Feb February 20 Wed 2019
Join us at the AACR meeting Modernizing Population Science in the Digital Age where Dr. Hernandez-Boussard will be giving a plenary talk on the lab's research and vision for the advancing cancer research using cutting edge technologes.
Jan January 07 Mon 2019
The Boussard lab is recruiting a postdoctoral scholar with experise in Artificial Intelligence technologies, including natural language processing (NLP) and machine learning. For more details, please click here.
Oct October 19 Fri 2018
Our team was awarded a seed grant to explore demographic biases in machine learning algorithms. See more here
Aug August 22 Wed 2018
Dr. Hernandez-Boussard hosted a panel of women at the AI in Medicine: Inclusion & Equity symposium: Frameworks for an Inclusive Future of AI in Healthcare. More information can be found here.
Predicting inadequate postoperative pain management in depressed patients: A machine learning approach
Widely-prescribed prodrug opioids (e.g., hydrocodone) require conversion by liver enzyme CYP-2D6 to exert their analgesic effects. The most commonly prescribed antidepressant, selective serotonin reuptake inhibitors (SSRIs), inhibits CYP-2D6 activity and therefore may reduce the effectiveness of prodrug opioids. We examined how SSRIs, such as Zoloft and Prozac may inhibit the effectiveness of prodrug opioids, such as hydrocodone (e.g. Vicodin and Norco). Using a machine-learning approach we found that patients using both an SSRI and a prodrug opioid had significantly worse pain control than those not prescribed a prodrug opioid. The study provides the first direct clinical evidence that SSRI use is associated with more difficult pain control. PlosOne
Weakly Supervised NLP to Advanced Patient-Centered Outcomes Research
We have developed a machine learning method to categorize clinical notes based on important PCOs that trains a classifier on sentence vector representations labeled with a domain-specific dictionary, which eliminates the need for manual engineering of linguistic rules or manual chart review for extracting the PCOs. The weakly supervised NLP pipeline showed promising sensitivity and specificity for identifying important PCOs in unstructured clinical text notes compared to rule-based algorithms.