Limitations of split-night polysomnography for the diagnosis of nocturnal hypoventilation and titration of non-invasive positive pressure ventilation in amyotrophic lateral sclerosis

SelANet: decision-assisting selective sleep apnea detection based on confidence score

BACKGROUND

One of the most common sleep disorders is sleep apnea syndrome. To diagnose sleep apnea syndrome, polysomnography is typically used, but it has limitations in terms of labor, cost, and time. Therefore, studies have been conducted to develop automated detection algorithms using limited biological signals that can be more easily diagnosed. However, the lack of information from limited signals can result in uncertainty from artificial intelligence judgments. Therefore, we performed selective prediction by using estimated respiratory signals from electrocardiogram and oxygen saturation signals based on confidence scores to classify only those sleep apnea occurrence samples with high confidence. In addition, for samples with high uncertainty, this algorithm rejected them, providing a second opinion to the clinician.

METHOD

Our developed model utilized polysomnography data from 994 subjects obtained from Massachusetts General Hospital. We performed feature extraction from the latent vector using the autoencoder. Then, one dimensional convolutional neural network-long short-term memory (1D CNN-LSTM) was designed and trained to measure confidence scores for input, with an additional selection function. We set a confidence score threshold called the target coverage and performed optimization only on samples with confidence scores higher than the target coverage. As a result, we demonstrated that the empirical coverage trained in the model converged to the target coverage.

RESULT

To confirm whether the model has been optimized according to the objectives, the coverage violation was used to measure the difference between the target coverage and the empirical coverage. As a result, the value of coverage violation was found to be an average of 0.067. Based on the model, we evaluated the classification performance of sleep apnea and confirmed that it achieved 90.26% accuracy, 91.29% sensitivity, and 89.21% specificity. This represents an improvement of approximately 7.03% in all metrics compared to the performance achieved without using a selective prediction.

CONCLUSION

This algorithm based on selective prediction utilizes confidence measurement method to minimize the problem caused by limited biological information. Based on this approach, this algorithm is applicable to wearable devices despite low signal quality and can be used as a simple detection method that determine the need for polysomnography or complement it.

Cerebrospinal fluid lipidomic fingerprint of obstructive sleep apnoea in Alzheimer's disease

BACKGROUND

Obstructive sleep apnoea (OSA) has a high prevalence in patients with Alzheimer's disease (AD). Both conditions have been shown to be associated with lipid dysregulation. However, the relationship between OSA severity and alterations in lipid metabolism in the brains of patients with AD has yet to be fully elucidated. In this context, we examined the cerebrospinal fluid (CSF) lipidome of patients with suspected OSA to identify potential diagnostic biomarkers and to provide insights into the pathophysiological mechanisms underlying the effect of OSA on AD.

METHODS

The study included 91 consecutive AD patients who underwent overnight polysomnography (PSG) to diagnose severe OSA (apnoea-hypopnea index ≥ 30/h). The next morning, CSF samples were collected and analysed by liquid chromatography coupled to mass spectrometry in an LC-ESI-QTOF-MS/MS platform.

RESULTS

The CSF levels of 11 lipid species were significantly different between AD patients with (N = 38) and without (N = 58) severe OSA. Five lipids (including oxidized triglyceride OxTG(57:2) and four unknown lipids) were significantly correlated with specific PSG measures of OSA severity related to sleep fragmentation and hypoxemia. Our analyses revealed a 4-lipid signature (including oxidized ceramide OxCer(40:6) and three unknown lipids) that provided an accuracy of 0.80 (95% CI: 0.71-0.89) in the detection of severe OSA. These lipids increased the discriminative power of the STOP-Bang questionnaire in terms of the area under the curve (AUC) from 0.61 (0.50-0.74) to 0.85 (0.71-0.93).

CONCLUSIONS

Our results reveal a CSF lipidomic fingerprint that allows the identification of AD patients with severe OSA. Our findings suggest that an increase in central nervous system lipoxidation may be the principal mechanism underlying the association between OSA and AD.

Blood-based lipidomic signature of severe obstructive sleep apnoea in Alzheimer's disease

Background

Obstructive sleep apnoea (OSA) is the most frequent form of sleep-disordered breathing in patients with Alzheimer’s disease (AD). Available evidence demonstrates that both conditions are independently associated with alterations in lipid metabolism. However, it is unknown whether the expression of lipids is different between AD patients with and without severe OSA. In this context, we examined the plasma lipidome of patients with suspected OSA, aiming to identify potential diagnostic biomarkers and to provide insights into the pathophysiological mechanisms underlying the disease.

Methods

The study included 103 consecutive patients from the memory unit of our institution with a diagnosis of AD. The individuals were subjected to overnight polysomnography (PSG) to diagnose severe OSA (apnoea-hypopnea index ≥30/h), and blood was collected the following morning. Untargeted plasma lipidomic profiling was performed using liquid chromatography coupled with mass spectrometry.

Results

We identified a subset of 44 lipids (mainly phospholipids and glycerolipids) that were expressed differently between patients with AD and severe and nonsevere OSA. Among the lipids in this profile, 30 were significantly correlated with specific PSG measures of OSA severity related to sleep fragmentation and hypoxemia. Machine learning analyses revealed a 4-lipid signature (phosphatidylcholine PC(35:4), cis-8,11,14,17-eicosatetraenoic acid and two oxidized triglycerides (OxTG(58:5) and OxTG(62:12)) that provided an accuracy (95% CI) of 0.78 (0.69–0.86) in the detection of OSA. These same lipids improved the predictive power of the STOP-Bang questionnaire in terms of the area under the curve (AUC) from 0.61 (0.50–0.74) to 0.80 (0.70–0.90).

Conclusion

Our results show a plasma lipidomic fingerprint that allows the identification of patients with AD and severe OSA, allowing the personalized management of these individuals. The findings suggest that oxidative stress and inflammation are potential prominent mechanisms underlying the association between OSA and AD.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13195-022-01102-8.

Validation of a Natural Language Processing Algorithm for the Extraction of the Sleep Parameters from the Polysomnography Reports

Background: There is a need to better understand the association between sleep and chronic diseases. In this study we developed a natural language processing (NLP) algorithm to mine polysomnography (PSG) free-text notes from electronic medical records (EMR) and evaluated the performance. Methods: Using the Veterans Health Administration EMR, we identified 46,093 PSG studies using CPT code 95,810 from 1 October 2000−30 September 2019. We randomly selected 200 notes to compare the accuracy of the NLP algorithm in mining sleep parameters including total sleep time (TST), sleep efficiency (SE) and sleep onset latency (SOL), wake after sleep onset (WASO), and apnea-hypopnea index (AHI) compared to visual inspection by raters masked to the NLP output. Results: The NLP performance on the training phase was >0.90 for precision, recall, and F-1 score for TST, SOL, SE, WASO, and AHI. The NLP performance on the test phase was >0.90 for precision, recall, and F-1 score for TST, SOL, SE, WASO, and AHI. Conclusions: This study showed that NLP is an accurate technique to extract sleep parameters from PSG reports in the EMR. Thus, NLP can serve as an effective tool in large health care systems to evaluate and improve patient care.

Noninvasive Ventilation in Amyotrophic Lateral Sclerosis

Amyotrophic lateral sclerosis is a progressive neurodegenerative disease involving upper and lower motor neurons and has limited treatment options. The weakness progresses to involve the diaphragms, resulting in respiratory failure and death. Home noninvasive ventilation has been shown to improve survival and quality of life, especially in those with intact bulbar function. Once initiated, close monitoring with nocturnal oximetry, remote downloads from the home noninvasive ventilation machine, and measurement of serum bicarbonate should be conducted. Additionally, transcutaneous CO2 monitoring can be considered if available. This article discusses the indications, timing, initiation, and management of noninvasive ventilation in amyotrophic lateral sclerosis.

Circulating MicroRNA Profile Associated with Obstructive Sleep Apnea in Alzheimer's Disease

The diagnosis of obstructive sleep apnea (OSA) in Alzheimer's disease (AD) by polysomnography (PSG) is challenging due to the required collaboration of the patients. In addition, screening questionnaires have demonstrated limited usefulness with this subpopulation. Considering this, we investigated the circulating microRNA (miRNA) profile associated with OSA in AD patients. This study included a carefully selected cohort of females with mild-moderate AD confirmed by biological evaluation (n = 29). The individuals were submitted to one-night PSG to diagnose OSA (apnea-hypopnea index ≥ 15/h) and the blood was collected in the following morning. The plasma miRNA profile was evaluated using RT-qPCR. The patients had a mean (SD) age of 75.8 (5.99) years old with a body mass index of 28.6 (3.83) kg m^-2. We observed a subset of 15 miRNAs differentially expressed between OSA and non-OSA patients, of which 10 were significantly correlated with the severity of OSA. Based on this, we built a prediction model that generated an AUC (95% CI) of 0.95 (0.88-1.00) including 5 of the differentially expressed miRNAs that correlated with OSA severity: miR-26a-5p, miR-30a-3p, miR-374a-5p, miR-377-3p, and miR-545-3p. Our preliminary results suggest a plasma miRNA signature associated with the presence of OSA in AD patients. Further studies will be necessary to validate these findings.

Sleep disorders and respiratory function in amyotrophic lateral sclerosis

Sleep disorders in amyotrophic lateral sclerosis (ALS) present a significant challenge to the management of patients. Issues include the maintenance of adequate ventilatory status through techniques such as non-invasive ventilation, which has the ability to modulate survival and improve patient quality of life. Here, a multidisciplinary approach to the management of these disorders is reviewed, from concepts about the underlying neurobiological basis, through to current management approaches and future directions for research.