Research

My research covers Spatial Big Data Management, Medical Imaging Informatics, Assistive Technologies, AI in Healthcare, Population Health and Blockchain. Supported applications include geospatial big data, Internet of Things, digital pathology (2D and 3D), human atlases, radiology imaging, opioid epidemic research, eye gaze and brain-computer interface based communication for patients, and healthcare data integration.

The work is sponsored by NSF, NIH, DOD CDMRP, PCORI, CDC, ALS Association, Pitney Bowes, Amazon and Google.

We are developing human-centered AI frameworks that bridge the gap between AI model developers and the clinicians and patients who use them. Our goal is to build AI that is not only accurate, but interpretable, trustworthy, and clinically actionable — with stakeholders engaged throughout model development, not just at the end.

Key innovations include interpretability by design, participatory co-design with clinicians and patients, and multi-level explanations at both population and individual patient levels. Funded by PCORI.

My research goal on big data management and analytics is to address the research challenges for delivering effective, scalable and high performance software systems for managing, querying and mining complex big data at multiple dimensions, including 2D and 3D spatial and imaging data, temporal data, spatial-temporal data, and sequencing data.

Project website: lensplatform.github.io

Systematic analysis of large-scale whole slide image data can involve many interrelated analyses on large amounts of images, generating tremendous quantifications such as shape and texture, classifications of the quantified features, and spatial queries to discover spatial relationships and patterns. Our research focuses on spatial and image analytics at extreme scale.

Project website: lensplatform.github.io

The United States is experiencing an opioid crisis, with an estimated 10 million people aged 12 or older misusing opioids, and 130 deaths a day from opioid overdose. We take an integrative big data driven approach by integrating multi-scale data such as electronic health records, social media and the Web, social-economic data and government policies for spatial-temporal and text analytics and predictive modeling.

Project website: ai4oe.github.io

EyeCanDo is the next generation communication platform to enable communication using eye gaze and brain-computer interfaces (BCI), with affordable off-the-shelf devices. People with motor disabilities (e.g., ALS patients) will be able to use the system to maximize their capabilities for communication using their choice of comfortable modality. EyeCanDo is built upon AI-powered interactions, machine learning and augmented reality, available on iOS devices.

Funded by ALS Association and DOD CDMRP.   Project website: eyecando.org

Electronic health records (EHRs) are critical information for diagnosis and treatment in healthcare, which need to be frequently distributed and shared among peers such as healthcare providers, insurance companies, pharmacies, researchers, and patient families. A patient-centric, blockchain-based EHR sharing system with a permissioned blockchain framework with an immutable and transparent ledger will help manage authentication, confidentiality, and accountability for EHR data sharing.