R-R interval-based sleep apnea screening by a recurrent neural network in a large clinical polysomnography dataset.

OBJECTIVE: Easily detecting patients with undiagnosed sleep apnea syndrome (SAS) requires a home-use SAS screening system. In this study, we validate a previously developed SAS screening methodology using a large clinical polysomnography (PSG) dataset (N = 938). METHODS: We combined R-R interval (RRI) and long short-term memory (LSTM), a type of recurrent neural networks, and created a model to discriminate respiratory conditions using the training dataset (N = 468). Its performance was validated using the validation dataset (N = 470). RESULTS: Our method screened patients with severe SAS (apnea hypopnea index; AHI ≥ 30) with an area under the curve (AUC) of 0.92, a sensitivity of 0.80, and a specificity of 0.84. In addition, the model screened patients with moderate/severe SAS (AHI ≥ 15) with an AUC of 0.89, a sensitivity of 0.75, and a specificity of 0.87. CONCLUSIONS: Our method achieved high screening performance when applied to a large clinical dataset. SIGNIFICANCE: Our method can help realize an easy-to-use SAS screening system because RRI data can be easily measured with a wearable heart rate sensor. It has been validated on a large dataset including subjects with various backgrounds and is expected to perform well in real-world clinical practice.

Screening of sleep apnea based on heart rate variability and long short-term memory.

PURPOSE: Sleep apnea syndrome (SAS) is a prevalent sleep disorder in which apnea and hypopnea occur frequently during sleep and result in increase of the risk of lifestyle-related disease development as well as daytime sleepiness. Although SAS is a common sleep disorder, most patients remain undiagnosed because the gold standard test polysomnography (PSG), is high-cost and unavailable in many hospitals. Thus, an SAS screening system that can be used easily at home is needed. METHODS: Apnea during sleep affects changes in the autonomic nervous function, which causes fluctuation of the heart rate. In this study, we propose a new SAS screening method that combines heart rate measurement and long short-term memory (LSTM) which is a type of recurrent neural network (RNN). We analyzed the data of intervals between adjacent R waves (R-R interval; RRI) on the electrocardiogram (ECG) records, and used an LSTM model whose inputs are the RRI data is trained to discriminate the respiratory condition during sleep. RESULTS: The application of the proposed method to clinical data showed that it distinguished between patients with moderate-to-severe SAS with a sensitivity of 100% and specificity of 100%, results which are superior to any other existing SAS screening methods. CONCLUSION: Since the RRI data can be easily measured by means of wearable heart rate sensors, our method may prove to be useful as an SAS screening system at home.

Resting Heart Rate Variability Is Associated With Subsequent Orthostatic Hypotension: Comparison Between Healthy Older People and Patients With Rapid Eye Movement Sleep Behavior Disorder.

Background: Orthostatic hypotension (OH) caused by autonomic dysfunction is a common symptom in older people and patients with idiopathic rapid eye movement sleep behavior disorder (iRBD). The orthostatic challenge test is a standard autonomic function test that measures a decrease of blood pressure during a postural change from supine to standing positions. Although previous studies have reported that changes in heart rate variability (HRV) are associated with autonomic dysfunction, no study has investigated the relationship between HRV before standing and the occurrence of OH in an orthostatic challenge test. This study aims to examine the connection between HRV in the supine position and the occurrence of OH in an orthostatic challenge test. Methods: We measured the electrocardiograms of patients with iRBD and healthy older people during an orthostatic challenge test, in which the supine and standing positions were held for 15 min, respectively. The subjects were divided into three groups: healthy controls (HC), OH-negative iRBD [OH (-) iRBD], and OH-positive iRBD [OH (+) iRBD]. HRV measured in the supine position during the test were calculated by time-domain analysis and Poincaré plots to evaluate the autonomic dysfunction. Results: Forty-two HC, 12 OH (-) iRBD, and nine OH (+) iRBD subjects were included. HRV indices in the OH (-) and the OH (+) iRBD groups were significantly smaller than those in the HC group. The multivariate logistic regression analysis for OH identification for the iRBD groups showed the model whose inputs were the HRV indices, i.e., standard deviation 2 (SD2) and the percentage of adjacent intervals that varied by more than 50 ms (pNN50), had a receiver operating characteristic curve with area under the curve of 0.840, the sensitivity to OH (+) of 1.000, and the specificity to OH (-) of 0.583 (p = 0.023). Conclusions: This study showed the possibility that short-term HRV indices in the supine position would predict subsequent OH in iRBD patients. Our results are of clinical importance in terms of showing the possibility that OH can be predicted using only HRV in the supine position without an orthostatic challenge test, which would improve the efficiency and safety of testing.

Obstructive sleep apnea screening by heart rate variability-based apnea/normal respiration discriminant model.

OBJECTIVE: Obstructive sleep apnea (OSA) is a common sleep disorder; however, most patients are undiagnosed and untreated because it is difficult for patients themselves to notice OSA in daily living. Polysomnography (PSG), which is the gold standard test for sleep disorder diagnosis, cannot be performed in many hospitals. This fact motivates us to develop a simple system for screening OSA at home. APPROACH: The autonomic nervous system changes during apnea, and such changes affect heart rate variability (HRV). This work develops a new apnea screening method based on HRV analysis and machine learning technologies. An apnea/normal respiration (A/N) discriminant model is built for respiration condition estimation for every heart rate measurement, and an apnea/sleep ratio is introduced for final diagnosis. A random forest is adopted for the A/N discriminant model construction, which is trained with the PhysioNet apnea-ECG database. MAIN RESULTS: The screening performance of the proposed method was evaluated by applying it to clinical PSG data. Sensitivity and specificity achieved 76% and 92%, respectively, which are comparable to existing portable sleep monitoring devices used in sleep laboratories. SIGNIFICANCE: Since the proposed OSA screening method can be used more easily than existing devices, it will contribute to OSA treatment.

Development of a Sleep Apnea Detection Algorithm Using Long Short-Term Memory and Heart Rate Variability.

Sleep apnea syndrome (SAS) is a prevalent disorder which causes daytime fatigue with the increased risk of lifestyle diseases. A large number of patients are undiagnosed and untreated partly because of the difficulty in performing its gold standard test, polysomnography (PSG). In this research, we propose a simple screening method utilizing heart rate variability (HRV) and long short-term memory (LSTM) which is a kind of neural network techniques. The result of applying this algorithm to clinical data demonstrates that it can discriminate between patients and healthy people with high sensitivity (100%) and specificity (100%).

Heart Rate Variability-Based Driver Drowsiness Detection and Its Validation With EEG.

OBJECTIVE: Driver drowsiness detection is a key technology that can prevent fatal car accidents caused by drowsy driving. The present work proposes a driver drowsiness detection algorithm based on heart rate variability (HRV) analysis and validates the proposed method by comparing with electroencephalography (EEG)-based sleep scoring. METHODS: Changes in sleep condition affect the autonomic nervous system and then HRV, which is defined as an RR interval (RRI) fluctuation on an electrocardiogram trace. Eight HRV features are monitored for detecting changes in HRV by using multivariate statistical process control, which is a well known anomaly detection method. RESULT: The performance of the proposed algorithm was evaluated through an experiment using a driving simulator. In this experiment, RRI data were measured from 34 participants during driving, and their sleep onsets were determined based on the EEG data by a sleep specialist. The validation result of the experimental data with the EEG data showed that drowsiness was detected in 12 out of 13 pre-N1 episodes prior to the sleep onsets, and the false positive rate was 1.7 times per hour. CONCLUSION: The present work also demonstrates the usefulness of the framework of HRV-based anomaly detection that was originally proposed for epileptic seizure prediction. SIGNIFICANCE: The proposed method can contribute to preventing accidents caused by drowsy driving.

Is hemifacial spasm affected by changes in the heart rate? A study using heart rate variability analysis.

OBJECTIVE: Hemifacial spasm (HFS) is caused by arterial conflict at the root exit zone of the facial nerve. As the offending artery is pulsatile in nature, this study investigated the association of heart rate fluctuation with HFS. METHODS: Twenty-four preoperative patients underwent simultaneous recordings of facial electromyogram and electrocardiogram overnight. Series of R-wave to R-wave intervals (RRIs) in the electrocardiogram were analyzed across subjects in relation to HFS. The degree of heart rate fluctuation was quantified by analyzing the heart rate variability (HRV). The sleep stage was evaluated during the period of HFS. RESULTS: A 0.1 Hz fluctuation in RRIs by 5% compared to the baseline preceded a few seconds the onset of the HFS, indicating that a significant increase in the heart rate coincided with HFS. HRV analysis demonstrated that fluctuations in the heart rate were significantly enhanced during HFS. Wake or light sleep stages were more often accompanied by HFS, suggesting an association with autonomic activities. CONCLUSION: Our findings suggest that the etiology of HFS is more than just a mechanical compression of the facial nerve and may involve changes in pulsatile frequency in offending arteries. SIGNIFICANCE: We propose the etiology of HFS from a unique standpoint.

Development of sleep apnea syndrome screening algorithm by using heart rate variability analysis and support vector machine.

Although sleep apnea syndrome (SAS) is a common sleep disorder, most patients with sleep apnea are undiagnosed and untreated because it is difficult for patients themselves to notice SAS in daily living. Polysomnography (PSG) is a gold standard test for sleep disorder diagnosis, however PSG cannot be performed in many hospitals. This fact motivates us to develop an SAS screening system that can be used easily at home. The autonomic nervous function of a patient changes during apnea. Since changes in the autonomic nervous function affect fluctuation of the R-R interval (RRI) of an electrocardiogram (ECG), called heart rate variability (HRV), SAS can be detected through monitoring HRV. The present work proposes a new HRV-based SAS screening algorithm by utilizing support vector machine (SVM), which is a well-known pattern recognition method. In the proposed algorithm, various HRV features are derived from RRI data in both apnea and normal respiration periods of patients and healthy people, and an apnea/normal respiration (A/N) discriminant model is built from the derived HRV features by SVM. The result of applying the proposed SAS screening algorithm to clinical data demonstrates that it can discriminate patients with sleep apnea and healthy people appropriately. The sensitivity and the specificity of the proposed algorithm were 100% and 86%, respectively.

A selective Sema3A inhibitor enhances regenerative responses and functional recovery of the injured spinal cord.

Axons in the adult mammalian central nervous system (CNS) exhibit little regeneration after injury. It has been suggested that several axonal growth inhibitors prevent CNS axonal regeneration. Recent research has demonstrated that semaphorin3A (Sema3A) is one of the major inhibitors of axonal regeneration. We identified a strong and selective inhibitor of Sema3A, SM-216289, from the fermentation broth of a fungal strain. To examine the effect of SM-216289 in vivo, we transected the spinal cord of adult rats and administered SM-216289 into the lesion site for 4 weeks. Rats treated with SM-216289 showed substantially enhanced regeneration and/or preservation of injured axons, robust Schwann cell-mediated myelination and axonal regeneration in the lesion site, appreciable decreases in apoptotic cell number and marked enhancement of angiogenesis, resulting in considerably better functional recovery. Thus, Sema3A is essential for the inhibition of axonal regeneration and other regenerative responses after spinal cord injury (SCI). These results support the possibility of using Sema3A inhibitors in the treatment of human SCI.

Brain-derived neurotrophic factor bound with lecithin derivative showed a markedly enhanced pharmacological potency due to its potent cell membrane affinity followed by prolonged MAPK activation.

We synthesized lecithinized brain-derived neurotrophic factor (lecithinized-BDNF), in which an average of three molecules of a lecithin derivative were bound to recombinant human BDNF. We evaluated its pharmacological activity in C57BL/KsJ-db/db mice, and assessed its targetability and affinity for the nervous system. Subcutaneously administered lecithinized-BDNF markedly reduced the plasma glucose level, food intake, and body weight in C57BL/KsJ-db/db diabetic mice. Its potency was more than 20 times greater than that of unmodified BDNF. We then studied the mechanism for the markedly enhanced pharmacological activity. In vitro cell growth activity of lecithinized-BDNF using the MTT assay was lower than unmodified BDNF, probably due to steric hindrance of the lecithin moieties. While the plasma BDNF level after subcutaneous administration of lecithinized-BDNF was not higher compared with unmodified BDNF. However, higher amount of lecithinized-BDNF accumulated in the spinal cord was observed. Lastly, we found that in vitro binding capacity of lecithinized-BDNF for PC-pAB1 neural cells was much higher than unmodified BDNF. Moreover, lecithinized-BDNF bound to PC-pAB1 cells did not exchange with an excessive amount of unmodified BDNF or an excess of lecithinized-BDNF. PC-pAB1 cells treated with lecithinized-BDNF showed sustained mitogen-activated protein kinase (MAPK, ERK1/2) activation. These data would indicate that the high affinity of lecithinized-BDNF for the target cells, followed by prolonged MAPK activation, would play an important role in its potent pharmacological activity.

Ciliary neurotrophic factor protects rat retina cells in vitro and in vivo via PI3 kinase.

PURPOSE: Neurotrophic factors and neurotrophins are well-known to have neuroprotective efficacy against retinal injury. The aim of this experiment is to investigate the signal transduction pathway of ciliary neurotrophic factor (CNTF) on the upregulation of viability of retinal primary culture and retinal protection against constant light damage in vivo. CNTF is known to enhance the viability of retinal culture and provide protection under constant light exposure conditions, but little is known about how the signal transduction pathways of CNTF affect retina function. METHODS: Primary retinal cultures were prepared from 7-day-old Wistar rats. Brain-derived neurotrophic factor (BDNF) (0.1, 1, 10 ng/ml), CNTF (0.1, 1, 10 ng/ml), PD98059 (10, 100, 1000 nM), or LY294002 (10, 100, 1000 nM) was added to these cultures at the time of cell preparation. After 3 days, the percentage of cells surviving was assessed using alamarBlue. For the in vivo experiment, inhibitors for the MAPKK (PD98059, 10 microg/eye) or PI3K (LY294002, 10 microg/eye) pathways were injected into the vitreous together with CNTF (1 microg/eye) 2 days before constant light exposure. Electroretinogram (ERG) analysis was performed to investigate which pathway was used by CNTF. RESULTS: CNTF at 1, 10, or 100 ng/ml enhanced cell viability in retinal cultures. The cell-survival activity of CNTF was blocked by 10 ng/ml LY294002 (Dunnet's test, p < 0.05). In vivo, the neuroprotective activity of CNTF in constant-light conditions was attenuated by 10 microg/eye LY294002 (Dunnet's test, p < 0.05). CONCLUSIONS: These data suggest that CNTF promotes cell survival via the PI3K signaling pathway in vitro and in vivo.

Riluzole slows the progression of neuromuscular dysfunction in the wobbler mouse motor neuron disease.

In the wobbler mouse motor neuron disease (MND), we firstly evaluated the effect of riluzole, the only approved drug for amyotrophic lateral sclerosis, and compared it with that of brain-derived neurotrophic factor (BDNF). Wobbler mice received either daily subcutaneous treatment with BDNF (5, 20, and 40 mg/kg) or oral riluzole in drinking water (100 and 200 microg/ml), beginning immediately after the clinical onset of MND. We examined motor functions, such as grip strength and rota-rod walking performance, weekly, and the amplitude of the compound muscle action potential (CMAP) in the forelimb biceps at the end of treatment. BDNF treatment slowed the disease progression maximally at a dose of 20 mg/kg, consistent to the previous evidence. Only high-dose riluzole treatment increased grip strength at weeks 1 (P=0.0023) and 2 (P=0.021), time before falling in the rota-rod test throughout all 4 weeks of treatment (P=0.0022 to 0.0282), and CMAP amplitude (P=0.0069) at the end of treatment, compared with the vehicle. Furthermore, the riluzole treatment increased the number of the cervical cord anterior horn neurons that were immunoreactive for SMI-32, a specific motor neuron marker, by the end of treatment (P=0.0063), although it did not affect the vacuolar degeneration on the SMI-32-positive neurons. This study demonstrated that riluzole was comparable to BDNF in slowing the progression of neuromuscular dysfunction in the wobbler mouse MND, which may provide a useful model for examining the mechanisms of selective motor neuron degeneration.

Brain-derived neurotrophic factor shows a protective effect and improves recovery of the ERG b-wave response in light-damage.

We investigated the neuroprotective effects of brain-derived neurotrophic factor (BDNF) and its influence on the functional recovery of the retina following light-induced retinal damage by electroretinogram (ERG). Rats were exposed to constant fluorescent light for 2, 5, 7, or 14 days, then returned to a cyclic light environment for 14 days. The result indicated that BDNF had few effects on the a-wave amplitude, but there was a statistically significant difference in the b-wave amplitudes between BDNF-treated and control eyes from day 0-14 of the recovery period following 2 days of light exposure (p < 0.05). Our findings suggest that BDNF not only protects the retinal neuronal function but also enhances the recovery from retinal light damage.

In vitro and in vivo characterization of a novel semaphorin 3A inhibitor, SM-216289 or xanthofulvin.

SM-216289 (xanthofulvin) isolated from the fermentation broth of a fungal strain, Penicillium sp. SPF-3059, was identified as a strong semaphorin 3A (Sema3A) inhibitor. Sema3A-induced growth cone collapse of dorsal root ganglion neurons in vitro was completely abolished in the presence of SM-216289 at levels less than 2 mum (IC50 = 0.16 mum). When dorsal root ganglion explants were co-cultured with Sema3A-producing COS7 cells in a collagen gel matrix, SM-216289 enabled neurites to grow toward the COS7 cells. SM-216289 diminished the binding of Sema3A to its receptor neuropilin-1 in vitro, suggesting a direct interference of receptor-ligand association. Moreover, our data suggest that SM-216289 interacted with Sema3A directly and blocked the binding of Sema3A to its receptor. We examined the efficacy of SM-216289 in vivo using a rat olfactory nerve axotomy model, in which strong Sema3A induction has been reported around regenerating axons. The regeneration of olfactory nerves was significantly accelerated by a local administration of SM-216289 in the lesion site, suggesting the involvement of Sema3A in neural regeneration as an inhibitory factor. SM-216289 is an excellent molecular probe to investigate the function of Sema3A, in vitro and in vivo, and may be useful for the treatment of traumatic neural injuries.

Enhancement of BDNF and activated-ERK immunoreactivity in spinal motor neurons after peripheral administration of BDNF.

Brain-derived neurotrophic factor (BDNF) shows neurotrophic effects on adult motor neurons when given systemically, But it is unknown whether systemically administered BDNF is transported to central cell bodies to affect them directly. Here we used immunohistochemistry to investigate the transport of peripherally injected BDNF to spinal motor neurons and the subsequent activation of a signaling pathway. We first injected BDNF into the flexor digitorum brevis (FDB) and analyzed the motor nucleus that projects to the FDB for BDNF immunoreactivity (BDNF-ir) and phosphorylated extracellular signal-regulated kinase (ERK) 1/2 immunoreactivity (pERK1/2-ir). Both immunoreactivities were observed in the motor neuron cell bodies. Next, BDNF was injected subcutaneously (s.c.) into rats with a unilaterally axotomized sciatic nerve. pERK1/2-ir was detected in motor neurons of the lesioned side. BDNF-ir and pERK1/2-ir were also observed on the unlesioned side when a high dose of BDNF was injected. Therefore, we examined BDNF-ir and pERK1/2-ir after injecting BDNF s.c. into normal rats. Both immunoreactivities were observed in motor nuclei on both sides. Finally, we examined pERK1/2-ir after a lower dose of BDNF was injected, which prevents the decrease in choline acetyl transferase that occurs in the motor neuron upon axotomy. Spinal motor nuclei contained a few cell bodies with pERK1/2-ir. These findings represent the first direct evidence that subcutaneously injected BDNF is transported to motor neurons and that it activates a signaling pathway in the spinal cord and exhibits neurotrophic effects in vivo.

Brain-derived neurotrophic factor suppresses delayed apoptosis of oligodendrocytes after spinal cord injury in rats.

We evaluated the effect of brain-derived neurotrophic factor (BDNF) on cell death after spinal cord injury. A rat spinal cord injury model was produced by static load, and continuous intrathecal BDNF or vehicle infusion was carried out either immediately or 3 days after the injury. Cell death was examined by nuclear staining and terminal deoxynucleotidyl transferase-mediated dUTP nick-end labeling (TUNEL). After injury, typical apoptotic cells were observed. Double staining with TUNEL and specific cell markers revealed that, soon after the injury, the apoptotic or necrotic cells at the injury site were neurons and microglia. One week after the injury, apoptotic oligodendrocytes, but not apoptotic astrocytes, were observed in the white matter rostral and caudal to the injury site, whereas few apoptotic cells were found in the gray matter. The immediate BDNF treatment significantly reduced the number of TUNEL-positive cells in the adjacent rostral site 1 and 2 weeks after the injury, and in the adjacent caudal site 3 days and 1 week after the injury, even though there was no significant difference between BDNF-treated and control rats at the injury site itself. In addition, similar antiapoptotic effects were observed in these regions 1 week after injury in rats that received BDNF treatment from the third day after injury. These findings suggest that BDNF suppresses delayed apoptosis of oligodendrocytes after spinal cord injury, for which even delayed injections are effective. BDNF administration may therefore be useful for the clinical treatment of spinal cord injury through the suppression of secondary events.

Methionine-free brain-derived neurotrophic factor in wobbler mouse motor neuron disease: dose-related effects and comparison with the methionyl form.

We compared the clinical and pharmacodynamic effects of N-terminal methionine brain-derived neurotrophic factor (met-BDNF) and endogenous met-free BDNF in wobbler mouse motor neuron disease (MND). Met- or met-free BDNF at 5 or 20 mg/kg was subcutaneously injected daily, six times/week for 4 weeks. At 20 mg/kg, grip strength (P<0.05, met-free BDNF; P<0.01, met-BDNF) and running speed (P<0.01 for both groups) improved compared to vehicle. At 5 mg/kg, the beneficial effect was more modest. Plasma BDNF levels after the final injection were dose-dependent and did not differ between BDNF groups. Endogenous met-free BDNF exerts effects similar to met-BDNF in wobbler MND.

Effects of brain-derived neurotrophic factor (BDNF) on compression-induced spinal cord injury: BDNF attenuates down-regulation of superoxide dismutase expression and promotes up-regulation of myelin basic protein expression.

Neurotrophins enhance the survival of cells in the nervous system under both physiological and pathological conditions, such as those caused by disease or trauma. We recently demonstrated that expression of brain-derived neurotrophic factor (BDNF) was up-regulated in neurons and glia after compression-induced spinal cord injury (SCI). We show here the effects of BDNF on the oligodendrocyte survival and functional recovery after SCI. The effects of intrathecally administered BDNF on both Cu/Zn superoxide dismutase (CuZnSOD) and myelin basic protein (MBP) expression were examined using rats that had received compression-induced spinal cord injury. CuZnSOD expression in the spinal cord was down-regulated within 24 h of compression-induced injury and then recovered. Continuous infusion of BDNF inhibited the acute down-regulation of CuZnSOD expression. In situ hybridization showed that CuZnSOD was expressed in both neurons and glia. Although MBP expression was greatly reduced after injury, BDNF administration promoted the recovery of MBP expression nearly to a control level after 2 wk. Furthermore, BDNF administration also prompted behavioral recovery. These results suggest BDNF's usefulness in human clinical applications. The attenuation of CuZnSOD down-regulation may be related to a protective effect of BDNF and the promotion of MBP up-regulation may be related to a long-lasting restorative effect.