Healthcare Informatics

Healthcare Informatics

Despite the rapid advances in medical science, the healthcare delivery system remains plagued with inefficiencies that hinder basic access to quality care at a reasonable price. Soaring costs are placing severe strains on an already overburdened system, and administrators are scrambling to organize an ever-increasing stream of information from a variety of data sources. There is a growing consensus that Information Technology (IT) provides the key to cost-effective quality care for all.

For years, the Almaden Research Center has been at the vanguard of research into healthcare informatics. Our contributions to the Nationwide Health Information Network (NHIN), developed under contract to the U.S. Department of Health and Human Services, have paved the way for many other health IT research advances. The NHIN prototype pioneered new standards-based technology for secure access and real time sharing and exchanging of health care data among all concerned parties—patients, physicians, hospitals, laboratories, and pharmacies. Other groundbreaking work in fields as diverse as privacy protection and interoperability has cemented IBM's status as a forerunner in the field.

Today, we continue to push forward in a number of new areas, including Information Integration, Multimodal Analytics, Healthcare Standards, and Public Health.

Information Integration and Analytics

The most untapped resource in health care services today is the very information that providers, payers, and patients already possess. Unfortunately, much of it is represented in various different formats and located in many disparate information stores, hindering its true value potential. We are currently working on finding methods to integrate the available data into easily searchable and structured databases.

MONGOOSE: MONGOOSE technology is the bedrock that enables the construction of data analytics platforms and systems, while allaying the issues associated with ingesting data in an error where failure is the norm and not the exception.

HIWAS: Healthcare Information Warehouse for Analytics and Sharing is a system designed to facilitate the analysis of XML healthcare data based on the recognition that clinical data can not only serve immediate patient care, but help with subjects like epidemiology, cost-benefit analysis, and evidence-based medicine as well. HIWAS enables the user to store clinical data in a representation that integrates pertinent reference data and analytic tools, and simplifies the extraction of data and allows for more in-depth analysis.

Multimodal Analytics

Healthcare data stretches far beyond insurance paperwork and patient records, and includes the vast amount of diagnostic data generated by medical equipment. We are very active in pursuing new analytical tools incorporating text with images, genomic data, and much more to maximize health care quality.

AALIM: Diagnostic decision support is still very much an art for physicians in their practices today due to a lack of quantitative tools. AALIM (Advanced Analytics for Information Management) is a decision support system for cardiology that exploits the consensus opinions of other physicians who have looked at similar patients to present statistical reports summarizing possible diagnoses. The key idea behind our statistical decision support system is the search for similar patients based on the underlying multimodal data consisting of cardiac echo videos, heart sounds, ECGs, and reports.

ODySSy: Our On-Demand Stethoscope System (ODySSy) is a cutting-edge tool that allows physicians to collect auscultation data from patients at home that is, the data gleaned from stethoscopes. The system makes it easy for electronic records to ingest the data, and for doctors to view and hear the sounds of the patient s internal organs through web portals. Due to stethoscopes cheap and effective diagnoses of a variety of ailments, ODySSy is an important step forward in remote medicine.

Healthcare Standards, Interoperability, and Open Source Software

Healthcare Information Exchanges (HIEs), which facilitate the sharing of patient data between various providers and centers, face a number of challenges in implementation. Data is stored in a plethora of different formats, semantic inconsistency can hinder searches, and disputes over data ownership and privacy are difficult to resolve. In response, we are developing new standards that incorporate both clinical and public health needs to provide an adaptable and scalable shared healthcare infrastructure. The use of open source software in the public domain is critical to achieving these goals.

OHT IHE: Open Health Tools Integrating the Healthcare Enterprise (IHE) Profiles Project is an initiative to improve the way computer systems in healthcare share information. IHE promotes the coordinated use of established standards such as DICOM and HL7 to address specific clinical needs in support of optimal patient care. Systems developed in accordance with IHE communicate with one another better, are easier to implement, and enable care providers to use information more effectively. The project currently offers client-side implementation of IHE profiles.

OHT MDHT: Open Health Tools Model-Driven Health Tools (MDHT) Project is a wide-ranging open source effort to promote interoperability in healthcare infrastructure. It promotes shared artifacts between related healthcare standards and standards development organizations, and works to develop localized specifications. It also delivers a common modeling framework and tools that support seamless integration of design, publication, and runtime artifact creation.

Public Health

It is not enough to focus on care at the individual level. In the case of widespread outbreaks of food poisoning or the flu, healthcare delivery systems can easily become overwhelmed. To confront this greater threat, we are working on expanding current HIE technology and developing new tools so that governmental agencies can easily share critical public health updates and chart real-time strategies to contain and eventually eliminate these outbreaks.

PHIAD: Our Public Health Information Affinity Domain (PHIAD) provides a standards based, interoperable infrastructure for scientists and public health officials to gather the information they need to combat pandemics. The system collects data from hospitals, clinics, laboratories, and health workers, and stores it in repositories easily accessed by all concerned parties. Israel, Jordan, and the Palestinian territories are currently utilizing the system to help paint a complete picture of shared health challenges with up-to-date medical information from across the region.

STEM: Our Spatiotemporal Epidemiological Modeler (STEM) helps health officials create spatial and temporal models of emerging pandemics. Rapidly classifying, analyzing, and incorporating all incoming data onto an ever-updating map, STEM offers scientists a never-before-seen real-time view of the spread of an infectious disease, and could allow officials to stamp out potential threats before they develop into threatening pandemics. In recognition of its enormous potential for public good, IBM has contributed STEM code to the Eclipse open source foundation. (http://www.eclipse.org/stem/)

Dr. Bill Cody, Senior Manager, Healthcare Informatics