Automated Prognosis of Alzheimer's Disease using Machine Learning Classifiers on Spontaneous Speech features

Early prediction of Alzheimer's disease and related Dementia has been a great challenge. Recently, preliminary research has shown that neurological symptoms in Covid-19 patients may accelerate the onset of Alzheimer's disease. With such a further rise in Alzheimer's and related Dementia cases, having an early prediction system becomes vital. Speech can provide a non-invasive diagnostic marker for such neurodegenerative diseases. This work mainly focuses on studying significant temporal speech features extracted directly from the recordings of the Dementia bank dataset and applying Machine Learning algorithms to classify the Alzheimer's disease related Dementia Group and the healthy control group. The result shows that Support Vector Machine outperformed other machine learning algorithms with an accuracy of 87%. Compared to prior research, which used manual transcriptions provided with the dataset, this study used audio recordings from the Dementia bank dataset and an advanced Automatic Speech Recognizer to extract speech features from the audio recordings. Furthermore, this method can be applied to the spoken responses of subjects during a neuropsychological assessment. © 2023, Ismail Saritas. All rights reserved.

MODELING AND SIMULATION FOR THE SPREAD OF COVID-19 IN AN INDIAN CITY: A CASE STUDY

We present a case study on modeling and predicting the course of Covid-19 in the Indian city of Pune. The results presented in this paper are concerned primarily with the wave of infections triggered by the Delta variant during the period between February and June 2021. Our work demonstrates the necessity for bringing together compartmental stock-and-flow and agent-based models and the limitations of each approach when used individually. Some of the work presented here was carried out in the process of advising the local city administration and reflects the challenges associated with employing these models in a real-world environment with its uncertainties and time pressures. Our experience, described in the paper, also highlights the risks associated with forecasting the course of an epidemic with evolving variants. © 2022 IEEE.

Agent Based Simulatable City Digital Twin to Explore Dynamics of Covid-19 Pandemic

Predicting the evolution of Covid19 pandemic has been a challenge as it is significantly influenced by the characteristics of people, places and localities, dominant virus strains, extent of vaccination, and adherence to pandemic control interventions. Traditional SEIR based analyses help to arrive at a coarse-grained 'lumped up' understanding of pandemic evolution which is found wanting to determine locality-specific measures of controlling the pandemic. We comprehend the problem space from system theory perspective to develop a fine-grained simulatable city digital-twin for 'in-silico' experimentations to systematically explore - Which indicators influence infection spread to what extent? Which intervention to introduce, and when, to control the pandemic with some a-priori assurance? How best to return to a new normal without compromising individual health safety? This paper presents a digital twin centric simulation-based approach, illustrates it in a real-world context of an Indian City, and summarizes the learning and insights based on this experience. © 2022 IEEE.

Drug Repurposing: An Effective Tool in Modern Drug Discovery.

Drug repurposing is using an existing drug for a new treatment that was not indicated before. It has received immense attention during the COVID-19 pandemic emergency. Drug repurposing has become the need of time to fasten the drug discovery process and find quicker solutions to the over-exerted healthcare scenario and drug needs. Drug repurposing involves identifying the drug, evaluating its efficiency using preclinical models, and proceeding to phase II clinical trials. Identification of the drug candidate can be made through computational and experimental approaches. This approach usually utilizes public databases for drugs. Data from primary and translational research, clinical trials, anecdotal reports regarding off-label uses, and other published human data information available are included. Using artificial intelligence algorithms and other bioinformatics tools, investigators systematically try to identify the interaction between drugs and protein targets. It can be combined with genetic data, clinical analysis, structure (molecular docking), pathways, signatures, targets, phenotypes, binding assays, and artificial intelligence to get an optimum outcome in repurposing. This article describes the strategies involved in drug repurposing and enlists a series of repurposed drugs and their indications.

Validation of a Deep Learning Model for Detecting Chest Pathologies from Digital Chest Radiographs.

Purpose: Manual interpretation of chest radiographs is a challenging task and is prone to errors. An automated system capable of categorizing chest radiographs based on the pathologies identified could aid in the timely and efficient diagnosis of chest pathologies. Method: For this retrospective study, 4476 chest radiographs were collected between January and April 2021 from two tertiary care hospitals. Three expert radiologists established the ground truth, and all radiographs were analyzed using a deep-learning AI model to detect suspicious ROIs in the lungs, pleura, and cardiac regions. Three test readers (different from the radiologists who established the ground truth) independently reviewed all radiographs in two sessions (unaided and AI-aided mode) with a washout period of one month. Results: The model demonstrated an aggregate AUROC of 91.2% and a sensitivity of 88.4% in detecting suspicious ROIs in the lungs, pleura, and cardiac regions. These results outperform unaided human readers, who achieved an aggregate AUROC of 84.2% and sensitivity of 74.5% for the same task. When using AI, the aided readers obtained an aggregate AUROC of 87.9% and a sensitivity of 85.1%. The average time taken by the test readers to read a chest radiograph decreased by 21% (p < 0.01) when using AI. Conclusion: The model outperformed all three human readers and demonstrated high AUROC and sensitivity across two independent datasets. When compared to unaided interpretations, AI-aided interpretations were associated with significant improvements in reader performance and chest radiograph interpretation time.

Computational search for potential COVID-19 drugs from ayurvedic medicinal plants to identify potential inhibitors against SARS-CoV-2 targets.

BACKGROUND: To date, very few small drug molecules are used for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) that has been discovered since the epidemic commenced in November 2019. SARS-CoV-2 RdRp and spike protein are essential targets for drug development amidst whole variants of coronaviruses. OBJECTIVE: This study aims to discover and recognize the most effective and promising small molecules against SARS-CoV-2 RNA-dependent RNA polymerase (RdRp) and spike protein targets through molecular docking screening of 39 phytochemicals from five different Ayurveda medicinal plants. METHODS: The phytochemicals were downloaded from PubChem, and SARS-CoV-2 RdRp and spike protein were taken from the protein data bank. The molecular interactions, binding energy, and ADMET properties were analyzed. RESULTS: Molecular docking analysis identified some phytochemicals, oleanolic acid, friedelin, serratagenic acid, uncinatone, clemaphnol A, sennosides B, trilobine and isotrilobine from ayurvedic medicinal plants possessing greater affinity against SARS-CoV-2-RdRp and spike protein targets. Two molecules, namely oleanolic acid and sennosides B, with low binding energies, were the most promising. Furthermore, based on the docking score, we carried out MD simulations for the oleanolic acid and sennosides B-protein complexes. CONCLUSION: Molecular ADMET profile estimation showed that the docked phytochemicals were safe. The present study suggested that active phytochemicals from medicinal plants could inhibit RdRp and spike protein of SARS-CoV-2.

A DIGITAL TWIN BASED APPROACH FOR ENSURING BUSINESS CONTINUITY PLAN AND SAFE RETURN TO WORKPLACE

Organizations are struggling to ensure business continuity without compromising on delivery excellence in the face of Covid19 pandemic related uncertainties. The uncertainty exists along multiple dimensions such as virus mutations, infectivity and severity of new mutants, efficacy of vaccines against new mutants, waning of vaccine induced immunity over time, and lockdown/opening-up policies effected by city authorities. Moreover, this uncertainty plays out in a non-uniform manner across nations, states, cities, and even within the cities thus leading to highly heterogeneous evolution of pandemic. While Work From Home (WFH) strategy has served well to meet ever-increasing business demands without compromising on individual health safety, there has been an undeniable reduction in social capital. With Covid19 pandemic showing definite waning trends, organizations are considering the possibility of safe transition from WFH to Work From Office (WFO) or a hybrid mode of operation. An effective strategy needs to score equally well on possibly interfering dimensions such as risk of infection, project delivery, and employee wellness. As large organizations will typically have a large number of offices spread across a geography, the problem of arriving at office-specific strategies becomes non-trivial. Moreover, the strategies need to adapt over time to changes that cannot be deduced upfront. This calls for an approach that is amenable to quick and easy adaptation. Our contribution in this regard is constructing a Digital Twin by leveraging various modelling techniques to realistically represent the above mentioned aspects of interest that can be subjected to what-if scenario analysis. We further demonstrate its efficacy using a case study from a large organization. © 2022 Society for Modeling & Simulation International (SCS)

Fine-Grained Prediction and Control of Covid-19 Pandemic in a City: Application to Post-Initial Stages

Predicting the evolution of the Covid-19 pandemic during its early phases was relatively easy as its dynamics were governed by few influencing factors that included a single dominant virus variant and the demographic characteristics of a given area. Several models based on a wide variety of techniques were developed for this purpose. Their prediction accuracy started deteriorating as the number of influencing factors and their interrelationships grew over time. With the pandemic evolving in a highly heterogeneous way across individual countries, states, and even individual cities, there emerged a need for a contextual and fine-grained understanding of the pandemic to come up with effective means of pandemic control. This paper presents a fine-grained model for predicting and controlling Covid-19 in a large city. Our approach borrows ideas from complex adaptive system-of-systems paradigm and adopts a concept of agent as the core modeling ion. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Agent Based Digital Twin of Sorting Terminal to Improve Efficiency and Resiliency in Parcel Delivery

Open economy, globalization and effect of Covid19 pandemic are transforming the consumer behavior rapidly. The business is nudging consumers towards hyper consumption through online shopping, e-commerce and other conveniences with affordable cost. The companies from courier, express and parcel (CEP) industry are trying to capitalize on this opportunity by tying up with business to consumers (B2C) companies with a promise of delivering parcels to the doorstep in an ever-shrinking time window. In this endeavor, the conventional optimization-based planning approach to manage the fixed parcel payload is turning out to be inadequate. The CEP companies need to quickly adapt to the situation more frequently so as to be efficient and resilient in this growing demand situation. We propose an agent-based digital twin of the sorting terminal, a key processing element of parcel delivery operation, as an experimentation aid to: (i) explore and arrive at the right configuration of the existing sorting terminal infrastructure, (ii) be prepared for possible outlier conditions, and (iii) identify plausible solutions for mitigating the outlier conditions in an evidence-backed manner. This paper presents digital twin of the sorting terminal and demonstrates its use as “in silico” experimentation aid for domain experts to support evidence-backed decision-making. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

A Digital Twin Based Approach For Ensuring Business Continuity Plan And Safe Return To Workplace

Organizations are struggling to ensure business continuity without compromising on delivery excellence in the face of Covid19 pandemic related uncertainties. The uncertainty exists along multiple dimensions such as virus mutations, infectivity and severity of new mutants, efficacy of vaccines against new mutants, waning of vaccine induced immunity over time, and lockdown / opening-up policies effected by city authorities. Moreover, this uncertainty plays out in a non-uniform manner across nations, states, cities, and even within the cities thus leading to highly heterogeneous evolution of pandemic. While Work From Home (WFH) strategy has served well to meet ever-increasing business demands without compromising on individual health safety, there has been an undeniable reduction in social capital. With Covid19 pandemic showing definite waning trends, organizations are considering the possibility of safe transition from WFH to Work From Office (WFO) or a hybrid mode of operation. An effective strategy needs to score equally well on possibly interfering dimensions such as risk of infection, project delivery, and employee wellness. As large organizations will typically have a large number of offices spread across a geography, the problem of arriving at office-specific strategies becomes non-trivial. Moreover, the strategies need to adapt over time to changes that cannot be deduced upfront. This calls for an approach that is amenable to quick and easy adaptation. Our contribution in this regard is constructing a Digital Twin by leveraging various modelling techniques to realistically represent the above mentioned aspects of interest that can be subjected to what-if scenario analysis. We further demonstrate its efficacy using a case study from a large organization. © 2022 SCS.

Transcriptional Interaction Between RelA and cJUN

Rationale: The SARS-CoV-2 pandemic has underscored the need for novel anti-infectious strategies, including host-directed therapeutics, against existing and emerging respiratory pathogens. We have reported that an aerosolized therapeutic comprised of a Toll-like receptor (TLR)-2/6 agonist, Pam2CSK4, and a TLR-9 agonist, ODN M362, stimulate pathogen-agnostic innate immune responses in lung epithelial cells. This therapeutic (“Pam2-ODN”) promotes synergistic microbicidal activity and host survival benefit against pneumonia caused by a wide range of pathogens. Here, we study the immunomodulatory signaling mechanisms required to effect this inducible epithelial resistance. Methods: Bioinformatic analysis of transcriptional responses from human and mouse lung epithelium al cells to influenza A H1N1 or SARS-CoV-2 (GSE147507) or Pam2-ODN (GSE289984, GSE26864) were analyzed using R and IPA software to identify essential transcription factors (TFs). Lung cell population dynamics were studied for TFs related to Pam2-ODN immunomodulatory signaling using high-throughput imaging flow cytometry (IFC). Human or mouse lung epithelial cells were stimulated with PBS or Pam2-ODN and single or dual inhibitors of TFs before challeng with influenza A H3N2 (IAV) or coronavirus OC43 (CoV) to compare the epithelium-specific transcriptional control of relevant TFs using in-cell western blotting, IFC and hemagglutination for viral burdens. Results: Functional enrichment analysis revealed RelA and cJUN to be major immunomodulatory TFs of Pam2-ODN and activators of leukocyte- and epithelial-derived antiviral immune mechanisms targeting replication of influenza A and SARS-CoV-2. Cell population dynamics studied from mouse lungs confirmed activation of RelA and cJUN in CD45+, EpCAM- leukocytes and in CD45-, EpCAM+ epithelial cells, with predominant activation of the lung epithelium and none or minimal activation of structural cell populations such as fibroblasts or endothelial cells. Studies of epithelium-specific signaling in vitro revealed co-activation of RelA-(pS536) and cJun- (pS73) TFs with Pam2-ODN, and earlier onset of cJUN phosphorylation and nuclear translocation with Pam2-ODN after IAV or CoV infection. Individual or dual inhibition of RelA and/or cJUN activity in vitro disrupted the antiviral activity of Pam2-ODN of IAV infected cells. Conclusion: Pam2-ODN induces unique, pathogen-agnostic protective signaling in lung epithelial cells that involves cooperative activation of RelA and cJUN. This combined TF signaling mechanism is not observed in other structural lung cell populations after Pam2-ODN exposure. Further, the phospho-regulation dynamics of RelA and cJUN are not replicated by IAV or CoV infection alone, suggesting a novel therapeutic process that can be leveraged to protect individuals against pneumonia. (Figure Presented).

Toward Data Visualization and Data Forecasting with COVID-19 Vaccination Statistics

The world runs on data. Various organizations, businesses, and institutions utilize and generate data. This information is a valuable commodity if availed of in the right way. Big data can be large and incomprehensible on its own, but when analyzed computationally, it can be a powerful tool for revealing patterns and trends, forecasting future values of certain data parameters as well as providing clarity about the metrics in the data. Data visualization and forecasting using such data are fields that have applications in every sector—from information technology, to education, to healthcare. Since the world was hit by the debilitating COVID-19 pandemic in 2019, life has become a blur of statistics—daily new case counts, daily deaths and recoveries, number of people vaccinated, etc. Such data are of paramount importance to everyone affected by the pandemic, and presenting it in a way that is easily understandable to a layperson and using it to glean insights into the spread and curb of the disease as well as the efficacy of the vaccines is necessary. This paper takes COVID vaccination statistics as a use case for the fields of data visualization and data forecasting. It elucidates the methodology and benefits of both interactive visualizations of vaccination data and forecasting future trends in vaccine and case metrics based on data over time. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Object Detection for COVID Rules Response and Crowd Analysis

Understanding the hotspots attracting massive crowds is a huge necessity during this pandemic times. The knowledge of analyzing crowds will help to plan and avoid the spread of the virus to a large extent by identifying exact hotspots. Understanding where the crowds flock and whether they are following the guidelines or not will help in taking appropriate actions, allotting concerned personnel in advance, and closing of areas which are at higher risks can be advantageous. In order to realize the situation, real-time analysis of the pandemic rules like social distancing, wearing masks is necessary. This paper proposes the use of video surveillance and provides a combined application to check the factors necessary during crowd situations as per rules set by the Government. This work uses python as a coding language, and YOLOv4 algorithm along with various libraries like darknet to improve video and image analysis for the identification of exact requirements. This work also uses Cuda software and Cudnn library for the acceleration of processing. The paper proposes importantly, counting people passing through a particular area, detecting whether people are following social distancing, detecting if the participants are wearing a mask, and counting the number of vehicles passing through an area. The knowledge of analyzing crowds will help to plan and avoid the spread of the virus to a large extent by identifying exact hotspots. All the applications are connected to the graphical user interface (GUI) and depending on the input each application proposed considers different analysis. The types of input are image, video, image directory and live feed are considered to obtain better results. © 2021 IEEE.

Automated Detection of COVID-19 from CT Scans using Convolutional Neural Networks

COVID-19 is an infectious disease that causes respiratory problems similar to those caused by SARS-CoV (2003). In this paper, we propose a prospective screening tool wherein we use chest CT scans to diagnose the patients for COVID-19 pneumonia. We use a set of open-source images, available as individual CT slices, and full CT scans from a private Indian Hospital to train our model. We build a 2D segmentation model using the U-Net architecture, which gives the output by marking out the region of infection. Our model achieves a sensitivity of 0.96 (95% CI: 0.88-1.00) and a specificity of 0.88 (95% CI: 0.82-0.94). Additionally, we derive a logic for converting our slice-level predictions to scan-level, which helps us reduce the false positives.

Antiviral immunomodulatory signaling of inducible epithelial resistance recalibrates host response to coronavirus and influenza infection

Rationale: The ongoing COVID-19 pandemic highlights the need to develop novel anti-pneumonia interventions against emerging and established pathogens. We previously reported a therapeutic dyad of immunostimulatory small molecules that induces innate immunity, termed inducible epithelial resistance, against a wide range of pneumonia-causing pathogens, including coronaviruses and influenza viruses. This combination (“Pam2-ODN”) is comprised of a Toll-like receptor (TLR)-2/6 agonist, Pam2CSK4, and a TLR-9 agonist, ODN M362, that stimulate protective responses from lung epithelial cells and promotes synergistic survival benefits and microbicidal effects that exceeds the additive effects of treatment with individual ligands. Here, we investigate the immunomodulatory signaling mechanism of Pam2-ODN that reduces susceptibility to viral infection in lung epithelial cells. Methods: Transcriptional responses of human and mouse lung epithelial cells to influenza A H1N1 or SARS-CoV-2 (GSE147507) or Pam2-ODN (GSE289984) were analyzed using R and IPA software to build host-based antiviral innate immune pathways to infections and identify relevant transcriptional factors (TFs) involved. Isolated human or mouse lung epithelial cells were stimulated with PBS or Pam2-ODN and challenged with influenza A H3N2 or coronavirus OC43 to study transcriptional control of relevant TFs by high-throughput methods of immunofluorescence (IF) staining, in-cell western blotting and imaging flow cytometry (IFC). Results: Network-based enrichment analysis reduced infection of epithelial cells with Pam2-ODN against both coronavirus and influenza through inhibition of viral budding and viral RNA replication. In silico prediction of pathogen-specific host-based responses with Pam2-ODN included disruption of SARS-CoV-2's IL-1, 6 and 8 signaling, and inhibition of influenza A's anti-interferon mechanisms. Functional enrichment analysis revealed activation of these host innate immune responses by Pam2-ODN prior to viral exposure through activity of NF-kB/RelA and AP-1/cJun. IFC and IF confirmed an NF-kB-dependent transcriptional cooperation of RelA and cJun with Pam2-ODN in both mouse and human lung epithelial cells. Phospho-kinetic studies revealed an early transient activity of RelA-(pS536), followed by a sustained cJun-(pS73) signal in lung epithelial cells after Pam2-ODN. Upon viral infection, Pam2-ODN treated cells activated cJun-(pS73) signaling more rapidly in response to both influenza and coronavirus infection. Coronavirus-induced activation of RelA-(pS536) after infection was suppressed in Pam2-ODN treated cells. Conclusion: Inducible epithelial resistance by Pam2- ODN enhances broad host-based antiviral innate immunity responses through signaling pathways of RelA and cJun, which also abrogate virus-specific pathogenic mechanisms. Furthermore, phospho-signaling control of these transcriptional responses in lung epithelium suggest a novel pathogen-dependent antiviral response immune mechanism to infection.

Achieving program outcomes through MIY model ensuring active learning and active engagement in learning

Post Covid-19 is a real challenge, as students’ faces are not visible to teachers during interaction or nor the students are available physically, leaving teachers clueless about their active learning and active engagement in learning. Achieving graduate attributes poses further challenge as it has to ensure imbibing Higher Order Thinking skills [HOTs] in students. There is a need to develop online integrated pedagogy to overcome this problem. It is observed that creating content specific videos, really creates interest in students and ensures active learning, if they are asked to upload in YouTube provided students are guided with Rubric based learning for video creation. Moodle integrated YouTube [MIY] channel is developed to let the teachers create their own Video of short duration with rubric guidance. The paper presents a case study dedicated to PO7 [Program Outcome Environment and Sustainability], supported by Open Education for better World [OE4BW]. The Moodle based methodology [73 activities in Moodle- Games like crossword, Quiz, Discussion Forum], integrating with google meet to interact with participants, Rubric guidance, query solving, active learner’s motivation and impact of posting in YouTube channel are presented in study. Out of 268 participants, 217 participants peer reviewed videos were selected and added in YouTube channel [Environment and sustainability OE4BW, https://www.youtube.com/channel/UCQWwEFdEMeS7Kc 3MuWw3Jkg/videos] based on quality content [Carbon foot print analysis, Environment and Sustainability computation] created by them. Participant’s happiness index for learning was attributed as A+ [4.79/5] during the entire video development process. © 2021, Rajarambapu Institute Of Technology. All rights reserved.