Challenge: Combine Disparate Data Sets in PreProcessing for ML
Summary: Compelling results show that combining data sources generally allowed better diagnostic performance than with any data set alone (Figures 1&2) Read More
In any data science pipeline there are a number of options that are selected for data processing (e.g. contrast settings for medical images, data imputation approaches, bandpass filter cut-offs for ecg signals). Typically, these options are selected manually based on previous experience of the Data Scientist or recommendations from previous, similar studies. In contingent AI, any “settable” parameter for data processing, data integration, or feature selection is permuted and the corresponding effects on the downstream predictive model measured. This process is similar to hyperparameter tuning in machine learning, however instead of optimizing only the machine learning model, the entire data science pipeline (including model selection) is subject to optimization.
Advocate for healthcare technology innovation joins BioSymetrics in a mission to empower the application of AI within biomedicine.
NEW YORK, February 7, 2019 (GLOBE NEWSWIRE) – BioSymetrics, an artificial intelligence and machine learning SaaS company, announces Dr. Calum MacRae as Senior Advisor. Dr. MacRae is an innovative pioneer in genetics, biology, and drug discovery. With his deep knowledge and expertise, Dr. MacRae will assist BioSymetrics in the design and application of the company’s software for use in drug discovery, precision medicine and health systems.
“The introduction of AI into medicine is challenged by a fundamental defect of information content and standards,” said Dr. Calum MacRae. “BioSymetrics is leading the promise that we are entering an era in which precision medicine and AI finally attain real world applications; overcoming a number of AI challenges across a wide spectrum of biomedicine.” Read More