Overview of the Harvard Data Science Initiative Postdoctoral Fellow Research Fund
The HDSI (Harvard Data Science Initiative) Public Service Data Science Graduate Fellowship supports Master’s students in Harvard’s data science programs (Biomedical Informatics, Health Data Science, Data Science) who want to explore career paths at not-for-profit and public sector organizations through a summer internship.
The fellowship includes a $10,000 stipend to support an unpaid summer 2022 internship at a not-for-profit or public sector organization that either (a) applies data science to solve social challenges, or (b) advocates for responsible data science. The stipend is intended to support living expenses during the summer and may not be used for tuition.
Deadline: 11:59 PM, March 15, 2022
Read about past projects by Postdoctoral Research Fellows Dr. Duo Peng and Dr. Maia Jacobs:
Machine learning methods for integrating biological multi-omic datasets to decipher parasite development in the malaria mosquito
Duo Peng (Harvard T.H. Chan School of Public Health)
In 2018, there were 405,000 deaths globally caused by malaria transmitted by Anopheles mosquitoes. Dr. Duo Peng, Postdoctoral Research Fellow (2019), developed machine learning methods for integrating biological multi-omics datasets to decipher key factors affecting malaria parasite development in mosquitos, specifically Plasmodium falciparum – the deadliest human malaria parasite – in the Anopheles gambiae mosquito. In this project, Peng and his team performed high-depth transcriptome sequencing and created a machine learning model to identify key mosquito gene candidates that shape malaria parasites’ development in mosquitos. The results of this project provide further support that the (mosquito) fatty acid metabolism is significant in shaping malaria parasite development. Peng’s findings also support a key biological finding that informs our understanding of malaria transmission biology. This research validates identifying mosquito genes and pathways which can serve as targets of malaria transmission control programs. In addition, it will be able to provide a framework for subsequent studies at a finer resolution.
Personalizing mental health care: Bringing machine learning support into the clinic through user-centered design
Maia Jacobs (Harvard John A. Paulson School of Engineering and Applied Sciences)
The promise of machine learning (ML) in medicine is alluring, but few tools are actually being used in clinical practice. Dr. Maia Jacobs, Postdoctoral Research Fellow (2019), designed her project to involve a cross-disciplinary collaboration between human-computer interaction, machine learning (ML), and psychiatrists at Massachusetts General Hospital in order to evaluate how machine learning algorithms can support complex clinical decision making. More specifically, her team evaluated the opportunities and barriers to implementing decision support tools, driven by machine-learning models, that provide clinicians with treatment recommendations for patient diagnosed with major depressive disorder (MDD). With the funding awarded by HDSI, Jacobs and her team explored to what extent clinical practice could be improved if clinicians were presented with recommendations produced by ML predictions. Using a series of experiments and co-design sessions with healthcare providers, Jacobs found that the implementation of ML tools with high accuracy rates may be insufficient to improve treatment selection accuracy, while also demonstrating the risk of overreliance when clinicians are shown incorrect treatment recommendations. Her findings also indicate that current trends in explainable AI may be inappropriate for clinical environments, and suggest paths towards designing these tools for real-world medical systems. Collectively, her work demonstrates the importance of human-computer interaction and data science collaborations in designing ML tools for clinical decision-making.