Healthcare Providers Use Hadoop to Improve Patient Care and Increase Efficiency
Healthcare expenses in the United States of America now represent 17.6 percent of GDP—nearly $600 billion more than the expected benchmark for a nation of its size and wealth. McKinsey estimates the system-wide impact of applying big data could account for $300 billion to $450 billion in reduced healthcare spending.
Unstructured data forms close to 80% of information in the healthcare industry and is growing exponentially. Getting access to this unstructured data—such as output from medical devices, doctor’s notes, lab results, imaging reports, medical correspondence, clinical data, and financial data—is an invaluable resource for improving patient care and increasing efficiency.
In the last few years there has been a move toward evidence-based medicine, which involves making use of all clinical data available and factoring that into clinical and advanced analytics. The outcomes of this movement include improved ability to detect and diagnose diseases in their early stages, assigning more effective therapies based on a patient’s genetic makeup, and adjusting drug doses to minimize side effects and improve effectiveness.
The MapR Converged Data Platform is well suited to capture all of the information about a patient to get a more complete view for insight into care coordination and outcomes-based reimbursement, population health management, and patient engagement and outreach.
Healthcare and Life Sciences Use Cases
These are some example use cases that illustrate how big data and Hadoop are being used in healthcare and genomics.
Genome Processing and DNA Sequencing
There is exponential growth occurring in the genomics sequencing market, as evidenced by increases in data volume produced by DNA sequencers and in the number of individuals being sequenced. The current architecture leverages SAN (Storage Area Networks) or NAS (Network Attached Storage) for storage and HPC (High Performance Computing) for computing. This architecture has shortcomings, which results in network bottlenecks, and makes it not well suited for global distributed sorting of data. MapR provides efficient storage and compute in a single platform; MapR is well suited for storing large volumes of sequencing data at a lower cost, while enabling efficient data processing with minimal downtime. This will accelerate the development of clinical applications, including drug re-targeting and diagnostic testing.
Personalized Treatment Planning
Personalized treatment planning is a way to customize treatment for a patient to continuously monitor the effects of medication. The dose can be adapted or the medication changed based on how the medication is working for that particular individual. This analysis can be applied at the individual level and is tailored to each patient’s specific needs and can include likes and dislikes of patients. The MapR Converged Data Platform provides real-time access, at both the summary and detailed level when it comes to patient data so treatment decisions can be adjusted in a timely manner.
Being able to access a broad combination of knowledge across multiple data sources aids in the accuracy of diagnosing patient conditions. Assisted diagnosis is accomplished using expert systems that contain detailed knowledge of conditions, symptoms, medications and side effects. Bringing together individual data sets into big-data algorithms often provides more accurate insights because nuances in subpopulations may be so rare that they are not apparent in small samples. The MapR Converged Data Platform can allow for predictive modeling and machine learning to be performed on large sample sizes and uncover the nuances that couldn’t be previously uncovered.
Healthcare organizations need to be able to detect fraud based on analysis of anomalies in billing data, procedural benchmark data or patient records. For example, they can analyze patient records and billing to detect anomalies such as a hospital’s overutilization of services in short time periods, patients receiving healthcare services from different hospitals in different locations simultaneously, or identical prescriptions for the same patient filled in multiple locations. The MapR Converged Data Platform uses anomaly detection to detect these incidents in real time and alert providers to investigate them before payment is made.
Monitor Patient Vital Signs
Healthcare facilities are looking to provide more proactive care to their patients by constantly monitoring patient vital signs. The data from these various monitors can be used in real time and send alerts to nurses or care providers so they know instantly about changes in a patient’s condition. The MapR Converged Data Platfrom can help in collecting this very fast growing data and stream it in real-time for actionable alerts that can help in detecting changes. Improved algorithms can be built that improve the likelihood of knowing when a particular patient might have an emergency and allow for effective interventions.
Leading Healthcare Organization
A leading healthcare organization that serves more than a hundred million members collects petabytes of claims and treatment data. It plans to create a new data repository service for its enterprise customers who can leverage their own customer data and run expanded set of analytics. MapR is the only Hadoop platform that delivers on the multi-tenancy needs of this company by providing volume-based isolated environment with quotas and secure access for the end users.
How Big Data is Reducing Costs and Improving Outcomes in Health Care