Predicting Fatigue-Associated Aberrant Driving Behaviors Using a Dynamic Weighted Moving Average Model With a Long Short-Term Memory Network Based on Heart Rate Variability.

OBJECTIVE: This study proposed a moving average (MA) approach to dynamically process heart rate variability (HRV) and developed aberrant driving behavior (ADB) prediction models by using long short-term memory (LSTM) networks. BACKGROUND: Fatigue-associated ADBs have traffic safety implications. Numerous models to predict such acts based on physiological responses have been developed but are still in embryonic stages. METHOD: This study recorded the data of 20 commercial bus drivers during their routine tasks on four consecutive days and subsequently asked them to complete questionnaires, including subjective sleep quality, driver behavior questionnaire and the Karolinska Sleepiness Scale. Driving behaviors and corresponding HRV were determined using a navigational mobile application and a wristwatch. The dynamic-weighted MA (DWMA) and exponential-weighted MA were used to process HRV in 5-min intervals. The data were independently separated for training and testing. Models were trained with 10-fold cross-validation strategy, their accuracies were evaluated, and Shapley additive explanation (SHAP) values were used to determine feature importance. RESULTS: Significant increases in the standard deviation of NN intervals (SDNN), root mean square of successive heartbeat interval differences (RMSSD), and normalized spectrum of high frequency (nHF) were observed in the pre-event stage. The DWMA-based model exhibited the highest accuracy for both driver types (urban: 84.41%; highway: 80.56%). The SDNN, RMSSD, and nHF demonstrated relatively high SHAP values. CONCLUSION: HRV metrics can serve as indicators of mental fatigue. DWMA-based LSTM could predict the occurrence of the level of fatigue associated with ADBs. APPLICATION: The established models can be used in realistic driving scenarios.

Continuous Positive Airway Pressure Reduces Plasma Neurochemical Levels in Patients with OSA: A Pilot Study.

Obstructive sleep apnea (OSA) is a risk factor for neurodegenerative diseases. This study determined whether continuous positive airway pressure (CPAP), which can alleviate OSA symptoms, can reduce neurochemical biomarker levels. Thirty patients with OSA and normal cognitive function were recruited and divided into the control (n = 10) and CPAP (n = 20) groups. Next, we examined their in-lab sleep data (polysomnography and CPAP titration), sleep-related questionnaire outcomes, and neurochemical biomarker levels at baseline and the 3-month follow-up. The paired t-test and Wilcoxon signed-rank test were used to examine changes. Analysis of covariance (ANCOVA) was performed to increase the robustness of outcomes. The Epworth Sleepiness Scale and Pittsburgh Sleep Quality Index scores were significantly decreased in the CPAP group. The mean levels of total tau (T-Tau), amyloid-beta-42 (Aß42), and the product of the two (Aß42 × T-Tau) increased considerably in the control group (ΔT-Tau: 2.31 pg/mL; ΔAß42: 0.58 pg/mL; ΔAß42 × T-Tau: 48.73 pg2/mL2), whereas the mean levels of T-Tau and the product of T-Tau and Aß42 decreased considerably in the CPAP group (ΔT-Tau: -2.22 pg/mL; ΔAß42 × T-Tau: -44.35 pg2/mL2). The results of ANCOVA with adjustment for age, sex, body mass index, baseline measurements, and apnea-hypopnea index demonstrated significant differences in neurochemical biomarker levels between the CPAP and control groups. The findings indicate that CPAP may reduce neurochemical biomarker levels by alleviating OSA symptoms.

Machine learning model for aberrant driving behaviour prediction using heart rate variability: a pilot study involving highway bus drivers.

Objectives. Current approaches via physiological features detecting aberrant driving behaviour (ADB), including speeding, abrupt steering, hard braking and aggressive acceleration, are developing. This study proposes using machine learning approaches incorporating heart rate variability (HRV) parameters to predict ADB occurrence. Methods. Naturalistic driving data of 10 highway bus drivers in Taiwan from their daily routes were collected for 4 consecutive days. Their driving behaviours and physiological data during a driving task were determined using a navigation mobile application and heart rate watch. Participants' self-reported data on sleep, driving-related experience, open-source data on weather and the traffic congestion level were obtained. Five machine learning models - logistic regression, random forest, naive Bayes, support vector machine and gated recurrent unit (GRU) - were employed to predict ADBs. Results. Most drivers with ADB had low sleep efficiency (≤80%), with significantly higher scores in driver behaviour questionnaire subcategories of lapses and errors and in the Karolinska sleepiness scale than those without ADBs. Moreover, HRV parameters were significantly different between baseline and pre-ADB event measurements. GRU had the highest accuracy (81.16-84.22%). Conclusions. Sleep deficit may be related to the increased fatigue level and ADB occurrence predicted from HRV-based models among bus drivers.

Associations between risk of Alzheimer's disease and obstructive sleep apnea, intermittent hypoxia, and arousal responses: A pilot study.

Objectives: Obstructive sleep apnea (OSA) may increase the risk of Alzheimer's disease (AD). However, potential associations among sleep-disordered breathing, hypoxia, and OSA-induced arousal responses should be investigated. This study determined differences in sleep parameters and investigated the relationship between such parameters and the risk of AD. Methods: Patients with suspected OSA were recruited and underwent in-lab polysomnography (PSG). Subsequently, blood samples were collected from participants. Patients' plasma levels of total tau (T-Tau) and amyloid beta-peptide 42 (Aß42) were measured using an ultrasensitive immunomagnetic reduction assay. Next, the participants were categorized into low- and high-risk groups on the basis of the computed product (Aß42 × T-Tau, the cutoff for AD risk). PSG parameters were analyzed and compared. Results: We included 36 patients in this study, of whom 18 and 18 were assigned to the low- and high-risk groups, respectively. The average apnea-hypopnea index (AHI), apnea, hypopnea index [during rapid eye movement (REM) and non-REM (NREM) sleep], and oxygen desaturation index (≥3%, ODI-3%) values of the high-risk group were significantly higher than those of the low-risk group. Similarly, the mean arousal index and respiratory arousal index (R-ArI) of the high-risk group were significantly higher than those of the low-risk group. Sleep-disordered breathing indices, oxygen desaturation, and arousal responses were significantly associated with an increased risk of AD. Positive associations were observed among the AHI, ODI-3%, R-ArI, and computed product. Conclusions: Recurrent sleep-disordered breathing, intermittent hypoxia, and arousal responses, including those occurring during the NREM stage, were associated with AD risk. However, a longitudinal study should be conducted to investigate the causal relationships among these factors.

Screening for Obstructive Sleep Apnea Risk by Using Machine Learning Approaches and Anthropometric Features.

Obstructive sleep apnea (OSA) is a global health concern and is typically diagnosed using in-laboratory polysomnography (PSG). However, PSG is highly time-consuming and labor-intensive. We, therefore, developed machine learning models based on easily accessed anthropometric features to screen for the risk of moderate to severe and severe OSA. We enrolled 3503 patients from Taiwan and determined their PSG parameters and anthropometric features. Subsequently, we compared the mean values among patients with different OSA severity and considered correlations among all participants. We developed models based on the following machine learning approaches: logistic regression, k-nearest neighbors, naïve Bayes, random forest (RF), support vector machine, and XGBoost. Collected data were first independently split into two data sets (training and validation: 80%; testing: 20%). Thereafter, we adopted the model with the highest accuracy in the training and validation stage to predict the testing set. We explored the importance of each feature in the OSA risk screening by calculating the Shapley values of each input variable. The RF model achieved the highest accuracy for moderate to severe (84.74%) and severe (72.61%) OSA. The level of visceral fat was found to be a predominant feature in the risk screening models of OSA with the aforementioned levels of severity. Our machine learning models can be employed to screen for OSA risk in the populations in Taiwan and in those with similar craniofacial structures.

Does ownership structure matter for overshooting manipulation of hospitality and tourism stocks?

We investigate whether the function of ownership structure influences stock price overshooting manipulation for Taiwan Stock Exchange-listed tourism and hospitality firms because stock price overshooting occurs frequently for these firms after Chinese authorities relax restrictions on tourists visiting Taiwan. As a result, we demonstrate that some of these firms with a poorly functioning ownership structure may manipulate their share prices, resulting in overshooting phenomena, especially for stock price overbought phenomena. Following that, we discover that the directors and managers of these firms reduce their shareholdings, implying that such firms are likely to have corporate governance issues.

Association between cyclic variation in the heart rate index and biomarkers of neurodegenerative diseases in obstructive sleep apnea syndrome: A pilot study.

PURPOSE: Obstructive sleep apnea syndrome (OSAS) has mostly been examined using in-laboratory polysomnography (Lab-PSG), which may overestimate severity. This study compared sleep parameters in different environments and investigated the association between the plasma levels of neurochemical biomarkers and sleep parameters. METHODS: Thirty Taiwanese participants underwent Lab-PSG while wearing a single-lead electrocardiogram patch. Participants' blood samples were obtained in the morning immediately after the recording. Participants wore the patch for the subsequent three nights at home. Sleep disorder indices were calculated, including the apnea-hypopnea index (AHI), chest effort index, and cyclic variation of heart rate index (CVHRI). The 23 eligible participants' derived data were divided into the normal-to-moderate (N-M) group and the severe group according to American Association of Sleep Medicine (AASM) guidelines (Lab-PSG) and the recommendations of a previous study (Rooti Rx). Spearman's correlation was used to examine the correlations between sleep parameters and neurochemical biomarker levels. RESULTS: The mean T-Tau protein level was positively correlated with the home-based CVHRI (r = 0.53, p < 0.05), whereas no significant correlation was noted between hospital-based CVHRI and the mean T-tau protein level (r = 0.25, p = 0.25). The home-based data revealed that the mean T-Tau protein level in the severe group was significantly higher than that in the N-M group (severe group: 24.75 ± 6.16 pg/mL, N-M group: 19.65 ± 3.90 pg/mL; p < 0.05). Furthermore, the mean in-hospital CVHRI was higher than the mean at-home values (12.16 ± 13.66 events/h). CONCLUSION: Severe OSAS patients classified by home-based CVHRI demonstrated the higher T-Tau protein level, and CVHRI varied in different sleep environments.

Associations among sleep-disordered breathing, arousal response, and risk of mild cognitive impairment in a northern Taiwan population.

STUDY OBJECTIVES: Dementia is associated with sleep disorders. However, the relationship between dementia and sleep arousal remains unclear. This study explored the associations among sleep parameters, arousal responses, and risk of mild cognitive impairment (MCI). METHODS: Participants with the chief complaints of memory problems and sleep disorders, from the sleep center database of Taipei Medical University Shuang-Ho Hospital, were screened, and the parameters related to the Cognitive Abilities Screening Instrument, Clinical Dementia Rating, and polysomnography were determined. All examinations were conducted within 6 months and without a particular order. The participants were divided into those without cognitive impairment (Clinical Dementia Rating = 0) and those with MCI (Clinical Dementia Rating = 0.5). Mean comparison, linear regression models, and logistic regression models were employed to investigate the associations among obtained variables. RESULTS: This study included 31 participants without MCI and 37 with MCI (17 with amnestic MCI, 20 with multidomain MCI). Patients with MCI had significantly higher mean values of the spontaneous arousal index and spontaneous arousal index in the non-rapid eye movement stage than those without MCI. An increased risk of MCI was significantly associated with increased spontaneous arousal index and spontaneous arousal index in the non-rapid eye movement stage with various adjustments. Significant associations between the Cognitive Abilities Screening Instrument scores and the oximetry parameters and sleep disorder indexes were observed. CONCLUSIONS: Repetitive respiratory events with hypoxia were associated with cognitive dysfunction. Spontaneous arousal, especially in non-rapid eye movement sleep, was related to the risk of MCI. However, additional longitudinal studies are required to confirm their causality. CITATION: Tsai C-Y, Hsu W-H, Lin Y-T, et al. Associations among sleep-disordered breathing, arousal response, and risk of mild cognitive impairment in a northern Taiwan population. J Clin Sleep Med. 2022;18(4): 1003-1012.

Machine learning approaches for screening the risk of obstructive sleep apnea in the Taiwan population based on body profile.

(a) Objective: Obstructive sleep apnea syndrome (OSAS) is typically diagnosed through polysomnography (PSG). However, PSG incurs high medical costs. This study developed new models for screening the risk of moderate-to-severe OSAS (apnea-hypopnea index, AHI ≥15) and severe OSAS (AHI ≥30) in various age groups and sexes by using anthropometric features in the Taiwan population.(b) Participants: Data were derived from 10,391 northern Taiwan patients who underwent PSG.(c) Methods: Patients' characteristics - namely age, sex, body mass index (BMI), neck circumference, and waist circumference - was obtained. To develop an age- and sex-independent model, various approaches - namely logistic regression, k-nearest neighbor, naive Bayes, random forest (RF), and support vector machine - were trained for four groups based on sex and age (men or women; aged <50 or ≥50 years). Dataset was separated independently (training:70%; validation: 10%; testing: 20%) and Cross-validated grid search was applied for model optimization. Models demonstrating the highest overall accuracy in validation outcomes for the four groups were used to predict the testing dataset.(d) Results: The RF models showed the highest overall accuracy. BMI was the most influential parameter in both types of OSAS severity screening models.(e) Conclusion: The established models can be applied to screen OSAS risk in the Taiwan population and those with similar craniofacial features.

Differentiation Model for Insomnia Disorder and the Respiratory Arousal Threshold Phenotype in Obstructive Sleep Apnea in the Taiwanese Population Based on Oximetry and Anthropometric Features.

Insomnia disorder (ID) and obstructive sleep apnea (OSA) with respiratory arousal threshold (ArTH) phenotypes often coexist in patients, presenting similar symptoms. However, the typical diagnosis examinations (in-laboratory polysomnography (lab-PSG) and other alternatives methods may therefore have limited differentiation capacities. Hence, this study established novel models to assist in the classification of ID and low- and high-ArTH OSA. Participants reporting insomnia as their chief complaint were enrolled. Their sleep parameters and body profile were accessed from the lab-PSG database. Based on the definition of low-ArTH OSA and ID, patients were divided into three groups, namely, the ID, low- and high-ArTH OSA groups. Various machine learning approaches, including logistic regression, k-nearest neighbors, naive Bayes, random forest (RF), and support vector machine, were trained using two types of features (Oximetry model, trained with oximetry parameters only; Combined model, trained with oximetry and anthropometric parameters). In the training stage, RF presented the highest cross-validation accuracy in both models compared with the other approaches. In the testing stage, the RF accuracy was 77.53% and 80.06% for the oximetry and combined models, respectively. The established models can be used to differentiate ID, low- and high-ArTH OSA in the population of Taiwan and those with similar craniofacial features.

A machine learning texture model for classifying lung cancer subtypes using preliminary bronchoscopic findings.

PURPOSE: Bronchoscopy is useful in lung cancer detection, but cannot be used to differentiate cancer types. A computer-aided diagnosis (CAD) system was proposed to distinguish malignant cancer types to achieve objective diagnoses. METHODS: Bronchoscopic images of 12 adenocarcinoma and 10 squamous cell carcinoma patients were collected. The images were transformed from a red-blue-green (RGB) to a hue-saturation-value (HSV) color space to obtain more meaningful color textures. By combining significant textural features (P < 0.05) in a machine learning classifier, a prediction model of malignant types was established. RESULTS: The performance of the CAD system achieved an accuracy of 86% (19/22), a sensitivity of 90% (9/10), a specificity of 83% (10/12), a positive predictive value of 82% (9/11), and a negative predictive value of 91% (10/11) in distinguishing lung cancer types. The area under the receiver operating characteristic curve was 0.82. CONCLUSIONS: On the basis of extracted HSV textures of bronchoscopic images, the CAD system can provide recommendations for clinical diagnoses of lung cancer types.

Classification of lung cancer subtypes based on autofluorescence bronchoscopic pattern recognition: A preliminary study.

BACKGROUND AND OBJECTIVES: Lung cancer is the leading cause of cancer deaths worldwide. With current use of autofluorescent bronchoscopic imaging to detect early lung cancer and limitations of pathologic examinations, a computer-aided diagnosis (CAD) system based on autofluorescent bronchoscopy was proposed to distinguish different pathological cancer types to achieve objective and consistent diagnoses. METHODS: The collected database consisted of 12 adenocarcinomas and 11 squamous cell carcinomas. The corresponding autofluorescent bronchoscopic images were first transformed to a hue (H), saturation (S), and value (V) color space to obtain better interpretation of the color information. Color textural features were respectively extracted from the H, S, and V channels and combined in a logistic regression classifier to classify malignant types by machine learning. RESULTS: After feature selection, the proposed CAD system achieved an accuracy of 83% (19/23), a sensitivity of 73% (8/11), a specificity of 92% (11/12), a positive predictive value of 89% (8/9), a negative predictive value of 79% (11/14), and an area under the receiver operating characteristic curve of 0.81 for distinguishing lung cancer types. CONCLUSIONS: The proposed CAD system based on color textures of autofluorescent bronchoscopic images provides a diagnostic method of malignant types in clinical use.

Anticancer activity of released doxorubicin from a folate-mediated polyelectrolyte complex.

Folic acid (FA) was selected to link with macromolecules for the selective and specific delivery of doxorubicin (DOX) to folate receptor (FR)-positive tumor cells, because of the high binding affinity of FA to the tumor-associated FR. We synthesized folate-mediated chondroitin sulfate (FA-PEG-ChS) for tumor cell targeting and non-folate-mediated naproxen-linked chondroitin sulfate (Nap-PEG-ChS) for comparison. Both the aforementioned polymers contain a PEG1000 spacer. We encapsulated an anticancer agent, DOX, during the formation of complexes with chitosan. Polyelectrolyte complexes (PEC) grafted with a fluorescent dye (FITC) served as a platform for online imaging cellular internalization. FR-positive KB and FR-deficient A549 cancer cells were tested. The concentration to kill 50% of the cells (IC(50)) of DOX-loaded FA-complex was 1.53 µg/ml, in comparison to 0.91 µg/ml of free DOX. The overlaid fluorescent images of DOX and FITC on confocal laser scanning microscopy demonstrated the co-internalization of DOX and the complex nanoparticles into the cytoplasm of KB cells followed by a gradual release of DOX.