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 3,372 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.

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.

Sleep disturbances increase with age and are predictors of mortality. Here, we present deep neural networks that estimate age and mortality risk through polysomnograms (PSGs). Aging was modeled using 2500 PSGs and tested in 10,699 PSGs from men and women in seven different cohorts aged between 20 and 90. Ages were estimated with a mean absolute error of 5.8 ± 1.6 years, while basic sleep scoring measures had an error of 14.9 ± 6.29 years. After controlling for demographics, sleep, and health covariates, each 10-year increment in age estimate error (AEE) was associated with increased all-cause mortality rate of 29% (95% confidence interval: 20–39%). An increase from −10 to +10 years in AEE translates to an estimated decreased life expectancy of 8.7 years (95% confidence interval: 6.1–11.4 years). Greater AEE was mostly reflected in increased sleep fragmentation, suggesting this is an important biomarker of future health independent of sleep apnea.

Background: Delirium in hospitalized patients is a syndrome of acute brain dysfunction. Diagnostic (International Classification of Diseases [ICD]) codes are often used in studies using electronic health records (EHRs), but they are inaccurate.

Objective: We sought to develop a more accurate method using natural language processing (NLP) to detect delirium episodes on the basis of unstructured clinical notes.

Methods: We collected 1.5 million notes from >10,000 patients from among 9 hospitals. Seven experts iteratively labeled 200,471 sentences. Using these, we trained three NLP classifiers: Support Vector Machine, Recurrent Neural Networks, and Transformer. Testing was performed using an external data set. We also evaluated associations with delirium billing (ICD) codes, medications, orders for restraints and sitters, direct assessments (Confusion Assessment Method [CAM] scores), and in-hospital mortality. F1 scores, confusion matrices, and areas under the receiver operating characteristic curve (AUCs) were used to compare NLP models. We used the φ coefficient to measure associations with other delirium indicators.

Results: The transformer NLP performed best on the following parameters: micro F1=0.978, macro F1=0.918, positive AUC=0.984, and negative AUC=0.992. NLP detections exhibited higher correlations (φ) than ICD codes with deliriogenic medications (0.194 vs 0.073 for ICD codes), restraints and sitter orders (0.358 vs 0.177), mortality (0.216 vs 0.000), and CAM scores (0.256 vs –0.028).

Conclusions: Clinical notes are an attractive alternative to ICD codes for EHR delirium studies but require automated methods. Our NLP model detects delirium with high accuracy, similar to manual chart review. Our NLP approach can provide more accurate determination of delirium for large-scale EHR-based studies regarding delirium, quality improvement, and clinical trails.

Based on the complex pathology of AD, a single chemical approach may not be sufficient to deal simultaneously with multiple pathways of amyloid-tau neuroinflammation. A polydrug approach which contains multiple bioactive components targeting multiple pathways in AD would be more appropriate. Here we focused on a Chinese medicine (HLXL), which contains 56 bioactive natural products identified in 11 medicinal plants and displays potent anti-inflammatory and immuno-modulatory activity.

We investigated the neuroimmune and neuroinflammation mechanisms by which HLXL may attenuate AD neuropathology. Specifically, we investigated the effects of HLXL on the neuropathology of AD using both transgenic mouse models as well as microglial cell-based models. The 5XFAD transgenic animals and microglial cell models were respectively treated with HLXL and Aβ42, and/or lipopolysaccharide (LPS), and then analyzed focusing on microglia mediated Aβ uptake and clearance, as well as pathway changes. We showed that HLXL significantly reduced amyloid neuropathology by upregulation of microglia-mediated phagocytosis of Aβ both in vivo and in vitro. HLXL displayed multi-modal mechanisms regulating pathways of phagocytosis and energy metabolism.

Our results may not only open a new avenue to support pharmacologic modulation of neuroinflammation and the neuroimmune system for AD intervention, but also identify HLXL as a promising natural medicine for AD. It is conceivable that the traditional wisdom of natural medicine in combination with modern science and technology would be the best strategy in developing effective therapeutics for AD.

This report presents an overview of how machine learning is rapidly advancing clinical translational imaging in ways that will aid in the early detection, prediction, and treatment of diseases that threaten brain health. Towards this goal, we aresharing the information presented at a symposium, “Neuroimaging Indicators of Brain Structure and Function - Closing the Gap Between Research and Clinical Application”, co-hosted by the McCance Center for Brain Health at Mass General Hospital and the MIT HST Neuroimaging Training Program on February 12, 2021. The symposium focused on the potential for machine learning approaches, applied to increasingly large-scale neuroimaging datasets, to transform healthcare delivery and change the trajectory of brain health by addressing brain care earlier in the lifespan. While not exhaustive, this overview uniquely addresses many of the technical challenges from image formation, to analysis and visualization, to synthesis and incorporation into the clinical workflow. Some of the ethical challenges inherent to this work are also explored, as are some of the regulatory requirements for implementation. We seek to educate, motivate, and inspire graduate students, postdoctoral fellows, and early career investigators to contribute to a future where neuroimaging meaningfully contributes to the maintenance of brain health.

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.

Conclusion
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.

Objectives: 
Delirium is a common and frequently underdiagnosed complication in acutely hospitalized patients, and its severity is associated with worse clinical outcomes. We propose a physiologically based method to quantify delirium severity as a tool that can help close this diagnostic gap: the Electroencephalographic Confusion Assessment Method Severity Score (E-CAM-S).

Design: 
Retrospective cohort study.

Setting: 
Single-center tertiary academic medical center.

Patients: 
Three-hundred seventy-three adult patients undergoing electroencephalography to evaluate altered mental status between August 2015 and December 2019.

Interventions: 
None.

Measurements and Main Results: 
We developed the E-CAM-S based on a learning-to-rank machine learning model of forehead electroencephalography signals. Clinical delirium severity was assessed using the Confusion Assessment Method Severity (CAM-S). We compared associations of E-CAM-S and CAM-S with hospital length of stay and inhospital mortality. E-CAM-S correlated with clinical CAM-S (R = 0.67; p < 0.0001). For the overall cohort, E-CAM-S and CAM-S were similar in their strength of association with hospital length of stay (correlation = 0.31 vs 0.41, respectively; p = 0.082) and inhospital mortality (area under the curve = 0.77 vs 0.81; p = 0.310). Even when restricted to noncomatose patients, E-CAM-S remained statistically similar to CAM-S in its association with length of stay (correlation = 0.37 vs 0.42, respectively; p = 0.188) and inhospital mortality (area under the curve = 0.83 vs 0.74; p = 0.112). In addition to previously appreciated spectral features, the machine learning framework identified variability in multiple measures over time as important features in electroencephalography-based prediction of delirium severity.

Conclusions: 
The E-CAM-S is an automated, physiologic measure of delirium severity that predicts clinical outcomes with a level of performance comparable to conventional interview-based clinical assessment.

OBJECTIVES: 
To develop a physiologic grading system for the severity of acute encephalopathy manifesting as delirium or coma, based on EEG, and to investigate its association with clinical outcomes.

DESIGN: 
This prospective, single-center, observational cohort study was conducted from August 2015 to December 2016 and October 2018 to December 2019.

SETTING: 
Academic medical center, all inpatient wards.

PATIENTS/SUBJECTS: 
Adult inpatients undergoing a clinical EEG recording; excluded if deaf, severely aphasic, developmentally delayed, non-English speaking (if noncomatose), or if goals of care focused primarily on comfort measures. Four-hundred six subjects were assessed; two were excluded due to technical EEG difficulties.

INTERVENTIONS: 
None.

MEASUREMENTS AND MAIN RESULTS: 
A machine learning model, with visually coded EEG features as inputs, was developed to produce scores that correlate with behavioral assessments of delirium severity (Confusion Assessment Method-Severity [CAM-S] Long Form [LF] scores) or coma; evaluated using Spearman R correlation; area under the receiver operating characteristic curve (AUC); and calibration curves. Associations of Visual EEG Confusion Assessment Method Severity (VE-CAM-S) were measured for three outcomes: functional status at discharge (via Glasgow Outcome Score [GOS]), inhospital mortality, and 3-month mortality. Four-hundred four subjects were analyzed (mean [sd] age, 59.8 yr [17.6 yr]; 232 [57%] male; 320 [79%] White; 339 [84%] non-Hispanic); 132 (33%) without delirium or coma, 143 (35%) with delirium, and 129 (32%) with coma. VE-CAM-S scores correlated strongly with CAM-S scores (Spearman correlation 0.67 [0.62–0.73]; p < 0.001) and showed excellent discrimination between levels of delirium (CAM-S LF = 0 vs ≥ 4, AUC 0.85 [0.78–0.92], calibration slope of 1.04 [0.87–1.19] for CAM-S LF ≤ 4 vs ≥ 5). VE-CAM-S scores were strongly associated with important clinical outcomes including inhospital mortality (AUC 0.79 [0.72–0.84]), 3-month mortality (AUC 0.78 [0.71–0.83]), and GOS at discharge (0.76 [0.69–0.82]).

CONCLUSIONS: 
VE-CAM-S is a physiologic grading scale for the severity of symptoms in the setting of delirium and coma, based on visually assessed electroencephalography features. VE-CAM-S scores are strongly associated with clinical outcomes.

Objective: Automatic detection and analysis of respiratory events in sleep using a single respiratory effort 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 0.417.8 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.

Background
We investigated the effect of delirium burden in mechanically ventilated patients, beginning in the ICU and continuing throughout hospitalization, on functional neurologic outcomes up to 2.5 years following critical illness.

Methods
Prospective cohort study of enrolling 178 consecutive mechanically ventilated adult medical and surgical ICU patients between October 2013 and May 2016. Altogether, patients were assessed daily for delirium 2941days using the Confusion Assessment Method for the ICU (CAM-ICU). Hospitalization delirium burden (DB) was quantified as number of hospital days with delirium divided by total days at risk. Survival status up to 2.5 years and neurologic outcomes using the Glasgow Outcome Scale were recorded at discharge 3, 6, and 12 months post-discharge.

Results
Of 178 patients, 19 (10.7%) were excluded from outcome analyses due to persistent coma. Among the remaining 159, 123 (77.4%) experienced delirium. DB was independently associated with >4-fold increased mortality at 2.5 years following ICU admission (adjusted hazard ratio [aHR], 4.77; 95% CI, 2.10–10.83; P < .001), and worse neurologic outcome at discharge (adjusted odds ratio [aOR], 0.02; 0.01–0.09; P < .001), 3 (aOR, 0.11; 0.04–0.31; P < .001), 6 (aOR, 0.10; 0.04–0.29; P < .001), and 12 months (aOR, 0.19; 0.07–0.52; P = .001). DB in the ICU alone was not associated with mortality (HR, 1.79; 0.93–3.44; P = .082) and predicted neurologic outcome less strongly than entire hospital stay DB. Similarly, the number of delirium days in the ICU and for whole hospitalization were not associated with mortality (HR, 1.00; 0.93–1.08; P = .917 and HR, 0.98; 0.94–1.03, P = .535) nor with neurological outcomes, except for the association between ICU delirium days and neurological outcome at discharge (OR, 0.90; 0.81–0.99, P = .038).

Conclusions
Delirium burden throughout hospitalization independently predicts long term neurologic outcomes and death up to 2.5 years after critical illness, and is more predictive than delirium burden in the ICU alone and number of delirium days.

Objectives
The purpose of this study was to examine critical care continuous electroencephalography (cEEG) utilization and downstream anti-seizure treatment patterns, their association with outcomes, and generate hypotheses for larger comparative effectiveness studies of cEEG-guided interventions.

Methods
Single-center retrospective study of critically ill patients (n = 14,523, age ≥18 years). Exposure defined as ≥24 h of cEEG and subsequent anti-seizure medication (ASM) escalation, with or without concomitant anesthetic. Exposure window was the first 7 days of admission. Primary outcome was in-hospital mortality. Multivariable analysis was performed using penalized logistic regression.

Results
One thousand and seventy-three patients underwent ≥24 h of cEEG within 7 days of admission. After adjusting for disease severity, ≥24 h of cEEG followed by ASM escalation in patients not on anesthetics (n = 239) was associated with lower in-hospital mortality (OR 0.76 [0.53–1.07]), though the finding did not reach significance. ASM escalation with concomitant anesthetic use (n = 484) showed higher odds for mortality (OR 1.41 [1.03–1.94]). In the seizures/status epilepticus subgroup, post cEEG ASM escalation without anesthetics showed lower odds for mortality (OR 0.43 [0.23–0.74]). Within the same subgroup, ASM escalation with concomitant anesthetic use showed higher odds for mortality (OR 1.34 [0.92–1.91]) though not significant.

Interpretation
Based on our findings we propose the following hypotheses for larger comparative effectiveness studies investigating the direct causal effect of cEEG-guided treatment on outcomes: (1) cEEG-guided ASM escalation may improve outcomes in critically ill patients with seizures; (2) cEEG-guided treatment with combination of ASMs and anesthetics may not improve outcomes in all critically ill patients.

Objective
Current cardiac surgery risk models do not address a substantial fraction of procedures. We sought to create models to predict the risk of operative mortality for an expanded set of cases.

Methods
Four supervised machine learning models were trained using preoperative variables present in the Society of Thoracic Surgeons (STS) data set of the Massachusetts General Hospital to predict and classify operative mortality in procedures without STS risk scores. A total of 424 (5.5%) mortality events occurred out of 7745 cases. Models included logistic regression with elastic net regularization (LogReg), support vector machine, random forest (RF), and extreme gradient boosted trees (XGBoost). Model discrimination was assessed via area under the receiver operating characteristic curve (AUC), and calibration was assessed via calibration slope and expected-to-observed event ratio. External validation was performed using STS data sets from Brigham and Women's Hospital (BWH) and the Johns Hopkins Hospital (JHH).

Results
Models performed comparably with the highest mean AUC of 0.83 (RF) and expected-to-observed event ratio of 1.00. On external validation, the AUC was 0.81 in BWH (RF) and 0.79 in JHH (LogReg/RF). Models trained and applied on the same institution's data achieved AUCs of 0.81 (BWH: LogReg/RF/XGBoost) and 0.82 (JHH: LogReg/RF/XGBoost).

Conclusions
Machine learning models trained on preoperative patient data can predict operative mortality at a high level of accuracy for cardiac surgical procedures without established risk scores. Such procedures comprise 23% of all cardiac surgical procedures nationwide. This work also highlights the value of using local institutional data to train new prediction models that account for institution-specific practices.

Objective
To determine the dose-response relation between epileptiform activity burden and outcomes in acutely ill patients.

Methods
Single center retrospective analysis of 1967 neurologic, medical and surgical patients who underwent > 16 hours of continuous EEG between 2011-2017. We developed an AI algorithm to annotate 11.02 terabytes of EEG and quantify epileptiform activity burden within 72 hours of recording. We evaluated burden in 1) the first 24 hours of recording, 2) the 12-hr epoch with highest burden (peak burden), and 3) cumulative through the first 72 hours of monitoring. Machine learning was applied to estimate the effect of epileptiform burden on outcome. Outcome measure was discharge modified Rankin Scale, dichotomized as good (0-4) vs. poor (5-6).

Results
Peak epileptiform burden was independently associated with poor outcomes (p<0.0001). Other independent associations included age, APACHE II, seizure on presentation, and diagnosis of hypoxic ischemic encephalopathy. Model calibration error was calculated across three strata based on the time interval between last EEG measurement (up to 72 hours of monitoring) and discharge: 1) < 5 days between last measurement and discharge: 0.0941 [CI 0.0706, 0.1191); 5-10 days between last measurement and discharge: 0.0946 [CI 0.0631, 0.1290]; > 10 days between last measurement and discharge: 0.0998 [CI 0.0698, 0.1335]. After adjusting for covariates, increase in peak epileptiform activity burden from 0% to 100% increased the probability of poor outcome by 35%.

Interpretation
Automated measurement of peak epileptiform activity burden affords a convenient, consistent, and quantifiable target for future multi-center randomized trials investigating whether suppressing epileptiform activity improves outcomes.

Purpose: 
Triphasic waves arising in patients with toxic metabolic encephalopathy (TME) are often considered different from generalized periodic discharges (GPDs) in patients with generalized nonconvulsive status epilepticus (GNCSE). The primary objective of this study was to investigate whether a common mechanism can explain key aspects of both triphasic waves in TME and GPDs in GNCSE.

Method: 
A neural mass model was used for the simulation of EEG patterns in patients with acute hepatic encephalopathy, a common etiology of TME. Increased neuronal excitability and impaired synaptic transmission because of elevated ammonia levels in acute hepatic encephalopathy patients were used to explain how triphasic waves and GNCSE arise. The effect of gamma-aminobutyric acid-ergic drugs on epileptiform activity, simulated with a prolonged duration of the inhibitory postsynaptic potential, was also studied.

Results: 
The simulations show that a model that includes increased neuronal excitability and impaired synaptic transmission can account for both the emergence of GPDs and GNCSE and their suppression by gamma-aminobutyric acid-ergic drugs.

Conclusions: 
The results of this study add to evidence from other studies calling into question the dichotomy between triphasic waves in TME and GPDs in GNCSE and support the hypothesis that all GPDs, including those arising in TME patients, occur via a common mechanism.

Background
Frailty has been associated with increased incidence of postoperative delirium and mortality. We hypothesised that postoperative delirium mediates a clinically significant (≥1%) percentage of the effect of frailty on mortality in older orthopaedic trauma patients.

Methods
This was a single-centre, retrospective observational study including 558 adults 65 yr and older, who presented with an extremity fracture requiring hospitalisation without initial ICU admission. We used causal statistical inference methods to estimate the relationships between frailty, postoperative delirium, and mortality.

Results
In the cohort, 180-day mortality rate was 6.5% (36/558). Frail and prefrail patients comprised 23% and 39%, respectively, of the study cohort. Frailty was associated with increased 180 day mortality from 1.4% to 12.2% (11% difference; 95% confidence interval [CI], 8.4–13.6), which translated statistically into an 88.7% (79.9–94.3%) direct effect and an 11.3% (5.7–20.1%) postoperative delirium mediated effect. Prefrailty was also associated with increased 180 day mortality from 1.4% to 4.4% (2.9% difference; 2.4–3.4), which was translated into a 92.5% (83.8–99.9%) direct effect and a 7.5% (0.1–16.2%) postoperative delirium mediated effect.

Conclusions
Frailty is associated with increased postoperative mortality, and delirium might mediate a clinically significant, but small percentage of this effect. Studies should assess whether, in patients with frailty, attempts to mitigate delirium might decrease postoperative mortality.

Objectives: Patients with comorbidities are at increased risk for poor outcomes in COVID-19, yet data on patients with prior neurological disease remains limited. Our objective was to determine the odds of critical illness and duration of mechanical ventilation in patients with prior cerebrovascular disease and COVID-19.

Methods: A observational study of 1,128 consecutive adult patients admitted to an academic center in Boston, Massachusetts, and diagnosed with laboratory-confirmed COVID-19. We tested the association between prior cerebrovascular disease and critical illness, defined as mechanical ventilation (MV) or death by day 28, using logistic regression with inverse probability weighting of the propensity score. Among intubated patients, we estimated the cumulative incidence of successful extubation without death over 45 days using competing risk analysis.

Results: Of the 1,128 adults with COVID-19, 350 (36%) were critically ill by day 28. The median age of patients was 59 years (SD: 18 years) and 640 (57%) were men. As of June 2nd, 2020, 127 (11%) patients had died. A total of 177 patients (16%) had a prior cerebrovascular disease. Prior cerebrovascular disease was significantly associated with critical illness (OR = 1.54, 95% CI = 1.14–2.07), lower rate of successful extubation (cause-specific HR = 0.57, 95% CI = 0.33–0.98), and increased duration of intubation (restricted mean time difference = 4.02 days, 95% CI = 0.34–10.92) compared to patients without cerebrovascular disease.

Interpretation: Prior cerebrovascular disease adversely affects COVID-19 outcomes in hospitalized patients. Further study is required to determine if this subpopulation requires closer monitoring for disease progression during COVID-19.

Study Objectives
Age-related comorbidities and immune activation raise concern for advanced brain aging in people living with HIV (PLWH). The brain age index (BAI) is a machine learning model that quantifies deviations in brain activity during sleep relative to healthy individuals of the same age. High BAI was previously found to be associated with neurological, psychiatric, cardiometabolic diseases, and reduced life expectancy among people without HIV. Here, we estimated the effect of HIV infection on BAI by comparing PLWH and HIV-controls.

Methods
Clinical data and sleep EEGs from 43 PLWH on antiretroviral therapy (HIV+) and 3,155 controls (HIV-) were collected from Massachusetts General Hospital. The effect of HIV infection on BAI, and on individual EEG features, was estimated using causal inference.

Results
The average effect of HIV on BAI was estimated to be +3.35 years (p < 0.01, 95% CI = [0.67, 5.92]) using doubly robust estimation. Compared to HIV- controls, HIV+ participants exhibited a reduction in delta band power during deep sleep and rapid eye movement sleep.

Conclusion
We provide causal evidence that HIV contributes to advanced brain aging reflected in sleep EEG. A better understanding is greatly needed of potential therapeutic targets to mitigate the effect of HIV on brain health, potentially including sleep disorders and cardiovascular disease