Impact of the First-Wave COVID-19 Pandemic on Medical Expenditure for Older Adults in China: Lessons from a Natural Experiment.

Older adults' access to healthcare services may have been affected by the COVID-19 pandemic. This study explored the effect of the first wave pandemic on the medical expenditure of older adults in China. Difference-in-Difference models captured both temporal and geographical variation in COVID-19 exposure to estimate the impacts of the pandemic on medical expenditure through a quasi-natural experiment. Data derived from the China Family Panel Studies. Results indicate that exposure to the pandemic significantly decreased total medical expenditures, hospital expenditures, and non-hospital medical expenditures of Chinese older adults by 15% (95% CI 12%-17%), 5% (95% CI 2%-7%), and 15% (95% CI 13%-16%), respectively, for each standardized severity increment. Females, less well-educated people, and individuals without internet access were most susceptible to experiencing these reductions. This study revealed that COVID-19 exerted a detrimental influence on the medical expenditure of older adults in mainland China. The "hidden epidemic" of non-COVID-19 medical needs of older adults deserves more attention on the part of policymakers.

ASS1 inhibits triple-negative breast cancer by regulating PHGDH stability and de novo serine synthesis.

Argininosuccinate synthase (ASS1), a critical enzyme in the urea cycle, acts as a tumor suppressor in many cancers. To date, the anticancer mechanism of ASS1 has not been fully elucidated. Here, we found that phosphoglycerate dehydrogenase (PHGDH), a key rate-limiting enzyme in serine synthesis, is a pivotal protein that interacts with ASS1. Our results showed that ASS1 directly binds to PHGDH and promotes its ubiquitination-mediated degradation to inhibit serine synthesis, consequently suppressing tumorigenesis. Importantly, the tumor suppressive effects of ASS1 were strongly abrogated by PHGDH knockout. In addition, ASS1 knockout and knockdown partially rescued cell proliferation when serine and glycine were depleted, while the inhibitory effect of ASS1 overexpression on cell proliferation was restored by the addition of serine and glycine. These findings unveil a novel role of ASS1 and suggest that the ASS1/PHGDH serine synthesis pathway is a promising target for cancer therapy.

Impact of a pandemic shock on unmet medical needs of middle-aged and older adults in 10 countries.

OBJECTIVE: The objective is to explore the impact of the pandemic shock on the unmet medical needs of middle-aged and older adults worldwide. METHODS: The COVID-19 pandemic starting in 2020 was used as a quasiexperiment. Exposure to the pandemic was defined based on an individual's context within the global pandemic. Data were obtained from the Integrated Values Surveys. A total of 11 932 middle-aged and older adults aged 45 years and above from 10 countries where the surveys conducted two times during 2011 and 2022 were analysed. We used logistic regression models with the difference-in-difference method to estimate the impact of pandemic exposure on unmet medical needs by comparing differences before and after the pandemic across areas with varying degrees of severity. RESULTS: Among the 11 932 middle-aged and older adults, 3647 reported unmet medical needs, with a pooled unmet rate of 30.56% (95% CI: 29.74% to 31.40%). The pandemic significantly increased the risk of unmet medical needs among middle-aged and older adults (OR: 2.33, 95% CI: 1.94 to 2.79). The deleterious effect of the pandemic on unmet medical needs was prevalent among middle-aged adults (2.53, 2.00 to 3.20) and older adults (2.00, 1.48 to 2.69), as well as among men (2.24, 1.74 to 2.90) and women (2.34, 1.82 to 3.03). The results remained robust in a series of sensitivity analyses. CONCLUSION: These findings suggest that efforts should be made by policymakers and healthcare professionals to balance healthcare resources to adequately address the comprehensive healthcare demands of individuals regarding multiple health issues, taking into account the challenges posed by pandemics.

The early-stage impacts of shock events on adult sleep: Lessons from the COVID-19 pandemic.

The present study aims to estimate the early-stage association of the coronavirus disease 2019 (COVID-19) pandemic with sleep duration, 4 months after the initial outbreak, at a national level. Using the China Family Panel Studies in 2018 and its follow-up in 2020, 16,563 adult participants were analyzed in our study. The first wave transmissibility of the COVID-19 pandemic in mainland China was used as a quasi-natural experiment. The difference in difference method was employed to compare variations across participants interviewed before or after the pandemic and between groups from provinces with different COVID-19 severity. The study observed a decline in workday sleep duration among adults, regardless of their employment status. Specifically, working adults experienced a significant decrease in sleep duration on work days (-1.54, 95% confidence interval -2.16 to -0.92), alongside an increase on work-free days (2.41, 1.56-3.24), leading to a wider sleep discrepancy in sleep patterns (3.95, 3.31-4.59). Noteworthy, working-age adults (-2.00, -2.79 to -1.22) and males (-3.31, -4.31 to -2.30) exhibited greater sleep decreases on work days, whereas females exhibited a more pronounced disparity in sleep patterns (6.18, 4.73-7.63) between work and work-free days. The pandemic is significantly associated with prolonged changes in adults' sleep duration, including sleep decreases on work days and catch-up sleep on work-free days for working adults. To prepare for future global emergencies, the government may need to promote resilience to mitigate the pandemic's adverse impacts on the working population. Guaranteeing adequate sleep among working adults and reducing sleep debt should be prioritized in such efforts.

Gender and Sexuality Disparities in Perception, Attitude and Social Intimacy Among Sinophone Youth Toward Transgender and Gender Non-Conforming Individuals: Based on an Internet Survey.

The study aims at assessing gender and sexuality characteristics (GSC) in perception, attitude, and social intimacy among Sinophone youth toward transgender and gender non-conforming (TGNC) people. Based on an internet survey with 3 825 valid questionnaires, we distinguished the general public into TGNC, cisgender heterosexual, and cisgender non-heterosexual individuals. Then we classified TGNC individuals into trans females, trans males, and non-binary/genderqueer people and cisgender individuals into cisgender females and cisgender males. The chi-square test, one-way analysis of variance (ANOVA), and multiple linear regression were used. We found that the evident gender and sexuality disparities in perception, attitude, and social intimacy toward TGNC individuals exist both in and out of TGNC individuals. Negative perceptions and attitudes as well as alienated social intimacy were most pronounced among cisgender heterosexual people (Chi-square test, one-way ANOVA, and multiple linear regression: all p < .001). Cisgender females exhibit higher levels of supportiveness compared to cisgender males. Trans females were the most positive while they also had more concerns regarding public space and gender expression-related issues. The findings are practical for community-based advocacy for raising public awareness of the presences and experiences of TGNC people in Sinophone societies.

Robotic-OCT guided inspection and microsurgery of monolithic storage devices.

Data recovery from monolithic storage devices (MSDs) is in high demand for legal or business purposes. However, the conventional data recovery methods are destructive, complicated, and time-consuming. We develop a robotic-arm-assisted optical coherence tomography (robotic-OCT) for non-destructive inspection of MSDs, offering ~7 µm lateral resolution, ~4 µm axial resolution and an adjustable field-of-view to accommodate various MSD sizes. Using a continuous scanning strategy, robotic-OCT achieves automated volumetric imaging of a micro-SD card in ~37 seconds, significantly faster than the traditional stop-and-stare scanning that typically takes tens of minutes. We also demonstrate the robotic-OCT-guided laser ablation as a microsurgical tool for targeted area removal with precision of ±10 µm and accuracy of ~50 µm, eliminating the need to remove the entire insulating layer and operator intervention, thus greatly improving the data recovery efficiency. This work has diverse potential applications in digital forensics, failure analysis, materials testing, and quality control.

Spinosyn A and Its Derivative Inhibit Colorectal Cancer Cell Growth via the EGFR Pathway.

Spinosyn A (SPA), derived from a soil microorganism, Saccharopolyspora spinosa, and its derivative, LM2I, has potential inhibitory effects on a variety of cancer cells. However, the effects of SPA and LM2I in inhibiting the growth of human colorectal cancer cells and the molecular mechanisms underlying these effects are not fully understood. Cell viability was tested by using a 3-(4,5-dimethylthiazol-2-yl-)-2,5-diphenyltetrazolium bromide (MTT) assay and a colony formation assay. On the basis of the IC50 values of SPA and LM2I in seven colorectal cancer (CRC) cell lines, sensitive (HT29 and SW480) and insensitive (SW620 and RKO) cell lines were screened. The GSE2509 and GSE10843 data sets were used to identify 69 differentially expressed genes (DEGs) between sensitive and insensitive cell lines. Gene Ontology (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analysis, and protein-protein interactions (PPI) were performed to elucidate the molecular mechanisms of the DEGs. The hub gene of the DEGs was detected by Western blot analysis and verified using the CRISPR/Cas9 system. Our data indicate that SPA and its derivative LM2I have significant antiproliferative activity in seven colorectal cancer cell lines and colorectal xenograft tumors. On the basis of bioinformatics analysis, it was demonstrated that epidermal growth factor receptor (EGFR) was the hub gene of the DEGs and was associated with the inhibitory effects of SPA and LM2I in CRC cell lines. The study also revealed that SPA and LM2I inhibited the EGFR pathway in vitro and in vivo.

An Isoxazoloquinone Derivative Inhibits Tumor Growth by Targeting STAT3 and Triggering Its Ubiquitin-Dependent Degradation.

BACKGROUND: Triple-negative breast cancer (TNBC) is the most aggressive breast cancer subtype, with shorter five-year survival than other breast cancer subtypes, and lacks targeted and hormonal treatment strategies. The signal transducer and activator of transcription 3 (STAT3) signaling is up-regulated in various tumors, including TNBC, and plays a vital role in regulating the expression of multiple proliferation- and apoptosis-related genes. RESULTS: By combining the unique structures of the natural compounds STA-21 and Aulosirazole with antitumor activities, we synthesized a class of novel isoxazoloquinone derivatives and showed that one of these compounds, ZSW, binds to the SH2 domain of STAT3, leading to decreased STAT3 expression and activation in TNBC cells. Furthermore, ZSW promotes STAT3 ubiquitination, inhibits the proliferation of TNBC cells in vitro, and attenuates tumor growth with manageable toxicities in vivo. ZSW also decreases the mammosphere formation of breast cancer stem cells (BCSCs) by inhibiting STAT3. CONCLUSIONS: We conclude that the novel isoxazoloquinone ZSW may be developed as a cancer therapeutic because it targets STAT3, thereby inhibiting the stemness of cancer cells.

Clustering analysis and prognostic model based on PI3K/AKT-related genes in pancreatic cancer.

Background: Pancreatic cancer is one of most aggressive malignancies with a dismal prognosis. Activation of PI3K/AKT signaling is instrumental in pancreatic cancer tumorigenesis. The aims of this study were to identify the molecular clustering, prognostic value, relationship with tumor immunity and targeting of PI3K/AKT-related genes (PARGs) in pancreatic cancer using bioinformatics. Methods: The GSEA website was searched for PARGs, and pancreatic cancer-related mRNA data and clinical profiles were obtained through TCGA downloads. Prognosis-related genes were identified by univariate Cox regression analysis, and samples were further clustered by unsupervised methods to identify significant differences in survival, clinical information and immune infiltration between categories. Next, a prognostic model was constructed using Lasso regression analysis. The model was well validated by univariate and multivariate Cox regression analyses, Kaplan-Meier survival analysis and ROC curves, and correlations between risk scores and patient pathological characteristics were identified. Finally, GSEA, drug prediction and immune checkpoint protein analyses were performed. Results: Pancreatic cancers were divided into Cluster 1 (C1) and Cluster 2 (C1) according to PARG mRNA expression. C1 exhibited longer overall survival (OS) and higher immune scores and CTLA4 expression, whereas C2 exhibited more abundant PD-L1. A 6-PARG-based prognostic model was constructed to divide pancreatic cancer patients into a high-risk score (HRS) group and a low-risk score (LRS) group, where the HRS group exhibited worse OS. The risk score was defined as an independent predictor of OS. The HRS group was significantly associated with pancreatic cancer metastasis, aggregation and immune score. Furthermore, the HRS group exhibited immunosuppression and was sensitive to radiotherapy and guitarbine chemotherapy. Multidrug sensitivity prediction analysis indicated that the HRS group may be sensitive to PI3K/AKT signaling inhibitors (PIK-93, GSK2126458, CAL-101 and rapamycin) and ATP concentration regulators (Thapsigargin). In addition, we confirmed the oncogenic effect of protein phosphatase 2 regulatory subunit B'' subunit alpha (PPP2R3A) in pancreatic cancer in vitro and in vivo. Conclusions: PARGs predict prognosis, tumor immune profile, radiotherapy and chemotherapy drug sensitivity and are potential predictive markers for pancreatic cancer treatment that can help clinicians make decisions and personalize treatment.

Auditory Receptive Field Net Based Automatic Snore Detection for Wearable Devices.

Although obstructive sleep apnea and hypopnea syndrome (OSAHS) is a common sleep disease, it is sometimes difficult to be detected in time because of the inconvenience of polysomnography (PSG) examination. Since snoring is one of the earliest symptoms of OSAHS, it can be used for early OSAHS prediction. With the recent development of wearable and IoT sensors, we proposed a deep learning-based accurate snore detection model for long-term home monitoring of snoring during sleep. To enhance the discriminability of features between snoring and non-snoring events, an auditory receptive field (ARF) net was proposed and integrated into the feature extraction network. Based on the feature maps derived by the feature extraction network, the detection model predicted a series of candidate boxes and corresponding confidence scores for each candidate box, which denoted whether the candidate box contained a snore event from the input sound waveforms. A snore detection dataset with a total duration of more than 4600 min was developed to evaluate the proposed model. The experimental results on this dataset revealed that the proposed model outperformed other traditional approaches and deep learning models.

Automated detection and classification of counterfeit banknotes using quantitative features captured by spectral-domain optical coherence tomography.

Counterfeiting of banknotes is still a severe crime problem in many countries. One of the most significant issue for solving the crime is to classify the counterfeit types and identify the sources. Most of the current methods to classify counterfeit banknotes rely on manual examination that is time-consuming and labor-intensive. Moreover, these methods only detect surface features which can be easily imitated through advanced printing technology. In this study, an automated method based on optical coherence tomography (OCT) and machine-learning algorithms was proposed to classify different types of banknotes based on the internal features. A spectral-domain OCT (SD-OCT) system was employed for sub-surface imaging and quantitative assessment of banknotes. A total of 29 Chinese 100-Yuan banknotes were collected, in which 4 of them were real and 25 of them were counterfeiting by three different printing processes. Each banknote was imaged 10 times in 3 distinct regions, which resulted in a dataset of 290 samples. Each sample was characterized by extracting 2 A-scan (OCT signal intensity along depth) based features and 14B-scan (cross-sectional OCT images) based features. Several machine-learning models, including logistic regression (LR), support vector machines (SVM), K-nearest neighbor (KNN) and random forest (RF), were built and optimized as the classifiers that were trained using 203 samples and applied to predict 87 testing samples. The best performance was achieved by SVM classifier in which the sensitivity of 96.55% and specificity of 98.85% were obtained in discriminating between authentic and counterfeit banknotes, and the sensitivity of 94.67% and specificity of 98.22% were obtained in predicting the types of counterfeit banknotes. These classifiers were also evaluated using the receiver operating characteristic (ROC) curves. To the best of our knowledge, this is the first study where A-scan and B-scan derived features from OCT images have been used for the detection and classification of different types of counterfeit banknotes.

Synchronizing Detection and Removal of Smoke in Endoscopic Images With Cyclic Consistency Adversarial Nets.

Smoke removal is an important and meaningful issue for endoscopic surgery, which can enhance the visual quality of endoscopic images. Because it is practically impossible to construct a large training dataset of pair-matched endoscopic images with/without smoke, the Generative Adversarial Nets (GANs) based models are usually used for endoscopic image desmoke. But they have difficulties in either locating the accurate smoke area, or recovering realistic internal organ or tissue details. In this paper, we propose a new approach, called Desmoke-CycleGAN, which combined detection, estimation, and removal of smoke together, to improve the CycleGAN model for endoscopic image smoke removal. In addition, both pixel-level and perceptual-level consistency loss have been incorporated in the proposed model, which helps the model to be more stable and efficient for recovering realistic details in endoscopic images. The experimental results have demonstrated that this method outperforms other state-of-the-art smoke removal approaches with unpaired real endoscopic images.

Bridging the Digital Divide: Childhood Social Relationships and Mobile Payment Use Among Chinese Middle-Aged and Older Adults.

This research accordingly examines the effect of childhood social relationships on the use of mobile payment and e-money among Chinese middle-aged and older adults from a life course perspective and tests the mediation role of social activities in such a path with the Karlson-Holm-Breen (KHB) method. The findings support that good childhood community relationships, peer relationships, and close relationships positively affect mobile payment and electronic money use when people enter middle and old age. These effects are significantly mediated by social activities in later life. The findings make marginal contributions to life course theory (LCT), with practical implications for individuals, commercial enterprises, governments, and societies in their efforts to facilitate a society that promotes the digital inclusion of middle-aged and older adults.

The effect of COVID-19 on public confidence in the World Health Organization: a natural experiment among 40 countries.

BACKGROUND: At a time when a highly contagious pandemic and global political and economic turmoil are intertwined, worldwide cooperation under the leadership of an international organization has become increasingly important. This study aimed to estimate the effect of COVID-19 on public confidence in the World Health Organization (WHO), which will serve as a reference for other international organizations regarding the maintenance of their credibility in crisis management and ability to play a greater role in global health governance. METHODS: We obtained individual data from the World Values Survey (WVS). A total of 44,775 participants aged 16 and older from 40 countries in six WHO regions were included in this study. The COVID-19 pandemic was used as a natural experiment. We obtained difference-in-differences (DID) estimates of the pandemic's effects by exploiting temporal variation in the timing of COVID-19 exposure across participants interviewed from 2017 to 2020 together with the geographical variation in COVID-19 severity at the country level. Public confidence in the WHO was self-reported by the respondents. RESULTS: Among the participants, 28,087 (62.73%) reported having confidence in the WHO. The DID estimates showed that the COVID-19 pandemic could significantly decrease the likelihood of people reporting confidence in the WHO after controlling for multiple covariates (adjusted OR 0.54, 95% CI: 0.49-0.61), especially during the global outbreak (0.35, 0.24-0.50). The effect was found in both younger individuals (0.58, 0.51-0.66) and older adults (0.49, 0.38-0.63) and in both males (0.47, 0.40-0.55) and females (0.62, 0.53-0.72), with a vulnerability in males (adjusted P for interaction = 0.008). CONCLUSION: Our findings are relevant regarding the impact of COVID-19 on people's beliefs about social institutions of global standing, highlighting the need for the WHO and other international organizations to shoulder the responsibility of global development for the establishment and maintenance of public credibility in the face of emergencies, as well as the prevention of confidence crises.

A three-dimensional evaluation model for green development: evidence from Chinese provinces along the belt and road.

The establishment of the green belt and road is an inevitable choice to conform to and lead the green and low-carbon cycle development and an inherent requirement for sustainable development. Therefore, we establish an evaluation system of green development oriented to carbon neutrality, and calculate the green development level (GDL) of the provinces along the belt and road in China from 2003 to 2018 by using a three-dimensional evaluation model. In addition, this paper employs the Obstacle Degree Model to identify the main obstacle factors that affect GDL, and provides targeted and differentiated countermeasures and suggestions for improving the regional GDL. Our results suggested that the overall GDL has improved, but not obvious, with a low level. The GDL and coordination degree between different regions exist certain differences, and its spatial pattern is characterized by "high in southeast and northeast, low in southwest and northwest". From a regional perspective, innovation capacity is the key factor that affects the green development of the region in southeast, northeast, northwest and southwest China. Driving economic green transformation and promoting industrial energy conservation and emission reduction through technological innovation are the internal driving forces to achieve regional green sustainable development.

Association between Olympic Games and children's growth: evidence from China.

OBJECTIVES: To estimate the association between the 2008 Beijing Olympic Games (BOG) and growth of children in China. METHODS: A total sample of 6 951 children aged 3-10 years were included, among which 3 201 were interviewed in 2014 and 3 750 were interviewed in 2018. The BOG was used as a natural experiment. Exposure to the BOG was established by triple differences measured by age group, survey period and whether child participants were living in BOG areas or not, respectively. Children's growth was assessed by binary variables of stunting, underweight, overweight and obesity. The difference-in-difference-in-differences (DDD) method was used to estimate the association between the BOG and children's growth. RESULTS: DDD estimates showed that the BOG was significantly associated with decreased risks of children's underweight (OR 0.12; 95% CI 0.02 to 0.69) and overweight (OR 0.43; 95% CI 0.19 to 0.98) after controlling for multiple covariates in fractional polynomial models. There was significant sex heterogeneity with regard to the association between BOG and obesity, that is, lower odds of obesity (OR 0.24; 95% CI 0.06 to 0.94) were found in female children but not in male children. CONCLUSION: The BOG was positively associated with healthier growth of children including decreased risks of both undernutrition and overnutrition. More attention should be given to the improvement of health surveillance and services before and after sporting events so that the active role of such mega-events in the lasting well-being of the public can be determined in more detail.

Cycle-Consistent Adversarial Networks for Smoke Detection and Removal in Endoscopic Images.

During endoscopic surgery, smoke removal is important and meaningful for increasing the visual quality of endoscopic images. However, unlike natural image dehaze, it is practical impossible to build a large paired endoscopic image training dataset with/without smoke. Therefore, in this paper, we propose a new approach, called Desmoke-CycleGAN, which combined detection and removal of smoke together, to improve the CycleGAN model for endoscopic image smoke removal. The detector can provide information about smoke locations and densities, which helps the GAN model to be more stable and efficient for smoke removal. Although some imperfections still exist, the experimental results have demonstrated that this method outperforms other state-of-the-art smoke removal approaches with unpaired real endoscopic images.Clinical Relevance- This can help improve the visibility in endoscopic surgery and to get smoke-free endoscopic images with better quality.

Longitudinal Association Between Oral Status and Depressive Symptoms Among Chinese Older Adults - China, 2014-2018.

WHAT IS ALREADY KNOWN ABOUT THIS TOPIC?: Previous studies on the importance of oral health in later life have mainly focused on nutritional and physical health indicators, while the effects of oral status on the mental health of older people, especially on depression, need to be further explored. WHAT IS ADDED BY THIS REPORT?: Longitudinal results show tooth loss was positively associated with depressive symptoms among older adults in the mainland of China, while denture use was associated with a decreased risk of depression. Effect modification by denture use was observed (Pfor interaction <0.001). WHAT ARE THE IMPLICATIONS FOR PUBLIC HEALTH PRACTICE?: Measures should be taken to help Chinese older adults promote oral health and strengthen the care of dentures by expanding basic health insurance coverage to include dental prosthodontics or providing affordable dental insurance for seniors.

Naturally-occurring spinosyn A and its derivatives function as argininosuccinate synthase activator and tumor inhibitor.

Argininosuccinate synthase (ASS1) is a ubiquitous enzyme in mammals that catalyzes the formation of argininosuccinate from citrulline and aspartate. ASS1 genetic deficiency in patients leads to an autosomal recessive urea cycle disorder citrullinemia, while its somatic silence or down-regulation is very common in various human cancers. Here, we show that ASS1 functions as a tumor suppressor in breast cancer, and the pesticide spinosyn A (SPA) and its derivative LM-2I suppress breast tumor cell proliferation and growth by binding to and activating ASS1. The C13-C14 double bond in SPA and LM-2I while the Cys97 (C97) site in ASS1 are critical for the interaction between ASS1 and SPA or LM-2I. SPA and LM-2I treatment results in significant enhancement of ASS1 enzymatic activity in breast cancer cells, particularly in those cancer cells with low ASS1 expression, leading to reduced pyrimidine synthesis and consequently the inhibition of cancer cell proliferation. Thus, our results establish spinosyn A and its derivative LM-2I as potent ASS1 enzymatic activator and tumor inhibitor, which provides a therapeutic avenue for tumors with low ASS1 expression and for those non-tumor diseases caused by down-regulation of ASS1.

Automatic classification of excitation location of snoring sounds.

STUDY OBJECTIVES: For surgical treatment of patients with obstructive sleep apnea-hypopnea syndrome, it is crucial to locate accurately the obstructive sites in the upper airway; however, noninvasive methods for locating the obstructive sites have not been well explored. Snoring, as the cardinal symptom of obstructive sleep apnea-hypopnea syndrome, should contain information that reflects the state of the upper airway. Through the classification of snores produced at four different locations, this study aimed to test the hypothesis that snores generated by various obstructive sites differ. METHODS: We trained and tested our model on a public data set that comprised 219 participants. For each snore episode, an acoustic and a physiological feature were extracted and concatenated, forming a 59-dimensional fusion feature. A principal component analysis and a support machine vector were used for dimensional reduction and snore classification. The performance of the proposed model was evaluated using several metrics: sensitivity, precision, specificity, area under the receiver operating characteristic curve, and F1 score. RESULTS: The unweighted average values of sensitivity, precision, specificity, area under the curve, and F1 were 86.36%, 89.09%, 96.4%, 87.9%, and 87.63%, respectively. The model achieved 98.04%, 80.56%, 72.73%, and 94.12% sensitivity for types V (velum), O (oropharyngeal), T (tongue), and E (epiglottis) snores. CONCLUSIONS: The characteristics of snores are related to the state of the upper airway. The machine-learning-based model can be used to locate the vibration sites in the upper airway.