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.



Selected Journal Articles

Text Guide: Improving the Quality of Long Text Classification by a Text Selection Method Based on Feature ImportanceThe performance of text classification methods has improved greatly over the last decade for text instances of less than 512 tokens. This limit has been adopted by most state-of-the-research transformer models due to the high computational cost of analyzing longer text instances. To mitigate this problem and to improve classification for longer texts, researchers have sought to resolve the underlying causes of the computational cost and have proposed optimizations for the attention mechanism, which is the key element of every transformer model. In our study, we are not pursuing the ultimate goal of long text classification, i.e., the ability to analyze entire text instances at one time while preserving high performance at a reasonable computational cost. Instead, we propose a text truncation method called Text Guide, in which the original text length is reduced to a predefined limit in a manner that improves performance over naive and semi-naive approaches while preserving low computational costs. Text Guide benefits from the concept of feature importance, a notion from the explainable artificial intelligence domain. We demonstrate that Text Guide can be used to improve the performance of recent language models specifically designed for long text classification, such as Longformer. Moreover, we discovered that parameter optimization is the key to Text Guide performance and must be conducted before the method is deployed. Future experiments may reveal additional benefits provided by this new method.


Optimizing COVID-19 vaccine distribution across the United States using deterministic and stochastic recurrent neural networksOptimizing COVID-19 vaccine distribution can help plan around the limited production and distribution of vaccination, particularly in early stages. One of the main criteria for equitable vaccine distribution is predicting the geographic distribution of active virus at the time of vaccination. This research developed sequence-learning models to predict the behavior of the COVID-19 pandemic across the US, based on previously reported information. For this objective, we used two time-series datasets of confirmed COVID-19 cases and COVID-19 effective reproduction numbers from January 22, 2020 to November 26, 2020 for all states in the US. The datasets have 310 time-steps (days) and 50 features (US states). To avoid training the models for all states, we categorized US states on the basis of their similarity to previously reported COVID-19 behavior. For this purpose, we used an unsupervised self-organizing map to categorize all states of the US into four groups on the basis of the similarity of their effective reproduction numbers. After selecting a leading state (the state with earliest outbreaks) in each group, we developed deterministic and stochastic Long Short Term Memory (LSTM) and Mixture Density Network (MDN) models. We trained the models with data from each leading state to make predictions, then compared the models with a baseline linear regression model. We also remove seasonality and trends from a dataset of non-stationary COVID-19 cases to determine the effects on prediction. We showed that the deterministic LSTM model trained on the COVID-19 effective reproduction numbers outperforms other prediction methods.
Predicting the Dynamics of the COVID-19 Pandemic in the United States Using Graph Theory-Based Neural NetworksThe COVID-19 pandemic has had unprecedented social and economic consequences in the United States. Therefore, accurately predicting the dynamics of the pandemic can be very beneficial. Two main elements required for developing reliable predictions include: (1) a predictive model and (2) an indicator of the current condition and status of the pandemic. As a pandemic indicator, we used the effective reproduction number (Rt), which is defined as the number of new infections transmitted by a single contagious individual in a population that may no longer be fully susceptible. To bring the pandemic under control, Rt must be less than one. To eliminate the pandemic, Rt should be close to zero. Therefore, this value may serve as a strong indicator of the current status of the pandemic. For a predictive model, we used graph neural networks (GNNs), a method that combines graphical analysis with the structure of neural networks. We developed two types of GNN models, including: (1) graph-theory-based neural networks (GTNN) and (2) neighborhood-based neural networks (NGNN). The nodes in both graphs indicated individual states in the United States. While the GTNN model’s edges document functional connectivity between states, those in the NGNN model link neighboring states to one another. We trained both models with Rt numbers collected over the previous four days and asked them to predict the following day for all states in the United States. The performance of these models was evaluated with the datasets that included Rt values reflecting conditions from 22 January through 26 November 2020 (before the start of COVID-19 vaccination in the United States). To determine the efficiency, we compared the results of two models with each other and with those generated by a baseline Long short-term memory (LSTM) model. The results indicated that the GTNN model outperformed both the NGNN and LSTM models for predicting Rt.

Contact Information

r.davahli@gmail.com