If this medical imaging collaborative develops a way to use the unstructured data in radiology images and anatomic pathology reports, it could create a new revenue stream for pathologists
Unstructured data has been regularly recognized as one Achilles heel for the anatomic pathology profession. It means invaluable information about the cancers and other diseases diagnosed by surgical pathologists are “locked up,” making it difficult for this information to be accessed in efforts to advance population health management (PHM) or conduct clinical studies.
Similarly, medical imaging has an essential role in the diagnosis of cancer and other diseases. And, like most anatomic pathology reports, medical imaging also is considered to be “unstructured” by data experts because it is not easily accessible by computers, reported Fortune magazine.
Unstructured Data in Anatomic Pathology and Radiology
Now one of the world’s largest information technology companies wants to tackle the challenge of unstructured data in radiology images. IBM (NYSE: IBM) Watson Health launched a global initiative involving 16 health systems, radiology providers, and imaging technology companies.
The Watson Health medical imaging collaborative is working to apply cognitive computing of radiology images to clinical practice. IBM aims to transform how physicians use radiology images to diagnose and monitor patients.
The initiative shows there is interest among key academic medical centers and other providers in big data, cognitive computing, and Watson. IBM describes Watson as the first commercially-available cognitive computing system accessible through the Cloud that can analyze high volumes of data and understand complex questions.
Fighting Cancer, Heart Disease, with Cognitive Computing
This newest medical imaging collaborative will initially focus on cancer, but will also leverage cognitive computing of medical images to tackle heart disease, eye health, diabetes, and brain disease.
The involved providers and companies will put Watson to work to:
1. Extract insights from previously “invisible” unstructured imaging data; and
2. Combine the insights with data from other sources, including anatomic pathology reports, medical laboratory results, electronic health records (EHRs), and more, according to an IBM Watson Health statement.
Solving the Problem of Unstructured Data to Improve Patient Care
According to Watson Health, the collaborative hopes to make it possible for healthcare professionals to improve care and reduce inefficiencies by enhancing their use of medical imaging data.
“With the ability to draw insights from massive volumes of integrated structured and unstructured data sources, cognitive computing could transform how clinicians diagnose, treat, and monitor patients,” declared Anne LeGrand,Vice President, Imaging, for Watson Health, in the company’s statement.
Anne LeGrand (above) is Vice President, Imaging, for IBM Watson Health. A preliminary step of the new Watson Health medical imaging collaborative of 16 worldwide healthcare providers and technology companies is to train the cognitive computer and feed imaging data into the Watson database to make connections between images and other available structured data. (Photo copyright: Health Imaging.)
Watson Health reportedly already has data on about 300 million patients. A story in Forbes states, “IBM Watson health is casting a wider net … to feed its artificial intelligence system and speed development of products that diagnose patients accurately the first time.”
Collaborative Attracts Health Providers and Companies
The members of the Watson Health medical imaging collaborative are:
• Anne Arundel Medical Center;
• Baptist Health South Florida;
• Eastern Virginia Medical School;
• Inoveon;
• Radiology Associates of South Florida;
• Topcon;
• University of Miami Health System;
• The University of Vermont Health Network;
• vRad; and
• Merge Healthcare (an IBM company).
How the Collaborative Works
Members of the collaborative—using their data or population-based disease registries—are teaming up with Watson Health cognitive computing experts to train Watson on health conditions.
“We want to get all kinds of source data to train Watson. We want to get to a point where you could turn this on for a rural community and academic medical center and get the same level of accuracy and specificity,” stated Steve Tolle, Global VP of Imaging Strategy, Watson Health, in the Forbes article.
Enabling Physician’s Efficacy, Predicting Disease
Here’s how Watson Health says a trained Watson could transform care and eventually help predict disease:
• Diagnosis Support: In cardiovascular disease, for example, overlooked health conditions such as congestive heart failure or myocardial infarction could be detected by Watson. The supercomputer could then analyze and “score” a coronary angiogram for a doctor’s review.
• Population Health Management: An annual mammogram could connect with a patient’s full EHR and be referenced against similar patients within the Watson database. Are there cells that pose higher risk for breast cancer? With a Watson warning, doctors may intervene earlier and possibly achieve better patient outcomes, the Fortune article stated.
• Disease Reporting: Collaborative members could participate in projects to develop evidence-based clinical decision support systems for, say, ophthalmologists and optometrists, for example. Offerings could include an online tool enabling early detection of eye diseases, such as diabetic retinopathy.
Other Healthcare Partnerships Include Watson Health
The medical imaging collaborative is just one of many Watson Health partnerships. Other projects that address predicting patient health and linking to cloud-based architecture involve companies such as CVS Health, Johnson and Johnson, and Medtronic.
However, pathologists and clinical laboratory leaders are advised to stay abreast of the Watson Health medical imaging collaborative in particular as the number of participants is likely to increase. Of greater significance, if the IBM Watson Health collaborative described above can solve the problem of how to work with unstructured data, that would be an immense benefit to anatomic pathology groups and radiology practices throughout the United States.
It would be a benefit because pathologists and radiologists have years of valuable diagnostic data that exists in an unstructured form. The ability to tap this data and incorporate it into clinical studies, healthcare big data analyses, and similar purposes would probably make it possible for pathologists and radiologists to generate new streams of revenue from their respective clinical data repositories.
—Donna Marie Pocius
Related Information:
How IBM is Improving Medical Imaging to Fight Cancer
IBM Watson Forms Imaging Coalition
IBM Watson Health Imaging Collaborative Adds 16 Health Systems, Tech Firms
IBM Closes Deal to Acquire Merge Healthcare
Strategy Behind Watson Health’s Medical Imaging Collaborative
Ms. LeGrand has come a long way since leaving VA. Tech’s Department of Chemistry. She left after a single year of graduate work. Chemistry was simply not her strength. However, she has made more money than she could have ever done as a research chemist.