Search

Opioid addiction rates in the United States have long been on the rise, but the expansion of rehabilitation programs have been falling behind. In 2013, an estimated 20.4 million people out of 22.7 million who required treatment for illicit drug addiction failed to receive proper treatment at specialty facilities. Without proper rehabilitation, patients can often fall back into a cycle of substance abuse. Considering the societal stigma of addiction and seeking treatment, technological rehabilitation provides a more conservative alternative for these patients in terms of cost, privacy, and convenience. Technological rehabilitation is threatened, however, by collaborative non-adherence (CNA), which is the process of giving one’s biosensor to someone else. The goal of this mathematical modeling project is to improve a previously made device, create an app that will be used in tandem with the device, and modify existing algorithms to increase accuracy. In this project we designed updated code models and smartwatch applications that best benefit a recovering opioid addiction patient. Our code models will be adapted to help prevent CNA, and our machine learning algorithms will be modified with the goal of at least 90% accuracy when used on patients outside of our database. Our application will keep track of a patient’s sobriety status and encourage healthy habits. We also plan to provide an online community consisting of past opioid addicts that can connect via the app and act as mutual support. This project has helped us to provide insight on how technology can be used for opioid addiction treatment, and has also examined how group rehabilitation may be more beneficial than isolated treatment. Our app and device are also the beginning to a cheaper avenue of solving the opioid crisis and is an innovative step into the realm of technological rehabilitation. We hope to further develop and deploy our prototype with the user community to validate the mathematical model, computational algorithms, and app., Journal of Student-Scientists' Research, Vol. 2 (2020)

Malaria is one of the deadliest endemic diseases in developing countries with millions of cases recorded each year. In 2018, there were over 200 million malaria cases and over 400,000 deaths worldwide. Having widespread access to efficient malaria detection would help reduce malaria cases in these countries. In recent years, several computational algorithms have been applied to detect malaria from a variety of approaches, including analysis of blood smear images and presence of protein biomarkers in urine and saliva. For blood smear images, recent literature employs a combination of image segmentation techniques and machine learning classifiers. While multiple techniques have been suggested, and advances are being made, there is still work that needs to be done to identify the best combination of these algorithms. The aim of this study was to perform a comparative analysis of four different image segmentation techniques and five machine learning classifiers on a dataset of roughly 27,000 blood smear images, half of which were infected with malaria. The focus of the work involved identifying combinations of image segmentation and machine learning algorithms that resulted in the highest accuracy in classifying a blood smear image as infected or uninfected, leading to improved malaria detection. The Python programming language with the libraries OpenCV and Scikit-learn were used for the implementation of the computational algorithms developed in this work. The resulting confusion matrices helped to identify efficient combinations of image segmentation techniques and machine learning classifiers. Using a random forest classifier with binary thresholding resulted in the highest accuracy, with around 90%, but some other combinations also performed reasonably well. Our computational experiments also found that adaptive and K-means thresholding were not efficient, averaging slightly above 50% accuracy. The findings from this work provide an insight to identifying the best combination of an image segmentation technique and a machine learning classifier that can potentially be programmed into a future real-time mobile app that can be deployed in developing countries., Journal of Student-Scientists' Research, Vol. 2 (2020)

The COVID-19 pandemic continues to present tremendous national challenges, as the number of cases in the United States rapidly increases. To understand this increase, many researchers have considered developing mathematical models that help to capture the dynamics of the spread of the disease. For COVID-19, the compartmental SEIR model and its variations have been widely employed. These models differ in the type of compartments included, nature of the transmission rates, seasonality, and several other factors. While the spread of COVID-19 is largely attributed to a wide range of human behaviors in the population, several of these traditional epidemiological SEIR models do not account for such behaviors. In this project, we consider a novel SEIR-based model that considers various behaviors including confinement, quarantine, and social distancing. We also explore having the transmission rate as a function of time. Furthermore, using the Next Generation Matrix method, we derive a basic reproduction number, which indicates the estimated number of new infectious cases per case. Numerical simulations for the various models we created was performed and a user-friendly graphical user interface was created. In the future, we plan to expand this project to incorporate control measures, such as face masks, age-based behaviors, transmission rates dependent on social behavior, and the CDC’s Five Pandemic Planning Scenarios. Ultimately, by accounting for behaviors in epidemiological models, we can investigate the COVID-19 pandemic more accurately and help educate the public about measures to mitigate it., Journal of Student-Scientists' Research, Vol. 2 (2020)

The COVID-19 pandemic has caused more than 16 million cases and 600,000 deaths worldwide in little over half a year. Most epidemic models studying the virus have focused on the macro scale, evaluating the progression of infected cases across large regions. However, the significant airborne infectivity of the virus has led to important public policy questions about safety measures in enclosed spaces like schools, aircraft, and hospitals. Alarmingly, there is a severe lack of coronavirus-specific literature that models the medium to long term progression of infections in these small spaces. In this work, we introduce a novel framework that combines the Wells-Riley airborne infection model, the SEIR epidemiological model, and an infectious concentration transport model. This flexible framework allows us to study the dynamics and progression of airborne diseases in enclosed spaces. While previous models of this type only studied timescales shorter than the incubation rate of the disease, our coupled model removes that limitation. We then apply this model to a benchmark application with parameters proposed by the CDC for COVID-19 and simulate scenarios that mimic the effects of control measures like wearing face-masks and changes in ventilation. We also build a graphical user interface to allow user-friendly scenario testing., Journal of Student-Scientists' Research, Vol. 2 (2020)