Evolution of Breast Cancer Recurrence Risk Prediction: A Systematic Review of Statistical and Machine Learning-Based Models.

PURPOSE: Selection of appropriate adjuvant therapy to ultimately reduce the risk of breast cancer (BC) recurrence is a challenge for medical oncologists. Several automated risk prediction models have been developed using retrospective clinical data and have evolved significantly over the years in terms of predictors of recurrence, data usage, and predictive techniques (statistical/machine learning [ML]). METHODS: Following PRISMA guidelines, we performed a systematic literature review of the aforementioned statistical and ML models published between January 2008 and December 2022 through searching five digital databases-PubMed, ScienceDirect, Scopus, Cochrane, and Web of Science. The comprehensive search yielded a total of 163 papers and after a screening process focusing on papers that dealt exclusively with statistical/ML methods, only 23 papers were deemed appropriate for further analysis. We benchmarked the studies on the basis of development, evaluation metrics, and validation strategy with an added emphasis on racial diversity of patients included in the studies. RESULTS: In total, 30.4% of the included studies use statistical techniques, while 69.6% are ML-based. Among these, traditional ML models (support vector machines, decision tree, logistic regression, and naïve Bayes) are the most frequently used (26.1%) along with deep learning (26.1%). Deep learning and ensemble learning provide the most accurate predictions (AUC = 0.94 each). CONCLUSION: ML-based prediction models exhibit outstanding performance, yet their practical applicability might be hindered by limited interpretability and reduced generalization. Moreover, predictive models for BC recurrence often focus on limited variables related to tumor, treatment, molecular, and clinical features. Imbalanced classes and the lack of open-source data sets impede model development and validation. Furthermore, existing models predominantly overlook African and Middle Eastern populations, as they are trained and validated mainly on Caucasian and Asian patients.

COVID-19-Related Scientific Literature Exploration: Short Survey and Comparative Study.

The urgency of the COVID-19 pandemic caused a surge in the related scientific literature. This surge made the manual exploration of scientific articles time-consuming and inefficient. Therefore, a range of exploratory search applications have been created to facilitate access to the available literature. In this survey, we give a short description of certain efforts in this direction and explore the different approaches that they used.

AsthmaKGxE: An asthma-environment interaction knowledge graph leveraging public databases and scientific literature.

MOTIVATION: Asthma is a complex heterogeneous disease resulting from intricate interactions between genetic and non-genetic factors related to environmental and psychosocial aspects. Discovery of such interactions can provide insights into the pathophysiology and etiology of asthma. In this paper, we propose an asthma knowledge graph (KG) built using a hybrid methodology for graph-based modeling of asthma complexity with a focus on environmental interactions. Using a heterogeneous set of public sources, we construct a genetic and pharmacogenetic asthma knowledge graph. The construction of this KG allowed us to shed more light on the lack of curated resources focused on environmental influences related to asthma. To remedy the lack of environmental data in our KG, we exploit the biomedical literature using state-of-the-art natural language processing and construct the first Asthma-Environment interaction catalog incorporating a continuously updated ensemble of environmental, psychological, nutritional and socio-economic influences. The catalog's most substantiated results are then integrated into the KG. RESULTS: The resulting environmentally rich knowledge graph "AsthmaKGxE" aims to provide a resource for several potential applications of artificial intelligence and allows for a multi-perspective study of asthma. Our insight extraction results indicate that stress is the most frequent asthma association in the corpus, followed by allergens and obesity. We contend that studying asthma-environment interactions in more depth holds the key to curbing the complexity and heterogeneity of asthma. AVAILABILITY: A user interface to browse and download the extracted catalog as well as the KG are available at http://asthmakgxe.moreair.info/. The code and supplementary data are available on github (https://github.com/ChaiAsaad/MoreAIRAsthmaKGxE).

An Exploration of Features Impacting Respiratory Diseases in Urban Areas.

Air pollution exposure has become ubiquitous and is increasingly detrimental to human health. Small Particulate matter (PM) is one of the most harmful forms of air pollution. It can easily infiltrate the lungs and trigger several respiratory diseases, especially in vulnerable populations such as children and elderly people. In this work, we start by leveraging a retrospective study of 416 children suffering from respiratory diseases. The study revealed that asthma prevalence was the most common among several respiratory diseases, and that most patients suffering from those diseases live in areas of high traffic, noise, and greenness. This paved the way to the construction of the MOREAIR dataset by combining feature abstraction and micro-level scale data collection. Unlike existing data sets, MOREAIR is rich in context-specific components, as it includes 52 temporal or geographical features, in addition to air-quality measurements. The use of Random Forest uncovered the most important features for the understanding of air-quality distribution in Moroccan urban areas. By linking the medical data and the MOREAIR dataset, we observed that the patients included in the medical study come mostly from neighborhoods that are characterized by either high average or high variations of pollution levels.

A Resource-Efficient CNN-Based Method for Moving Vehicle Detection.

There has been significant interest in using Convolutional Neural Networks (CNN) based methods for Automated Vehicular Surveillance (AVS) systems. Although these methods provide high accuracy, they are computationally expensive. On the other hand, Background Subtraction (BS)-based approaches are lightweight but provide insufficient information for tasks such as monitoring driving behavior and detecting traffic rules violations. In this paper, we propose a framework to reduce the complexity of CNN-based AVS methods, where a BS-based module is introduced as a preprocessing step to optimize the number of convolution operations executed by the CNN module. The BS-based module generates image-candidates containing only moving objects. A CNN-based detector with the appropriate number of convolutions is then applied to each image-candidate to handle the overlapping problem and improve detection performance. Four state-of-the-art CNN-based detection architectures were benchmarked as base models of the detection cores to evaluate the proposed framework. The experiments were conducted using a large-scale dataset. The computational complexity reduction of the proposed framework increases with the complexity of the considered CNN model's architecture (e.g., 30.6% for YOLOv5s with 7.3M parameters; 52.2% for YOLOv5x with 87.7M parameters), without undermining accuracy.

Machine Learning for Predicting the Risk for Childhood Asthma Using Prenatal, Perinatal, Postnatal and Environmental Factors.

The prevalence rate for childhood asthma and its associated risk factors vary significantly across countries and regions. In the case of Morocco, the scarcity of available medical data makes scientific research on diseases such as asthma very challenging. In this paper, we build machine learning models to predict the occurrence of childhood asthma using data from a prospective study of 202 children with and without asthma. The association between different factors and asthma diagnosis is first assessed using a Chi-squared test. Then, predictive models such as logistic regression analysis, decision trees, random forest and support vector machine are used to explore the relationship between childhood asthma and the various risk factors. First, data were pre-processed using a Chi-squared feature selection, 19 out of the 36 factors were found to be significantly associated (p-value < 0.05) with childhood asthma; these include: history of atopic diseases in the family, presence of mites, cold air, strong odors and mold in the child's environment, mode of birth, breastfeeding and early life habits and exposures. For asthma prediction, random forest yielded the best predictive performance (accuracy = 84.9%), followed by logistic regression (accuracy = 82.57%), support vector machine (accuracy = 82.5%) and decision trees (accuracy = 75.19%). The decision tree model has the advantage of being easily interpreted. This study identified important maternal and prenatal risk factors for childhood asthma, the majority of which are avoidable. Appropriate steps are needed to raise awareness about the prenatal risk factors.

Real-Time Infoveillance of Moroccan Social Media Users' Sentiments towards the COVID-19 Pandemic and Its Management.

The impact of COVID-19 on socio-economic fronts, public health related aspects and human interactions is undeniable. Amidst the social distancing protocols and the stay-at-home regulations imposed in several countries, citizens took to social media to cope with the emotional turmoil of the pandemic and respond to government issued regulations. In order to uncover the collective emotional response of Moroccan citizens to this pandemic and its effects, we use topic modeling to identify the most dominant COVID-19 related topics of interest amongst Moroccan social media users and sentiment/emotion analysis to gain insights into their reactions to various impactful events. The collected data consists of COVID-19 related comments posted on Twitter, Facebook and Youtube and on the websites of two popular online news outlets in Morocco (Hespress and Hibapress) throughout the year 2020. The comments are expressed in Moroccan Dialect (MD) or Modern Standard Arabic (MSA). To perform topic modeling and sentiment classification, we built a first Universal Language Model for the Moroccan Dialect (MD-ULM) using available corpora, which we have fine-tuned using our COVID-19 dataset. We show that our method significantly outperforms classical machine learning classification methods in Topic Modeling, Emotion Recognition and Polar Sentiment Analysis. To provide real-time infoveillance of these sentiments, we developed an online platform to automate the execution of the different processes, and in particular regular data collection. This platform is meant to be a decision-making assistance tool for COVID-19 mitigation and management in Morocco.

D2D Mobile Relaying Meets NOMA-Part II: A Reinforcement Learning Perspective.

Structureless communications such as Device-to-Device (D2D) relaying are undeniably of paramount importance to improving the performance of today's mobile networks. Such a communication paradigm requires a certain level of intelligence at the device level, thereby allowing it to interact with the environment and make proper decisions. However, decentralizing decision-making may induce paradoxical outcomes, resulting in a drop in performance, which sustains the design of self-organizing yet efficient systems. We propose that each device decides either to directly connect to the eNodeB or get access via another device through a D2D link. In the first part of this article, we describe a biform game framework to analyze the proposed self-organized system's performance, under pure and mixed strategies. We use two reinforcement learning (RL) algorithms, enabling devices to self-organize and learn their pure/mixed equilibrium strategies in a fully distributed fashion. Decentralized RL algorithms are shown to play an important role in allowing devices to be self-organized and reach satisfactory performance with incomplete information or even under uncertainties. We point out through a simulation the importance of D2D relaying and assess how our learning schemes perform under slow/fast channel fading.

D2D Mobile Relaying Meets NOMA -Part I:A Biform Game Analysis.

Structureless communications such as Device-to-Device (D2D) relaying are undeniably of paramount importance to improving the performance of today's mobile networks. Such a communication paradigm requires implementing a certain level of intelligence at device level, allowing to interact with the environment and select proper decisions. However, decentralizing decision making sometimes may induce some paradoxical outcomes resulting, therefore, in a performance drop, which sustains the design of self-organizing, yet efficient systems. Here, each device decides either to directly connect to the eNodeB or get access via another device through a D2D link. Given the set of active devices and the channel model, we derive the outage probability for both cellular link and D2D link, and compute the system throughput. We capture the device behavior using a biform game perspective. In the first part of this article, we analyze the pure and mixed Nash equilibria of the induced game where each device seeks to maximize its own throughput. Our framework allows us to analyse and predict the system's performance. The second part of this article is devoted to implement two Reinforcement Learning (RL) algorithms enabling devices to self-organize themselves and learn their equilibrium pure/mixed strategies, in a fully distributed fashion. Simulation results show that offloading the network by means of D2D-relaying improves per device throughput. Moreover, detailed analysis on how the network parameters affect the global performance is provided.

A Systematic Literature Review on e-Mental Health Solutions to Assist Health Care Workers During COVID-19.

Background: e-Mental health is an established field of exploiting information and communication technologies for mental health care. It offers different solutions and has shown effectiveness in managing many psychological issues. Introduction: The coronavirus disease 2019 (COVID-19) pandemic has critically influenced health care systems and health care workers (HCWs). HCWs are working under hard conditions, and are suffering from different psychological issues, including anxiety, stress, and depression. Consequently, there is an undeniable need of mental care interventions for HCWs. Under the circumstances caused by COVID-19, e-health interventions can be used as tools to assist HCWs with their mental health. These solutions can provide mental health care support remotely, respecting the recommended safety measures. Materials and Methods: This study aims to identify e-mental health interventions, reported in the literature, that are developed for HCWs during the COVID-19 pandemic. A systematic literature review was conducted following the PRISMA protocol by searching the following digital libraries: IEEE, ACM, ScienceDirect, Scopus, and PubMed. Results and Discussion: Eleven publications were selected. The identified e-mental health interventions consisted of social media platforms, e-learning content, online resources and mobile applications. Only 27% of the studies included empirical evaluation of the reported interventions, 55% listed challenges and limitations related to the adoption of the reported interventions. And 45% presented interventions developed specifically for HCWs in China. The overall feedback on the identified interventions was positive, yet a lack of empirical evaluation was identified, especially regarding qualitative evidence. Conclusions: The COVID-19 pandemic has highlighted the importance and need for e-mental health solutions for HCWs.

Practical Acoustic Energy-Based Estimation of Inhalation Flow Rate for Asthma Monitoring.

The estimation of inhalation flow rate (IFR) using acoustic devices has recently received attention. While existing work often assumes that the microphone is placed at a fixed distance from the acoustic device, this assumption does not hold in real settings. This leads to poor estimation of the IFR since the received acoustic energy varies significantly with the distance. Despite the fact that the acoustic source is passive and only one microphone is used, we show in this paper that the distance can be estimated by exploiting the inhaler actuation sound, generated when releasing the medication. Indeed, this sound is used as a reference acoustic signal which is leveraged to estimate the distance in real settings. The resulting IFR estimation is shown to be highly accurate (R2 = 80.3%).

Connected Mental Health: Systematic Mapping Study.

BACKGROUND: Although mental health issues constitute an increasing global burden affecting a large number of people, the mental health care industry is still facing several care delivery barriers such as stigma, education, and cost. Connected mental health (CMH), which refers to the use of information and communication technologies in mental health care, can assist in overcoming these barriers. OBJECTIVE: The aim of this systematic mapping study is to provide an overview and a structured understanding of CMH literature available in the Scopus database. METHODS: A total of 289 selected publications were analyzed based on 8 classification criteria: publication year, publication source, research type, contribution type, empirical type, mental health issues, targeted cohort groups, and countries where the empirically evaluated studies were conducted. RESULTS: The results showed that there was an increasing interest in CMH publications; journals were the main publication channels of the selected papers; exploratory research was the dominant research type; advantages and challenges of the use of technology for mental health care were the most investigated subjects; most of the selected studies had not been evaluated empirically; depression and anxiety were the most addressed mental disorders; young people were the most targeted cohort groups in the selected publications; and Australia, followed by the United States, was the country where most empirically evaluated studies were conducted. CONCLUSIONS: CMH is a promising research field to present novel approaches to assist in the management, treatment, and diagnosis of mental health issues that can help overcome existing mental health care delivery barriers. Future research should be shifted toward providing evidence-based studies to examine the effectiveness of CMH solutions and identify related issues.

An analysis on self-management and treatment-related functionality and characteristics of highly rated anxiety apps.

BACKGROUND AND OBJECTIVE: Anxiety is a common emotion that people often feel in certain situations. But when the feeling of anxiety is persistent and interferes with a person's day to day life then this may likely be an anxiety disorder. Anxiety disorders are a common issue worldwide and can fall under general anxiety, panic attacks, and social anxiety among others. They can be disabling and can impact all aspects of an individual's life, including work, education, and personal relationships. It is important that people with anxiety receive appropriate care, which in some cases may prove difficult due to mental health care delivery barriers such as cost, stigma, or distance from mental health services. A potential solution to this could be mobile mental health applications. These can serve as effective and promising tools to assist in the management of anxiety and to overcome some of the aforementioned barriers. The objective of this study is to provide an analysis of treatment and management-related functionality and characteristics of high-rated mobile applications (apps) for anxiety, which are available for Android and iOS systems. METHOD: A broad search was performed in the Google Play Store and App Store following the Preferred Reporting Items for Systematic reviews and Meta-Analysis (PRISMA) protocol to identify existing apps for anxiety. A set of free and highly rated apps for anxiety were identified and the selected apps were then installed and analyzed according to a predefined data extraction strategy. RESULTS: A total of 167 anxiety apps were selected (123 Android apps and 44 iOS apps). Besides anxiety, the selected apps addressed several health issues including stress, depression, sleep issues, and eating disorders. The apps adopted various treatment and management approaches such as meditation, breathing exercises, mindfulness and cognitive behavioral therapy. Results also showed that 51% of the selected apps used various gamification features to motivate users to keep using them, 32% provided social features including chat, communication with others and links to sources of help; 46% offered offline availability; and only 19% reported involvement of mental health professionals in their design. CONCLUSIONS: Anxiety apps incorporate various mental health care management methods and approaches. Apps can serve as promising tools to assist large numbers of people suffering from general anxiety or from anxiety disorders, anytime, anywhere, and particularly in the current COVID-19 pandemic.

IMPEC: An Integrated System for Monitoring and Processing Electricity Consumption in Buildings.

Non-intrusive Load Monitoring (NILM) systems aim at identifying and monitoring the power consumption of individual appliances using the aggregate electricity consumption. Many issues hinder their development. For example, due to the complexity of data acquisition and labeling, datasets are scarce; labeled datasets are essential for developing disaggregation and load prediction algorithms. In this paper, we introduce a new NILM system, called Integrated Monitoring and Processing Electricity Consumption (IMPEC). The main characteristics of the proposed system are flexibility, compactness, modularity, and advanced on-board processing capabilities. Both hardware and software parts of the system are described, along with several validation tests performed at residential and industrial settings.

MoreAir: A Low-Cost Urban Air Pollution Monitoring System.

MoreAir is a low-cost and agile urban air pollution monitoring system. This paper describes the methodology used in the development of this system along with some preliminary data analysis results. A key feature of MoreAir is its innovative sensor deployment strategy which is based on mobile and nomadic sensors as well as on medical data collected at a children's hospital, used to identify urban areas of high prevalence of respiratory diseases. Another key feature is the use of machine learning to perform prediction. In this paper, Moroccan cities are taken as case studies. Using the agile deployment strategy of MoreAir, it is shown that in many Moroccan neighborhoods, road traffic has a smaller impact on the concentrations of particulate matters (PM) than other sources, such as public baths, public ovens, open-air street food vendors and thrift shops. A geographical information system has been developed to provide real-time information to the citizens about the air quality in different neighborhoods and thus raise awareness about urban pollution.

Mobile Apps for Post Traumatic Stress Disorder.

Post Traumatic Stress Disorder (PTSD) is a serious mental disorder that is caused by exposure to traumatic stress and not being able to recover from it. PTSD often results in a severe reduction of the quality of life, and is significantly associated with the risk of suicide. This paper identifies the current list of free mobile applications (apps) available in Android platform for smartphone users with PTSD. This paper also assesses the functionalities of the apps selected. The result of this study may assist PTSD apps seekers for self-support, and serve as a reference for researchers and developers, who intend proposing stress management apps.