Solutions for Medical and Pharmaceutical Research

There are many factors driving the need for better medical research, including rising costs of health care and the aging population. Doctors and hospitals have kept great records as to the treatment, examinations, and outcomes of individual patients. For example, looking at medical records collectively can yield insight into patterns relating to disease and conditions that may not be apparent when looking at just one or two medical records.

Collective analysis of medical records has been difficult because there are many reasons for the patient to encounter medical providers, including emergencies, routine physicals, periodic doctor visits, employment requirements, and so forth. Likewise, there are quite a few possible episodes of care, including diagnoses, examinations, test procedures, surgeries, and many others.

Every time the patient undergoes an episode of care, careful records are taken, primarily in text form. The amount of text and the nature of the language depends on the physician, the nature of the encounter, and many other factors. For a given patient the collection of the records forms the personal medical history of the patient. There is much value to the patient from these records.

But there is an even greater value to these records when the records are examined collectively. When you have the ability to examine 10,000, 100,000, and even a million or more records at a time, patterns relating to disease and medical conditions start to emerge that are extremely important in the prevention and treatment of a particular condition.

In the past, there have been several challenges to achieving the ability to analyze large amounts of disparate medical records.

Challenge one: Records are stored in various textual formats (unstructured text) and standard technology does not handle unstructured text well.

Challenge two: Much of the data resides on very different sources and technologies, and these technologies were never designed to work seamlessly together.

Challenge three: There are significant differences in terminology among medical specialties, and these differences make it difficult to accurately analyze the data.

Fortunately, the IDS solution overcomes all these challenges and collects and transforms medical records wherever they are found and regardless on the underlying technology. The IDS solution resolves all terminology differences and creates an integrated foundation of medical data that provides you with the great benefits of collective information analysis. Once the foundation is created, all the information is available to you in a visualization and reporting engine that creates Self Organizing Maps (SOM’s) of the data. SOM’s are great tools for grouping data and showing correlations in an easy to use format, but they are also able to represent thousands of documents and millions of words and phrases.

Those who use conventional analytical tools such as SAS, Business Objects, and Cognos, will be pleased to know that in addition to visual analysis, once the medical data is identified and transformed to the structured environment (e.g. your current database), it is also available for further analysis using these tools.

For a more in-depth look at the subject of how the IDS solution helps you to analyze medical and pharmaceutical records, please go to our white paper titled Analyzing Medical Records.