A comprehensive bibliometric survey of micro-expression recognition system based on deep learning.

Micro-expressions (ME) are rapidly occurring expressions that reveal the true emotions that a human being is trying to hide, cover, or suppress. These expressions, which reveal a person's actual feelings, have a broad spectrum of applications in public safety and clinical diagnosis. This study provides a comprehensive review of the area of ME recognition. A bibliometric and network analysis techniques is used to compile all the available literature related to ME recognition. A total of 735 publications from the Web of Science (WOS) and Scopus databases were evaluated from December 2012 to December 2022 using all relevant keywords. The first round of data screening produced some basic information, which was further extracted for citation, coupling, co-authorship, co-occurrence, bibliographic, and co-citation analysis. Additionally, a thematic and descriptive analysis was executed to investigate the content of prior research findings, and research techniques used in the literature. The year wise publications indicated that the published literature between 2012 and 2017 was relatively low but however by 2021, a nearly 24-fold increment made it to 154 publications. The three topmost productive journals and conferences included IEEE Transactions on Affective Computing (n = 20 publications) followed by Neurocomputing (n = 17) and Multimedia tools and applications (n = 15). Zhao G was the most proficient author with 48 publications and the top influential country was China (620 publications). Publications by citations showed that each of the authors acquired citations ranging from 100 to 1225. While publications by organizations indicated that the University of Oulu had the most published papers (n = 51). Deep learning, facial expression recognition, and emotion recognition were among the most frequently used terms. It has been discovered that ME research was primarily classified in the discipline of engineering, with more contribution from China and Malaysia comparatively.

An In Silico Deep Learning Approach to Multi-Epitope Vaccine Design: A Hepatitis E Virus Case Study.

Hepatitis E Virus (HEV) is a major cause of acute and chronic hepatitis. The severity of HEV infection increases manyfold in pregnant women and immunocompromised patients. Despite the extensive research on HEV in the last few decades, there is no widely available vaccine yet. In the current study, immunoinformatic analyses were applied to predict a multi-epitope vaccine candidate against HEV. From the ORF2 region, 41 conserved and immunogenic epitopes were prioritized. These epitopes were further analyzed for their probable antigenic and non-allergenic combinations with several linkers. The stability of the vaccine construct was confirmed by molecular dynamic simulations. The vaccine construct is potentially antigenic and docking analysis revealed stable interactions with TLR3. These results suggest that the proposed vaccine can efficiently stimulate both cellular and humoral immune responses. However, further studies are needed to determine the immunogenicity of the vaccine construct.

The Diagnostic Accuracy of Carotid Doppler in Detecting Anechoic Thrombus Against CT Angiography as the Gold Standard.

Objective In this study, we aimed to assess the diagnostic accuracy of carotid Doppler ultrasound (CDU) in detecting anechoic carotid artery thrombus when compared to CT angiography (CTA) as the gold standard. Materials and methods This prospective comparative study was conducted at the Radiology Department of the Pakistan Institute of Medical Sciences, Islamabad from January 2022 to May 2022. The study enrolled 32 patients who met the inclusion criteria. We evaluated patients admitted to the neurology ward/OPD who were referred to radiology as part of a stroke workup based on their clinical examination and medical history. In all patients, CDU was used to detect free-floating thrombus (FFT)/anechoic thrombus. CTA was used as the gold standard to assess the diagnostic accuracy of CDU. Results The mean age of the study participants was 45.63 ± 7.05 years (range: 33-59 years). Out of 32 patients, 19 (59.4%) were male and 13 (40.6%) were female. The results of CDU were confirmed by CTA in all patients. The diagnostic accuracy of CDU was 53.12% for detecting FFT. The values for sensitivity (54.55%), specificity (50%), positive predictive value (PPV, 70.59%), and negative predictive value (NPV, 33.33%) were also calculated. Conclusion Despite the limited sample size, the study concludes that CDU has a diagnostic accuracy of 53%. CTA still remains the gold standard imaging modality for anechoic thrombus if strong clinical suspicion is present.

COVID-19-associated Coagulopathy and Thromboembolism: Determination of Their Patterns and Risk Factors as Predictors of Mortality Among Severe COVID-19 Patients.

BACKGROUND: Coronavirus Disease 2019 (COVID-19) is associated with Coagulopathy (CAC) and Venous Thromboembolism (VTE). These are well-reported complications of COVID-19 infection. Earlier publications have shown that CAC and thromboembolism are predictors of mortality among COVID-19 patients with severe disease. MATERIALS AND METHODS: A prospective study was conducted in the Intensive Care Unit (ICU) where all confirmed COVID-19 patients were enrolled and followed until death or ICU discharge. CAC, VTE, along with all comorbidities, were recorded. Predictors of mortality were determined by univariate and multivariate regression. RESULTS: Among 261 patients with COVID-19, 48.3% survived and 51.7% died. CAC was present in 53.2% and 76.3% of the survivors and non-survivors, respectively (p<0.001); 89 patients (31.4%) had VTE (p=0.36) and 11 patients (4.2%) had arterial thrombosis (p=0.76) among survivors and nonsurvivors. Age between 71-80 years (p=0.009), male gender (p=0.045), CAC (p<0.001), comorbidities like chronic kidney disease (CKD, p=0.013), chronic obstructive pulmonary disease (COPD, p=0.001) and asthma (p=0.046), were significant predictors of mortality. CONCLUSION: A severe complication of COVID-19 is CAC, such as sepsis-induced coagulopathy, overt disseminated-coagulopathy and VTE. Old age, various comorbidities (e.g., COPD, CKD, or asthma), CAC, VTE (pulmonary embolism) and coagulation parameters with critical severity score (D-dimers, platelets, prothrombin time) and the SOFA (Sequential Organ Failure Assessment) score were significant predictors of mortality among COVID-19 patients.

Frequency of Hyperthermia in Acute Ischemic Stroke Patients Visiting a Tertiary Care Hospital.

OBJECTIVE: To determine the frequency of hyperthermia in acute ischemic stroke patients visiting a tertiary care hospital in a developing country. STUDY DESIGN: Cross-sectional, observational study. PLACE AND DURATION OF STUDY: Medical Wards of Civil Hospital, Karachi, from January to June 2013. METHODOLOGY: Patients aged ≥18 years of either gender with acute ischemic stroke presenting within 24 hours of onset of symptoms were included. Written informed consent was obtained from all participants as well as approval of ethical review committee of the institute. Axillary temperature by mercury thermometer was monitored at the time of admission and after every 6 hours for 3 days. The data was analyzed using SPSS version 17.0 (SPSS Inc., IL, Chicago, USA). RESULTS: Atotal of 106 patients of ischemic stroke were included. The mean age of enrolled participants was 60.1 ±9.5 years. Among these, 61 (57.5%) were males and 45 (42.5%) females. Among all patients, 51.9% presented with loss of consciousness, 30.2% with slurred speech, 77.4% with limb weakness, and 9.4% with decrease vision. Atotal of 17 (16%) patients with ischemic stroke developed hyperthermia. When the prevalence of hyperthermia was stratified according to age, among patients of < 60 years of age, 26% developed hyperthermia compared to 7.1% in patients of ≥60 years of age (p=0.008). On gender stratification, among male patients, 14.8% developed hyperthermia compared to 17.8% in female patients (p=0.43). CONCLUSION: It is concluded from this study that the frequency of hyperthermia in ischemic stroke was 16% and it should be looked for as it has significant impact on the outcome. The hyperthermia was significantly more common in younger adults as compared to older adults. However, gender had no influence on the prevalence rate of hyperthermia.

Continuous-time Q-learning for infinite-horizon discounted cost linear quadratic regulator problems.

This paper presents a method of Q-learning to solve the discounted linear quadratic regulator (LQR) problem for continuous-time (CT) continuous-state systems. Most available methods in the existing literature for CT systems to solve the LQR problem generally need partial or complete knowledge of the system dynamics. Q-learning is effective for unknown dynamical systems, but has generally been well understood only for discrete-time systems. The contribution of this paper is to present a Q-learning methodology for CT systems which solves the LQR problem without having any knowledge of the system dynamics. A natural and rigorous justified parameterization of the Q-function is given in terms of the state, the control input, and its derivatives. This parameterization allows the implementation of an online Q-learning algorithm for CT systems. The simulation results supporting the theoretical development are also presented.