating dementia screening techniques using routine sleep EEG. The findings strengthen the concept of sleep as a window into neurodegenerative diseases.

Prolonged Unconsciousness is Common in COVID-19 and Associated with Hypoxemia.

OBJECTIVE: The purpose of this study was to estimate the time to recovery of command-following and associations between hypoxemia with time to recovery of command-following. METHODS: In this multicenter, retrospective, cohort study during the initial surge of the United States' pandemic (March-July 2020) we estimate the time from intubation to recovery of command-following, using Kaplan Meier cumulative-incidence curves and Cox proportional hazard models. Patients were included if they were admitted to 1 of 3 hospitals because of severe coronavirus disease 2019 (COVID-19), required endotracheal intubation for at least 7 days, and experienced impairment of consciousness (Glasgow Coma Scale motor score <6). RESULTS: Five hundred seventy-one patients of the 795 patients recovered command-following. The median time to recovery of command-following was 30 days (95% confidence interval [CI] = 27-32 days). Median time to recovery of command-following increased by 16 days for patients with at least one episode of an arterial partial pressure of oxygen (PaO2 ) value ≤55 mmHg (p < 0.001), and 25% recovered ≥10 days after cessation of mechanical ventilation. The time to recovery of command-following  was associated with hypoxemia (PaO2 ≤55 mmHg hazard ratio [HR] = 0.56, 95% CI = 0.46-0.68; PaO2 ≤70 HR = 0.88, 95% CI = 0.85-0.91), and each additional day of hypoxemia decreased the likelihood of recovery, accounting for confounders including sedation. These findings were confirmed among patients without any imagining evidence of structural brain injury (n = 199), and in a non-overlapping second surge cohort (N = 427, October 2020 to April 2021). INTERPRETATION: Survivors of severe COVID-19 commonly recover consciousness weeks after cessation of mechanical ventilation. Long recovery periods are associated with more severe hypoxemia. This relationship is not explained by sedation or brain injury identified on clinical imaging and should inform decisions about life-sustaining therapies. ANN NEUROL 2022;91:740-755.

Optimal spindle detection parameters for predicting cognitive performance.

STUDY OBJECTIVES: Alterations in sleep spindles have been linked to cognitive impairment. This finding has contributed to a growing interest in identifying sleep-based biomarkers of cognition and neurodegeneration, including sleep spindles. However, flexibility surrounding spindle definitions and algorithm parameter settings present a methodological challenge. The aim of this study was to characterize how spindle detection parameter settings influence the association between spindle features and cognition and to identify parameters with the strongest association with cognition. METHODS: Adult patients (n = 167, 49 ± 18 years) completed the NIH Toolbox Cognition Battery after undergoing overnight diagnostic polysomnography recordings for suspected sleep disorders. We explored 1000 combinations across seven parameters in Luna, an open-source spindle detector, and used four features of detected spindles (amplitude, density, duration, and peak frequency) to fit linear multiple regression models to predict cognitive scores. RESULTS: Spindle features (amplitude, density, duration, and mean frequency) were associated with the ability to predict raw fluid cognition scores (r = 0.503) and age-adjusted fluid cognition scores (r = 0.315) with the best spindle parameters. Fast spindle features generally showed better performance relative to slow spindle features. Spindle features weakly predicted total cognition and poorly predicted crystallized cognition regardless of parameter settings. CONCLUSIONS: Our exploration of spindle detection parameters identified optimal parameters for studies of fluid cognition and revealed the role of parameter interactions for both slow and fast spindles. Our findings support sleep spindles as a sleep-based biomarker of fluid cognition.

A machine learning approach to predict progression on active surveillance for prostate cancer.

PURPOSE: Robust prediction of progression on active surveillance (AS) for prostate cancer can allow for risk-adapted protocols. To date, models predicting progression on AS have invariably used traditional statistical approaches. We sought to evaluate whether a machine learning (ML) approach could improve prediction of progression on AS. PATIENTS AND METHODS: We performed a retrospective cohort study of patients diagnosed with very-low or low-risk prostate cancer between 1997 and 2016 and managed with AS at our institution. In the training set, we trained a traditional logistic regression (T-LR) classifier, and alternate ML classifiers (support vector machine, random forest, a fully connected artificial neural network, and ML-LR) to predict grade-progression. We evaluated model performance in the test set. The primary performance metric was the F1 score. RESULTS: Our cohort included 790 patients. With a median follow-up of 6.29 years, 234 developed grade-progression. In descending order, the F1 scores were: support vector machine 0.586 (95% CI 0.579 - 0.591), ML-LR 0.522 (95% CI 0.513 - 0.526), artificial neural network 0.392 (95% CI 0.379 - 0.396), random forest 0.376 (95% CI 0.364 - 0.380), and T-LR 0.182 (95% CI 0.151 - 0.185). All alternate ML models had a significantly higher F1 score than the T-LR model (all p <0.001). CONCLUSION: In our study, ML methods significantly outperformed T-LR in predicting progression on AS for prostate cancer. While our specific models require further validation, we anticipate that a ML approach will help produce robust prediction models that will facilitate individualized risk-stratification in prostate cancer AS.

Sleep apnea and respiratory anomaly detection from a wearable band and oxygen saturation.

OBJECTIVE: Sleep-related respiratory abnormalities are typically detected using polysomnography. There is a need in general medicine and critical care for a more convenient method to detect sleep apnea automatically from a simple, easy-to-wear device. The objective was to detect abnormal respiration and estimate the Apnea-Hypopnea Index (AHI) automatically with a wearable respiratory device with and without SpO2 signals using a large (n = 412) dataset serving as ground truth. DESIGN: Simultaneously recorded polysomnography (PSG) and wearable respiratory effort data were used to train and evaluate models in a cross-validation fashion. Time domain and complexity features were extracted, important features were identified, and a random forest model was employed to detect events and predict AHI. Four models were trained: one each using the respiratory features only, a feature from the SpO2 (%)-signal only, and two additional models that use the respiratory features and the SpO2 (%) feature, one allowing a time lag of 30 s between the two signals. RESULTS: Event-based classification resulted in areas under the receiver operating characteristic curves of 0.94, 0.86, and 0.82, and areas under the precision-recall curves of 0.48, 0.32, and 0.51 for the models using respiration and SpO2, respiration-only, and SpO2-only, respectively. Correlation between expert-labelled and predicted AHI was 0.96, 0.78, and 0.93, respectively. CONCLUSIONS: A wearable respiratory effort signal with or without SpO2 signal predicted AHI accurately, and best performance was achieved with using both signals.

Automated Scoring of Respiratory Events in Sleep With a Single Effort Belt and Deep Neural Networks.

OBJECTIVE: Automatic detection and analysis of respiratory events in sleep using a single respiratoryeffort belt and deep learning. METHODS: Using 9,656 polysomnography recordings from the Massachusetts General Hospital (MGH), we trained a neural network (WaveNet) to detect obstructive apnea, central apnea, hypopnea and respiratory-effort related arousals. Performance evaluation included event-based analysis and apnea-hypopnea index (AHI) stratification. The model was further evaluated on a public dataset, the Sleep-Heart-Health-Study-1, containing 8,455 polysomnographic recordings. RESULTS: For binary apnea event detection in the MGH dataset, the neural network obtained a sensitivity of 68%, a specificity of 98%, a precision of 65%, a F1-score of 67%, and an area under the curve for the receiver operating characteristics curve and precision-recall curve of 0.93 and 0.71, respectively. AHI prediction resulted in a mean difference of 0.41 ± 7.8 and a r2 of 0.90. For the multiclass task, we obtained varying performances: 84% of all labeled central apneas were correctly classified, whereas this metric was 51% for obstructive apneas, 40% for respiratory effort related arousals and 23% for hypopneas. CONCLUSION: Our fully automated method can detect respiratory events and assess the AHI accurately. Differentiation of event types is more difficult and may reflect in part the complexity of human respiratory output and some degree of arbitrariness in the criteria used during manual annotation. SIGNIFICANCE: The current gold standard of diagnosing sleep-disordered breathing, using polysomnography and manual analysis, is time-consuming, expensive, and only applicable in dedicated clinical environments. Automated analysis using a single effort belt signal overcomes these limitations.

Predicting survival after radical prostatectomy: Variation of machine learning performance by race.

BACKGROUND: Robust prediction of survival can facilitate clinical decision-making and patient counselling. Non-Caucasian males are underrepresented in most prostate cancer databases. We evaluated the variation in performance of a machine learning (ML) algorithm trained to predict survival after radical prostatectomy in race subgroups. METHODS: We used the National Cancer Database (NCDB) to identify patients undergoing radical prostatectomy between 2004 and 2016. We grouped patients by race into Caucasian, African-American, or non-Caucasian, non-African-American (NCNAA) subgroups. We trained an Extreme Gradient Boosting (XGBoost) classifier to predict 5-year survival in different training samples: naturally race-imbalanced, race-specific, and synthetically race-balanced. We evaluated performance in the test sets. RESULTS: A total of 68,630 patients met inclusion criteria. Of these, 57,635 (84%) were Caucasian, 8173 (12%) were African-American, and 2822 (4%) were NCNAA. For the classifier trained in the naturally race-imbalanced sample, the F1 scores were 0.514 (95% confidence interval: 0.513-0.511), 0.511 (0.511-0.512), 0.545 (0.541-0.548), and 0.378 (0.378-0.389) in the race-imbalanced, Caucasian, African-American, and NCNAA test samples, respectively. For all race subgroups, the F1 scores of classifiers trained in the race-specific or synthetically race-balanced samples demonstrated similar performance compared to training in the naturally race-imbalanced sample. CONCLUSIONS: A ML algorithm trained using NCDB data to predict survival after radical prostatectomy demonstrates variation in performance by race, regardless of whether the algorithm is trained in a naturally race-imbalanced, race-specific, or synthetically race-balanced sample. These results emphasize the importance of thoroughly evaluating ML algorithms in race subgroups before clinical deployment to avoid potential disparities in care.

Cortical responses to noninvasive perturbations enable individual brain fingerprinting.

BACKGROUND: In recent years, it has become increasingly apparent that characterizing individual brain structure, connectivity and dynamics is essential for understanding brain function in health and disease. However, the majority of neuroimaging and brain stimulation research has characterized human brain function by averaging measurements from groups of subjects and providing population-level inferences. External perturbations applied directly to well-defined brain regions can reveal distinctive information about the state, connectivity and dynamics of the human brain at the individual level. OBJECTIVES: In a series of studies, we aimed to characterize individual brain responses to MRI-guided transcranial magnetic stimulation (TMS), and explore the reproducibility of the evoked effects, differences between brain regions, and their individual specificity. METHODS: In the first study, we administered single pulses of TMS to both anatomically (left dorsolateral prefrontal cortex- 'L-DLPFC', left Intra-parietal lobule- 'L-IPL) and functionally (left motor cortex- 'L-M1', right default mode network- 'R-DMN, right dorsal attention network- 'R-DAN') defined cortical nodes in the frontal, motor, and parietal regions across two identical sessions spaced one month apart in 24 healthy volunteers. In the second study, we extended our analyses to two independent data sets (n = 10 in both data sets) having different sham-TMS protocols. RESULTS: In the first study, we found that perturbation-induced cortical propagation patterns are heterogeneous across individuals but highly reproducible within individuals, specific to the stimulated region, and distinct from spontaneous activity. Most importantly, we demonstrate that by assessing the spatiotemporal characteristics of TMS-induced brain responses originating from different cortical regions, individual subjects can be identified with perfect accuracy. In the second study, we demonstrated that subject specificity of TEPs is generalizable across independent data sets and distinct from non-transcranial neural responses evoked by sham-TMS protocols. CONCLUSIONS: Perturbation-induced brain responses reveal unique "brain fingerprints" that reflect causal connectivity dynamics of the stimulated brain regions, and may serve as reliable biomarkers of individual brain function.

Algorithm for automatic detection of self-similarity and prediction of residual central respiratory events during continuous positive airway pressure.

STUDY OBJECTIVES: Sleep-disordered breathing is a significant risk factor for cardiometabolic and neurodegenerative diseases. High loop gain (HLG) is a driving mechanism of central sleep apnea or periodic breathing. This study presents a computational approach that identifies "expressed/manifest" HLG via a cyclical self-similarity feature in effort-based respiration signals. METHODS: Working under the assumption that HLG increases the risk of residual central respiratory events during continuous positive airway pressure (CPAP), the full night similarity, computed during diagnostic non-CPAP polysomnography (PSG), was used to predict residual central events during CPAP (REC), which we defined as central apnea index (CAI) higher than 10. Central apnea labels are obtained both from manual scoring by sleep technologists and from an automated algorithm developed for this study. The Massachusetts General Hospital sleep database was used, including 2466 PSG pairs of diagnostic and CPAP titration PSG recordings. RESULTS: Diagnostic CAI based on technologist labels predicted REC with an area under the curve (AUC) of 0.82 ± 0.03. Based on automatically generated labels, the combination of full night similarity and automatically generated CAI resulted in an AUC of 0.85 ± 0.02. A subanalysis was performed on a population with technologist-labeled diagnostic CAI higher than 5. Full night similarity predicted REC with an AUC of 0.57 ± 0.07 for manual and 0.65 ± 0.06 for automated labels. CONCLUSIONS: The proposed self-similarity feature, as a surrogate estimate of expressed respiratory HLG and computed from easily accessible effort signals, can detect periodic breathing regardless of admixed obstructive features such as flow limitation and can aid the prediction of REC.

CoVA: An Acuity Score for Outpatient Screening that Predicts Coronavirus Disease 2019 Prognosis.

BACKGROUND: We sought to develop an automatable score to predict hospitalization, critical illness, or death for patients at risk for coronavirus disease 2019 (COVID-19) presenting for urgent care. METHODS: We developed the COVID-19 Acuity Score (CoVA) based on a single-center study of adult outpatients seen in respiratory illness clinics or the emergency department. Data were extracted from the Partners Enterprise Data Warehouse, and split into development (n = 9381, 7 March-2 May) and prospective (n = 2205, 3-14 May) cohorts. Outcomes were hospitalization, critical illness (intensive care unit or ventilation), or death within 7 days. Calibration was assessed using the expected-to-observed event ratio (E/O). Discrimination was assessed by area under the receiver operating curve (AUC). RESULTS: In the prospective cohort, 26.1%, 6.3%, and 0.5% of patients experienced hospitalization, critical illness, or death, respectively. CoVA showed excellent performance in prospective validation for hospitalization (expected-to-observed ratio [E/O]: 1.01; AUC: 0.76), for critical illness (E/O: 1.03; AUC: 0.79), and for death (E/O: 1.63; AUC: 0.93). Among 30 predictors, the top 5 were age, diastolic blood pressure, blood oxygen saturation, COVID-19 testing status, and respiratory rate. CONCLUSIONS: CoVA is a prospectively validated automatable score for the outpatient setting to predict adverse events related to COVID-19 infection.

COVID-19 Outpatient Screening: a Prediction Score for Adverse Events.

BACKGROUND: We sought to develop an automatable score to predict hospitalization, critical illness, or death in patients at risk for COVID-19 presenting for urgent care during the Massachusetts outbreak. METHODS: Single-center study of adult outpatients seen in respiratory illness clinics (RICs) or the emergency department (ED), including development (n = 9381, March 7-May 2) and prospective (n = 2205, May 3-14) cohorts. Data was queried from Partners Enterprise Data Warehouse. Outcomes were hospitalization, critical illness or death within 7 days. We developed the COVID-19 Acuity Score (CoVA) using automatically extracted data from the electronic medical record and learning-to-rank ordinal logistic regression modeling. Calibration was assessed using predicted-to-observed event ratio (E/O). Discrimination was assessed by C-statistics (AUC). RESULTS: In the development cohort, 27.3%, 7.2%, and 1.1% of patients experienced hospitalization, critical illness, or death, respectively; and in the prospective cohort, 26.1%, 6.3%, and 0.5%. CoVA showed excellent performance in the development cohort (concurrent validation) for hospitalization (E/O: 1.00, AUC: 0.80); for critical illness (E/O: 1.00, AUC: 0.82); and for death (E/O: 1.00, AUC: 0.87). Performance in the prospective cohort (prospective validation) was similar for hospitalization (E/O: 1.01, AUC: 0.76); for critical illness (E/O 1.03, AUC: 0.79); and for death (E/O: 1.63, AUC=0.93). Among 30 predictors, the top five were age, diastolic blood pressure, blood oxygen saturation, COVID-19 testing status, and respiratory rate. CONCLUSIONS: CoVA is a prospectively validated automatable score to assessing risk for adverse outcomes related to COVID-19 infection in the outpatient setting.