Artificial Intelligence approaches to predict COVID-19 infection in Senegal.

The SARS-CoV2 virus, which causes COVID-19 (coronavirus disease) has become a pandemic and has expanded all over the world. Because of increasing number of cases day by day, it takes time to interpret the data thus the limitations in terms of both treatment and findings are emerged. Due to such limitations, the need for clinical decisions making system with predictive algorithms has arisen. Predictive algorithms could potentially ease the strain on healthcare systems by identifying the diseases. In this study, we design clinical predictive models that estimate, using artificial intelligence and data, which patients are susceptible to receive a COVID-19 disease. To evaluate the predictive performance of our models, accuracy, AUROC, and scores calculated. From 12,727 individuals, models were tested with basic information (sex, age) and the patient's type of case, which is the combination of their symptoms, their travel during the last 14 days, their contact with an infected person or their participation in a festival requiring a gathering. We used 5 machine learning algorithms (LR, SVM, k-NN, RF, XGBoost) and 1 deep learning algorithm (ANN). Our models were validated with train-test split approach. The experimental results indicate that our predictive models identify patients that have COVID-19 disease at an accuracy of 73% and AUC of 69%. It is observed that predictive models trained on patients' basic information and type of case could be used to predict COVID-19 infection in Senegal and can be helpful for medical experts to optimize the resources efficiently.

Iconic Visualization of Sickle Cell Patients Current and Past Health Status.

Rapid access to patient overall health status is essential for a physician during a medical consultation. The use of a HIS for the management of neonatal screening and follow-up of sickle cell disease patients at CERPAD in the Saint-Louis region of Senegal leads the patient electronic records growing in volume and complexity. To facilitate access to relevant information and shortens the time required to analyze and understand these clinical data, an original solution is to set up a data visualization system. In this article, we propose the integration of two iconic visualization tools into the SIMENS-CERPAD module designed for sickle cell screening and healthcare. The two tools use the VCM iconic language and consist of a simplified anatomical schema showing the current health status of the patient and a timeline to visualize its temporal evolution.

SIMENS-LIS4SC, a Laboratory Information System for Biological Tests of Sickle Cell Screening and Healthcare.

Neonatal screening and ongoing follow-up of children with sickle cell disease are essential to reduce the mortality caused by this disease. To ensure care continuity, it is essential to include in the patient's record the history and details of biological tests. Thus, it is necessary to provide a Laboratory Information System for electronic management of biological test prescription and results, and the laboratory system must integrate well with Health Information Systems. In this paper, we propose a Laboratory Information System for the management of biological tests for the neonatal screening and healthcare of sickle cell disease in Senegal.

IDOMEN: An Extension of Infectious Disease Ontology for MENingitis.

In sub-Saharan African countries the prevention and control of epidemic diseases requires the improvement of the surveillance system for these diseases. Biomedical ontologies are a growing field that can improve health information systems. Indeed biomedical ontologies allow semantic support, data integration, automated reasoning. We are building a meningitis ontology to assist filtering messages relevant to meningitis domain on social media in order to predict a possible epidemic. Indeed, the messages filtered are used for data and event extraction that serve as input for a meningitis surveillance system. In this paper we focused on the modeling and formalization of different perspectives of the meningitis disease such as biological perspective, clinical perspective, epidemiological and public health perspective. This paper presents the three modules in the global Infection Disease Ontology for Meningitis (IDOMEN) and at the end, we illustrate a case of reasoning with our ontology.

Model-Driven Architecture Based Software Development for Epidemiological Surveillance Systems.

Epidemiological surveillance systems enable collection, analysis and dissemination of information on the monitored disease to different stakeholders. It may be done manually or using a software. Given the poor performances of manual systems, the software approach is generally adopted. Epidemiological surveillance systems are based on existing softwares, softwares developed from scratch given the specifications or softwares provided by a vendor. These solutions are not always suitable because epidemiological surveillance systems evolve quickly (new drugs, new treatment protocols, etc.), leading to software updates, which can take time (while waiting for a new version) and be expensive. In this article, we present the use of the Model-Driven Architecture (MDA) approach to model and generate epidemiological surveillance systems. The result is a complete MDA based methodology and tool to develop epidemiological surveillance systems. The tool was used to model and generate softwares that are now used for epidemiological surveillance of tuberculosis in Cameroon.

Towards an Information System for Sickle Cell Neonatal Screening in Senegal.

Sickle cell disease is a major public health problem in Senegal. It is an inherited disease that affects about 300,000 births worldwide each year. There are 70 million people affected worldwide, 80% of whom live in sub-Saharan Africa. In Senegal, 1 in 10 people carries the sickle cell disease gene. This disease requires follow-up from birth and for life. The patient care requires the integration and the analysis of biological, clinical, social, economic data., etc. In this paper, we propose a health information system for data management of the blood sampling from the newborn at the maternity wards and the disease screening at the Center for Research and Ambulatory Care of the Sickle Cell Disease (CERPAD).

Communicable and non-communicable disease risks at the Grand Magal of Touba: The largest mass gathering in Senegal.

BACKGROUND: An estimated 4-5 million individuals gather each year in the holy city of Touba, Senegal during the Grand Magal religious pilgrimage. Pilgrims come from across Senegal and the surrounding countries, as well as from countries outside Africa. It is the largest mass gathering (MG) of the Mouride community and the largest Muslim religious MG in West Africa. METHOD: A cross-sectional study was conducted on all patients who attended a public healthcare structure during the November 2015 Grand Magal. RESULT: Data were collected on a total of 32,229 healthcare contacts. The most frequent reasons for consultation were trauma, followed by fatigue and heatstroke. Infectious diseases were also prevalent with, notably, a high rate of febrile systemic illnesses and malaria, diarrheal diseases, and respiratory tract infections. Such results are likely to be linked to overcrowding and climatic conditions, the relative lack of sanitary facilities, and limited medical resources available during the event. CONCLUSION: The context of the Grand Magal MG is unique, given its location in a tropical developing country and its international component which may favor the globalization of locally endemic diseases. As such, it warrants investment in modern methods for public health surveillance and planning of the event.

A National Medical Information System for Senegal: Architecture and Services.

In Senegal, great amounts of data are daily generated by medical activities such as consultation, hospitalization, blood test, x-ray, birth, death, etc. These data are still recorded in register, printed images, audios and movies which are manually processed. However, some medical organizations have their own software for non-standardized patient record management, appointment, wages, etc. without any possibility of sharing these data or communicating with other medical structures. This leads to lots of limitations in reusing or sharing these data because of their possible structural and semantic heterogeneity. To overcome these problems we have proposed a National Medical Information System for Senegal (SIMENS). As an integrated platform, SIMENS provides an EHR system that supports healthcare activities, a mobile version and a web portal. The SIMENS architecture proposes also a data and application integration services for supporting interoperability and decision making.

Design of schistosomiasis ontology (IDOSCHISTO) extending the infectious disease ontology.

Epidemiological monitoring of the schistosomiasis' spreading brings together many practitioners working at different levels of granularity (biology, host individual, host population), who have different perspectives (biology, clinic and epidemiology) on the same phenomenon. Biological perspective deals with pathogens (e.g. life cycle) or physiopathology while clinical perspective deals with hosts (e.g. healthy or infected host, diagnosis, treatment, etc.). In an epidemiological perspective corresponding to the host population level of granularity, the schistosomiasis disease is characterized according to the way (causes, risk factors, etc.) it spreads in this population over space and time. In this paper we provide an ontological analysis and design for the Schistosomiasis domain knowledge and spreading dynamics. IDOSCHISTO - the schistosomiasis ontology - is designed as an extension of the Infectious Disease Ontology (IDO). This ontology aims at supporting the schistosomiasis monitoring process during a spreading crisis by enabling data integration, semantic interoperability, for collaborative work on one hand and for risk analysis and decision making on the other hand.