Deep learning based multimodal urban air quality prediction and traffic analytics.

Urban activities, particularly vehicle traffic, are contributing significantly to environmental pollution with detrimental effects on public health. The ability to anticipate air quality in advance is critical for public authorities and the general public to plan and manage these activities, which ultimately help in minimizing the adverse impact on the environment and public health effectively. Thanks to recent advancements in Artificial Intelligence and sensor technology, forecasting air quality is possible through the consideration of various environmental factors. This paper presents our novel solution for air quality prediction and its correlation with different environmental factors and urban activities, such as traffic density. To this aim, we propose a multi-modal framework by integrating real-time data from different environmental sensors and traffic density extracted from Closed Circuit Television footage. The framework effectively addresses data inconsistencies arising from sensor and camera malfunctions within a streaming dataset. The dataset exhibits real-world complexities, including abrupt camera or station activations/deactivations, noise interference, and outliers. The proposed system tackles the challenge of predicting air quality at locations having no sensors or experiencing sensor failures by training a joint model on the data obtained from nearby stations/sensors using a Particle Swarm Optimization (PSO)-based merit fusion of the sensor data. The proposed methodology is evaluated using various variants of the LSTM model including Bi-directional LSTM, CNN-LSTM, and Convolutions LSTM (ConvLSTM) obtaining an improvement of 48%, 67%, and 173% for short-term, medium-term, and long-term periods, respectively, over the ARIMA model.

Vertical Integration and Reinforcement of Basic Science Concepts in an Engaging Clinically Oriented Physiology Pharmacology Session (COPPS).

Medical educators are finding it challenging to ensure strong basic sciences knowledge is built in the allocated time assigned in the innovative medical school curriculum. In this article, we introduce a novel method to vertically integrate basic sciences knowledge during clinical training.

Regulation of Nrf2 and Nrf2-related proteins by ganoderma lucidum in hepatocellular carcinoma.

BACKGROUND: HCC is among the most common cancer. Ganoderma lucidum (G.lucidum) has been essential in preventing and treating cancer. The Nrf2 signaling cascade is a cell protective mechanism against further damage, such as cancer development. This signaling pathway upregulates the cytoprotective genes and is vital in eliminating xenobiotics and reactive oxygen. This study aimed to show the potential cytotoxic activity of G. lucidum aqueous extract in HCC. METHODS AND RESULTS: MTT assay was used to detect cell viability. Nrf2-related proteins were measured by western blotting, and the flow cytometry method assayed cell population in different cycle phases. Cell viability was 49% and 47% following G. lucidum extract at 100 µg/ml at 24 and 48 h treatments, respectively. G. lucidum extract (aqueous, 100 or 50 µg/ml) treatments for 24, 48, or 72 h were able to significantly change the cytoplasmic/nuclear amount of Nrf2 and HO-1, NQO1 protein levels. Moreover, at both concentrations, arrest of the G0/G1 cell cycle was stimulated in HCC. CONCLUSIONS: The activation of the Nrf2 signaling pathways seems to be among the mechanisms underlining the protective and therapeutic action of G. lucidum against HCC.

Visual Sentiment Analysis from Disaster Images in Social Media.

The increasing popularity of social networks and users' tendency towards sharing their feelings, expressions, and opinions in text, visual, and audio content have opened new opportunities and challenges in sentiment analysis. While sentiment analysis of text streams has been widely explored in the literature, sentiment analysis from images and videos is relatively new. This article focuses on visual sentiment analysis in a societally important domain, namely disaster analysis in social media. To this aim, we propose a deep visual sentiment analyzer for disaster-related images, covering different aspects of visual sentiment analysis starting from data collection, annotation, model selection, implementation, and evaluations. For data annotation and analyzing people's sentiments towards natural disasters and associated images in social media, a crowd-sourcing study has been conducted with a large number of participants worldwide. The crowd-sourcing study resulted in a large-scale benchmark dataset with four different sets of annotations, each aiming at a separate task. The presented analysis and the associated dataset, which is made public, will provide a baseline/benchmark for future research in the domain. We believe the proposed system can contribute toward more livable communities by helping different stakeholders, such as news broadcasters, humanitarian organizations, as well as the general public.

Global User-Level Perception of COVID-19 Contact Tracing Applications: Data-Driven Approach Using Natural Language Processing.

BACKGROUND: Contact tracing has been globally adopted in the fight to control the infection rate of COVID-19. To this aim, several mobile apps have been developed. However, there are ever-growing concerns over the working mechanism and performance of these applications. The literature already provides some interesting exploratory studies on the community's response to the applications by analyzing information from different sources, such as news and users' reviews of the applications. However, to the best of our knowledge, there is no existing solution that automatically analyzes users' reviews and extracts the evoked sentiments. We believe such solutions combined with a user-friendly interface can be used as a rapid surveillance tool to monitor how effective an application is and to make immediate changes without going through an intense participatory design method. OBJECTIVE: In this paper, we aim to analyze the efficacy of AI and NLP techniques for automatically extracting and classifying the polarity of users' sentiments by proposing a sentiment analysis framework to automatically analyze users' reviews on COVID-19 contact tracing mobile apps. We also aim to provide a large-scale annotated benchmark data set to facilitate future research in the domain. As a proof of concept, we also developed a web application based on the proposed solutions, which is expected to help the community quickly analyze the potential of an application in the domain. METHODS: We propose a pipeline starting from manual annotation via a crowd-sourcing study and concluding with the development and training of artificial intelligence (AI) models for automatic sentiment analysis of users' reviews. In detail, we collected and annotated a large-scale data set of user reviews on COVID-19 contact tracing applications. We used both classical and deep learning methods for classification experiments. RESULTS: We used 8 different methods on 3 different tasks, achieving up to an average F1 score of 94.8%, indicating the feasibility of the proposed solution. The crowd-sourcing activity resulted in a large-scale benchmark data set composed of 34,534 manually annotated reviews. CONCLUSIONS: The existing literature mostly relies on the manual or exploratory analysis of users' reviews on applications, which is tedious and time-consuming. In existing studies, generally, data from fewer applications are analyzed. In this work, we showed that AI and natural language processing techniques provide good results for analyzing and classifying users' sentiments' polarity and that automatic sentiment analysis can help to analyze users' responses more accurately and quickly. We also provided a large-scale benchmark data set. We believe the presented analysis, data set, and proposed solutions combined with a user-friendly interface can be used as a rapid surveillance tool to analyze and monitor mobile apps deployed in emergency situations leading to rapid changes in the applications without going through an intense participatory design method.

Metastatic melanoma in the Mid-West of Ireland: a retrospective review.

BACKGROUND: Melanoma is the fifth most common invasive cancer in Ireland, and incidence is increasing. Metastatic melanoma has been associated with poor overall survival historically. New systemic anti-cancer treatment (SACT) options for advanced melanoma have emerged in the last decade, and outcomes are improving. AIMS: The aim of our study was to assess the incidence and clinicopathological features of metastatic melanoma in our centre, and subsequent treatment with SACT. METHODS: We analysed retrospectively patients with metastatic melanoma in the Mid-West of Ireland, over a 6-year period (2014-2019). RESULTS: In 6 years, a total of 620 patients were diagnosed with melanoma, 28 (5%) had metastatic or unresectable disease at diagnosis. Mean age at primary diagnosis was 64.5 years (range 24-90 years) and 20 (71%) were male. Median Breslow depth was 4.3 mm (mean 5.5 mm, SD ± 4.4 mm). Thirteen patients (46%) had metastases at initial presentation. Fifteen (53%) received systemic treatment in the regional cancer centre. Of 13 who did not have systemic treatment, 8 had radiological and clinical surveillance, 3 declined further treatment or surveillance and 2 were lost to follow-up. Eleven patients died from the disease with median overall survival of 1.5 years (SD ± 1.3 years). CONCLUSION: Patients with metastatic melanoma commonly had metastases at the time of first presentation. Just over half of patients with metastatic melanoma received SACT. Early detection of melanoma is key. Further research on factors involved in late presentation, and those precluding systemic treatment, may contribute to improved outcomes in advanced melanoma.

Medial stabilised total knee arthroplasty achieves comparable clinical outcomes when compared to other TKA designs: a systematic review and meta-analysis of the current literature.

PURPOSE: The purpose of this study was to perform a systematic review and meta-analysis to compare clinical and patient-reported outcome measures of medially stabilised (MS) TKA when compared to other TKA designs. METHODS: The Preferred Reporting Items for Systematic Review and Meta-Analyses algorithm was used. The Cochrane Central Register of Controlled Trials, MEDLINE, EMBASE, and EMCARE databases were searched to June 2020. Studies with a minimum of 12 months of follow-up comparing an MS TKA design to any other TKA design were included. The statistical analysis was completed using Review Manager (RevMan), Version 5.3. RESULTS: The 22 studies meeting the inclusion criteria included 3011 patients and 4102 TKAs. Overall Oxford Knee Scores were significantly better (p = 0.0007) for MS TKA, but there was no difference in the Forgotten Joint Scores (FJS), Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC), Knee Society Score (KSS)-Knee, KSS-Function, and range of motion between MS and non-MS TKA designs. Significant differences were noted for sub-group analyses; MS TKA showed significantly worse KSS-Knee (p = 0.02) and WOMAC (p = 0.03) scores when compared to Rotating Platform (RP) TKA while significantly better FJS (p = 0.002) and KSS-knee scores (p = 0.0001) when compared to cruciate-retaining (CR) TKA. CONCLUSION: This review and meta-analysis show that MS TKA designs result in both patient and clinical outcomes that are comparable to non-MS implants. These results suggest implant design alone may not provide further improvement in patient outcome following TKA, surgeons must consider other factors, such as alignment to achieve superior outcomes. LEVEL OF EVIDENCE: III.

Practical experience of secukinumab in the treatment of psoriasis: experience from a single centre.

Secukinumab is a novel anti-interleukin-17A agent that has achieved a 75% decrease from baseline in Psoriasis Area and Severity Index (PASI 75) in 77-81% of patients treated in clinical trials Langley et al. (N Engl J Med 371:326-338, 2014). There is limited data on the use of secukinumab outside of clinical trials. We provide real-world data on the efficacy and safety of secukinumab in patients with severe psoriasis attending an outpatient dermatology service. In our retrospective review, we demonstrate (PASI 75) a response rate of 47% in patients previously treated with multiple systemic and biologics. Our efficacy is comparable to that seen in the Signature study who examined similar populations. Response was maintained at follow-up of almost 1 year with acceptable safety data. Patients with psoriatic arthritis were more likely to remain on secukinumab than those without at last clinic follow-up.

How COVID-19 Transformed Problem-Based Learning at Carle Illinois College of Medicine.

The Carle Illinois College of Medicine is creating an innovative model for medical education that integrates engineering principles into an active learning curriculum. At the Carle Illinois due to the state order of social distancing during the COVID-19 pandemic, students were mandated to terminate in-person instruction. The goal of this work is to show the pros and cons of online versus in person Problem Based Learning (PBL) sessions. In the online environment, the sessions tend to run slower since we need to pause to allow time for people to speak and others to understand. There is more risk for students to become distracted by increased screen-time and access. Thus, the facilitator has a greater role in keeping the students engaged and focused while managing time. Despite these differences, we found that overall student performance with respect to generating and researching learning issues was similar between online and in-person PBL sessions.

Introducing First-Year Medical Students to Product Innovation and Entrepreneurship.

Medical education is changing and evolving, and it is evident there is a need for emerging technologies that will improve patient outcomes and healthcare (Brazile et al. Med Teach. 40(12):1264-74, 2018). The Carle Illinois College of Medicine is creating an innovative model for medical education that integrates engineering principles into an active learning curriculum.

Medical Engineering Education: Designing a Product Innovation and Technology Session for First-Year Medical Students.

The Carle Illinois College of Medicine created an innovative model for medical education that integrates engineering principles into an active learning curriculum. First-year students were introduced to a medical device in an engaging product innovation and technology session. The goals were to discuss the physiology of oxygen saturation and demonstrate the ability to use observation and research to develop a new product idea. Students hypothetically competed with others to raise money from investors to pursue an efficient medical device and attend the users' needs. Student's feedback reflected a positive impact on their understanding of oximetry measurements and product innovation.

An Evolutionary Bootstrapping Development Approach for a Mental Health Conversational Agent.

Conversational agents are being used to help in the screening, assessment, diagnosis, and treatment of common mental health disorders. In this paper, we propose a bootstrapping approach for the development of a digital mental health conversational agent (i.e., chatbot). We start from a basic rule-based expert system and iteratively move towards a more sophisticated platform composed of specialized chatbots each aiming to assess and pre-diagnose a specific mental health disorder using machine learning and natural language processing techniques. During each iteration, user feedback from psychiatrists and patients are incorporated into the iterative design process. A survival of the fittest approach is also used to assess the continuation or removal of a specialized mental health chatbot in each generational design. We anticipate that our unique and novel approach can be used for the development of conversational mental health agents with the ultimate goal of designing a smart chatbot that delivers evidence-based care and contributes to scaling up services while decreasing the pressure on mental health care providers.

Presence of Diverse Sugarcane Bacilliform Viruses Infecting Sugarcane in China Revealed by Pairwise Sequence Comparisons and Phylogenetic Analysis.

Sugarcane bacilliform viruses (SCBV), which belong to the genus Badnavirus, family Caulimoviridae, are an important DNA virus complex that infects sugarcane. To explore the genetic diversity of the sugarcane-infecting badnavirus complex in China, we tested 392 sugarcane leaf samples collected from Fujian, Yunnan, and Hainan provinces for the occurrence of SCBV by polymerase chain reaction (PCR) assays using published primers SCBV-F and SCBV-R that target the reverse transcriptase/ribonuclease H (RT/RNase H) regions of the viral genome. A total of 111 PCR-amplified fragments (726 bp) from 63 SCBV-positive samples were cloned and sequenced. A neighbor-joining phylogenetic tree was constructed based on the SCBV sequences from this study and 34 published sequences representing 18 different phylogroups or genotypes (SCBV-A to -R). All SCBV-tested isolates could be classified into 20 SCBV phylogenetic groups from SCBV-A to -T. Of nine SCBV phylogroups reported in this study, two novel phylogroups, SCBV-S and SCBV-T, that share 90.0-93.2% sequence identity and show 0.07-0.11 genetic distance with each other in the RT/ RNase H region, are proposed. SCBV-S had 57.6-92.2% sequence identity and 0.09-0.66 genetic distance, while SCBV-T had 58.4-90.0% sequence identity and 0.11-0.63 genetic distance compared with the published SCBV phylogroups. Additionally, two other Badnavirus species, Sugarcane bacilliform MO virus (SCBMOV) and Sugarcane bacilliform IM virus (SCBIMV), which originally clustered in phylogenetic groups SCBV-E and SCBV-F, respectively, are first reported in China. Our findings will help to understand the level of genetic heterogeneity present in the complex of Badnavirus species that infect sugarcane.