17 November, 2015
While healthcare reform has many challenges, there are some very positive things happening behind the scenes. One of them is how we diagnose and treat patients with complicated diseases. Healthcare today is t...
Published on 17th November
While healthcare reform has many challenges, there are some very positive things happening behind the scenes. One of them is how we diagnose and treat patients with complicated diseases. Healthcare today is transaction based. Our (U.S.) system treats one patient at a time, one step at a time. Many tests and procedures are unnecessary, but the incentive system and fear of liability drive them. In a world of big data and analytics, following anecdotal evidence for diagnosis and treatment is no longer adequate. The new model relies on evidence based medicine where outcomes become part of the evidence.
Evidence based medicine is practiced when the patient sees the doctor and the doctor consults with a database that contains anonymized (contains no personally identifiable information) information about similar patients and what treatments produced what outcomes. Evidence based medicine gives the doctor access to data about large numbers of patients and outcomes, not just the ones he or she has seen.
When Watson, the IBM supercomputer, defeated Brad Rutter and Ken Jennings on the TV game show Jeopardy, it was the tip of the iceberg for future use of supercomputing. The Watson supercomputer is built with cognitive technology, a human brain-like capability, giving it mental abilities and processes related to knowledge capable of processing information more like a human than a computer. Watson can understand the meaning of words, generate hypotheses about a problem or question, and compare potential results against a vast amount of knowledge fed to it.
Physicians are increasingly able to sequence a cancer tumor and use the data to find a match with a treatment that can cure the patient. The problem is the analysis can take weeks. IBM is deploying its Watson supercomputer technology to reduce the analysis to minutes.
Sifting through data
Supercomputers can help clinicians quickly sift through this data and provide comprehensive insights on cancer-causing mutations and how they might be treated by analyzing each mutation and the available medical literature. Cognitive (thinking) capabilities can look for variations in the full human genome and compare them to vast amounts of information from treatment guidelines, research, clinical studies, journal articles and information about the patient.
The result is a report of the patient’s case, including recommendations and evidence-based insight on potential drugs that may be relevant to the patient’s unique DNA profile. The recommendation would take into account, based on the DNA, how a certain medication would be assimilated by the patient and exactly how much of the drug to take and when to take it. The clinician can then evaluate the evidence to determine whether the recommended therapy may be more effective than standard care for the patient. Analytics, will be used for patients who are battling all types of cancer, including lymphoma, melanoma, pancreatic, ovarian, brain, lung, breast, and colorectal cancer. The best part is supercomputer can continuously learn from each case and develop more and more accurate insights over time.
The accumulated learning can be applied for the benefit of healthcare at four levels. The basic level provides assistance to physicians by analyzing and presenting information which helps in diagnosis and treatment of patients. The second level supplements basic knowledge with analysis of patterns and conditions specific to a patient, based upon input from physicians. The third level provides potential diagnoses based on physician inputs plus a mapping of conditions and patterns of data about the patient. At the fourth capability tier is discovery where Watson can read hundreds of thousands of scholarly journal articles and other subject matter expert inputs related to research on the specific condition being studied. 
Medical futurist Dr. Bertalan Meskó said, “IBM’s Watson is the stethoscope of the 21st century.”  As the stethoscope enhanced the abilities of physicians by providing a new tool to listen to heart and lung sounds, Watson will provide a cognitive tool to enhance the diagnostic capabilities of physicians. Meskó said doctors, “may keep a few dozen study results and papers in mind, but IBM’s Watson can process millions of pages in seconds.”  Artificial intelligence does not have to lead to the loss of the human touch. In 1997, IBM’s supercomputer Deep Blue beat Garry Kasparov, the reigning chess grand master. Kasparov later said he could have performed better if he had access to the same databases as Deep Blue.  Physicians now will be able to perform better by leveraging their knowledge and compassion with the cognitive abilities of supercomputers and big data.
A New Way of Practicing Cancer Medicine
Consumers will expect genetic analysis as a routine part of their care, not just for research. President Obama’s 2015 call for 1 million volunteers to have their genes sequenced is just the beginning. The Joint Center for Cancer Precision Medicine, a collaborative initiative among Dana-Farber Cancer Institute, Brigham and Women’s Hospital, Boston Children’s Hospital, and the Broad Institute of MIT and Harvard are developing a new way of practicing cancer medicine. Rather than treating all patients with a particular type of cancer in the same way, the scientists at the new center study the DNA, RNA, and protein from individual biopsy samples to determine how cancers will respond to typical cancer drugs physicians prescribed. Some patients may respond very well to a certain cancer drug while others may respond poorly. By knowing which response a patient may have, the pain and suffering of side effects can be avoided when the genetic analysis suggests the drug would provide no benefit to the patient.
The Joint Center is deploying state-of-the-art capabilities including “DNA sequencing and other tumor molecular profiling technologies, pathology, radiology, surgery, computational interpretation, and new tumor model systems, which are not available at most hospitals.” The genetic analysis performed at the center is utilizing the skills of biologists, bioinformaticians, and software engineers to develop new algorithms for processing and interpreting the gene sequencing data with the goal of directly applying the results to individual patients. While what Dana-Farber is doing may sound more like research than patient care, it will not be long before patients will expect such interventions.
Being able to provide personalized medicine will become a competitive differentiator for healthcare providers.
November 17, 2015 | Corresponding Author Dr. John R. Patrick | doi: 10.14229/jadc.2015.11.17.001 Received: October 16, 2015 | Published online November 17, 2015
Disclosures: Dr. John R. Patrick president of Attitude LLC, a Connecticut-based consulting firm, and former Vice President of Internet Technology at IBM.
Dr. John R. Patrick’s book, “Health Attitude: Unraveling and Solving the Complexities of Healthcare“, is now available online in print, Kindle, Audible, and Apple iTunes Audio Book formats.
Feature Image: An image of a selection of the 46 chromosomes making up the diploid genome of a human male. (The mitochondrial chromosome is not shown.) Feature image Courtesy: This file was derived from NHGRI human male karyotype and made available under the Creative Commons CC0 1.0 Universal Public Domain Dedication.
This work is published by InPress Media Group, LLC (Editorial: New Learning Makes ADC Development Less Empirical) and is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. Non-commercial uses of the work are permitted without any further permission from InPress Media Group, LLC, provided the work is properly attributed. Permissions beyond the scope of this license may be available at adcreview.com/about-us/permission.
Last Editorial Review: November 17, 2015