Publications

I am excited to share my research in the field of medical informatics. I have an upcoming publication about my Cognibot Dementia Speech System project, and currently published work includes an article published at the 2022 IEEE ICMLA conference and the peer-reviewed journal Psych. I am looking forward to sharing my knowledge and experiences with others in the field, and I welcome any opportunities for further collaboration or discussion.

Predicting Myalgic Encepalomyelitis/Chronic Fatigue Syndrome from Early Symptoms of COVID-19 Infection

Hua C, Schwabe J, Jason LA, Furst J, Raicu D. Predicting Myalgic Encephalomyelitis/Chronic Fatigue Syndrome from Early Symptoms of COVID-19 Infection. Psych. 2023; 5(4):1101-1108. https://doi.org/10.3390/psych5040073.

We investigated if predicting myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) development after contracting COVID-19 is possible by analyzing symptoms from the first two weeks of COVID-19 infection. Using participant responses to the 54-item DePaul Symptom Questionnaire, we built predictive models based on a random forest algorithm using the participants’ symptoms from the initial weeks of COVID-19 infection to predict if the participants would go on to meet the criteria for ME/CFS approximately 6 months later. Early symptoms, particularly those assessing post-exertional malaise, did predict the development of ME/CFS, reaching an accuracy of 94.6%. We then investigated a minimal set of eight symptom features that could accurately predict ME/CFS. The feature reduced models reached an accuracy of 93.5%. Our findings indicated that several IOM diagnostic criteria for ME/CFS occurring during the initial weeks after COVID-19 infection predicted Long COVID and the diagnosis of ME/CFS after 6 months.

Keywords: Long COVID; PASC; Myalgic Encephalomyelitis/Chronic Fatigue Syndrome; ME/CFS

Predicting ME/CFS After Infectious Mononucleosis Using Cytokine Network Correlations

J. Schwabe, C. Hua, E. M. Allen, L. A. Jason, J. Furst and D. Raciu, “Predicting ME/CFS After Infectious Mononucleosis Using Cytokine Network Correlations,” 2022 21st IEEE International Conference on Machine Learning and Applications (ICMLA), Nassau, Bahamas, 2022, pp. 555-559, doi: 10.1109/ICMLA55696.2022.00091.

We investigated if a predictive modeling strategy based on the interdependence of the cytokine network could accurately predict if a patient would develop Myalgic Encephalomyelitis/Chronic Fatigue Syndrome (ME/CFS) after contracting infectious mononucleosis (IM). We analyzed previously collected data from Northwestern University (NU) students in a three-stage experiment, following them from the start of the school year (Stage 1), to development of IM (Stage 2), to six months post development of IM (Stage 3). At all three stages, blood was stored from participants for cytokine measurement and analysis. Additionally, eight psychological and behavioral scales were used to identify participants as healthy controls or as ME/CFS. Using participants’ measured cytokine expression levels, we built a predictive model based on the inherent correlations within the cytokine network. We found that we could predict ME/CFS in patients 6 months after IM with 86.84% accuracy using correlation matrices made from cytokines taken during IM infection. These results suggest that there may be potential in using an approach that is based on the interdependence of the cytokine network to predict ME/CFS post IM. Future work may explore the validity of these findings and if such an approach could have applications in other diseases.

Keywords: Correlation; Atmospheric measurements; Psychology; Machine learning; Predictive models; Particle measurements; Fatigue; Myalgic Encephalomyelitis/Chronic Fatigue Syndrome; Cytokines; Infectious mononucleosis; Cytokine Correlation