Artificial intelligence-enabled detection and assessment of Parkinson's disease using nocturnal breathing signals.

There are currently no effective biomarkers for diagnosing Parkinson's disease (PD) or tracking its progression. Here, we developed an artificial intelligence (AI) model to detect PD and track its progression from nocturnal breathing signals. The model was evaluated on a large dataset comprising 7,671 individuals, using data from several hospitals in the United States, as well as multiple public datasets. The AI model can detect PD with an area-under-the-curve of 0.90 and 0.85 on held-out and external test sets, respectively. The AI model can also estimate PD severity and progression in accordance with the Movement Disorder Society Unified Parkinson's Disease Rating Scale (R = 0.94, P = 3.6 × 10-25). The AI model uses an attention layer that allows for interpreting its predictions with respect to sleep and electroencephalogram. Moreover, the model can assess PD in the home setting in a touchless manner, by extracting breathing from radio waves that bounce off a person's body during sleep. Our study demonstrates the feasibility of objective, noninvasive, at-home assessment of PD, and also provides initial evidence that this AI model may be useful for risk assessment before clinical diagnosis.

Effects of Experimental Sleep Restriction on Ambulatory and Sleep Blood Pressure in Healthy Young Adults: A Randomized Crossover Study.

[Figure: see text].

Increased heart rate with sleep disordered breathing in hypertrophic cardiomyopathy.

BACKGROUND: Current guidelines recommend medications with rate control properties for symptomatic patients with hypertrophic cardiomyopathy (HCM) based on the rationale that lowering heart rate (HR) improves their symptoms. Whether sleep disordered breathing (SDB) is associated with increased HR in HCM patients is not known. METHOD: We diagnosed uncontrolled SDB (oxygen desaturation index ≥5) in consecutive echocardiographically confirmed HCM patients seen at Mayo Clinic, Rochester, and analyzed their HR as recorded by a 24-h Holter monitor. We compared mean, minimum, maximum HR between those with vs without SDB. In a pilot subanalysis of HCM patients with SDB who also underwent subsequent diagnostic polysomnography (PSG), we analyzed RR interval changes coinciding with obstructive sleep apnea and hypopnea episodes. RESULTS: Of the 230 HCM patients included in this study (age 54 ± 16 years; 138 male; LVOT pressure gradient at rest 45 ± 39 mmHg), 115 (50%) patients had SDB. HCM patients with SDB were recorded to have higher mean HR (71 vs. 67 bpm; p = .002, adjusted p = .001), and this difference was most pronounced during night hours of 10 PM to 5 AM (61 vs. 67 bpm; p < .001). In the pilot analysis of the available PSG data, the release of obstructive sleep apneas and hypopneas coincided with fluctuation of HR. CONCLUSIONS: SDB is independently associated with higher mean HR in patients with HCM, and this difference is most significant during sleep. Treatment of SDB, which is readily available, should be tested as a complementary modality to the currently recommended pharmacotherapy aimed at lowering HR in patients with symptomatic HCM.

Cardiac autonomic control and complexity during sleep are preserved after chronic sleep restriction in healthy subjects.

Acute sleep deprivation (SD) alters cardiovascular autonomic control (CAC) and is associated with an increased risk of cardiovascular disorders. However, the effects of partial SD on CAC are unclear. Thus, we aimed to investigate the effects of partial SD on CAC during sleep. We randomized seventeen healthy subjects to a restriction group (RES, n = 8, subjects slept two-thirds of normal sleep time based on individual habitual sleep duration for 8 days and 8 nights) or a Control group (CON, n = 9, subjects were allowed to sleep their usual sleep time). Attended polysomnographic (PSG) studies were performed every night; a subset of them was selected for the analysis at baseline (day 3-D3), the first night after sleep restriction (day 5-D5), at the end of sleep restriction period (day 11-D11), and at the end of recovery phase (day 14-D14). We extracted electrocardiogram (ECG) and respiration from the PSG and divided into wakefulness (W), nonrapid eye movements (REM) sleep (N2 and N3) and REM sleep. CAC was evaluated by means of linear spectral analysis, nonlinear symbolic analysis and complexity indexes. In both RES and CON groups, sympathetic modulation decreased and parasympathetic modulation increased during N2 and N3 compared to W and REM at D3, D5, D11, D14. Complexity analysis revealed a reduction in complexity during REM compared to NREM sleep in both DEP and CON After 8 days of moderate SD, cardiac autonomic dynamics, characterized by decreased sympathetic, and increased parasympathetic modulation, and higher cardiac complexity during NREM sleep, compared to W and REM, are preserved.

Novel Bloodless Potassium Determination Using a Signal-Processed Single-Lead ECG.

BACKGROUND: Hyper- and hypokalemia are clinically silent, common in patients with renal or cardiac disease, and are life threatening. A noninvasive, unobtrusive, blood-free method for tracking potassium would be an important clinical advance. METHODS AND RESULTS: Two groups of hemodialysis patients (development group, n=26; validation group, n=19) underwent high-resolution digital ECG recordings and had 2 to 3 blood tests during dialysis. Using advanced signal processing, we developed a personalized regression model for each patient to noninvasively calculate potassium values during the second and third dialysis sessions using only the processed single-channel ECG. In addition, by analyzing the entire development group's first-visit data, we created a global model for all patients that was validated against subsequent sessions in the development group and in a separate validation group. This global model sought to predict potassium, based on the T wave characteristics, with no blood tests required. For the personalized model, we successfully calculated potassium values with an absolute error of 0.36±0.34 mmol/L (or 10% of the measured blood potassium). For the global model, potassium prediction was also accurate, with an absolute error of 0.44±0.47 mmol/L for the training group (or 11% of the measured blood potassium) and 0.5±0.42 for the validation set (or 12% of the measured blood potassium). CONCLUSIONS: The signal-processed ECG derived from a single lead can be used to calculate potassium values with clinically meaningful resolution using a strategy that requires no blood tests. This enables a cost-effective, noninvasive, unobtrusive strategy for potassium assessment that can be used during remote monitoring.

Noninvasive potassium determination using a mathematically processed ECG: proof of concept for a novel "blood-less, blood test".

OBJECTIVE: To determine if ECG repolarization measures can be used to detect small changes in serum potassium levels in hemodialysis patients. PATIENTS AND METHODS: Signal-averaged ECGs were obtained from standard ECG leads in 12 patients before, during, and after dialysis. Based on physiological considerations, five repolarization-related ECG measures were chosen and automatically extracted for analysis: the slope of the T wave downstroke (T right slope), the amplitude of the T wave (T amplitude), the center of gravity (COG) of the T wave (T COG), the ratio of the amplitude of the T wave to amplitude of the R wave (T/R amplitude), and the center of gravity of the last 25% of the area under the T wave curve (T4 COG) (Fig. 1). RESULTS: The correlations with potassium were statistically significant for T right slope (P<0.0001), T COG (P=0.007), T amplitude (P=0.0006) and T/R amplitude (P=0.03), but not T4 COG (P=0.13). Potassium changes as small as 0.2mmol/L were detectable. CONCLUSION: Small changes in blood potassium concentrations, within the normal range, resulted in quantifiable changes in the processed, signal-averaged ECG. This indicates that non-invasive, ECG-based potassium measurement is feasible and suggests that continuous or remote monitoring systems could be developed to detect early potassium deviations among high-risk patients, such as those with cardiovascular and renal diseases. The results of this feasibility study will need to be further confirmed in a larger cohort of patients.

Experimental sleep restriction causes endothelial dysfunction in healthy humans.

BACKGROUND: Epidemiologic evidence suggests a link between short sleep duration and cardiovascular risk, although the nature of any relationship and mechanisms remain unclear. Short sleep duration has also been linked to an increase in cardiovascular events. Endothelial dysfunction has itself been implicated as a mediator of heightened cardiovascular risk. We sought to determine the effect of 8 days/8 nights of partial sleep restriction on endothelial function in healthy humans. METHODS AND RESULTS: Sixteen healthy volunteers underwent a randomized study of usual sleep versus sleep restriction of two-thirds normal sleep time for 8 days/8 nights in a hospital-based clinical research unit. The main outcome was endothelial function measured by flow-mediated brachial artery vasodilatation (FMD). Those randomized to sleep restriction slept 5.1 hours/night during the experimental period compared with 6.9 hours/night in the control group. Sleep restriction was associated with significant impairment in FMD (8.6±4.6% during the initial pre-randomization acclimation phase versus 5.2±3.4% during the randomized experimental phase, P=0.01) whereas no change was seen in the control group (5.0±3.0 during the acclimation phase versus 6.73±2.9% during the experimental phase, P=0.10) for a between-groups difference of -4.40% (95% CI -7.00 to -1.81%, P=0.003). No change was seen in non-flow mediated vasodilatation (NFMD) in either group. CONCLUSION: In healthy individuals, moderate sleep restriction causes endothelial dysfunction. CLINICAL TRIAL REGISTRATION URL: ClinicalTrials.gov. Unique identifier: NCT01334788.

Interatrial pressure gradients during simulated obstructive sleep apnea: a catheter-based study.

OBJECTIVES: We set to measure the interatrial pressure gradient during simulated obstructive sleep apnea (OSA). BACKGROUND: OSA occurs when a sleeping patient attempts to inhale against an obstructed airway. How this event affects the interatrial pressure gradient has not been defined. We hypothesized that simulated OSA in a conscious subject (Mueller maneuver [MM], inspiration against obstruction) would promote increased right-to-left pressure gradient, and then the substrate for right-to-left atrial shunting. METHODS: Selected patients underwent simultaneous measurement of airway and atrial pressures (both left and right atrium [LA, RA]) using high-fidelity micromanometry at rest, during MM, and during VM, during right heart catheterization. RESULTS: Ten patients (age 55 ± 11 years, two women) were successfully studied. During the onset of MM, RA pressure transiently but consistently exceeded LA pressure in response to the steep decline in intrathoracic pressure (maximum RA-LA pressure gradient increased from 0.1 ± 1.4 mm Hg at baseline to 7.0 ± 4.3 mm Hg during MM, P < 0.001). The maximum right-to-left atrial pressure gradient during Mueller maneuver was higher than that achieved during the Valsalva maneuver release (P < 0.007). CONCLUSIONS: The onset of MM increased right-to-left pressure gradient across the atrial septum, likely as a result of greater blood return to the RA from extrathoracic veins. The RA-LA pressure gradient achieved during MM was greater than that observed during VM. These findings delineate the hemodynamic substrate for right to left shunting during OSA.

Effects of experimental sleep restriction on caloric intake and activity energy expenditure.

BACKGROUND: Epidemiologic studies link short sleep duration to obesity and weight gain. Insufficient sleep appears to alter circulating levels of the hormones leptin and ghrelin, which may promote appetite, although the effects of sleep restriction on caloric intake and energy expenditure are unclear. We sought to determine the effect of 8 days/8 nights of sleep restriction on caloric intake, activity energy expenditure, and circulating levels of leptin and ghrelin. METHODS: We conducted a randomized study of usual sleep vs a sleep restriction of two-thirds of normal sleep time for 8 days/8 nights in a hospital-based clinical research unit. The main outcomes were caloric intake, activity energy expenditure, and circulating levels of leptin and ghrelin. RESULTS: Caloric intake in the sleep-restricted group increased by +559 kcal/d (SD, 706 kcal/d, P=.006) and decreased in the control group by -118 kcal/d (SD, 386 kcal/d, P=.51) for a net change of +677 kcal/d (95% CI, 148-1,206 kcal/d; P=.014). Sleep restriction was not associated with changes in activity energy expenditure (P=.62). No change was seen in levels of leptin (P=.27) or ghrelin (P=.21). CONCLUSIONS: Sleep restriction was associated with an increase in caloric consumption with no change in activity energy expenditure or leptin and ghrelin concentrations. Increased caloric intake without any accompanying increase in energy expenditure may contribute to obesity in people who are exposed to long-term sleep restriction. TRIAL REGISTRATION: ClinicalTrials.gov; No.: NCT01334788; URL: www.clinicaltrials.gov.

Diagnostic accuracy of the Berlin Questionnaire in detecting sleep-disordered breathing in patients with a recent myocardial infarction.

BACKGROUND: The Berlin Questionnaire (BQ) has been used to identify patients at high risk for sleep-disordered breathing (SDB) in a variety of populations. However, there are no data regarding the validity of the BQ in detecting the presence of SDB in patients after myocardial infarction (MI). The aim of this study was to determine the performance of the BQ in patients after MI. METHODS: We conducted a cross-sectional study of 99 patients who had an MI 1 to 3 months previously. The BQ was administered, scored using the published methods, and followed by completed overnight polysomnography as the "gold standard." SDB was defined as an apnea-hypopnea index of ≥ 5 events/h. The sensitivity, specificity, and positive and negative predictive values of the BQ were calculated. RESULTS: Of the 99 patients, the BQ identified 64 (65%) as being at high-risk for having SDB. Overnight polysomnography showed that 73 (73%) had SDB. The BQ sensitivity and specificity was 0.68 and 0.34, respectively, with a positive predictive value of 0.68 and a negative predictive value of 0.50. Positive and negative likelihood ratios were 1.27 and 0.68, respectively, and the BQ overall diagnostic accuracy was 63%. Using different apnea-hypopnea index cutoff values did not meaningfully alter these results. CONCLUSION: The BQ performed with modest sensitivity, but the specificity was poor, suggesting that the BQ is not ideal in identifying SDB in patients with a recent MI.

Effect of weight gain on cardiac autonomic control during wakefulness and sleep.

Obesity has been associated with increased cardiac sympathetic activation during wakefulness, but the effect on sleep-related sympathetic modulation is not known. The aim of this study was to investigate the effect of fat gain on cardiac autonomic control during wakefulness and sleep in humans. We performed a randomized, controlled study to assess the effects of fat gain on heart rate variability. We recruited 36 healthy volunteers, who were randomized to either a standardized diet to gain ≈4 kg over 8 weeks followed by an 8-week weight loss period (n=20) or to serve as a weight-maintainer control (n=16). An overnight polysomnogram with power spectral analysis of heart rate variability was performed at baseline, after weight gain, and after weight loss to determine the ratio of low-frequency to high-frequency power and to examine the relationship between changes in heart rate variability and changes in insulin, leptin, and adiponectin levels. Mean weight gain was 3.9 kg in the fat gain group versus 0.1 kg in the maintainer group. Low frequency/high frequency increased both during wakefulness and sleep after fat gain and returned to baseline after fat loss in the fat gain group and did not change in the control group. Insulin, leptin, and adiponectin also increased after fat gain and fell after fat loss, but no clear pattern of changes was seen that correlated consistently with changes in heart rate variability. Short-term fat gain in healthy subjects is associated with increased cardiac sympathetic activation during wakefulness and sleep, but the mechanisms remain unclear.

Sleep-disordered breathing in patients with the Brugada syndrome.

We investigated breathing patterns and the occurrence of arrhythmias and ST-segment changes during sleep in patients with Brugada syndrome. Patients with Brugada syndrome are more likely to die from ventricular arrhythmias during sleep. ST-segment changes have been correlated with risk of sudden cardiac death. Whether sleep disturbances may contribute to arrhythmogenesis is unknown. Patients with Brugada syndrome underwent overnight polysomnography with simultaneous 12-lead electrocardiographic recording. A control group matched by age, gender, and body mass index (BMI) also underwent polysomnography. Twenty patients were included (50 ± 15 years old, 75% men). Despite their normal BMI (24.7 ± 2.7 kg/m(2)), 45% had sleep-disordered breathing (SDB), with a mean apnea-hypopnea index of 17.2 ± 14 events/hour. In patients with a high risk of arrhythmias, 5 (63%) had SDB. In the control group, 27% had SDB. Atrial or ventricular arrhythmias were not observed. Spontaneous ST-segment changes occurred in 2 patients over 45 different time points. Most ST-segment changes were observed during rapid eye movement sleep (31%) or within 1 minute of arousals (44%). Regarding respiratory events, 25 (56%) of ST-segment changes were related to occurrence of apnea or hypopnea. In conclusion, patients with Brugada syndrome have a high prevalence of SDB even in the setting of normal BMI. The higher incidence of nocturnal death in patients with Brugada syndrome may be conceivably related to co-morbid SDB. Moreover, autonomic instability encountered in rapid eye movement sleep and arousals could potentiate the risk of arrhythmias.

Diagnostic accuracy of split-night polysomnograms.

STUDY OBJECTIVES: American Academy of Sleep Medicine (AASM) practice parameters indicate that split-night polysomnograms (SN-PSG) may be performed when the apnea hypopnea index (AHI) is > or = 20 to 40, depending on clinical factors. The aim of this study was to determine the diagnostic accuracy of SN-PSG, including at the lower range of AHIs. METHODS: We reviewed 114 consecutive full-night PSGs (FN-PSG) performed at our center between August 2006 and November 2008 on subjects enrolled in studies in which obstructive sleep apnea (OSA) was the sleep disorder of interest. We compared the AHI from the first 2 hours (2 hr-AHI) and 3 hours (3 hr-AHI) of sleep with the "gold standard" AHI from FN-PSG (FN-AHI), considering OSA present if FN-AHI > or = 5. RESULTS: The 2 hr-AHI and 3 hr-AHI correlated strongly with the FN-AHI (concordance correlation coefficient [CCC] = 0.93 and 0.97, respectively). After adjusting for percentage of sleep in stage REM sleep and in supine position, the correlation of 2 hr- and 3 hr-AHI with FN-AHI remained strong (0.92 and 0.96, respectively). The area under the receiver operating curves (AUC) for 2 hr-AHI and 3 hr-AHI using FN-AHI > or = 5 were 0.93 and 0.95, respectively. CONCLUSIONS: The AHI derived from the first 2 or 3 hours of sleep is of sufficient diagnostic accuracy to rule-in OSA at an AHI threshold of 5 in patients suspected of having OSA. This study suggests that the current recommended threshold for split-night studies (AHI > or = 20 to 40) may be revised to a lower number, allowing for more efficient use of resources.