Applications of Natural Language Processing and Machine Learning to Develop Oncology Decision Aid for Multiple Myeloma in Alberta using Administrative Health Data
September 30, 2019

In Canada, approximately 1,700 men and 1,200 women were diagnosed with multiple myeloma (MM) in 2017. While this only corresponds to 1.6% and 1.2% of new cancer cases each year, the approximate five-year net survival rate according to the Canadian Cancer Society (estimated for the years 2006-2008) is relatively low at 42%.

Novel, targeted therapies are in development for multiple myeloma (MM) and will likely alter the disease course and survival rates. A critical step in the delivery of targeted therapies is the accurate identification of eligible patients. Testing for MM begins with histopathology and results inform further testing for molecular biomarkers and sensitizing mutations before selecting a line of treatment. Thus, histopathology results must be accurate and easily combined with other patient characteristics to inform clinical decision making. In Alberta, histopathology results are presented to physicians as written pathology reports, where extracting the relevant information may be time-consuming. Moreover, studies show that the traditional narrative style of reporting may lead to the omission of clinical information and may be subject to misinterpretation.

This proof-of-concept study will employ natural language processing to first extract the relevant data elements from free-text histopathology reports and create a searchable, structured dataset which can be combined with other electronic health data. The integrated structured dataset will then be used to develop machine learning algorithms with the potential to perform tailored survival and risk assessments, predict patient response and relapse, and identify a clinical course with the highest efficacy and lowest cost. Results of this study can provide an example for applications to other health systems.

Medlior is partnering with the University of Calgary and Mount Royal University for two students to conduct this research study. The project has received research ethics board approval from the Health Research Ethics Board of Alberta – Community Health Community and is currently underway for the fall semester.

Medlior brings a phenomenal team of experienced researchers to support the needs of your business, Contact Us to see how Medlior can add value to your next research project.

 

Image Source