Emotional Intelligence Attention Unsupervised Learning Using Lexicon Analysis for Irony Based Advertising

Social media platforms have made increasing use of irony in recent years. Users can express their ironic thoughts with audio, video, and images attached to text content. When you use irony, you are making fun of a situation or trying to make a point. It can also express frustration or highlight the absurdity of a situation. The use of irony in social media is likely to continue to increase, no matter the reason. By using syntactic information in conjunction with semantic exploration, we show that attention networks can be enhanced. Using learned embedding, unsupervised learning encodes word order into a joint space. By evaluating the entropy of an example class and adding instances, the active learning method uses the shared representation as a query to retrieve semantically similar sentences from a knowledge base. In this way, the algorithm can identify the instance with the maximum uncertainty and extract the most informative example from the training set. An ironic network trained for each labelled record is used to train a classifier (model). The partial training model and the original labelled data generate pseudo-labels for the unlabeled data. To correctly predict the label of a dataset, a classifier (attention network) updates the pseudo-labels for the remaining datasets. After the experimental evaluation of the 1,021 annotated texts, the proposed model performed better than the baseline models, achieving an F1 score of 0.63 on ironic tasks and 0.59 on non-ironic tasks. We also found that the proposed model generalized well to new instances of datasets.

Cell surface GRP78 regulates TGFβ1-mediated profibrotic responses via TSP1 in diabetic kidney disease

Introduction: Diabetic kidney disease (DKD) is the leading cause of kidney failure in North America, characterized by glomerular accumulation of extracellular matrix (ECM) proteins. High glucose (HG) induction of glomerular mesangial cell (MC) profibrotic responses plays a central role in its pathogenesis. We previously showed that the endoplasmic reticulum resident GRP78 translocates to the cell surface in response to HG, where it mediates Akt activation and downstream profibrotic responses in MC. Transforming growth factor β1 (TGFβ1) is recognized as a central mediator of HG-induced profibrotic responses, but whether its activation is regulated by cell surface GRP78 (csGRP78) is unknown. TGFβ1 is stored in the ECM in a latent form, requiring release for biological activity. The matrix glycoprotein thrombospondin 1 (TSP1), known to be increased in DKD and by HG in MC, is an important factor in TGFβ1 activation. Here we determined whether csGRP78 regulates TSP1 expression and thereby TGFβ1 activation by HG. Methods: Primary mouse MC were used. TSP1 and TGFβ1 were assessed using standard molecular biology techniques. Inhibitors of csGRP78 were: 1) vaspin, 2) the C-terminal targeting antibody C38, 3) siRNA downregulation of its transport co-chaperone MTJ-1 to prevent GRP78 translocation to the cell surface, and 4) prevention of csGRP78 activation by its ligand, active α2-macroglobulin (α2M*), with the neutralizing antibody Fα2M or an inhibitory peptide. Results: TSP1 transcript and promoter activity were increased by HG, as were cellular and ECM TSP1, and these required PI3K/Akt activity. Inhibition of csGRP78 prevented HG-induced TSP1 upregulation and deposition into the ECM. The HG-induced increase in active TGFβ1 in the medium was also inhibited, which was associated with reduced intracellular Smad3 activation and signaling. Overexpression of csGRP78 increased TSP-1, and this was further augmented in HG. Discussion: These data support an important role for csGRP78 in regulating HG-induced TSP1 transcriptional induction via PI3K/Akt signaling. Functionally, this enables TGFβ1 activation in response to HG, with consequent increase in ECM proteins. Means of inhibiting csGRP78 signaling represent a novel approach to preventing fibrosis in DKD.

Presentation, management, and outcomes of cauda equina syndrome up to one year after surgery, using clinician and participant reporting: A multi-centre prospective cohort study

Background

Cauda equina syndrome (CES) results from nerve root compression in the lumbosacral spine, usually due to a prolapsed intervertebral disc. Evidence for management of CES is limited by its infrequent occurrence and lack of standardised clinical definitions and outcome measures.

Methods

This is a prospective multi-centre observational cohort study of adults with CES in the UK. We assessed presentation, investigation, management, and all Core Outcome Set domains up to one year post-operatively using clinician and participant reporting. Univariable and multivariable associations with the Oswestry Disability Index (ODI) and urinary outcomes were investigated.

Findings

In 621 participants with CES, catheterisation for urinary retention was required pre-operatively in 31% (191/615). At discharge, only 13% (78/616) required a catheter. Median time to surgery from symptom onset was 3 days (IQR:1–8) with 32% (175/545) undergoing surgery within 48 h. Earlier surgery was associated with catheterisation (OR:2.2, 95%CI:1.5–3.3) but not with admission ODI or radiological compression. In multivariable analyses catheter requirement at discharge was associated with pre-operative catheterisation (OR:10.6, 95%CI:5.8–20.4) and one-year ODI was associated with presentation ODI (r = 0.3, 95%CI:0.2–0.4), but neither outcome was associated with time to surgery or radiological compression. Additional healthcare services were required by 65% (320/490) during one year follow up.

Interpretation

Post-operative functional improvement occurred even in those presenting with urinary retention. There was no association between outcomes and time to surgery in this observational study. Significant healthcare needs remained post-operatively.

Funding

DCN Endowment Fund funded study administration. Castor EDC provided database use. No other study funding was received.

Automatically Temporal Labeled Data Generation Using Positional Lexicon Expansion for Focus Time Estimation of News Articles

Many facts change over time, which is a fundamental aspect of our physical environment. In the case of pandemic articles, the user is not interested in the creation date of the document, but in the facts and the cause of the last pandemic. Fake news can be better combated by having a document with a temporal focus. Currently, neither the sequence of events nor the temporal focus is considered when obtaining news documents. Despite the limited number of temporal aspects in the available datasets, it is difficult to test and evaluate the temporal conclusions of the model. The goal of this work is to develop a temporal focus news article retrieval model based on co-training to advance research in semi-supervised learning. A mapping of the dataset is performed using 1) the evolving focus time of news articles, 2) the semi-supervised method based on coincidence contexts for learning low-dimensional continuous vectors for learning neural contrast embedding models generating focus time-based query in sequential news articles to facilitate temporal understanding by learning low-dimensional continuous vectors. A diverse dataset of news articles is used to evaluate the effectiveness of the proposed method. With semi-supervised learning and lexicon expansion, the result of the developed model can achieve 89%. The method performed better than previous baselines and traditional machine learning models with improvements of 12.65% and 4.7%, respectively.

Focused ultrasound stimulation of the inflammatory reflex at the spleen ameliorates pulmonary arterial hypertension in rodents

Background

Inflammation is a major contributor in pulmonary arterial hypertension (PAH) pathogenesis. Non-invasive, focused ultrasound stimulation (FUS) of the spleen activates the neuroimmune inflammatory reflex (IR) and suppresses systemic inflammation [1].

Purpose

We aimed to explore whether daily FUS of the spleen improves haemodynamics and biomarkers by modulating the IR, in a rat model of PAH.

Methods

Sprague-Dawley rats (n=12) were injected s.c. with Sugen5416 (VEGF receptor inhibitor) and then, were placed in a hypoxic chamber (FiO2=10%) for 21 days, followed by 14 days of re-exposure to normoxia (FiO2=10%). At day 21, rats were randomized to either FUS (n=6) or sham-stimulation of the spleen (n=6). Each FUS- or sham-stimulation session consisted of 12 minutes. After 14 days of treatment, in a terminal experiment, right ventricular systolic pressure (RVSP) and arterial pressure were measured invasively, as well as biomarkers, in each animal (Figure 1A).

Results

FUS significantly reduced RVSP compared with the sham-stimulation (Mean±SEM, 50.83±3.57 mmHg vs 72.50±5.81; p=0.009), resulting in a 30% relative reduction (Figure 1B). Mean systemic arterial pressure was similar in the 2 groups (Mean±SEM, 79.83±3.73 mmHg vs. 87.00±2.95; p=0.137) (Figure 1C), as was the change in heart rate between day 1 and day 14 of treatment period (−19.53±5.36% vs. −16.79±3.1, p=0.61) (Figure 1D). Consistently, plasma brain natriuretic peptide (BNP) levels are reduced in the FUS group (119.45±19.93 ng/μl vs. 319.39±91.85; p=0.019), indicative of reduced myocardial wall stress in the FUS group (Figure 1E).

Conclusion

Non-invasive FUS of the spleen reduced RVSP by ∼30% and BNP without significantly affecting systemic pressure or heart rate, in rats with severe PAH. Non-invasive FUS, by modulating the IR, may exert an anti-inflammatory effect in PAH. FUS of the spleen is noninvasive, safe, widely available and easy to perform, and should be further explored as a possible therapeutic option in PAH.

Funding Acknowledgement

Type of funding sources: Private hospital(s). Main funding source(s): Northwell Health

Multi-Aspect Deep Active Attention Network for Healthcare Explainable Adoption

Depression is a serious illness that significantly affects the lives of those affected. Recent studies have looked at the possibility of detecting and diagnosing this mental disorder using user-generated data from various forms of online media. Therefore, we addressed the issue of detecting sadness in social media by focusing on terms in personal remarks. To overcome the limitations in classifying depression texts, this study aims to develop attention networks that use covert levels of self-attention. Since nodes/words can express the properties/emotions of their neighbors, this paper naturally assigns each node in a neighborhood its weight without performing costly matrix operations such as similarity or network architecture knowledge. The paper extended the emotion lexicon by using hypernyms. For this reason, our method is superior to the performance of the other designs. According to the results of our experiments, the emotion lexicon combined with an attention network achieves a ROC of 0.87 while maintaining its interpretability and transparency level. Subsequently, the learned embedding is used to display the contribution of each symptom to the activated word, and the psychiatrist is polled to obtain his qualitative agreement with this representation. By using unlabeled forum language, the method increases the rate at which depression symptoms can be identified from information in Internet forums.

Explainable Deep Attention Active Learning for Sentimental Analytics of Mental Disorder

With the increasing use of online mediums, Internet-delivered psychological treatments (IDPs) are becoming an essential tool for improving mental disorders. Online-based health therapies can help a large segment of the population with little resource investment. The task is greatly complicated by the overlapping emotions for specific mental health. Early adoption of a deep learning system presented severe difficulties, including ethical and legal considerations that contributed to a lack of trust. Modern models required highly interpretable, intuitive explanations that humans could understand. To achieve this, we present a deep attention model based on fuzzy classification that uses the linguistic features of patient texts to build emotional lexicons. In medical applications, a diversified dataset generates work. Active learning techniques are used to extend fuzzy rules and the learned dataset gradually. From this, the model can gain a reduction in labeling efforts in mental health applications. In this way, difficulties such as the amount of vocabulary per class, method of generation, the source of data, and the baseline for human performance level can be solved. Moreover, this work illustrates fuzzy explainability by using weighted terms. The proposed method incorporates a subset of unstructured data into the set for training and uses a similarity-based approach. The approach then updates the model training using the new training points in the subsequent cycle of the active learning mechanism. The cycle is repeated until the optimal solution is found. At this point, all unlabeled text is converted into the set for training. The experimental results show that the emotion-based enhancement improves test accuracy and helps develop quality criteria. In the blind test, the bidirectional LSTM architecture with an attention mechanism and fuzzy classification achieved an F1 score of 0.89.

How much does a Medical and Healthcare Products Regulatory Agency medical device alert for metal-on-metal hip arthroplasty patients really cost?

BACKGROUND

Many worldwide regulatory authorities recommend regular surveillance of metal-on-metal hip arthroplasty patients given high failure rates. However, concerns have been raised about whether such regular surveillance, which includes asymptomatic patients, is evidence-based and cost-effective. We determined: (1) the cost of implementing the 2015 MHRA surveillance in "at-risk" Birmingham Hip Resurfacing (BHR) patients; and (2) how many asymptomatic hips with adverse reactions to metal debris (ARMD) would have been missed without patient recall.

METHODS

All BHR patients eligible for the 2015 MHRA recall (all females, and males with head sizes ⩽46 mm, regardless of symptoms) at one centre were invited for review (hips = 707; patients = 593). All patients were investigated (Oxford Hip Score, radiographs, blood metal ions, and targeted cross-sectional imaging) and managed accordingly. Surveillance costs were calculated using finance department data.

RESULTS

The surveillance cost £105,921.79 (range £147.76-£257.50/patient). Radiographs (£39,598) and nurse practitioner time/assistance (£23,618) accounted for 60% of overall costs. 31 hips had ARMD on imaging (12 revised; 19 under surveillance). All revisions were symptomatic. 7 hips with ARMD under surveillance were asymptomatic and remain under regular review. The number needed to treat to avoid missing one asymptomatic ARMD case was 101 patients, representing a cost of £18,041 to avoid one asymptomatic case.

CONCLUSIONS

Implementing MHRA surveillance for "at-risk" BHR patients was extremely costly. The risk of asymptomatic ARMD was low with the BHR (1%), suggesting recommended follow-up in asymptomatic patients is not cost efficient. This raises concerns about the increasingly intensive surveillance recommended in the 2017 MHRA guidance for metal-on-metal hip patients.

Potential anti-acanthamoebic effects through inhibition of CYP51 by novel quinazolinones

Acanthamoeba spp. are free living amoebae which can give rise to Acanthamoeba keratitis and granulomatous amoebic encephalitis. The surface of Acanthamoeba contains ergosterol which is an important target for drug development against eukaryotic microorganisms. A library of ten functionally diverse quinazolinone derivatives (Q1-Q10) were synthesised to assess their activity against Acanthamoeba castellanii T4. The in-vitro effectiveness of these quinazolinones were investigated against Acanthamoeba castellanii by amoebicidal, excystation, host cell cytopathogenicity, and NADPH-cytochrome c reductase assays. Furthermore, wound healing capability was assessed at different time durations. Maximum inhibition at 50 μg/mL was recorded for compounds Q5, Q6 and Q8, while the compound Q3 did not exhibit amoebicidal effects at tested concentrations. Moreover, LDH assay was conducted to assess the cytotoxicity of quinazolinones against HaCaT cell line. The results of wound healing assay revealed that all compounds are not cytotoxic and are likely to promote wound healing at 10 μg/mL. The excystation assays revealed that these compounds significantly inhibit the morphological transformation of A. castellanii. Compound Q3, Q7 and Q8 elevated the level of NADPH-cytochrome c reductase up to five folds. Sterol 14alpha-demethylase (CYP51) a reference enzyme in ergosterol pathway was used as a potential target for anti-amoebic drugs. In this study using i-Tasser, the protein structure of Acanthamoeba castellanii (AcCYP51) was developed in comparison with Naegleria fowleri protein (NfCYP51) structure. The sequence alignment of both proteins has shown 42.72% identity. Compounds Q1-Q10 were then molecularly docked with the predicted AcCYP51. Out of ten quinazolinones, three compounds (Q3, Q7 and Q8) showed good binding activity within 3 Å of TYR 114. The in-silico study confirmed that these compounds are the inhibitor of CYP51 target site. This report presents several potential lead compounds belonging to quinazolinone derivatives for drug discovery against Acanthamoeba infections.

New synthetic phenylquinazoline derivatives induce apoptosis by targeting the pro-survival members of the BCL-2 family

Chemo-resistant cancer cells acquire robust growth potential through cell signaling mechanisms such as the down-regulation of tumor suppressors and the up-regulation of pro-survival proteins, respectively. To overcome chemo-resistance of cancer, small molecule drugs that interact with the cell signaling proteins to enhance sensitization of cancer cells toward cancer therapies are likely to be effective for the treatment of chemo-drug resistant cancer. To identify high potency small molecules, a series of ten novel phenylquinazoline derivatives were synthesized to determine their cellular effects in MCF-7 and MCF-7- cisplatin-resistant (CR) human breast cancer cells which led to the identification of two bioactive compounds, SMS-IV-20 and SMS-IV-40, that exhibited an elevated level of cytotoxicity against the human breast cancer cells and spheroid cells. In addition, both compounds enhanced chemo-sensitization of the human breast cancer cells that were genetically engineered to express the tumor suppressor and pro-apoptotic proteins, MOAP-1, Bax, and RASSF1a (MBR), suggesting that the compounds interact with the MBR signaling pathway. Furthermore, when MCF-7-CR cells were treated with SMS-IV-20 and SMS-IV-40 in the presence of ABT-737, a BCL-XL and BCL-2 inhibitor, enhanced chemo-sensitization was observed, suggesting SMS-IV-20 and SMS-IV-40 exert antagonistic activity to regulate the functional activity of BCL-2 and BCL-XL. Western blot analysis showed that both SMS-IV-20 and SMS-IV-40 induced down-regulation of BCL-2 or both BCl-2 and BCL-XL expression, respectively while promoting the release of mitochondrial Cytochrome C. Taken together, the data showed that SMS-IV-20 and SMS-IV-40 are potent activators of apoptosis that enhance chemo-sensitization through their antagonistic actions on the pro-survival activity of the BCl-2 family in human cancer cells.

Heterogeneous Energy-aware Load Balancing for Industry 4.0 and IoT Environments

With the improvement of global infrastructure, Cyber-Physical Systems (CPS) have become an important component of Industry 4.0. Both the application as well as the machine work together to improve the task of interdependencies. Machine learning methods in CPS require the monitoring of computational algorithms, including adopting optimizations, fine-tuning cyber systems, improving resource utilization, as well as reducing vulnerability as well as computation time. By leveraging the tremendous parallelism provided by General-Purpose Graphics Processing Units (GPGPU) as well as OpenCL, it is possible to dramatically reduce the execution time of data-parallel programs. However, when running an application with tiny amounts of data on a GPU, GPU resources are wasted because the program may not be able to fully utilize the GPU cores. This is because there is no mechanism for kernels to share a GPU due to the lack of OS support for GPUs. Optimal device selection is required to reduce the high power of the GPU. In this paper, we propose an energy reduction method for heterogeneous clustering. This study focuses on load balancing; resource-aware processor selection based on machine learning is performed using code features. The proposed method identifies energy-efficient kernel candidates (from the employment pool). Then, it selects a pair of kernel candidates from all possibilities that lead to a reduction in both energy consumption as well as execution time. Experimental results show that the proposed kernel approach reduces execution time by 2.23 times compared to a baseline scheduling system. Experiments have also shown that the execution time is 1.2 times faster than state-of-the-art approaches.

Hyper-Graph Attention Based Federated Learning Method For Mental Health Detection

Internet-Delivered Psychological Treatment (IDPT) has become necessary in the medical field. Deep neural networks (DNNs) require large, diverse patient populations to train models that achieve clinician-level performance. However, DNN models trained on limited datasets have poor clinical performance when used in a new location with different data. Thus, increasing the availability of diverse as well as distinct training data is vital. This study proposes a structural hypergraph as well as an emotional lexicon for word representation. An embedding model based on federated learning was developed for mental health symptom detection. The model treats text data as a collection of consecutive words. The model then learns a low-dimensional continuous vector while maintaining contextual linkage. The generated models with attention-based mechanisms as well as federated learning are then tested experimentally. Our strategy is suitable for vocabulary diversification, grammatical word representation, as well as dynamic lexicon analysis. The goal is to create semantic word representations using an attention network model. Later, clinical processes are used to mark the text by embedding it. Experimental results show the encoding of emotional words using the structural hypergraph. The 0.86 ROC was achieved using the bidirectional LSTM architecture with an attention mechanism.

Deep active reinforcement learning for privacy preserve data mining in 5G environments

Frequent pattern mining (FIM) identifies the most important patterns in data sets. However, due to the huge and high-dimensional nature of transactional data, classical pattern mining techniques suffer from the limitations of dimensions and data annotations. Recently, data mining while preserving privacy is considered as an important research area. Information privacy is a tradeoff that must be considered when using data. Through many years, privacy-preserving data mining (PPDM) made use of methods that are mostly based on heuristics. The operation of deletion was used to hide the sensitive information in PPDM. In this study, we used deep active learning to protect private and sensitive information. This paper combines entropy-based active learning with an attention-based approach to effectively hide sensitive patterns. The constructed models are then validated using high-dimensional transactional data with attention-based and active learning methods in a reinforcement environment. The results show that the proposed model can support and improve the effectiveness of decision-making by increasing the number of training instances through the use of a pooling technique and an entropy uncertainty measure. The proposed paradigm can achieve data sanitization by the hiding sensitive items and avoiding to hide the non-sensitive items. The model outperforms greedy, genetic, and particle swarm optimization approaches.

Ensemble-based deep meta learning for medical image segmentation

Deep learning methods have led to the state-of-the-art medical applications, such as image classification and segmentation. The data-driven deep learning application can help stakeholders for further collaboration. However, limited labeled data set limits the deep learning algorithms to be generalized for one domain into another. To handle the problem, meta-learning helps to solve this issue especially it can learn from a small set of data. We proposed a meta-learning-based image segmentation model that combines the learning of the state-of-the-art models and then used it to achieve domain adoption and high accuracy. Also, we proposed a prepossessing algorithm to increase the usability of the segment part and remove noise from the new test images. The proposed model can achieve 0.94 precision and 0.92 recall. The ability is to increase 3.3% among the state-of-the-art algorithms.

17 Establishment of Virtual Fracture Clinic in Princess Royal Hospital Telford: Experience and Recommendations During the First 9 Months

Introduction

Virtual fracture clinics (VFC) have been shown to be a safe and cost-effective way of managing outpatient referrals to the orthopaedic department. During the coronavirus pandemic there has been a push to reduce unnecessary patient contact whilst maintaining patient safety.

Method

A protocol was developed by the clinical team on how to manage common musculoskeletal presentations to A&E prior to COVID as part of routine service development. Patients broadly triaged into 4 categories; discharge with advice, referral to VFC, referral to face to face clinic or discussion with on call team. The first 9 months of data were analysed to assess types of injury seen and outcomes.

Results

In total 2489 patients were referred to VFC from internal and external sources. 734 patients were discharged without follow-up and 182 patients were discharged for physiotherapy review. Only 3 patients required admission. Regarding follow-ups, 431 patients had a virtual follow-up while 1036 of patients required further face to face follow up. 87 patients were triaged into subspecialty clinics. 37 patients were felt to have been referred inappropriately.

Conclusions

BOA guidelines state all patients must be reviewed within 72 hours of their orthopaedic injury. Implementation of a VFC allows this target to be achieved and at the same time reduce patient contact. Almost half the patients were discharged following VFC review, the remaining patients were followed up. This is especially relevant in the current pandemic where reducing unnecessary trips to hospital will benefit the patient and make the most of the resources available.

18 The Rise in Trauma & Orthopaedic Trainee-Led Research and Audit Collaborative Projects in the United Kingdom Since the Start of the COVID-19 Pandemic

Introduction

There has been a significant rise in trainee-led trauma & orthopaedic (T&O) multi-centre research collaborative projects globally. Since the start of the COVID-19 pandemic, more emphasis has been on global collaborative research efforts to tackle important research questions. The aim was to evaluate the number of T&O trainee-led research collaborative projects that took part since the start of the COVID-19 pandemic in the UK.

Method

A retrospective study that evaluated T&O trainee-led national collaborative projects within the UK since the start of the COVID-19 pandemic lockdown (March 2020 to June 2021). Our exclusion criteria included any regional collaborative projects, projects that were started pre-COVID and projects of other surgical specialities. The number of projects identified was compared to that in 2019.

Results

In 2019, 0 trainee-led collaborative projects were commenced nationally in the UK. Since the COVID-19 pandemic, we identified 10 trainee-led collaborative trauma & orthopaedic projects with 3 being published so far. The level of evidence ranged between 3 and 4.

Conclusions

Covid has placed significant challenges across healthcare. One positive aspect that has been noted is the increase in multi-centre trainee-led collaborative projects within the UK. Our study highlights the feasibility of a trainee-led high quality collaborative research projects in the UK, emphasising the growing contribution of trainees towards research. Wide-spread availability of new technological tools such as social media and Redcap® facilitates such projects in terms of recruitment and data collection. We would, therefore, recommend expanding this trainee-led collaborative platform across in Europe and Worldwide.

Fuzzy Contrast Set Based Deep Attention Network for Lexical Analysis and Mental Health Treatment

Internet-Delivered Psychological Treatments (IDPT) consider the mental problems based on Internet interaction. As the increases of the pandemic, more online tools are then widely used to result in evidence-based mental health serves. This increase helps to cover more population by using fewer resources for mental health treatments. Adaptivity and customization for the remedy routine can help to solve mental health issues speedily. In this research, we propose a fuzzy contrast-based model that uses the attention network for positional weighted words, classifies mental patient authored text into distinct symptoms. After that, the trained embedding is then used to label the mental data. Then attention network expands its lexicons to adapt to the usage of transfer learning techniques. The proposed model uses similarity and contrast sets to classify the weighted attention words. The fuzzy model then uses the sets to classify the mental health data into distinct classes. The method is compared with non-embedding and traditional techniques to demonstrate the proposed model. From the experiments, the feature vector can achieve a high ROC-Curve of 0.82 with nine symptoms problems.

Potent antibacterial activity of MXene–functionalized graphene nanocomposites

(A) SEM and (B) HRTEM images of 75% F graphene:25% Ti3C2Tx nanocomposite.

A Machine-Learning-Based System for Prediction of Cardiovascular and Chronic Respiratory Diseases

Cardiovascular and chronic respiratory diseases are global threats to public health and cause approximately 19 million deaths worldwide annually. This high mortality rate can be reduced with the use of technological advancements in medical science that can facilitate continuous monitoring of physiological parameters-blood pressure, cholesterol levels, blood glucose, etc. The futuristic values of these critical physiological or vital sign parameters not only enable in-time assistance from medical experts and caregivers but also help patients manage their health status by receiving relevant regular alerts/advice from healthcare practitioners. In this study, we propose a machine-learning-based prediction and classification system to determine futuristic values of related vital signs for both cardiovascular and chronic respiratory diseases. Based on the prediction of futuristic values, the proposed system can classify patients' health status to alarm the caregivers and medical experts. In this machine-learning-based prediction and classification model, we have used a real vital sign dataset. To predict the next 1-3 minutes of vital sign values, several regression techniques (i.e., linear regression and polynomial regression of degrees 2, 3, and 4) have been tested. For caregivers, a 60-second prediction and to facilitate emergency medical assistance, a 3-minute prediction of vital signs is used. Based on the predicted vital signs values, the patient's overall health is assessed using three machine learning classifiers, i.e., Support Vector Machine (SVM), Naive Bayes, and Decision Tree. Our results show that the Decision Tree can correctly classify a patient's health status based on abnormal vital sign values and is helpful in timely medical care to the patients.

TP8.2.7 The Post Graduate Virtual Learning Environment: an effective platform for the delivery of a surgical teaching programme in the West Midlands

Aim

The Postgraduate Virtual Learning Environment (PGVLE) is a digital platform developed by HEEWM in response to the COVID-19 pandemic to deliver a virtual teaching programme to surgical trainees. The programme is delivered through the BigBlueButton; an integrated virtual classroom. All teaching sessions are recorded and archived to allow trainees to review content at their convenience. We performed a contemporaneous study to review the effectiveness and quality of the platform in delivering teaching and suggest its future role in the surgical curriculum.

Method

Anonymised feedback was gathered of trainee’s perspective of the platform experience, the quality of teaching and the archived content. All trainees were General Surgery higher trainees (HST) (ST3-ST8). The data from sequential teaching days was analysed.

Results

Of 90 HST, on average 40 attended each monthly training day (consistent with pre-COVID attendance). 122 trainee responses were completed. 68% of respondents were between ST3-ST5. 91% rated the administration and delivery of the teaching sessions as excellent or very good. 16% of trainees watched the archived sessions after the teaching day of which 46% felt it met their educational expectations.

Conclusions

The PGVLE is an effective platform for the delivery of a virtual surgical teaching programme. It met with high levels of trainee satisfaction in the context of the pandemic. The archived content provides advantages to consolidation of learning. It is thought that the PGVLE platform will become a key feature of the surgical training programme in a hybrid learning model, related to relevant curricula, in the future.

511 Organising A Surgical Conference During The COVID-19 Pandemic – Is It ‘Virtually’ The Same?

Introduction

Surgical conferences are invaluable events for healthcare professionals; they provide opportunities to engage with upcoming scientific discoveries, network professionally with peers as well as expand learning through lectures and workshops. For medical students, conferences provide an opportunity to expand understanding beyond the undergraduate curriculum in an interactive manner. COVID-19 has caused disruption to the organisation and attendance of in-person conferences (IPCs). Virtual conferences (VCs) offer a viable solution, allowing delegates to attend from the comfort of their own homes.

Method

The aim of our study was to evaluate an organised VC and explore the perceived benefits and limitations of VCs compared to IPCs. A virtual one-day trauma & orthopaedics (T&O) conference was organised involving lectures, workshops, poster, and oral presentations. Anonymous questionnaire forms were distributed to delegates following the conference to assess the aims of our paper.

Results

From 106 responses, 96.2% rated the conference as ‘Excellent’ or ‘Good’ with 92.5% stating that it increased their passion for T&O surgery. Based on a five-point Likert scale (5= strongly agree, 1= strongly disagree), mean score of agreement for preferring VCs to IPCs was 3.30(± 1.24). Key advantages of the VC were a lower cost (70.8%) and not having to travel (77.4%), whereas the main limitation was the inability to participate in hands-on workshops (84.9%).

Conclusions

Despite the success of our VC, delegate feedback indicates a mixed response comparing VCs to IPCs. We share our findings to encourage similar events to be organised and for other specialties.

483 A Quality Improvement Project: Novel Electronic Operative Note Templates to Improve the Continuity of Post-Operative Patient Care

Introduction

Good Surgical Practice from RCS England encourages the use of e-health records and detailed typed operative notes. The Covid-19 pandemic has led to multi-site operating. ENT operations in our trust were split over three sites including the private sector leading to potential disruption in continuity of patient care. Physical operation notes are difficult to access in emergencies, telephonic clinics or for audit purposes. We aim to have operative notes available on patients’ e-records which adhere to RCSEng guidelines.

Method

In this QIP, we reviewed all ENT operations over a retrospective one-month period recording percentage of notes uploaded to patient e-record and the number of surgeons in theatre. We created two novel RCSEng compliant e-operative notes with a user guide, generic and tonsillectomy-specific, and prospectively collected data to complete the cycle.

Results

261 patients were included in both study periods. Only 36/134(27%) had e-operative pre-intervention improving to 71/127(56%) post-intervention. In the latter period, 76% of operations included a registrar and were more likely to have e-operative notes(72%) compared to when a consultant was operating alone(6%). There was low uptake of our tonsillectomy e-proforma(33%).

Conclusions

Our QIP has already proved effective with our templates increasing operative documentation on e-records. Increased use of e-template was more likely with the presence of a registrar in theatre. Room for improvement remains and we will re-audit after the introduction of further user-friendly operative templates and IT training. This QIP has also revealed additional operative training opportunities of which registrars can take advantage.

1434 An Audit of Surgical Consent Standards in Patients Undergoing Elective ENT Surgery

Aim

Good Surgical Practice (RCS England) and GMC guidelines inform a surgeon’s practice in the consent process for an operation. Since the Covid-19 pandemic, many surgical departments have converted from face-to-face to telephonic consultations. The clinic letter is of increased importance given that it forms a key part of the medical record which the patient should receive to ensure sufficient time and information to make an informed decision.

Method

Clinic letters of patients undergoing elective ENT surgery at our trust over a four-week period were examined in this retrospective audit of compliance with RCSEng and GMC guidelines. Additional data was collected on clinician grade and proportion of letters sent to patients. Patients rated satisfaction with consultation on a five-point Likert scale.

Results

135 eligible patients were included in our audit and the majority were listed by a consultant (57%). In all domains, consultant letters were more likely to be comprehensive as compared to registrars. Overall quality of clinic letters was highly variable regarding documentation of diagnosis (52%), surgical risks (50%), discussion of alternative or no treatment (30%) and registrar discussion with consultant (31%). There was also a stark difference between registrars and consultants sending patients copies of clinic letters (10% vs 47%). Only 10% of patients received a leaflet on their condition. 90% of patients were either satisfied or very satisfied with their clinic consultation.

Conclusions

Refresher sessions on consent, updated template letters and increased provision of patient information leaflets will be introduced to the ENT department, and improvements monitored with further re-audit.