MST-net: A multi-scale swin transformer network for EEG-based cognitive load assessment.

Cognitive load assessment plays a crucial role in monitoring safe production, resource allocation, and subjective initiative in human-computer interaction. Due to its high time resolution and convenient acquisition, Electroencephalography (EEG) is widely applied in brain monitoring and cognitive state assessment. In this study, a multi-scale Swin Transformer network (MST-Net) was proposed for cognitive load assessment, which extracts local features with different sensory fields using a multi-scale parallel convolution model and introduces the attention mechanism of the Swin Transformer to obtain the feature correlations among multi-scale local features. The performance of the proposed network was validated using the EEG signals collected during cognitive tasks and N-back tasks with three different load levels. Results show that the MST-Net network achieved the best classification accuracy on both local and public datasets, and was higher than the mainstream Swin Transformer and CNN. Furthermore, results of ablation experiments and feature visualization revealed that the proposed MST-Net could well characterize different cognitive loads, which not only provided novel and powerful tools for cognitive load assessment but also showed potential for broad application in brain-computer interface (BCI) systems.

Preoperative Frailty Assessment Predicts Postoperative Mortality, Delirium and Pneumonia in Elderly Lung Cancer Patients: A Retrospective Cohort Study.

BACKGROUND: The purpose of this study was to investigate the predictive value of the 5-factor modified frailty index (mFI-5) for postoperative mortality, delirium and pneumonia in patients over 65 years of age undergoing elective lung cancer surgery. METHODS: Data were collected from a single-center retrospective cohort study conducted in a general tertiary hospital from January 2017 to August 2019. In total, the study included 1372 elderly patients aged over 65 who underwent elective lung cancer surgery. They were divided into frail group (mFI-5, 2-5), prefrail group (mFI-5, 1) and robust group (mFI-5, 0) on the basis of mFI-5 classification. The primary outcome was postoperative 1-year all-cause mortality. Secondary outcomes were postoperative pneumonia and postoperative delirium. RESULTS: Frailty group had the highest incidence of postoperative delirium (frailty 31.2% versus prefrailty 1.6% versus robust 1.5%, p < 0.001), postoperative pneumonia (frailty 23.5% versus prefrailty 7.2% versus robust 7.7%, p < 0.001), and postoperative 1-year mortality (frailty 7.0% versus prefrailty 2.2% versus robust 1.9%. p < 0.001). Frail patients have significantly longer length of hospitalization than those in the robust group and prefrail patients (p < 0.001). Multivariate analysis showed a clear link between frailty and increased risk of postoperative delirium (aOR 2.775, 95% CI 1.776-5.417, p < 0.001), postoperative pneumonia (aOR 3.291, 95% CI 2.169-4.993, p < 0.001) and postoperative 1-year mortality (aOR 3.364, 95% CI, 1.516-7.464, p = 0.003). CONCLUSIONS: mFI-5 has potential clinical utility in predicting postoperative death, delirium and pneumonia incidence in elderly patients undergoing radical lung cancer surgery. Frailty screening of patients (mFI-5) may provide benefits in risk stratification, targeted intervention efforts, and assist physicians in clinical decision-making.

Explainable synthetic image generation to improve risk assessment of rare pediatric heart transplant rejection.

Expert microscopic analysis of cells obtained from frequent heart biopsies is vital for early detection of pediatric heart transplant rejection to prevent heart failure. Detection of this rare condition is prone to low levels of expert agreement due to the difficulty of identifying subtle rejection signs within biopsy samples. The rarity of pediatric heart transplant rejection also means that very few gold-standard images are available for developing machine learning models. To solve this urgent clinical challenge, we developed a deep learning model to automatically quantify rejection risk within digital images of biopsied tissue using an explainable synthetic data augmentation approach. We developed this explainable AI framework to illustrate how our progressive and inspirational generative adversarial network models distinguish between normal tissue images and those containing cellular rejection signs. To quantify biopsy-level rejection risk, we first detect local rejection features using a binary image classifier trained with expert-annotated and synthetic examples. We converted these local predictions into a biopsy-wide rejection score via an interpretable histogram-based approach. Our model significantly improves upon prior works with the same dataset with an area under the receiver operating curve (AUROC) of 98.84% for the local rejection detection task and 95.56% for the biopsy-rejection prediction task. A biopsy-level sensitivity of 83.33% makes our approach suitable for early screening of biopsies to prioritize expert analysis. Our framework provides a solution to rare medical imaging challenges currently limited by small datasets.

GABAergic neurons in the dorsomedial hypothalamus regulate states of consciousness in sevoflurane anesthesia.

The neural inhibitory gamma-aminobutyric acid (GABA) system in the regulation of anesthetic consciousness is heterogeneous, and the medial hypothalamus (MH), consisting of ventromedial hypothalamus (VMH) and dorsomedial hypothalamus (DMH), plays an important role in sleep and circadian rhythm. However, the role of MH GABAergic neurons (MHGABA) in anesthesia remains unclear. In this study, we used righting reflex, electroencephalogram (EEG), and arousal behavioral score to evaluate the sevoflurane anesthesia. Activation of MHGABA or DMHGABA neurons prolonged the anesthesia induction time, shortened the anesthesia emergence time, and induced EEG arousal and body movement during anesthesia; meanwhile, VMHGABA neurons activated only induced EEG changes during 1.5% sevoflurane anesthesia. Furthermore, inhibition of DMHGABA neurons significantly deepened sevoflurane anesthesia. Therefore, DMHGABA neurons exert a strong emergence-promoting effect on induction, maintenance, and arousal during sevoflurane general anesthesia, which helps to reveal the mechanism of anesthesia.

Application of Bayesian network and regression method in treatment cost prediction.

Charging according to disease is an important way to effectively promote the reform of medical insurance mechanism, reasonably allocate medical resources and reduce the burden of patients, and it is also an important direction of medical development at home and abroad. The cost forecast of single disease can not only find the potential influence and driving factors, but also estimate the active cost, and tell the management and reasonable allocation of medical resources. In this paper, a method of Bayesian network combined with regression analysis is proposed to predict the cost of treatment based on the patient's electronic medical record when the amount of data is small. Firstly, a set of text-based medical record data conversion method is established, and in the clustering method, the missing value interpolation is carried out by weighted method according to the distance, which completes the data preparation and processing for the realization of data prediction. Then, aiming at the problem of low prediction accuracy of traditional regression model, this paper establishes a prediction model combined with local weight regression method after Bayesian network interpretation and classification of patients' treatment process. Finally, the model is verified with the medical record data provided by the hospital, and the results show that the model has higher prediction accuracy.

Variations in disease burden of laryngeal cancer attributable to alcohol use and smoking in 204 countries or territories, 1990-2019.

BACKGROUND: Alcohol consumption and smoking are the leading risk factors for laryngeal cancer (LC). Understanding the variations in disease burden of LC attributable to alcohol use and smoking is critical for LC prevention. METHODS: Disease burden data of LC were retrieved from the Global Burden of Disease Study 2019. We used estimated average percentage change (EAPC) to measure the temporal trends of the age-standardized mortality rate (ASMR) of LC. RESULTS: Globally, while the ASMR of LC decreased by 1.49% (95% CI, 1.41-1.57%) per year between 1990 and 2019, the number of deaths from LC has increased 41.0% to 123.4 thousand in 2019. In 2019, 19.4 and 63.5% of total LC-related deaths were attributable to alcohol use and smoking worldwide, respectively. The ASMR of alcohol- and smoking-related LC decreased by 1.78 and 1.93% per year, whereas the corresponding death number has increased 29.2 and 25.1% during this period, respectively. The decreasing trend was more pronounced in developed countries. In some developing countries, such as Guinea and Mongolia, the LC mortality has shown an unfavorable trend. CONCLUSION: The ubiquitous decrease in LC mortality was largely attributed to the smoking control and highlighted the importance of smoking control policies. However, the disease burden of LC remained in increase and more effective strategies are needed to combat the global increase of alcohol consumption.

Cervical vestibular evoked myogenic potential testing for assessment of vestibular functions in cochlear implant patients.

This study aims to investigate the vestibular function status of cochlear implant patients using cervical vestibular evoked myogenic potential (cVEMP) testing and estimate the effects of cochlear implants on vestibular function. The cVEMPs of 50 cochlear implant patients were measured preoperatively, and at one and six months postoperatively. Then, implanted ears and non-implanted ears were compared in terms of p13/n23 wave response rates, latency, amplitude and threshold. Preoperatively, the binaural cVEMP response rate was 92%, while the cVEMP response rates of implanted ears vs. non-implanted ears at postoperative one and six months were 24% vs. 80% and 52% vs. 82%, respectively. No significant difference between implanted and non-implanted ears was found preoperatively, in terms of latent period, amplitude, or threshold. However, significant changes were found in amplitude and threshold for implanted ears after the operation, but not in latency. No significant postoperative change was found in amplitude, latent period, or threshold for non-implanted ears. Significant differences between implanted and non-implanted ears were found in both amplitude and threshold. Cochlear implants affect vestibular function, especially saccular function, and reduce the cVEMP amplitude and threshold of implanted ears.

Trends in surgery and disparities in receipt of surgery for intrahepatic cholangiocarcinoma in the US: 2005-2014.

BACKGROUND: Intrahepatic cholangiocarcinoma (IHC) is a malignancy with an increasing incidence. Surgery is the only treatment modality associated with long term survival. The objective of this study is to utilize a nationwide representative database to quantify the trends in incidence, and surgery for IHC in the United States from 2004-2014, as well as identify any disparities in the receipt of surgery. METHODS: All patients admitted with a diagnosis of IHC between 2005 and 2014 were identified from the Nationwide Inpatient Sample (NIS) database. Trends in the number of IHC admissions and surgery procedures as well as outcomes were examined, and a multivariate analysis was used to determine the effects of demographic and clinical co-variables on resection rates. RESULTS: An estimated total of 104,045 IHC related admissions occurred between 2005 and 2014. The hospitalization rate for IHC increased by nearly 2-fold in 2014 [38.9 per 100,000 (95% CI, 35.7-42.2)] from 18.1 per 100,000 (95% CI, 15.8-20.3) in 2005. Liver resections increased 248% (P<0.01) with an increasing majority being performed at teaching hospitals and 56% being minor resections. There was an increase in estimated hospital charges from $87,124 to $148,613 (P<0.001) and decrease in LOS from 12 days to 10 days (P<0.01). Inpatient mortality for IHC decreased significantly from 11% to 8.4% (P=0.004), from year 2005 to 2014 respectively. Age >80 years (OR =0.45; 95% CI, 0.33-0.60), Black race (OR =0.50; 95% CI, 0.39-063), Hispanic race (OR =0.59; 95% CI, 0.45-0.79), Medicaid insurance (OR =0.58; 95% CI, 0.42-0.79) and Elixhauser comorbidity score >3 (OR =0.58; 95% CI, 0.47-0.73) were associated with decreased rates of resection. CONCLUSIONS: Overall hospitalization and volume of surgery for IHC has increased dramatically over the past decade. There has been an increase in cost, decrease in LOS and inpatient mortality during the period. Socioeconomic and racial disparities were observed in the receipt of surgery for IHC. Additional work is needed to understand the complex interplay between socioeconomic status and race in in the treatment of IHC.