IBM’s famous cognitive computer can already beat the world’s best Jeopardy players. It can create gourmet meals (sort of), help banks with complex financial operations, and attack important health care problems. Now you can add seeing to its skill set.
Today, Big Blue announced a $1 billion acquisition of Merge Healthcare, and thanks to a marriage of Watson’s existing image analytics and cognitive capabilities and Merge’s data and imagery, the computer should soon be able to recognize many types of medical imagery. In essence, Watson will be able to “see,” IBM said…and eventually save a lot of M.D. eye strain.
According to a release, Merge is a major provider of “medical image handling and processing, interoperability, and clinical systems designed to advance healthcare quality and efficiency.” Its systems are in use at more than 7,500 sites around the United States, and in many medical institutions around the world. Along the way, it has accumulated a massive database of medical imagery.
“The vision is that these organizations could use the Watson Health Cloud to surface new insights form a consolidated, patient-centric view of current and historical images,” IBM wrote in its release, “electronic health records, data from wearable devices, and other related medical data.”
Merge is IBM’s third major health care company acquisition since it launched its Watson Health unit in April. The others were Phytel and Explorys.
By incorporating Merge’s technology into the Watson platform, the computer’s capabilities are expected to move beyond analyzing natural language into a computer version of vision. This could be vital to medical professionals like radiologists in emergency rooms, IBM said, who collectively grapple with as many as 100,000 images per day.
In essence, Watson’s vision will be used to analyze and cross-reference countless medical images against genomic tests, lab results, clinical studies, electronic health records, and other data sources. Together those sources already account for 315 billion data points and 90 million unique records, IBM said.
“Merge’s clients could compare new medical images with a patient’s image history as well as populations of similar patients to detect changes and anomalies,” IBM wrote. “Insights generated by Watson could then help health care providers in fields including radiology, cardiology, orthopedics, and ophthalmology to pursue more personalized approaches to diagnosis, treatment, and monitoring of patients.”
Work being done at IBM Research could enable further progress such as helping Watson learn to filter clinical and diagnostic imaging data in a bid to assist medical professionals find anomalies and make recommendations. That could help doctors cut the number of images they have to look at.