Visual Neural Networking with Mobile Medical Imaging:Disruptive Tools and Technologies for Value Care­Giving Teams

Authors:Jim Smurro, MS, MBA; Eliot L. Siegel, MD, FSIIM; Krishna Surapaneni, MD

BackgroundRadiologists are adapting to challenges presented by a dynamic ecosystem –

requirements for clinical documentation for "meaningful use," changing

reimbursement models, ONC/CMS/IOM concerns about quality, safety, efficiency,

and increased regulatory scrutiny regarding exposures to harmful radiation.

Mobile medical imaging offers potentially disruptive technology for communications-

enhanced care delivery, including more timely clinician-specialist and provider-

patient communications, and providing clinical decision support at point of care in

real time or asynchronously.

Evaluation:Mobile medical imaging allows care-giving teams to communicate, collaborate, and

train together – anywhere, anytime – with medical images and video.

Annotated medical images, telestrated cine clips, and encapsulated audio files help

teams document and share episodes of care. Clinical encounters and specialist

consultations are captured at the POC in standards-compliant clinical notes for

provider-mandated EHR’s and patient-directed PHR’s, pursuant to ONC’s Health

Outcomes Policy Priorities for Meaningful Use.

Secure, encrypted imaging portals with digital identity verification enable multi-

disciplinary teams to communicate, collaborate, coordinate, and deliver "faster,

smarter, better" patient-centric care to informed and engaged patients and families.

Visual Neural Networking with Mobile Medical Imaging:Disruptive Tools and Technologies for Value Care­Giving Teams

Background:Radiologists are adapting to challenges presented by a dynamic ecosystem –requirements for clinical documentation for "meaningful use," changing reimbursementmodels, ONC/CMS/IOM concerns about quality, safety, efficiency, and increasedregulatory scrutiny regarding exposures to harmful radiation.

Mobile medical imaging offers potentially disruptive technology for communications-enhanced care delivery, including more timely clinician-specialist and provider-patientcommunications, and providing clinical decision support at point of care in real time orasynchronously.

Evaluation:Mobile medical imaging allows care-giving teams to communicate, collaborate, and traintogether – anywhere, anytime – with medical images and video.

Annotated medical images, telestrated cine clips, and encapsulated audio files help teamsdocument and share episodes of care. Clinical encounters and specialist consultations arecaptured at the POC in standards-compliant clinical notes for provider-mandated EHR’sand patient-directed PHR’s, pursuant to ONC’s Health Outcomes Policy Priorities forMeaningful Use.

Secure, encrypted imaging portals with digital identity verification enable multi-disciplinary teams to communicate, collaborate, coordinate, and deliver "faster, smarter,better" patient-centric care to informed and engaged patients and families.

Discussion:Visual Neural Networking with Mobile Medical Imaging – Some illustrative real-worldclinical use cases:

Rapid evaluation and emergent treatment of acute ischemic stroke ["Time isBrain"] with neurological expertise and remote telestroke support for rescue therapiesthat limit permanent damage and disability

Collaborative medical image sharing by clinicians and specialists that reducesredundant testing, avoids unnecessary exposures to harmful radiation and improvesdiagnostic detection, evaluation and treatment

Virtual tumor boards networks with multi-specialist collaborations that can boostrecruitment (and retention) of patients for oncology clinical trials, treatment and care,especially from rural and under-served patient populations

Surgical "road mapping," simulation and training, including pre-operative team"warm-ups" with actual patient images, prior to interventional radiology, cardiaccatheterization, and endovascular procedures

Remote patient monitoring following emergency surgery – from recovery in the ICUto convalescence in the "medical home" - that can reduce post-operative complicationsfrom sepsis (especially dangerous for elderly patients) and avoids preventable re-admission hospitalizations

Presentation Outline:

Part 1 – Visual Neural Networking: Vision and Value Proposition – Jim SmurroAdapting to Change in Dynamic Ecosystems [reimbursement models; ACO’s]Pro-active response to IOM (and FDA) concerns: Quality, Safety, EfficiencyMobile Medical Imaging: Disruptive Technology for Value Care-Giving Teams

Part 2 – Mobile Medical Imaging: Status report on current apps – Krishna SurapaneniIllustrative Use Cases: Acute Stroke; AppendicitisEmerging Apps: Physician, Medical Student and Patient EducationHow-to videos for Doctors; Instructional videos for Patients

Part 3 – Implications for Radiologists: Value Innovation through Services Differentiation –Eliot SiegelMobile Medical Imaging as a communications platform: Specialist-Clinician and Clinician-Patient communicationsMobile Medical Imaging as a tool for Clinical Data Capture at the Point of CareRedefine radiologist potential role as "Conductor" of Visual Communications for Care-Giving Teams in the brave new world of EHR’s and "Meaningful Use" leverage radiologystandards for media-rich clinical documentationPotential new revenue streams: reimbursable teleconsults, virtual tumor boards,oncology clinical trials, telestroke networks

Conclusion:Visual neural networking with mobile medical imaging empowers care-giving teams todeliver ‘value care’ for the 21st century –'faster, smarter, better' patient-centric care –with higher quality, lower costs, and healthier outcomes.

Disruptive technologies such as these, enrich, enhance andaugment team skills in a "virtuouscircle" of communications, collaboration, cooperation and coordination. Teamworkand training boost productivity and performance. "Deliberate practice" improves quality,

safety and clinical outcomes. Team "checklists" reinforce and sustain learning curve improvements.

"Anywhere, Anytime" medical imaging "revitalizes" aging technology infrastructures withubiquitous connectivity, bi-directional "pixel liquidity," and ad hoc collaborations thatextend the range, reach, and effectiveness of medical devices and equipment.

Visual neural networking transforms workflows for teams empowered with mHealthconnectivity. Smart, agile teams, working in concert from off-campus locations, consumefewer and less costly RVU resources to orchestrate delivery of team value care.

With fewer medical errors, less redundant care, and more skilled labor delivering bettercare in less costly venues, cost savings begin to accrue, compound and multiply. Workingtogether, care-giving teams start bending the cost curve.

Visual neural networking with mobile medical imaging – connecting patients to providerswith pictures – helps transform knowledge workers with talent, training and expertiseinto visually­networked teams for innovation, growth and prosperity.

Authors:Krishna Surapaneni, MD, MPh, New York Presbyterian Hospital/Columbia University Medical Center; Jim Smurro, MS, MBA; Eliot L. Siegel, MD, FSIIM

Disclosures and Conflicts

Eliot Siegel, M.D.

Dr. Siegel is Professor and Vice Chair at the University of Maryland School of Medicine, Department of Diagnostic Radiology, as well as Chief of Radiology andNuclear Medicine for the Veterans Affairs Maryland Healthcare System, both in Baltimore, MD. Dr. Siegel is also responsible for the NCI's National Cancer ImageArchive and is Workspace Lead of the National Cancer Institute's caBIG In Vivo Imaging Workspace.

Under his guidance, the VA Maryland Healthcare System became the first filmless healthcare enterprise in the United States. He has written over 200 articles andbook chapters about PACS (Picture Archiving and Communication Systems) and digital imaging, and has edited six books on the topic, including FilmlessRadiology and Security Issues in the Digital Medical Enterprise. He has made more than 1,000 presentations throughout the world on a broad range of topicsinvolving the use of computers in medicine. He has been named as Researcher of the Year, received multiple awards for innovation, including the Smithsonianaward, and was selected as runner up Educator of the Year for Diagnostic Radiology. The readers and editorial board of Medical Imaging have selected Dr. Siegelas one of the top ten radiologists for the past two years. He was symposium chairman for the Society of Photo-optical and Industrial Engineers (SPIE) MedicalImaging Meeting for three years, is currently chair of Publications for the Society of Computer Applications in Radiology (SIIM) and has been honored as a fellowin that organization. He is chairman of the RSNA's Medical Imaging Resource Committee. His areas of interest and responsibility at both the local and nationallevels include digital imaging and PACS, telemedicine, the electronic medical record, and informatics. Dr. Siegel holds an M.D. from the University of Maryland.

Jim Smurro

Jim Smurro is Director of Corporate Development for Foresight Imaging. His responsibilities encompass strategy formulation and execution of strategic businessinitiatives, including new ventures, technology partnerships and marketing alliances. Mr. Smurro brings a wealth of experience as principal, investor and advisor toentrepreneurs and emerging growth companies in healthcare services and information technology. He holds both undergraduate and masters degrees inEngineering and Applied Physics from Harvard University. Mr. Smurro earned his MBA in Management of Technology from Harvard Business School, where also hecompleted doctoral (DBA) studies in disruptive technology innovation

Krishna Surapaneni, MD

Dr. Surapaneni joined P&S July 1, 2010, as assistant professor of clinical radiology.Dr. Surapaneni received his MD from Ross University School of Medicine. He

completed a radiology residency at Long Island College Hospital and a neuroradiology fellowship at NewYork-Presbyterian Hospital/Columbia.

June 2011 Volume 21, Number 6

A L S O I N S I D E :

CTC Use Grows Despite Reimbursement Obstacles

New ACGME Standards Concern Program Directors

Diligence Necessary to Minimize Gadolinium-related Events

MDCT Angiography Effective in Ischemic Stroke, SAH Diagnosis

Course Enrollment for RSNA 2011 Begins July 6See Page 21

No Contest: Watson Poised to

Revolutionize Healthcare

NEWS YOU CAN USE

13 RSNA News | June 2011 June 2011 | RSNA News 14

FEATURE

Well before Watson’s gameshow victory, experts at the University of Maryland (UM) School of Medi-cine in Baltimore and Columbia University Medical Center began working with IBM to apply Watson’s analytics capabilities to healthcare. Specifically, Watson is being developed as an assistant capable of reading electronic health records (EHR) and providing instant feedback to physicians in ways not always available from doctors and nurses. “This breakthrough in computer sci-ence will allow us to explore this tech-nique for medical diagnosis,” said Eliot Siegel, M.D., a professor and vice-chair of imaging informatics at the University of Mary-land School of Medicine (MSM), chief of imaging services for the Maryland Veterans Affairs (VA) Healthcare System at the Baltimore VA Medical Center and co-chair of RSNA’s Medical Imaging Resource Center (MIRC) committee. “The potential for a renaissance in electronic health records really lies in the evolution of com-puter systems,” said Dr. Siegel, director of UM’s Maryland Imaging Research Technologies Labo-ratory, who was instrumental in the partnership between MSM and IBM. “I’m really surprised it has taken this long for that renaissance to start.” Physicians at Columbia University are helping identify critical medical issues to which Watson may be able to contribute, according to IBM.

Analytics Capability Critical to HealthcarePowered by 90 servers and 360 computer chips, Watson was built in four years by IBM researchers seeking to develop a machine that could quickly answer complex questions. Through IBM’s Deep Question Answering, Natural Language Process-ing and Machine Learning statistical techniques, Watson works to understand questions and develop answers—a capability critical to the technology’s potential value to healthcare. IBM is also working with speech-recognition software developer Nuance Communications to give

Winning the $1 million “Jeopardy!” challenge earlier this year was just the tip of the iceberg for Watson, the IBM supercomputer that experts believe has the potential to revolutionize the healthcare industry.

Watson the analytics capabilities necessary for physician-patient consultations. Earlier attempts at artificial intelligence required every possible question and answer to be hard-coded into the system, a time-consuming process with little value in healthcare, said Martin Kohn, M.D., Chief Medical Sci-entist, Care Delivery Systems, IBM Research. “Watson uses a probabilistic, evidence-based approach,” Dr. Kohn said. “It generates and scores many

hypotheses using an extensible collection of natural language processing, machine learning and reasoning algorithms. Many

previous such efforts relied on programmed decision rules. Watson is a self-learning system that does not rely on such rules. It gathers and weighs evidence to refine its hypotheses.”

Decision Support Boosted to New LevelRadiology stands to benefit tremendously from Watson’s capabilities, experts say. “The technology has the potential to provide deci-sion support on a scale not dreamt of prior to this,” said Nancy Knight, Ph.D., the director of Academic and Research Development and a founder of the Maryland Imaging Research Technologies Laboratory at UM. “Watson can supply the radiologist at the point of care with complete patient information from the elec-tronic health record, including imaging history, allow-ing the radiologist to mine an often exhaustive number of records to identify the most important points,” Dr. Knight said. “It also provides the latest and most exten-

sive scientific knowledge and clinical experience that can be used to inform decisions about diagnosis, additional tests, management and likely prognoses.” Watson is currently in the testing phase in that learning process, said Dr. Siegel, who pointed out the similarity to real-life students progressing from medical school to residencies. The first step—acquiring book knowledge—is already under way. Watson’s database already includes information from medical journals and textbooks such as the Merck Manual of Diagnosis and Therapy, Harrison’s Principles of Internal Medicine, the American College of Physicians Medicine and Stein’s Inter-nal Medicine. Next, experts will work to develop Watson’s understanding of the physiol-ogy of the human body, followed by the third step: gathering experience. “Watson not only needs the general knowledge that made him so successful on ‘Jeopardy!,’ but also information from the databases specific to medicine,” Dr. Siegel said.

Watson is an Assistant, not a PhysicianIn time, Dr. Siegel would like to see Watson function as a physician’s assistant. He envisions Watson being used for chart review, providing assistance on drug interactions or inconsistencies in prescriptions. Regardless of the technology’s potential, Dr. Siegel stresses that Watson is designed to act as an assistant to a physician, rather than a replacement. “I don’t see this technology supplanting physicians or radiologists,” Dr. Sie-gel said. “It’s a tool that will gather, summarize and analyze information—very similar to the role now performed by our best residents and fellows.” As the technology progresses and expands, it will be especially important to rural hospitals or areas where there may be fewer experts, but healthcare orga-nizations across the board stand to benefit, he said. “Watson’s eventual expansion into healthcare has profound implications for radiology and will certainly improve the safety, effectiveness and potentially the cost of healthcare delivery overall.”

No Contest: Watson Poised to Revolutionize Healthcare

“ Watson’s eventual expansion into healthcare has profound implications for radiology and will certainly improve the safety, effectiveness and potentially the cost of healthcare delivery overall.”Eliot Siegel, M.D.

SIEGEL DISCUSSES WATSON’S ROLE AT UMTo view a video podcast of Eliot Siegel, M.D., discussing the development of Watson as an assistant capable of reading elec-tronic health records and provid-ing instant feedback to physicians at the University of Maryland School of Medicine, go to www.umm.edu/media/video/misc_siegel_watson.htm.

Radiology stands to benefit enormously from Watson, the IBM supercomputer with the potential to create a renaissance in the application of “artificial intelligence,” in medical data mining, data analysis and decision support. Watson cemented its star status by defeating celebrated contes-tants Ken Jennings and Brad Rutter on “Jeopardy!” earlier this year. Images courtesy of IBM.

ON THE COVEREliot Siegel, M.D., pictured with IBM’s Watson at the University of Maryland, believes the su-percomputer may soon become a routine tool for diagnostic radiologists in addition to PACS, advanced visualiza-tion and speech recognition.

TechnologyForum