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.
Association between patient‐initiated emails and overall 2‐year survival in cancer patients undergoing chemotherapy: Evidence from the real‐world setting
In this real-world study, we assessed the association between patient-initiated emails and overall sruvival among cancer patients undergoing chemotherapy. Overall 2‐year survival was higher in patients who were email users. Email users also had higher rates of healthcare utilization, including face‐to‐face visits. Patient portals provide a tool for patients to communicate with their care team that provides overall clinical benefit for advanced cancer patients. Patient emails are a novel source of patient-generated data that may play a vital role in patient symptom monitoring.
MINIMAR (MINimum Information for Medical AI Reporting): Developing reporting standards for artificial intelligence in health care.
Significant advancements in artificial intelligence (AI) has lead to the use of classification and prediction models in health care to enhance clinical decision-making. However, these advances are limited by the lack of reporting standards for the data used to develop those models, model architecture, and model evaluation. 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 in these emerging technologies. This may promote the development and use of associated clinical decision support tools, as well as manage concerns regarding accuracy and bias.