I have several years of experience in data science including my time working in a leading engineering company, my involvement in different health-related research grants, and carrying out studies at Dr. Waldemar Karwowski’s lab.
During PhD program, I mainly focused on analyzing human behavior, human emotions, and the COVID-19 pandemic using different methodologies including Machine Learning (ML), Natural Language Processing (NLP), and sequence-learning predictive models.
In human behavior and emotions, my objective was to identify and predict human behavior and emotions in social media by using NLP. In this area, I identified personality traits through mining unstructured textual data, compared the quality and speed of sentence classifications, improved the quality of text classifications, and designed intelligent filters based on NLP. Furthermore, I studied different language models including BERT, Word2Vec, Glove, and RoBERTa.
In the COVID-19 topic, I developed accurate, sequence-learning predictive models to determine the dynamics of COVID-19. The development of these models was originally born out of my determination that predictive models of the pandemic’s effects had been undertheorized, and so I used my expertise with Deterministic and Stochastic Neural Networks as well as Graph Neural Networks to construct accurate models. Using time-series COVID-19 data, I used the effective reproduction number (Rt) of the disease to predict the dynamics of the pandemic. In this topic, I also used different theories and approaches such as chaotic behavior, connectivity networks, time-series analysis, system dynamics, and graph theory to better understand the non-linear behavior of the COVID-19 pandemic. The results were published in PloS One and the International Journal of Environmental Research and Public Health.
Looking forward, I’d like to continue my research in the application of NLP and graph neural networks in healthcare. I expect these areas to be fruitful and have a significant impact on medical care. My general research plan is to adapt forefront and leading-edge artificial intelligence (AI) models in healthcare to address challenging problems. I am very passionate about building novel, interdisciplinary, complex, interactive systems based on forefront AI approaches. There are several concrete directions I’d like to pursue in the near term and long term.
1- Transfer learning in healthcare. I have significant experience in using different transfer learning models especially BERT and I’d like to use these models to better detect patterns of unstructured textual data in electronic health records (EHR). Different aspects of unstructured textual data of EHR such as patient-centered outcomes, clinical trial outcomes, risks of developing complications, clinical trail-derived survival models can be analyzed using transfer learning models.
2- Graph neural networks in healthcare. Deterministic and stochastic Neural Networks cannot represent complex interactions among different types of medical information in EHR. However, graph neural networks addressed this issue by creating networks among data in EHR. I’d like to use my significant experience in graph theory and graph neural networks to study different areas of healthcare such as diagnosis prediction, drug repurposing, safe medicines, and drug combinations.
3- Virtual electronic health records (vEHR). In healthcare, data privacy plays an important role in developing and implementing AI. Because of the complexity of protecting data in healthcare, data privacy has had a significant impact on data availability. In this situation, AI can be trained in virtual environments containing patient demographics, disease states, and health conditions. Creating virtual health data based on virtual environment is one of my main objectives.