Tiny data generators
Over a thousand pieces of unique information
With premature babies, even the slightest variation in biomedical readings such as heart rate can signal a turn for the worse. And such changes can be detected up to 24 hours in advance.
IBM and the University of Ontario Institute of Technology embarked on a first-of-a-kind research project to help doctors detect these subtle changes. The project will use advanced stream computing software that ingests a constant stream of biomedical data, such as temperature and respiration, along with environmental data gathered from advanced sensors and more traditional monitoring equipment on and around the babies.
A computerised crystal ball for HIV/AIDS
It's estimated that over 33 million people are living with HIV/AIDS worldwide. Today, HIV can be a treatable, though still not curable disease. But even if the patient is fortunate enough to receive treatment, there is still a risk of developing resistance to the antiretroviral drugs. And that renders the medication powerless against the virus.
EuResist Network GEIE is a nonprofit dedicated to promoting medical research. Working with a consortium that includes IBM Research, EuResist developed the largest clinically oriented antiretroviral drug resistance database in the world—a modeling tool that lets users predict the success rate and impact on virus evolution of various drug combinations via an online portal.
The prediction engine, operating within an IBM WebSphere® Application Server environment, leverages medical data such as viral gene sequences and patient histories from seven sources hosted within an IBM DB2® data server.
With the prediction engine at work, patient response to antiretroviral drug therapy has experienced an increase in accuracy of up to 76%, the highest achieved to date. And what's truly remarkable? The system is absolutely free to use by any physician in Europe.
Medical insights from the family tree
You get your eye color from your mother. Your hair comes from your grandfather's side of the family. But what about fibrous dysplasia? Or Gorham's disease? Who might you inherit that from?
Italy's Rizzoli Orthopaedic Institute is looking for those answers in the genetic underpinnings of rare hereditary bone diseases. Rizzoli engaged IBM Research to develop a first-of-a-kind pedigree analytics platform that integrates genomic data, medical images and family history into a powerful research tool.
The platform helps researchers discover and better understand correlations between genotypic and phenotypic data—genetic makeup and what the condition actually looks like. In addition to streamlining the research process, the insights derived from this complementary capability provide guidance to Rizzoli physicians in offering the most effective treatment options.
Electronic health records get a booster
Since most patient information lives in a database already, an electronic health record (EHR) system means patients don't need to take the time to explain medical history to new doctors. EHRs can help doctors diagnose faster, significantly cut down on the time it takes hospital staff to chart patients' information and ultimately reduce the length of an average patient visit.
Pennsylvania-based Geisinger Health System wanted to enhance its own electronic health record systems, organising information and integrating real-time clinical data with medical history. They wanted to garner more than just information from their vast stores of data. They wanted intelligence.
IBM implemented a Clinical Decision Intelligence System (CDIS) solution. Based on IBM InfoSphere™ (DB2®) Warehouse 9 platform, the solution forms the foundation for integrating everything from clinical to financial information, plus operational, claims, genomic and other data.