Explainable Mortality Prediction Model for Congestive Heart Failure with Nature-Based Feature Selection Method

A mortality prediction model can be a great tool to assist physicians in decision making in the intensive care unit (ICU) in order to ensure optimal allocation of ICU resources according to the patient's health conditions. The entire world witnessed a severe ICU patient capacity crisis a few years ago during the COVID-19 pandemic. Various widely utilized machine learning (ML) models in this research field can provide poor performance due to a lack of proper feature selection. Despite the fact that nature-based algorithms in other sectors perform well for feature selection, no comparative study on the performance of nature-based algorithms in feature selection has been conducted in the ICU mortality prediction field. Therefore, in this research, a comparison of the performance of ML models with and without feature selection was performed. In addition, explainable artificial intelligence (AI) was used to examine the contribution of features to the decision-making process. Explainable AI focuses on establishing transparency and traceability for statistical black-box machine learning techniques. Explainable AI is essential in the medical industry to foster public confidence and trust in machine learning model predictions. Three nature-based algorithms, namely the flower pollination algorithm (FPA), particle swarm algorithm (PSO), and genetic algorithm (GA), were used in this study. For the classification job, the most widely used and diversified classifiers from the literature were used, including logistic regression (LR), decision tree (DT) classifier, the gradient boosting (GB) algorithm, and the random forest (RF) algorithm. The Medical Information Mart for Intensive Care III (MIMIC-III) dataset was used to collect data on heart failure patients. On the MIMIC-III dataset, it was discovered that feature selection significantly improved the performance of the described ML models. Without applying any feature selection process on the MIMIC-III heart failure patient dataset, the accuracy of the four mentioned ML models, namely LR, DT, RF, and GB was 69.9%, 82.5%, 90.6%, and 91.0%, respectively, whereas with feature selection in combination with the FPA, the accuracy increased to 71.6%, 84.8%, 92.8%, and 91.1%, respectively, for the same dataset. Again, the FPA showed the highest area under the receiver operating characteristic (AUROC) value of 83.0% with the RF algorithm among all other algorithms utilized in this study. Thus, it can be concluded that the use of feature selection with FPA has a profound impact on the outcome of ML models. Shapley additive explanation (SHAP) was used in this study to interpret the ML models. SHAP was used in this study because it offers mathematical assurances for the precision and consistency of explanations. It is trustworthy and suitable for both local and global explanations. It was found that the features that were selected by SHAP as most important were also most common with the features selected by the FPA. Therefore, we hope that this study will help physicians to predict ICU mortality for heart failure patients with a limited number of features and with high accuracy.

Should COVID-19 pandemic mitigations in the myeloma clinic continue? A summary of patient opinions

Introduction: The COVID-19 pandemic necessitated multiple changes to the format of myeloma clinics to minimise the risk of infection among patients and staff. These included changing in-person clinic appointments to telephone appointments when there was no medical need for face-to- face review and instituting a courier service for delivery of oral or self-administered medications. As COVID-19 restrictions relaxed, we sought to investigate the acceptability of these changes to our patients and to determine which, if any, of the new arrangements should continue. Method(s): Patients who attended the Myeloma Clinic at The Royal Marsden Hospital, both in-person and by telephone, on four separate dates in August and September 2022 were asked to complete a questionnaire to provide their opinions using a combination of multiple-choice, Likert scale and free-text questions. These covered the main domains of change outlined above along with questions about blood test location and attendance with family and friends. Result(s): Questionnaires were returned by 59 patients, 11 relating to in-person appointments and 48 to telephone appointments. 86.0% of patients were in favour of continuing the option of telephone appointments, with many highlighting their convenience and the avoidance of long travel and waiting times, with some also mentioning their COVID-19 security. However, a number of patients expressed concerns including communication difficulties, the inability to effectively assess physical health with an examination and a lack of reassurance. Furthermore, those who attended in-person appointments felt they were very COVID-secure, assigning them a mean of score of 4.5, where 1 was very insecure and 5 very secure. Several suggested that the optimum schedule would include regular telephone appointments with occasional in-person meetings. Interestingly, only 25.5% of patients wanted a video calling option. Patients were also very positive about receiving medications by courier, with 94.1% of patients receiving their medications within two working days of their clinic appointment. 81.8% of patients expressed a wish for this option to continue, highlighting the increased convenience and reduction in waiting times. Conclusion(s): These results suggest that changes made to the Myeloma Clinic in response to the COVID-19 pandemic have improved the patient experience. A mixture of telephone and in-person appointments may be preferable for this cohort of patients, many of whom require regular appointments for chemotherapy approval but are medically stable, and whose frailty makes long travel and waiting times challenging. These findings have implications for the planning of myeloma clinics across the UK.

Emotional robustness in times of crisis: the effects of venture funding on the digital communication styles of entrepreneurs

PurposeEntrepreneurial communication describes the communication activities of entrepreneurs and is an essential tool for entrepreneurs to build relationships. However, there is a lack of research regarding how entrepreneurs adapt their communication styles in times of crisis. Nevertheless, entrepreneurial communication during a crisis is essential because entrepreneurs must continue communicating with their stakeholders and be visible. In this regard, communication has the central aim of preventing the startup from suffering any damage that may result from the crisis. Thus, the present paper explores potential shifts in the communication styles of entrepreneurs during the first wave of the COVID-19 pandemic.Design/methodology/approachThe authors examined the digital footprints of 780 entrepreneurs based in the USA on the social network Twitter. This study used a longitudinal dataset with the software Linguistic Inquiry and Word Count (LIWC) to analyze 110,283 tweets sent pre-crisis and during the first wave of COVID-19.FindingsThe results of the exploratory analysis revealed a connection between crisis and both analytical thinking and emotional responses. In the case of emotions, the results also suggest that entrepreneurs who had already received funding from venture capital investors remained emotionally robust during the crisis, as evidenced by the expression of more positive emotions compared to entrepreneurs without funding.Originality/valueThis study contributes to the understanding of entrepreneurial communication and adds the context of an exogenous shock to this research stream. Furthermore, this study highlights the effects of venture funding on the digital communication style of entrepreneurs, especially in the context of expressed emotions, and suggests emotional robustness for these entrepreneurs.

Detecting COVID-19 from Lung Computed Tomography Images: A Swarm Optimised Artificial Neural Network Approach

COVID-19 has affected many people across the globe. Though vaccines are available now, early detection of the disease plays a vital role in the better management of COVID-19 patients. An Artificial Neural Network (ANN) powered Computer Aided Diagnosis (CAD) system can automate the detection pipeline accounting for accurate diagnosis, overcoming the limitations of manual methods. This work proposes a CAD system for COVID-19 that detects and classifies abnormalities in lung CT images using Artificial Bee Colony (ABC) optimised ANN (ABCNN). The proposed ABCNN approach works by segmenting the suspicious regions from the CT images of non-COVID and COVID patients using an ABC optimised region growing process and extracting the texture and intensity features from those suspicious regions. Further, an optimised ANN model whose input features, initial weights and hidden nodes are optimised using ABC optimisation classifies those abnormal regions into COVID and non-COVID classes. The proposed ABCNN approach is evaluated using the lung CT images collected from the public datasets. In comparison to other available techniques, the proposed ABCNN approach achieved a high classification accuracy of 92.37% when evaluated using a set of 470 lung CT images. Author

COVID-19 Chest X-Ray Classification with Augmented GAN

Coronavirus disease (COVID-19) is a major concern now. According to the Globe Health Organization, the coronavirus (COVID-19) epidemic is straining healthcare systems worldwide (WHO). Early-stage detection using artificial intelligence of this virus will help in the fast recovery. Early identification of this infection utilizing artificial intelligence will aid in its quick recovery. In the fight against COVID-19, it’s critical to have a positive chest X-ray for infected patients. Early research suggests that chest X-ray abnormalities in COVID-19 patients are common. Using augmented chest X-ray images, this research proposes a novel model for identifying the presence of COVID-19. As medical images are sensitive, GAN (Generative Adversarial Networks) augments chest X-Ray images. Augmented images are classified through our proposed model. Then classified images are segmented for validation. GAN augmentation model consists of a generator and a discriminator. Convolutional neural networks (CNNs) based classification model needs a substantial amount of training data. Augmentation increased dataset into 10x amount. Before augmentation, our initial model received 94.42% accuracy, and after augmentation, our final model accuracy raised to 98.58%. We hope our model will detect COVID-19 presence accurately through X-Ray images. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Inverted bell-curve-based ensemble of deep learning models for detection of COVID-19 from chest X-rays

Novel Coronavirus 2019 disease or COVID-19 is a viral disease caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). The use of chest X-rays (CXRs) has become an important practice to assist in the diagnosis of COVID-19 as they can be used to detect the abnormalities developed in the infected patients’ lungs. With the fast spread of the disease, many researchers across the world are striving to use several deep learning-based systems to identify the COVID-19 from such CXR images. To this end, we propose an inverted bell-curve-based ensemble of deep learning models for the detection of COVID-19 from CXR images. We first use a selection of models pretrained on ImageNet dataset and use the concept of transfer learning to retrain them with CXR datasets. Then the trained models are combined with the proposed inverted bell curve weighted ensemble method, where the output of each classifier is assigned a weight, and the final prediction is done by performing a weighted average of those outputs. We evaluate the proposed method on two publicly available datasets: the COVID-19 Radiography Database and the IEEE COVID Chest X-ray Dataset. The accuracy, F1 score and the AUC ROC achieved by the proposed method are 99.66%, 99.75% and 99.99%, respectively, in the first dataset, and, 99.84%, 99.81% and 99.99%, respectively, in the other dataset. Experimental results ensure that the use of transfer learning-based models and their combination using the proposed ensemble method result in improved predictions of COVID-19 in CXRs.

ACCU3RATE: A mobile health application rating scale based on user reviews.

BACKGROUND: Over the last decade, mobile health applications (mHealth App) have evolved exponentially to assess and support our health and well-being. OBJECTIVE: This paper presents an Artificial Intelligence (AI)-enabled mHealth app rating tool, called ACCU3RATE, which takes multidimensional measures such as user star rating, user review and features declared by the developer to generate the rating of an app. However, currently, there is very little conceptual understanding on how user reviews affect app rating from a multi-dimensional perspective. This study applies AI-based text mining technique to develop more comprehensive understanding of user feedback based on several important factors, determining the mHealth app ratings. METHOD: Based on the literature, six variables were identified that influence the mHealth app rating scale. These factors are user star rating, user text review, user interface (UI) design, functionality, security and privacy, and clinical approval. Natural Language Toolkit package is used for interpreting text and to identify the App users' sentiment. Additional considerations were accessibility, protection and privacy, UI design for people living with physical disability. Moreover, the details of clinical approval, if exists, were taken from the developer's statement. Finally, we fused all the inputs using fuzzy logic to calculate the new app rating score. RESULTS AND CONCLUSIONS: ACCU3RATE concentrates on heart related Apps found in the play store and App gallery. The findings indicate the efficacy of the proposed method as opposed to the current device scale. This study has implications for both App developers and consumers who are using mHealth Apps to monitor and track their health. The performance evaluation shows that the proposed mHealth scale has shown excellent reliability as well as internal consistency of the scale, and high inter-rater reliability index. It has also been noticed that the fuzzy based rating scale, as in ACCU3RATE, matches more closely to the rating performed by experts.

Fitness, a UK Myeloma Research Alliance (UK-MRA) Frailty-Adjusted Therapy Study, Supports the Feasibility of Recruiting Frail Newly Diagnosed Myeloma Patients to Large Clinical Trials

Background Although the median age of patients with newly diagnosed multiple myeloma (MM) is 70-74 years, recruitment of frail older patients to clinical trials is poor. The International Myeloma Working Group (IMWG) frailty score predicts survival, adverse events and treatment tolerability using age, the Katz Activity of Daily Living, the Lawton Instrumental Activity of Daily Living, and the Charlson Comorbidity Index, rather than age alone. Despite IMWG score prognostic biomarker capability, to date no evidence exists of its predictive biomarker potential. The UK-MRA Myeloma Risk Profile (MRP) has also been shown in both clinical trial and real-world populations to be a prognostic biomarker in transplant ineligible patients but prospective comparisons of the two scores have not been previously conducted. Study Design/Methods The FiTNEss trial (Myeloma XIV, NCT03720041, Figure 1A) is a UK-MRA phase III, multi-centre, randomised controlled trial for newly diagnosed MM patients not suitable for stem cell transplant. The primary objectives are 1) to compare early treatment cessation (<60 days from randomisation) between patients randomised to standard (reactive) and frailty-adjusted (adaptive, based on IMWG score) induction therapy delivery with the triplet ixazomib, lenalidomide and dexamethasone (IRd) 2) to compare progression free survival for maintenance lenalidomide plus placebo (R) and lenalidomide plus ixazomib (IR). The FiTNEss trial is designed as an all-comers study with few exclusion criteria other than necessary for safety including some haematological and biochemical parameters, but there is no exclusion based on renal function. Patients with grade 2 or greater baseline peripheral neuropathy, current systemic infection or recent surgery or other cancer are excluded. Here we report the demographics for the first patients recruited, including IMWG frailty assessments and MRP to demonstrate the feasibility of recruiting frail patients to randomised phase III clinical trials. Results The FiTNEss trial opened on 04/08/2020 during the second wave of the COVID-19 pandemic in the UK. At the time of data cut off (14/07/2021) recruitment is active at 84 sites, with 180 patients randomised. Baseline characteristics for the randomised patients are shown in Figure 1B. The median age of patients is 77 years (range 64, 93) with 36.1% aged 76-80 and 26.1% over 80. In keeping with the older patient population 26.6% have an ECOG performance status of 2 or 3 and 31.7% ISS stage III. The IMWG frailty classification at baseline is FIT 43/180 (23.9%), UNFIT 53/180 (29.4%) and FRAIL 84/180 (46.7%). The effect of using age groups on the definition of patient frailty was explored. The IMWG frailty score defines all patients over 80 as FRAIL whilst an age of 76-80 contributes one point to the score. An analysis of patients' frailty was repeated with the contribution of age removed. For those aged over 80 years (n=47, 100% FRAIL) we found that 20 (42.6%) would have been re-classified as FIT and 18 (38.3%) as UNFIT, with only 9 (19.2%) retaining the FRAIL category. For those aged 76-80 (n=65, 53.8% UNFIT, 46.2% FRAIL) all 35 patients previously classified as UNFIT became FIT (53.8%) whilst 19 (29.2%) classed as FRAIL became UNFIT with 11 (16.9%) remaining FRAIL. The MRP classification, using age as a continuous variable, was Low-risk 45/180 (25.0%), Medium-risk 46/180 (25.6%), High-risk 75/180 (41.7%) and not available for 14/180 (7.8%) patients. Concordance between the IMWG frailty score and the MRP occurred in 48.9% of patients (88/180). 37.2% of FIT patients were classified as MRP Low-risk, 32.1% of UNFIT patients as MRP Medium-risk and 65.5% of FRAIL patients as MRP High-risk. Discussion The FiTNEss trial demonstrates the feasibility of recruiting older, less fit patients to clinical trials. Recruitment of patients classified as FRAIL was very high despite the COVID pandemic, likely due to the all-oral nature of the regimen under investigation enabling patients to avoid attendance at hospital day units for treatment and associa ed exposure risk. In the population recruited to date we found age to be a key contributor to the FRAIL category of the IMWG frailty score. Concordance between IMWG frailty score and MRP was highest in FRAIL/High-risk patients. The first interim analysis of the primary objectives is planned when 50% of required participants for R1 have reached 60 days post R1, which is anticipated in Q2 of 2022. [Formula presented] Disclosures: Cook: Amgen: Consultancy, Honoraria, Research Funding;BMS: Consultancy, Honoraria, Research Funding;Sanofi: Consultancy, Honoraria;Karyopharm: Consultancy, Honoraria;Roche: Consultancy, Honoraria;Pfizer: Consultancy, Honoraria;Oncopeptides: Consultancy, Honoraria;Takeda: Consultancy, Honoraria, Research Funding;Janssen: Consultancy, Honoraria, Research Funding. Pawlyn: Sanofi: Honoraria, Membership on an entity's Board of Directors or advisory committees;Celgene / BMS: Honoraria, Membership on an entity's Board of Directors or advisory committees;Janssen: Honoraria, Membership on an entity's Board of Directors or advisory committees;Amgen: Honoraria. Royle: BMS: Research Funding;Merck Sharpe and Dohme: Research Funding;Amgen: Research Funding;Takeda: Research Funding. Coulson: BMS / Celgene: Honoraria;Merck Sharpe and Dohme: Research Funding;Amgen: Research Funding;Takeda: Research Funding. Jenner: BMS/Celgene: Consultancy, Honoraria, Speakers Bureau;Janssen: Consultancy, Honoraria, Speakers Bureau;Pfizer: Consultancy;Takeda: Consultancy. Kishore: Sanofi: Other: Attending fees;Celgene: Other: Attending fees;Takeda: Other: Attending fees;Jannsen: Other: Attending fees. Rabin: BMS / Celgene: Consultancy, Honoraria, Other: Travel support for meetings;Takeda: Consultancy, Honoraria, Other: Travel support for meetings;Janssen: Consultancy, Honoraria, Other: Travel support for meetings. Best: BMS/Celgene: Research Funding;Merck Sharpe and Dohme: Research Funding;Amgen: Research Funding;Takeda: Research Funding. Gillson: BMS / Celgene: Research Funding;Meck Sharpe and Dohme: Research Funding;Amgen: Research Funding;Takeda: Research Funding. Henderson: Takeda: Research Funding;Amgen: Research Funding;Merck Sharpe and Dohme: Research Funding;BMS / Celgene: Research Funding. Olivier: Merck Sharpe and Dohme: Research Funding;Takeda: Research Funding;Amgen: Research Funding;Celgene / BMS: Research Funding. Kaiser: AbbVie: Consultancy;GSK: Consultancy;Karyopharm: Consultancy, Research Funding;Pfizer: Consultancy;Amgen: Honoraria;Seattle Genetics: Consultancy;Takeda: Consultancy, Other: Educational support;Janssen: Consultancy, Other: Educational support, Research Funding;BMS/Celgene: Consultancy, Other: Travel support, Research Funding. Drayson: Abingdon Health: Current holder of individual stocks in a privately-held company. Jones: Janssen: Honoraria;BMS/Celgene: Other: Conference fees. Cairns: Merck Sharpe and Dohme: Research Funding;Amgen: Research Funding;Takeda: Research Funding;Celgene / BMS: Other: travel support, Research Funding. Jackson: celgene BMS: Consultancy, Honoraria, Research Funding, Speakers Bureau;amgen: Consultancy, Honoraria, Speakers Bureau;takeda: Consultancy, Honoraria, Research Funding, Speakers Bureau;GSK: Consultancy, Honoraria, Speakers Bureau;J and J: Consultancy, Honoraria, Speakers Bureau;oncopeptides: Consultancy;Sanofi: Honoraria, Speakers Bureau. OffLabel Disclosure: Frailty-score adapted dosing strategies

Response to COVID-19 Vaccines in Patients Receiving Intensified Post-ASCT Therapy with Daratumumab, Lenalidomide, Bortezomib (Dara-VR) Due to Ultra-High Risk (UHiR) Newly Diagnosed Myeloma (NDMM) or Primary Plasma Cell Leukemia (pPCL): Exploratory Analysis of the UK Optimum/Muknine Trial

Background: Successful vaccination against SARS-CoV2 is highly effective in preventing serious COVID-19 illness and is particularly recommended for at risk populations including patients with multiple myeloma (MM). However, there is uncertainty to which extent modern intensified therapies targeting plasma cell features might attenuate vaccination responses;some early vaccination recommendations for MM have proposed extended treatment breaks of several weeks to maximise vaccination success. Such an approach can be challenging in UHiR MM and pPCL, where maintaining treatment intensity is hallmark for preventing rapid relapse of the aggressive tumor. To address this uncertainty, we measured post-vaccination serological responses in patients treated uniformly with intensified Dara-VR consolidation and Dara-R maintenance post-ASCT for UHiR NDMM or pPCL in the UK OPTIMUM/MUKnine trial (NCT03188172). Methods: Between Sep 2017 and Jul 2019, 107 patients with UHiR NDMM or pPCL were recruited to OPTIMUM and received intensified post-ASCT consolidation with Dara-VR(d) for 18 cycles followed by maintenance with Dara-R until progression. In an exploratory analysis, centrally stored serum samples available for patients with a completed and documented vaccination history of two doses of an anti-SARS-CoV2 vaccine were analyzed for serological vaccine responses Total IgG/IgA/IgM Anti-SARS-CoV-2 spike glycoprotein was measured by ELISA (MK654;The Binding Site). As per UK national guidance and local availability, patients received two vaccine doses 12 weeks apart of either tozinameran (Pfizer/Biontech) or vaxzevria (AstraZeneca);serum taken at least 3 weeks after patients received their second dose was analyzed. Results were correlated with baseline characteristics and annotated with treatment and response data. Patient with available matched serological and vaccination status data at time of data cut-off (09 JUL 2021) were included. Collection of vaccination status data is ongoing and updated results comprising additional patients enrolled in OPTIMUM, as well as antigen levels, will be presented. Data will also comprise longitudinal antibody level measurements for patient with available sequential material. Results: Serological vaccine response data was available for 40 OPTIMUM patients with documented completed double vaccination status. Median patient age was 58.5 years (range 39-70) and clinical and molecular tumor features were similar to the overall trial safety population. All patients had received their second dose before June 2021. Of the 40 patients, 42.5% had received tozinameran and 57.5% vaxzevria. Baseline characteristics of the two groups were comparable. At time of second vaccine dose, 55% of patients were receiving Dara-VR consolidation treatment and 45% Dara-R maintenance. There was no recommendation to pause trial treatment for purposes of vaccination and no extended times off treatment for this reason were reported. Overall, 72.5% of patients had a positive vaccine antibody level as per manufacturer cut-point for high specificity evidence of antigen exposure (infection or vaccine). The response rate was nominally higher for vaxzevria (91.3%) than for tozinameran (47.1%), a dysbalance that will be further investigated with ongoing extension of the cohort. Of note, 90% of patients analyzed had reached a complete response (CR) of their MM prior to being vaccinated, and the majority of patients not in CR had a positive vaccine response. Response rates were nominally slightly higher in patients in receipt of Dara-R maintenance at time of second dose with 77.8% compared to Dara-VR consolidation with 68.2%. Conclusions: These results show a high serological response rate to COVID-19 vaccination in UHiR MM patients receiving intensified post-ASCT consolidation and maintenance therapy in remission. Findings suggest that continuation of intensified post-ASCT therapy for patients with aggressive tumors and a high risk of relapse are compatible with serological responses to commonly used COVID-19 vaccines. Disclosures: Jen er: Janssen: Consultancy, Honoraria, Speakers Bureau;BMS/Celgene: Consultancy, Honoraria, Speakers Bureau;Takeda: Consultancy;Pfizer: Consultancy. Hall: BMS/Celgene: Research Funding;Janssen: Research Funding. Garg: University Hospital Leicester: Current Employment;Takeda Janssen Novartis Sanofi: Other: Travel Accommodations, Expenses;Amgen Janssen Novartis Sanofi Takeda: Honoraria. Jackson: J and J: Consultancy, Honoraria, Speakers Bureau;GSK: Consultancy, Honoraria, Speakers Bureau;takeda: Consultancy, Honoraria, Research Funding, Speakers Bureau;amgen: Consultancy, Honoraria, Speakers Bureau;celgene BMS: Consultancy, Honoraria, Research Funding, Speakers Bureau;oncopeptides: Consultancy;Sanofi: Honoraria, Speakers Bureau. Pratt: Binding Site: Consultancy;BMS/Celgene: Consultancy;Gilead: Consultancy;Janssen: Consultancy;Takeda: Consultancy;Amgen: Consultancy. Cook: Karyopharm: Consultancy;Sanofi: Consultancy;Takeda: Consultancy, Research Funding;Janssen: Consultancy, Research Funding;BMS/Celgene: Consultancy, Research Funding;Amgen: Consultancy. Drayson: Abingdon Health: Current holder of individual stocks in a privately-held company. Kaiser: BMS/Celgene: Consultancy, Other: Travel support, Research Funding;Janssen: Consultancy, Other: Educational support, Research Funding;GSK: Consultancy;Karyopharm: Consultancy, Research Funding;Pfizer: Consultancy;Amgen: Honoraria;Seattle Genetics: Consultancy;Takeda: Consultancy, Other: Educational support;AbbVie: Consultancy.

Indoor Navigation Support System for Patients with Neurodegenerative Diseases

A handheld device (such as a smartphone/wearable) can be used for tracking and delivering navigation within a building using a wireless interface (such as WiFi or Bluetooth Low Energy), in situations when a traditional navigation system (such as a global positioning system) is unable to function effectively. In this paper, we present an indoor navigation system based on a combination of wall-mounted wireless sensors, a mobile health application (mHealth app), and WiFi/Bluetooth beacons. Such a system can be used to track and trace people with neurological disorders, such as Alzheimer’s disease (AD) patients, throughout the hospital complex. The Contact tracing is accomplished by using Bluetooth low-energy beacons to detect and monitor the possibilities of those who have been exposed to communicable diseases such as COVID-19. The communication flow between the mHealth app and the cloud-based framework is explained elaborately in the paper. The system provides a real-time remote monitoring system for primary medical care in cases where relatives of Alzheimer’s patients and doctors are having complications that may demand medical care or hospitalization. The proposed indoor navigation system has been found to be useful in assisting patients with Alzheimer’s disease (AD) while in the hospital building. © 2021, Springer Nature Switzerland AG.

Towards Artificial Intelligence Driven Stress monitoring for mental wellbeing tracking During COVID-19

The stresses and patterns of life are often demanding and require physical and psychological actions to support themselves. An individual responds to mental stresses that is potentially detrimental to health. The mental stress may result hormonal imbalance and noxious stimulus in the body. The 2 (SARS-COV-2) or COVID-19 infection not only stopped people's daily routine, but also created many political, social, financial, psychological and health problems. Mental stress has become common during this pandemic with limited opportunity to reach outhealth professionals in person. We have proposed artificial intelligence driven cloud based self-stress detection model which takes physiological signals such as Galvanic Skin Response, Heart Rate Variability, Peripheral Capillary Oxygen Saturation to determine the stress level. The sensors are embedded into a wearable device and collects physiological signals and thereby detect stress level of an individual. Finally, we have also suggested some recommendations to manage stress for any individual during COVID-19 for their wellbeing.

COVID-19 Detection Using Chest X-Ray Images with a RegNet Structured Deep Learning Model

AI-based medical image processing has made significant progress, and it has a significant impact on biomedical research. Among the imaging variants, Chest x-rays imaging is cheap, simple, and can be used to detect influenza, tuberculosis, and various other illnesses. Researchers discovered that coronavirus spreads through the lungs, causing severe injuries during the COVID19 pandemic. As a result, chest x-rays can be used to detect COVID-19, making it a more robust detection method. In this paper, a RegNet hierarchical deep learning-based model has been proposed to detect COVID-19 positive and negative cases using CXI. The RegNet structure is designed to develop a model with a small number of epochs and parameters. The performance measurement found that the model takes five periods to reach a total accuracy of 98.08%. To test the model, we used two sets of data. The first dataset consists of 1200 COVID-19 positive CXRs and 1,341 COVID-19 negative CXRs, and the second dataset consists of 195 COVID-19 positive CXRs and 2,000 COVID-19 negative CXRs;all of these are publicly available. We obtained precision of 99.02% and 97.13% for these datasets, respectively. As a result of this finding, the proposed approach could be used for mass screening, and, as far as we are aware, the results achieved indicate that this model could be used as a screen guide. © 2021, Springer Nature Switzerland AG.

Learning Through One Shot: A Phase by Phase Approach for COVID-19 Chest X-ray Classification

Today globally, coronavirus disease (COVID-19) has infected over more than 81 million people and killed at least 1771K. This is an infectious disease caused by a newly discovered coronavirus. As a result, scientists and researchers around the globe are now trying to find out the path to battle this disease in the most effective way. Chest X-rays are a widely available modality for immediate care in diagnosing COVID-19. Detection and diagnosis of COVID-19 chest X-rays would be more precise for the current situation. In this paper, a phase by phase approach using the concept of one shot learning is introduced for effective classification of chest X-ray images. The proposed method utilizes the application of Entropy for selecting best describing images for effective learning purposes. The proposed model is evaluated on a publically available large dataset of size 24614 images comprising of three classes viz COVID-19, Normal and Non-COVID. The obtained results are promising and encouraging.

Security Threats and Artificial Intelligence Based Countermeasures for Internet of Things Networks: A Comprehensive Survey

The Internet of Things (IoT) has emerged as a technology capable of connecting heterogeneous nodes/objects, such as people, devices, infrastructure, and makes our daily lives simpler, safer, and fruitful. Being part of a large network of heterogeneous devices, these nodes are typically resource-constrained and became the weakest link to the cyber attacker. Classical encryption techniques have been employed to ensure the data security of the IoT network. However, high-level encryption techniques cannot be employed in IoT devices due to the limitation of resources. In addition, node security is still a challenge for network engineers. Thus, we need to explore a complete solution for IoT networks that can ensure nodes and data security. The rule-based approaches and shallow and deep machine learning algorithms- branches of Artificial Intelligence (AI)- can be employed as countermeasures along with the existing network security protocols. This paper presented a comprehensive layer-wise survey on IoT security threats, and the AI-based security models to impede security threats. Finally, open challenges and future research directions are addressed for the safeguard of the IoT network.

Challenges Ahead in Healthcare Applications for Vision and Sensors

The trend of todays healthcare demands prognostic, precautionary, customized and participatory care spawning an increase in stipulation for healthcare resources and services because of growing world population with rapid increase of people with special needs, such as the elderly population. Besides, the World Health Organization (WHO) conducted a survey back in 2013 which highlighted the fact that, global health workforce shortage to reach 12.9 million incoming decades;with more chronic diseases to be observed with an increasing rate of 10% each year like current pandemic situation of COVID-19. Owing to such factors, the researchers and healthcare professionals should seamlessly consolidate, coordinate and contrive new technologies to facilitate patients services;moderating healthcare transformation costs and risks at the same time. Following that, a widespread adoption of sensor technology and computer vision have been witnessed due to their superior performance for a variety of healthcare applications comprising not only remote monitoring and tracking of diseases with computer vision based diagnostic health examination methods but also early detection and prediction of stages of various chronics as well and many more. However, there remain several challenges which include the interoperability and expandability issues of technological devices and sensors including the familiarity of users with the usage of those technologies. Another prime obstacle remains the domain specific datasets, which are required for training user oriented models in terms of data driven approaches. This chapter demonstrates study of advances in modern computer vision techniques along with the development of faster and more accurate sensors for healthcare applications highlighting their challenges, open issues, and performance considerations in healthcare research. abstract environment. © 2021, Springer Nature Switzerland AG.

Short-Term Prediction of COVID-19 Cases Using Machine Learning Models

The first case in Bangladesh of the novel coronavirus disease (COVID-19) was reported on 8 March 2020, with the number of confirmed cases rapidly rising to over 175,000 by July 2020. In the absence of effective treatment, an essential tool of health policy is the modeling and forecasting of the progress of the pandemic. We, therefore, developed a cloud-based machine learning short-term forecasting model for Bangladesh, in which several regression-based machine learning models were applied to infected case data to estimate the number of COVID-19-infected people over the following seven days. This approach can accurately forecast the number of infected cases daily by training the prior 25 days sample data recorded on our web application. The outcomes of these efforts could aid the development and assessment of prevention strategies and identify factors that most affect the spread of COVID-19 infection in Bangladesh.

COVID-19: Update, Forecast and Assistant-An Interactive Web Portal to Provide Real-Time Information and Forecast COVID-19 Cases in Bangladesh

Since December 2019, Novel coronavirus disease has been shown an extensive impact on social, mental, personal, and economic fields throughout the world. In this pandemic situation, people are worried and interested to know what is going on in the upcoming days. Therefore, it is very important to provide relevant information about how many people are affected and will infect in near future. Moreover, they need to know how to spread different symptoms and prevention steps of this disease. Hence, we developed an informative and prediction-based web portal named COVID-19: Update, Forecast and Assistant which provides real-Time information on COVID-19 cases in Bangladesh and worldwide. In this model, we also provide a machine learning-based short-Term forecasting web tool that is used to predict infectious and fatality cases in an upcoming couple of days. Also, we provide precaution steps against coronavirus, emergency contacts of testing, and treatment centers for individuals. © 2021 IEEE.

COVID-19 Infection Detection from Chest X-Ray Images Using Hybrid Social Group Optimization and Support Vector Classifier.

A novel strain of Coronavirus, identified as the Severe Acute Respiratory Syndrome-2 (SARS-CoV-2), outbroke in December 2019 causing the novel Corona Virus Disease (COVID-19). Since its emergence, the virus has spread rapidly and has been declared a global pandemic. As of the end of January 2021, there are almost 100 million cases worldwide with over 2 million confirmed deaths. Widespread testing is essential to reduce further spread of the disease, but due to a shortage of testing kits and limited supply, alternative testing methods are being evaluated. Recently researchers have found that chest X-Ray (CXR) images provide salient information about COVID-19. An intelligent system can help the radiologists to detect COVID-19 from these CXR images which can come in handy at remote locations in many developing nations. In this work, we propose a pipeline that uses CXR images to detect COVID-19 infection. The features from the CXR images were extracted and the relevant features were then selected using Hybrid Social Group Optimization algorithm. The selected features were then used to classify the CXR images using a number of classifiers. The proposed pipeline achieves a classification accuracy of 99.65% using support vector classifier, which outperforms other state-of-the-art deep learning algorithms for binary and multi-class classification.