Lab News

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.

Orthogonal NLP Methods for Clinical Phenotyping

Clinical care guidelines recommend that newly diagnosed cancer patients at high risk for metastatic spread receive a bone scan prior to treatment. A comprehensive system to assess bone scan utilization for prostate cancer patients includes the the synthesis of diverse, complex data from EHR. We developed CNN and rule-based models to capture bone scan documentation in clinical notes. The comparison of NLP models to maximize prediction accuracy suggests the CNN model outperformed the rule-based model. We further demonstrate a combination of both models could maximize precision or recall, based on the study question.

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 may inhibit the effectiveness of prodrug opioids. 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