AMPEL BioSolutions' Machine Learning Could Help Treatment of Chronic Diseases
Tuesday, July 9, 2019
AMPEL BioSolutions announced a breakthrough in precision and personalized medicine that could revolutionize the way doctors treat chronic diseases, like Lupus. Revealed in the peer-reviewed journal Nature's Scientific Reports, the paper details their breakthrough machine learning approach to predict disease activity from gene data obtained from patient blood samples. The lab test, only a concept for the last few years, is now ready for development for practical use. AMPEL's initial focus was Lupus, but the test can be used for many autoimmune or inflammatory diseases.
George Washington University researchers, including Keith A. Crandall, director of the Computational Biology Institute at Milken Institute School of Public Health (Milken Institute SPH), worked with AMPEL BioSolutions, a genomics technology company, to train a computer to analyze genetic and patient data to predict whether an individual living with lupus was experiencing a flare in disease activity. The genetic analysis, called gene expression analysis, examines the number and pattern of genes expressed at a single moment and can provide insight into various genomic abnormalities.
“This work is a great example of the insights gained by using artificial intelligence such as machine learning approaches to analyze diverse types of data, in this case integrating clinical data with genomics, to make effective and individualized insights on patient health,” said Crandall, who is also a professor of biostatistics and bioinformatics at Milken Institute SPH.
AMPEL's innovative machine learning approach, which is now ready to be developed as a decision support biomarker blood test, could greatly impact health care by allowing physicians to identify the cause of patient disease symptoms and select appropriate treatment more precisely. The application of our machine learning approach could assist pharmaceutical companies in drug development and clinical trials.
Patients of chronic autoimmune diseases, like Lupus, often suffer from unpredictable flares that impact daily activities like work and family life. Since unpredictable flares in disease activity often result in trips to the Emergency Room, the ability to predict flares with a simple blood test has important health care and health economics implications. Paired with our pipeline of tools to analyze very large and complex clinical datasets ("Big Data") AMPEL's machine learning program is a significant step towards implementing a routine blood test for monitoring disease activity and providing decision support for drugs prescribed based on a patient's genes. This will transform the way doctors treat chronic diseases by using the information gathered by the lab test and analyzed by machine learning to predict a flare and treat it before it even begins, saving patients from pain and inconvenience of a disease that otherwise drastically affects their lives.
Pharmaceutical companies test drugs in clinical trials and face the challenge of enrolling patients that have the best potential to respond to the treatment being tested. Enrolling the "wrong" patients can result in trial failure, often leading to cancellation of a drug's development towards FDA approval that may have benefit in a sub-group of the overall patient population. AMPEL's blood test will help pharmaceutical companies identify which patients are most likely to respond to specific treatments, thereby helping improve outcomes in clinical trials.