Projects and Publications

Analyzing Community Health Worker (CHW) Perceptions of AI-Enabled mHealth

As researchers and technology companies rush in to develop AI applications that aid the health of marginalized communities, it is critical to consider the needs and perceptions of the community health workers (CHWs) and other stakeholders involved in integrating these AI applications into the essential healthcare services provided to low-resource communities. For this work, we piloted a 3-month study, the first of its kind, examining CHW perceptions of AI in rural India. Accepted to CHI 2021 (Pre-print).

Building Smartphone-based Methods for Low-Resource Diagnostic Monitoring of Pneumonia

People in Africa are burdened with 71% of the global distribution of infectious diseases, despite only making up 12% of the global population. A shortage of medical professionals and lack of access to basic healthcare contributes heavily to this disparity. The ubiquity of mobile phones and strong mobile network coverage across the African continent has led to a surge of mobile health (mHealth) applications that have been developed to identify a variety of infectious and tropical diseases. Our work involves leveraging computer vision and deep learning methods such as RNNs and motion magnification to detect fine-grained respiratory motions such as chest indrawing, coughing, and other symptoms associated with pneumonia with the goal of improving healthcare access throughout the Global South. Work in progress.

Developing Frameworks to Evaluate Patient Reception to the Introduction of AI-enabled Healthcare

In healthcare, the role of artificial inteliigence is continually evolving and understanding the challenges its introduction poses on relationships between healthcare providers and patients will require a regulatory and behavioural approach that can provide a guiding base for all users involved. Our work proposes a framework to set guidelines for how AI-enabled technologies should be formally introduced to patients in healthcare settings. The core principles of this framework are set into 5 parts: Acceptability, Comfortability, Informed Consent, Privacy, and Security. Preliminary work acccepted to the Data4Good: Designing for Diversity and Development Workshop (AVI), expanded work under review at FAccT 2021.

Please check out my full list of publications here.


News & Media




My 2021 internship search was successful but I’ll be on the lookout for research internships in the area of Human-AI interaction, Ethical AI, AI/ML for Healthcare, and related fields for next summer!


Interested in applying to grad school or finding fellowships to fund your studies?

If you have any opportunities to share, please feel free to make a pull request!