About

Syed Arefinul Haque is an NLP Research Scientist working at the Advanced Analytics team at Independence Blue Cross (IBX), where he primarily focuses on extracting insights from unstructured text data, such as call center transcripts, electronic health records, and benefit documents using various NLP methods. His collaborative research projects include creating and evaluating large language models from insurance claims to predict future healthcare visit sequences of individuals. He has developed generative AI and classical NLP based solutions for entity disambiguation, keyword extraction, and knowledge graph visualization pipelines from unstructured texts.

Before this role, he worked as an Artificial Intelligence Fellow at office of translation sciences, Food and Drug Administration (FDA), and created a pioneering AI-enabled software prototype to identify adverse drug event (ADE) safety signals from free-text discharge summaries in clinical notes to enhance opioid drug safety and aid related research activities at the FDA.

He received his Ph.D. in Network Science from Network Science Institute, Northeastern University on 2022. This interdiscplinary program allowed him to interact and collaborate with mentors who come from diverse range of disciplines such as Physics, Sociology, Epidemiology, Computer Science, and Communication Studies. In his PhD projects, he used Network Science and NLP methods to identify gender and racial diversity in researchers and experts, and how ideas related to gender diversity move between one university to another. One of his other PhD research projects involved working on epidemiology. Specifically, he created contact matrices to model the transmission of influenza and other infectious diseases.

He is from Bangladesh where he completed BBA in finance from IBA, University of Dhaka, and MSc in Computer Science from United International University.

Education

Ph.D. in Network Science (2022, expected)
Northeastern University
Boston, MA, USA

M.Sc. in Computer Science and Engineering (2015)
United International University
Dhaka, Bangladesh

B.B.A in Finance (Minor: Marketing) (2013)
Institute of Business Administration, University of Dhaka
Dhaka, Bangladesh

Publications

Refereed Journal Articles

  • Sorbello, A., Haque, S.A., Hasan, R., Jermyn, R., Hussein, A., Vega, A., Zembrzuski, K., Ripple, A. and Ahadpour, M., 2023. Artificial Intelligence–Enabled Software Prototype to Inform Opioid Pharmacovigilance From Electronic Health Records: Development and Usability Study. JMIR AI, 2, p.e45000. [link]

  • Gold, J. R., Gates, A. J., Haque, S. A., Melson, M. C., Nelson, L. K. & Zippel, K., 2022. The NSF ADVANCE network of organizations. ADVANCE Journal 3 (1). [link]

  • Nelson, L. K., Getman, R. & Haque, S. A. (2021). And the Rest is History: Measuring the Scope and Recall of Wikipedia’s Coverage of Three Women’s Movement Subgroups. Sociology Methods & Research, Online First. [link]

  • Cevik, M., Haque, S. A., Manne, J., Kuppalli, K., Sax, P. E., Majumder, M. S. & Orkin C., 2021, Gender disparities in COVID-19 clinical trial leadership. Clinical Microbiology and Infection.
    [link]

  • Mistry, D., Litvinova, M., y Piontti, A.P., Chinazzi, M., Fumanelli, L., Gomes, M.F., Haque, S. A., Liu, Q.H., Mu, K., Xiong, X. Halloran, M.E., Longini Jr., I. M., Merler S., Ajelli, M. & Vespignani A., 2021, Inferring high-resolution human mixing patterns for disease modeling. Nature Communications. 12(1), pp.1-12. [link]

  • Hassan, M. K., Islam, L. & Haque, S. A., 2017, Degree distribution, rank-size distribution, and leadership persistence in mediation-driven attachment networks. Physica A: Statistical Mechanics and its Applications, 469, 23-30.
    [link]

  • Haque, S. A., Islam, S., Islam, M. J., & Grégoire, J. C., 2016. An architecture for client virtualization: A case study. Computer Networks, 100, 75-89.
    [link]

Refereed Conference Articles

  • Saquib, N., Huq, F., & Haque, S. A., 2022. graphiti: Sketch-based Graph Analytics for Images and Videos. CHI ‘22: CHI Conference on Human Factors in Computing Systems.
    [link]

  • Chowdhury, S. S., Saquib, N., Zawad, N., Mandal, M. K., & Haque, S. A., 2018. Statement networks: a power structure narrative as depicted by newspapers. Machine learning for developing world (ML4D) workshop at NeurIPS 2018. arXiv preprint arXiv:1812.03632.
    [link]

  • Haque, S. A., Islam, S., & Grégoire, J. C., 2015. Short Paper:’Virtual P2P client: Accessing P2P applications using virtual terminals’. In 2015 18th International Conference on Intelligence in Next Generation Networks (pp. 142-144). IEEE.
    [link]