Ensemble learning with speaker embeddings in multiple speech task stimuli for depression detection.

Introduction: As a biomarker of depression, speech signal has attracted the interest of many researchers due to its characteristics of easy collection and non-invasive. However, subjects' speech variation under different scenes and emotional stimuli, the insufficient amount of depression speech data for deep learning, and the variable length of speech frame-level features have an impact on the recognition performance. Methods: The above problems, this study proposes a multi-task ensemble learning method based on speaker embeddings for depression classification. First, we extract the Mel Frequency Cepstral Coefficients (MFCC), the Perceptual Linear Predictive Coefficients (PLP), and the Filter Bank (FBANK) from the out-domain dataset (CN-Celeb) and train the Resnet x-vector extractor, Time delay neural network (TDNN) x-vector extractor, and i-vector extractor. Then, we extract the corresponding speaker embeddings of fixed length from the depression speech database of the Gansu Provincial Key Laboratory of Wearable Computing. Support Vector Machine (SVM) and Random Forest (RF) are used to obtain the classification results of speaker embeddings in nine speech tasks. To make full use of the information of speech tasks with different scenes and emotions, we aggregate the classification results of nine tasks into new features and then obtain the final classification results by using Multilayer Perceptron (MLP). In order to take advantage of the complementary effects of different features, Resnet x-vectors based on different acoustic features are fused in the ensemble learning method. Results: Experimental results demonstrate that (1) MFCC-based Resnet x-vectors perform best among the nine speaker embeddings for depression detection; (2) interview speech is better than picture descriptions speech, and neutral stimulus is the best among the three emotional valences in the depression recognition task; (3) our multi-task ensemble learning method with MFCC-based Resnet x-vectors can effectively identify depressed patients; (4) in all cases, the combination of MFCC-based Resnet x-vectors and PLP-based Resnet x-vectors in our ensemble learning method achieves the best results, outperforming other literature studies using the depression speech database. Discussion: Our multi-task ensemble learning method with MFCC-based Resnet x-vectors can fuse the depression related information of different stimuli effectively, which provides a new approach for depression detection. The limitation of this method is that speaker embeddings extractors were pre-trained on the out-domain dataset. We will consider using the augmented in-domain dataset for pre-training to improve the depression recognition performance further.

Antibody Response 3 Months After 2-Dose SARS-CoV-2 mRNA Vaccination in Patients With Inflammatory Bowel Disease.

INTRODUCTION: The response to SARS-CoV-2 vaccination of patients with inflammatory bowel disease (IBD) on immune-modifying therapies requires further investigation because previous studies indicate that patients on immune therapy might have decreased antibody concentrations. METHODS: We present the antireceptor binding domain antibody response over a period of 3 months in 217 patients with IBD who completed standard 2-dose SARS-CoV-2 mRNA vaccine series. RESULTS: Almost all (98.6%) IBD vaccine recipients had a positive antireceptor binding domain antibody response at least 3 months after vaccination. Decreased antibody titers at 3 months were seen in a subset of patients on antitumor necrosis factor-alpha. Approximately 10% of the participants with high-titer antibodies at 1 month had a decrease to low-positive titers at 3 months, which was mostly observed in those on combination therapy and antitumor necrosis factor-alpha monotherapy. DISCUSSION: Larger longitudinal studies are required to define the response in IBD population and its clinical impact.

Malnutrition Increases Hospital Length of Stay and Mortality among Adult Inpatients with COVID-19.

BACKGROUND: Malnutrition has been linked to adverse health economic outcomes. There is a paucity of data on malnutrition in patients admitted with COVID-19. METHODS: This is a retrospective cohort study consisting of 4311 COVID-19 adult (18 years and older) inpatients at 5 Johns Hopkins-affiliated hospitals between 1 March and 3 December 2020. Malnourishment was identified using the malnutrition universal screening tool (MUST), then confirmed by registered dietitians. Statistics were conducted with SAS v9.4 (Cary, NC, USA) software to examine the effect of malnutrition on mortality and hospital length of stay among COVID-19 inpatient encounters, while accounting for possible covariates in regression analysis predicting mortality or the log-transformed length of stay. RESULTS: COVID-19 patients who were older, male, or had lower BMIs had a higher likelihood of mortality. Patients with malnutrition were 76% more likely to have mortality (p < 0.001) and to have a 105% longer hospital length of stay (p < 0.001). Overall, 12.9% (555/4311) of adult COVID-19 patients were diagnosed with malnutrition and were associated with an 87.9% increase in hospital length of stay (p < 0.001). CONCLUSIONS: In a cohort of COVID-19 adult inpatients, malnutrition was associated with a higher likelihood of mortality and increased hospital length of stay.

SARS-CoV-2 on the ocular surface: is it truly a novel transmission route?

Since December 2019, the novel COVID-19 outbreak has spread rapidly around the globe and infected millions of people. Although the major transmission route of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is considered to be airborne droplets and close contact, the ocular transmission route has been reported with great concern. The current work summarises the characteristics of SARS-CoV-2, the ocular distribution of the major SARS-CoV-2 binding protein, and the experimental and clinical evidence of the ocular transmission route. Although it seems that the likelihood of the ocular surface being an infection gateway is low, SARS-CoV-2 infection or transmission via the ocular surface may cause conjunctivitis and other ocular discomfort. Therefore, good eye protection is an essential safeguard procedure, especially for medical staff.

The evidence of SARS-CoV-2 infection on ocular surface.

This is a cross-sectional study of patients who received a COVID-19 diagnosis between December 30, 2019 and February 7, 2020 at Tongji Hospital. A total of 102 patients (48 Male [47%] and 54 Female [53%]) with clinical symptoms, Rt, and chest Computed Tomography (CT) abnormalities were identified with a clinical diagnosis of COVID-19. Patients had a mean [SD] gestational age of 57.63 [14.90] years. Of a total of 102 patients identified, 72 patients (36 men [50%] and 36 women [50%]; mean [SD] age, 58.68 [14.81] years) were confirmed to have COVID-19 by laboratory diagnosis with a SARS-CoV-2 RT-PCR assay. Only two patients (2.78%) with conjunctivitis were identified from 72 patients with a laboratory confirmed COVID-19. Of those two patients, SARS-CoV-2 RNA fragments were found in ocular discharges by SARS-CoV-2 RT-PCR in only one patient. Our findings suspect the incidence of SARS-CoV-2 infection through the ocular surface is extremely low, while the nosocomial infection of SARS-CoV-2 through the eyes after occupational exposure is a potential route. To lower the SARS-CoV-2 nosocomial infection, all health care professionals should wear protective goggles. The inefficient diagnostic method and the sampling time lag may contribute to the lower positive rate of conjunctival swab samples of SARS-CoV-2.