- The Evolution of A.I. in Health: Where Humans Meet Machines
- Read about a recent webinar we participated in with FORTUNE Media. The event convened experts from government, technology, and academia to discuss how A.I. can benefit our health care system and guide clinicians in their decision making.
The Boussad lab has established a network study (PORPOISE) on the OHDSI community to identify patients at risk of postoperative prolonged opioid use. PORPOISE aims to develop and validate machine learning models in a diverse, multisite cohort by evaluating their generalizability, discrimination, and calibration. The research protocol and materials can be found in the GitHub repository for the OHDSI Study.
Check out this MedCity News article highlighting our study on opioid dependency in opioid-naive Medicaid patients. Highlighted publication: Presription quantity and duration predict progression from acute to chronic opioid use in opioid-naive Medicaid patients.
Our AI ethics work was recently featured in VentureBeat. Read up on the discussion of how artificial intelligence is transforming medicine and how we make sure it works for everyone.
Leveraging weak supervision to perform named entity recognition in electronic health records progress notes to identify the ophthalmology exam
We have developed a deep learning pipeline to recognize eye examination components from progress notes. Our system leverages a weakly supervised system to produce nearly cleanly labeled notes to train BERT-based models. Our work holds many potential research applications, from precise cohort design to feature engineering for predictive model development.
The AI life cycle: a holistic approach to creating ethical AI for health decisions
Artificial intelligence (AI) has the potential to revolutionize many aspects of clinical care, but it can also lead to patient and community harm, the misallocation of health resources and the exacerbation of existing health inequities, which greatly threaten its overall efficacy and social impact. These issues have prompted the movement toward ethical AI, a field devoted to raising and addressing ethical issues related to the development and application of AI. Read this paper to learn about the AI life cycle to create ethicial AI for health decision.
Picture a data scientist: A call to action for increasing diversity, equity, and inclusion in the age of AI
The lack of diversity, equity, and inclusion continues to hamper the artificial intelligence (AI) field and is especially problematic for healthcare applications. In this article, we expand on the need for diversity, equity, and inclusion, specifically focusing on the composition of AI teams. We call to action leaders at all levels to make team inclusivity and diversity the centerpieces of AI development, not the afterthought.