Adaptive neighborhood rough set model for hybrid data processing: a case study on Parkinson's disease behavioral analysis.

Extracting knowledge from hybrid data, comprising both categorical and numerical data, poses significant challenges due to the inherent difficulty in preserving information and practical meanings during the conversion process. To address this challenge, hybrid data processing methods, combining complementary rough sets, have emerged as a promising approach for handling uncertainty. However, selecting an appropriate model and effectively utilizing it in data mining requires a thorough qualitative and quantitative comparison of existing hybrid data processing models. This research aims to contribute to the analysis of hybrid data processing models based on neighborhood rough sets by investigating the inherent relationships among these models. We propose a generic neighborhood rough set-based hybrid model specifically designed for processing hybrid data, thereby enhancing the efficacy of the data mining process without resorting to discretization and avoiding information loss or practical meaning degradation in datasets. The proposed scheme dynamically adapts the threshold value for the neighborhood approximation space according to the characteristics of the given datasets, ensuring optimal performance without sacrificing accuracy. To evaluate the effectiveness of the proposed scheme, we develop a testbed tailored for Parkinson's patients, a domain where hybrid data processing is particularly relevant. The experimental results demonstrate that the proposed scheme consistently outperforms existing schemes in adaptively handling both numerical and categorical data, achieving an impressive accuracy of 95% on the Parkinson's dataset. Overall, this research contributes to advancing hybrid data processing techniques by providing a robust and adaptive solution that addresses the challenges associated with handling hybrid data, particularly in the context of Parkinson's disease analysis.

A lightweight deep learning approach for COVID-19 detection using X-ray images with edge federation.

Objective: This study aims to develop a lightweight convolutional neural network-based edge federated learning architecture for COVID-19 detection using X-ray images, aiming to minimize computational cost, latency, and bandwidth requirements while preserving patient privacy. Method: The proposed method uses an edge federated learning architecture to optimize task allocation and execution. Unlike in traditional edge networks where requests from fixed nodes are handled by nearby edge devices or remote clouds, the proposed model uses an intelligent broker within the federation to assess member edge cloudlets' parameters, such as resources and hop count, to make optimal decisions for task offloading. This approach enhances performance and privacy by placing tasks in closer proximity to the user. DenseNet is used for model training, with a depth of 60 and 357,482 parameters. This resource-aware distributed approach optimizes computing resource utilization within the edge-federated learning architecture. Results: The experimental results demonstrate significant improvements in various performance metrics. The proposed method reduces training time by 53.1%, optimizes CPU and memory utilization by 17.5% and 33.6%, and maintains accurate COVID-19 detection capabilities without compromising the F1 score, demonstrating the efficiency and effectiveness of the lightweight convolutional neural network-based edge federated learning architecture. Conclusion: Existing studies predominantly concentrate on either privacy and accuracy or load balancing and energy optimization, with limited emphasis on training time. The proposed approach offers a comprehensive performance-centric solution that simultaneously addresses privacy, load balancing, and energy optimization while reducing training time, providing a more holistic and balanced solution for optimal system performance.

Machine learning based approaches for clinical and non-clinical depression recognition and depression relapse prediction using audiovisual and EEG modalities: A comprehensive review.

Mental disorders are rapidly increasing each year and have become a major challenge affecting the social and financial well-being of individuals. There is a need for phenotypic characterization of psychiatric disorders with biomarkers to provide a rich signature for Major Depressive Disorder, improving the understanding of the pathophysiological mechanisms underlying these mental disorders. This comprehensive review focuses on depression and relapse detection modalities such as self-questionnaires, audiovisuals, and EEG, highlighting noteworthy publications in the last ten years. The article concentrates on the literature that adopts machine learning by audiovisual and EEG signals. It also outlines preprocessing, feature extraction, and public datasets for depression detection. The review concludes with recommendations that will help improve the reliability of developed models and the determinism of computational intelligence-based systems in psychiatry. To the best of our knowledge, this survey is the first comprehensive review on depression and relapse prediction by self-questionnaires, audiovisual, and EEG-based approaches. The findings of this review will serve as a useful and structured starting point for researchers studying clinical and non-clinical depression recognition and relapse through machine learning-based approaches.

Interobserver Variability in the Assessment of Fluorescence Angiography in the Colon.

BACKGROUND: Fluorescence angiography in colorectal surgery is a technique that may lead to lower anastomotic leak rates. However, the interpretation of the fluorescent signal is not standardised and there is a paucity of data regarding interobserver agreement. The aim of this study is to assess interobserver variability in selection of the transection point during fluorescence angiography before anastomosis. METHODS: An online survey with still images of fluorescence angiography was distributed through colorectal surgery channels containing images from 13 patients where several areas for transection were displayed to be chosen by raters. Agreement was assessed overall and between pre-planned rater cohorts (experts vs non-experts; trainees vs consultants; colorectal specialists vs non colorectal specialists), using Fleiss' kappa statistic. RESULTS: 101 raters had complete image ratings. No significant difference was found between raters when choosing a point of optimal bowel transection based on fluorescence angiography still images. There was no difference between pre-planned cohorts analysed (experts vs non-experts; trainees vs consultants; colorectal specialists vs non colorectal specialists). Agreement between these cohorts was poor (<.26). CONCLUSION: Whilst there is no learning curve for the technical adoption of FA, understanding the fluorescent signal characteristics is key to successful use. We found significant variation exists in interpretation of static fluorescence angiography data. Further efforts should be employed to standardise fluorescence angiography assessment.

Multipath Routing in Wireless Body Area Sensor Network for Healthcare Monitoring.

Mobility and low energy consumption are considered the main requirements for wireless body area sensor networks (WBASN) used in healthcare monitoring systems (HMS). In HMS, battery-powered sensor nodes with limited energy are used to obtain vital statistics about the body. Hence, energy-efficient schemes are desired to maintain long-term and steady connectivity of the sensor nodes. A sheer amount of energy is consumed in activities such as idle listening, excessive transmission and reception of control messages, packet collisions and retransmission of packets, and poor path selection, that may lead to more energy consumption. A combination of adaptive scheduling with an energy-efficient protocol can help select an appropriate path at a suitable time to minimize the control overhead, energy consumption, packet collision, and excessive idle listening. This paper proposes a region-based energy-efficient multipath routing (REMR) approach that divides the entire sensor network into clusters with preferably multiple candidates to represent each cluster. The cluster representatives (CRs) route packets through various clusters. For routing, the energy requirement of each route is considered, and the path with minimum energy requirements is selected. Similarly, end-to-end delay, higher throughput, and packet-delivery ratio are considered for packet routing.

Facial palsy as a manifestation of COVID-19: A systematic review of cases.

Background and Aims: Facial palsy is a rare complication of the COVID-19 infection. Herein, we conducted a systematic review of all published cases of facial palsy post-COVID-19 infection in an attempt to educate the general population and medical practitioners regarding the likely occurrence of facial palsy in COVID-19 patients, its detection, effective treatment plan, and prognosis of the condition. Methods: We searched PubMed, Google Scholar, and Directory of Open Access Journals (DOAJ) from December 1, 2019 to September 21, 2021. Results: We included 49 studies bearing accounts of 75 cases who had facial palsy. The mean age of patients was 42.9 ± 19.59 years, with a male-to-female ratio of 8:7. The majority of the cases were reported from Brazil (n = 14), USA (n = 9), Turkey (n = 9), and Spain (n = 9). Noticeably, 30.14% of COVID-19 patients were diagnosed with Guillain-Barré syndrome. In total, 22.97% of patients complained of bilateral facial paralysis (n = 17), whereas ipsilateral paralysis was observed in 77.03% (n = 57). These were common complaints of Lagophthalmos, otalgia, facial drooping, dysarthria, and compromised forehead wrinkling. The treatment regimen mainly included the use of corticosteroids (n = 51) (69.86%), antivirals (n = 23) (31.51%), IVIG (n = 18) (24.66%), antibiotics (n = 13) (17.81%), antiretroviral (n = 9) (12.33%), and antimalarial (n = 8) (10.96%) medications. In all, 35.62% of patients (n = 26) adhered to a combination of antiviral and corticosteroid-based therapy. Positive treatment outcomes were observed in 83.58% (n = 56) of cases. In contrast, 10 patients (14.93%) showed nonsignificant recovery, out of which 3 (4.48%) died from the disease. Conclusion: The association of facial palsy with COVID-19 is controversial and therefore requires further investigation and published work to confirm a causal relationship. However, physicians should not overlook the likelihood of facial palsy post-COVID-19 infection and treat it accordingly.

Neonatal haemolytic disease with co-existing Anti-D and Anti-C antibodies.

Neonatal haemolytic disease in the new-born remains of prime importance for paediatricians due to high perinatal morbidity and mortality rates. The Rh antigen family comprises several different antigens, out of which, D antigen incompatibility is well known for causing severe haemolytic disease in the foetus. Although the current literature shows anomalous cases where coexisting non-D-Rh and D-Rh antigens are the causative agents, there is very little information regarding post-natal outcomes in neonates bearing two different incompatibilities simultaneously. Herein, we discuss an unusual case of anti-D as well as anti-C antibodies (non-D-Rh) in a male neonate born to a Rh-negative mother, who developed jaundice and haemolysis in post-natal life. The neonate underwent exchange transfusion and photo therapy due to raised serum bilirubin levels, supplemented with repeated blood transfusions, intravenous immunoglobulin therapy, and immunosuppressive therapy. He responded well to the management and was later discharged from the hospital. Long-term follow-up revealed no side-effects.

EEG based Major Depressive disorder and Bipolar disorder detection using Neural Networks:A review.

Mental disorders represent critical public health challenges as they are leading contributors to the global burden of disease and intensely influence social and financial welfare of individuals. The present comprehensive review concentrate on the two mental disorders: Major depressive Disorder (MDD) and Bipolar Disorder (BD) with noteworthy publications during the last ten years. There is a big need nowadays for phenotypic characterization of psychiatric disorders with biomarkers. Electroencephalography (EEG) signals could offer a rich signature for MDD and BD and then they could improve understanding of pathophysiological mechanisms underling these mental disorders. In this review, we focus on the literature works adopting neural networks fed by EEG signals. Among those studies using EEG and neural networks, we have discussed a variety of EEG based protocols, biomarkers and public datasets for depression and bipolar disorder detection. We conclude with a discussion and valuable recommendations that will help to improve the reliability of developed models and for more accurate and more deterministic computational intelligence based systems in psychiatry. This review will prove to be a structured and valuable initial point for the researchers working on depression and bipolar disorders recognition by using EEG signals.

Association of Pro198Leu polymorphism in glutathione peroxidase one (GPX1) gene with peripheral neuropathy in type 2 diabetic patients.

OBJECTIVE: To evaluate the association of Pro198Leu polymorphism in glutathione peroxidase 1 gene in type 2 diabetic patients with neuropathy. METHODS: The comparative cross-sectional study was conducted from February 2 to November 30, 2018, at the Department of Biochemistry and Molecular Biology, Army Medical College, Rawalpindi, Pakistan, in collaboration with the Department of Neurology, Military Hospital, Rawalpindi. Diagnosed type 2 diabetics of either genders aged 40-70 years were divided into two equal groups of neuropathy and non- neuropathy subjects. Deoxyribonucleic acid was subjected to restriction fragment length polymorphism for glutathione peroxidase 1gene analysis. Hardy Weinberg equation was used to check the genotype frequency equilibrium. RESULTS: Of the 60 patients, there were 30(50%) each in the two groups. Age, fasting glucose level and diabetes duration were significantly different between the groups (p<0.05). Even though the frequency of TT genotype was higher, no association of the polymorphism and any of the genotypes was found with diabetic neuropathy (p>0.05). CONCLUSIONS: There was no association found between Pro198 Lue polymorphism in glutathione peroxidase 1 and diabetic neuropathy.

Damage control resuscitation using blood component therapy in standard doses has a limited effect on coagulopathy during trauma hemorrhage.

OBJECTIVE: To determine the effectiveness of blood component therapy in the correction of trauma-induced coagulopathy during hemorrhage. BACKGROUND: Severe hemorrhage remains a leading cause of mortality in trauma. Damage control resuscitation strategies target trauma-induced coagulopathy (TIC) with the early delivery of high-dose blood components such as fresh frozen plasma (FFP) and platelet transfusions. However, the ability of these products to correct TIC during hemorrhage and resuscitation is unknown. METHODS: This was an international prospective cohort study of bleeding trauma patients at three major trauma centers. A blood sample was drawn immediately on arrival and after 4, 8 and 12 packed red blood cell (PRBC) transfusions. FFP, platelet and cryoprecipitate use was recorded during these intervals. Samples were analyzed for functional coagulation and procoagulant factor levels. RESULTS: One hundred six patients who received at least four PRBC units were included. Thirty-four patients (32 %) required a massive transfusion. On admission 40 % of patients were coagulopathic (ROTEM CA5 ≤ 35 mm). This increased to 58 % after four PRBCs and 81 % after eight PRBCs. On average all functional coagulation parameters and procoagulant factor concentrations deteriorated during hemorrhage. There was no clear benefit to high-dose FFP therapy in any parameter. Only combined high-dose FFP, cryoprecipitate and platelet therapy with a high total fibrinogen load appeared to produce a consistent improvement in coagulation. CONCLUSIONS: Damage control resuscitation with standard doses of blood components did not consistently correct trauma-induced coagulopathy during hemorrhage. There is an important opportunity to improve TIC management during damage control resuscitation.

Hemostatic resuscitation is neither hemostatic nor resuscitative in trauma hemorrhage.

BACKGROUND: Trauma hemorrhage continues to carry a high mortality rate despite changes in modern practice. Traditional approaches to the massively bleeding patient have been shown to result in persistent coagulopathy, bleeding, and poor outcomes. Hemostatic (or damage control) resuscitation developed from the discovery of acute traumatic coagulopathy and increased recognition of the negative consequences of dilutional coagulopathy. These strategies concentrate on early delivery of coagulation therapy combined with permissive hypotension. The efficacy of hemostatic resuscitation in correcting coagulopathy and restoring tissue perfusion during acute hemorrhage has not been studied. METHODS: This is a prospective cohort study of ROTEM and lactate measurements taken from trauma patients recruited to the multicenter Activation of Coagulation and Inflammation in Trauma (ACIT) study. A blood sample is taken on arrival and during the acute bleeding phase after administration of every 4 U of packed red blood cells (PRBCs), up to 12 U. The quantity of blood products administered within each interval is recorded. RESULTS: Of the 106 study patients receiving at least 4 U of PRBC, 27 received 8 U to 11 U of PRBC and 31 received more than 12 U of PRBC. Average admission lactate was 6.2 mEq/L. Patients with high lactate (≥5 mEq/L) on admission did not clear lactate until hemorrhage control was achieved, and no further PRBC units were required. On admission, 43% of the patients were coagulopathic (clot amplitude at 5 minutes ≤ 35 mm). This increased to 49% by PRBC 4; 62% by PRBC 8 and 68% at PRBC 12. The average fresh frozen plasma/PRBC ratio between intervals was 0.5 for 0 U to 4 U of PRBC, 0.9 for 5 U to 8 U of PRBC, 0.7 for 9 U to 12 U of PRBC. There was no improvement in any ROTEM parameter during ongoing bleeding. CONCLUSION: While hemostatic resuscitation offers several advantages over historical strategies, it still does not achieve correction of hypoperfusion or coagulopathy during the acute phase of trauma hemorrhage. Significant opportunities still exist to improve management and improve outcomes for bleeding trauma patients. LEVEL OF EVIDENCE: Epidemiologic study, level III.