Latest information on COVID-19

Lab News

Jan January 29 Wed 2020

Stanford Strong. Diversity & Inclusion Week 2020 #BoussardLab

Dec December 03 Tue 2019

We are hosting a monthly workshop for clinical informatics: DDAMES: Data Divas for AI in Medcine at Stanford. More information can be found here.

Sep September 17 Tue 2019

Dr. Hernandez-Boussard received a new R01 award from NLM, Advancing Knowledge Discovery for Postoperative Pain Management. This work will apply deep learning techniques to identify patients at high risk for adverse postoperative pain outcomes. Check out our recruiting page to join our team!

Sep September 04 Wed 2019

Dr. Hernandez-Boussard discusses the use of real world data for clinical assertions in a recent interview with Stanford Medicine based on findings from her recent JAMIA article. More details can be found here.

Recent Publications

MINIMAR (MINimum Information for Medical AI Reporting): Developing reporting standards for artificial intelligence in health care.

The rise of digital data and computing power have contributed to significant advancements in artificial intelligence (AI), leading to the use of classification and prediction models in health care to enhance clinical decision-making for diagnosis, treatment and prognosis. However, such advances are limited by the lack of reporting standards for the data used to develop those models, the model architecture, and the model evaluation and validation processes. Here, we present MINIMAR (MINimum Information for Medical AI Reporting), a proposal describing the minimum information necessary to understand intended predictions, target populations, and hidden biases, and the ability to generalize these emerging technologies. We call for a standard to accurately and responsibly report on AI in health care. This will facilitate the design and implementation of these models and promote the development and use of associated clinical decision support tools, as well as manage concerns regarding accuracy and bias

Real world evidence in cardiovascular medicine: ensuring data validity in electronic health record-based studies

With growing availability of digital health data and technology, health-related studies are increasingly augmented or implemented using real world data (RWD). Recent federal initiatives promote the use of RWD to make clinical assertions that influence regulatory decision-making. Here we assess the credibility of clinical assertions in cardiovascular medicine using electronic health records (EHR). In this study, recall varied greatly between EHR data types; EHR structured data did not meet regulatory grade criteria, while EHR unstructured data did. These results suggest that recall should be routinely measured in EHR-based studes intended for regulatory use. Furthermore, advanced data and technologies may be required to achieve regulatory grade results.