How Big Data is Changing Current Research Methodology: Cancer
Cancer is the second leading cause of death in the United States. Current treatments are ineffective with over 75% of patients not responding to treatments, despite the $50 billion pharmaceutical companies spend in research and development every year. In addition, patients go from one failed drug to another, trying each one until they find one that works. This process not only incurs extra costs but causes patients to lose time in the fight against a progressive disease.
Using genomic big data, cancer is now being identified by cell type (HER2 cell), and not a body part (breast cancer). Genomics research has made it possible for researchers and doctors to sequence the genome of cancer tumors to determine the genome of each cancer. Using these methods, researchers have found that there are actually four distinct types of breast cancer. This explains that a treatment for one type is not necessarily effective for another type of breast cancer. Thus, doctors can prescribe the right medication for the certain type of cancer.
How Data Can Change Current Methodology: Clinical Trials
Clinicians have the tools to choose realistic clinical trials using EMR/EHR data combined with genomics and smartphone device trackers. There are a number of diseases with ineffective treatments including cancer, Alzheimer’s, depression, diabetes, asthma and arthritis. With a number of new data streams in healthcare – from medical records being converted from paper to digital, wearable trackers and sensors, genomics data and pharmaceutical data – doctors can make a more informed diagnosis.
Furthermore, the aggregated data aspect of health allows for doctors to look at a patient’s data holistically and determine which patients are good candidates for clinical trials. Through sensors and at-home monitors, clinicians can create clinical trials in real time. Clinicians can now monitor patient’s normal progress outside of the hospital between visits. This revolutionary new approach is possible using healthcare Big Data: a combination of data sources including genomics data, EMR data, environmental data and fitness tracker data. All of these combine to allow more effective treatment and personalized medicine.
Why We Care: The Future of Medicine
The trend in clinical trials and cancer research represents a new age of personalized medicine.
For the data scientists, the new research into cancer and clinical trials is one that relies on the aggregation of vast stores of data from many different sources. Medical records are becoming digital, genomic data is more widely available, pharmaceutical data is adding to the pot, and mobile data streams are coming together to get a more complete picture of a patient.
Alternatively, doctors will learn more about drugs by creating more effective clinical trials and discovering strengths and weaknesses of drug treatments. This has potential to save the healthcare system $300 billion dollars a year, not to mention the number of lives it will save.
Applications of Analytic Methods to Improve Clinical Trials and Cancer
Companies are using different methods to analyze the multidimensional data sets collected from multiple streams for cancer and clinical trial research. Ayasdi, GNS and Explorys are a few of these companies using topology, causal models, and multiprocessors to analyze the data.
- Ayasdi uses topological analysis and math of shapes on their Iris platform. It allows them to visualize data in a multidimensional graphic that readily shows outliers and high or low response groups in the data, without pre-specifying the characteristics of those clusters. The outliers can represent unknown biomarkers, or subgroups of patients that would be well or poorly suited to a clinical trial of a particular drug. Other clusters in visualization could point to data sets that demand further analysis that are invisible through other analytic methods. Ayasdi has found a number of novel biomarkers. The first of which was a new subset of “triple negative” survivors that had elevated expression levels of genes involved in the immune system for breast cancer.
- GNS Healthcare uses standard math and statistical principles to create “what if” scenario models. Their next-generation REF machine learning engine (on a cloud platform) extracts predictive models from the data. Being doing this, they can determine comparative effectiveness and create simulations individually as well as across an entire patient population. This can help determine which treatment or course of action would be best for individuals and for the health system. Additionally, GNS announced that they are using EMR and genomic data to create a computer model that can predict which pregnant women are at risk of preterm labor.
- Explorys focuses on the aggregation, storage ,and analysis of multiple data sources/ This includes all clinical, financial, and operational data related to patient care. Massive parallel processing allows Explorys to look at multiple data sets from varying angles simultaneously — processing the data in real time for real time results.
That is to say, these trends in clinical trials and cancer research represent the dawn of a new age of personalized medicine.
Tune in on Sept 18th at 10am PST to find out more about the companies that have turned their attention to using Big Data to call in the new age of personalized healthcare.