Perils & Prospects of Practicing Medicine in a Digital Era g - - PDF document

1

Perils & Prospects of Practicing Medicine in a Digital Era g

Kent Bottles, MD Chief Medical Officer, PYA Analytics Thomas Jefferson University School of Population Health kent@kentbottlesmd.com; 610 639 4956 NAMS 2013 Annual Meeting Plenary Symposium 1

The Digital Revolution in Medicine Traditional Medicine

• Biomedical model reduces every illness to a

biological mechanism of cause and effect

• Attention on acute episodic illness
• Generalists replaced by specialists
• Focus on individuals
• Cure as uncompromised goal
• Focus on disease
• Antibiotics & infectious disease

Traditional Medicine

• Diagnose and treat
• Health is defined as absence of disease
• Patient story is subjective and untrustworthy
• Patient story is subjective and untrustworthy
• Lab results are objective and true
• Pathologists are the most important doctors
• Clinicians are paralyzed until lab provides

dx

Jeff Goldsmith on Digital Future

• “David never spent a day in the hospital,

and had one home and two office visits with his physicians during the course of p y g treatment, which consisted in its entirety of six weeks’ worth of home infusion therapy.

2

Jeff Goldsmith on Digital Future

• The bill for all these services was created,

evaluated, and paid electronically, with David’s nominal portion of the cost billed to p his Visa card, per agreement with his health

• plan. He never saw a paper bill, though he

could view the billing process in real time

• n his health plan’s web site.”

The End of Illness

David Agus, New York: Free Press, 2011

• “Take a moment to imagine what it would be

like to live robustly to a ripe old age of one hundred or more. Then, as if your master switch clicked off, your body just goes kaput. , y y j g p You die peacefully in your sleep after your last dance that evening. You don’t die of any particular illness, and you haven’t gradually been wasting away under the spell of some awful, enfeebling disease that began years or decades earlier.”

Eric Topol on MI prevention

• “Monitoring would ideally use an implanted

nanosensor, smaller than a grain of sand and capable of finding its targets in even one- p g g millionth of a liter of blood, communicating with a patient’s smartphone. Individuals who would get the nanosensors would be those whose genome sequence or other biomarkers had already put them at risk for a heart attack.

Eric Topol on MI prevention

• Well before the horse was out of the barn,

the nanosensor could alert the individual to seek attention; therapy then would consist ; py

• f both ant-clotting and anti-inflammatory
• medications. At some point in the future,

nanosensors will likely have the capacity to release medications on their own in response to high levels of circulating cells

• r nucleic acids”

Digital Medicine Convergence

• Genomics
• Wireless sensors
• Imaging

g g

• Information Systems
• Social networks
• Ubiquity of smartphones
• Unlimited computing power via cloud server

farms makes Big Data Analytics possible

Digital Medicine

• Digitizing a human being

– Genome – Remotely, continuously monitor vital signs, Remotely, continuously monitor vital signs, mood, activity – Image any part of body, 3d reconstruction, print an organ – Readily available on your smartphone, integrated with traditional medical record, constantly updated

3 Digital Medicine of Present & Future

• Human body and disease is complex

emergent system that may never be fully understood

• Attention on chronic diseases
• Managing chronic diseases rather than cure
• Focus on person and the disease

Digital Medicine of Present & Future

• Agus consulted on treatment or Steve Jobs
• Jobs had both his cancer and normal cells

sequenced for molecular targeted therapy sequenced for molecular targeted therapy

• Oncologists customized his chemotherapy

to target specific defective molecular pathways in his tumor

• Treatment changed when tumor mutated

during therapy

Digital Medicine of Present & Future

• One of Steve Jobs’ doctors said there was hope

that his cancer would soon be considered a manageable chronic disease, which could be kept at bay until he died of something else kept at bay until he died of something else

• “I’m either going to be one of the first to be

able to outrun a cancer like this, or I’m going to be one of the last to die from it. Either among the first to make it to shore, or the last to get dumped”

Systems Biology Yields New Therapies

• Zoledronic acid affects bone metabolism

and is used to reduce fractures but does nothing to cancer cells. g

• Zoledronic acid decreases breast cancer

recurrence by 36% presumably because it changes the environment of bones so cancer cells cannot spread

Systems Biology Yields New Therapies

http://www.nytimes.com/2012/06/03/business/geneticists-research-finds-his-own- diabetes.html?_r=1&pagewanted=print

• Michael Snyder sequenced his genome that

showed he was at high risk for Type 2 Diabetes

• Blood tests every 2 months of 40,000

molecules

• After 7 months showed he had developed DM
• Early detection, early treatment
• “This study is a landmark for personalized

medicine.” Eric Topol

Systems Biology Yields New Therapies

http://www.nytimes.com/2012/07/08/health/in-gene-sequencing- treatment-for-leukemia-glimpses-of-the-future.html?pagewanted=all

• Dr. Lukas Wartman of Washington

University developed Adult Acute Lymboblastic Leukemia

• Sequenced cancer cells & healthy cells
• Discovered normal gene in overdrive

producing huge amounts of protein

• Drug for kidney cancer shut down the

malfunctioning gene

• Whole genome sequencing

4 Sizing Up Big Data

Steve Lohr, NY Times, June 20, 2013

• Philosophy about how decisions should be

made

– Decisions based on data and analysis Decisions based on data and analysis – Less based on experience and gut intuition – Eliminates anchoring bias and confirmation bias

• Revolution in measurement

– Digital equivalent of the telescope – Digital equivalent of the microscope

Sizing Up Big Data

Steve Lohr, NY Times, June 20, 2013

• Bundle of technologies

– Web pages, browsing habits, sensor signals, social media, GPS location data, genomic , , g information, surveillance videos – Advances in data storage and processing – Machine learning/AI software to find actionable correlations from the big data

Jeffrey Hammerbacher

http://www.youtube.com/watch?v=OVBZTDREg7c

• All industries are being disrupted

– Moneyball, 538, Large Hadron Collider

• McKinsley: Big Data: The Next Frontier
• McKinsley: Big Data: The Next Frontier

for Competition

– $338 billion potential annual value to US healthcare

– $165 billion in clinical operations – $105 billion in research and development

Jeffrey Hammerbacher

http://www.youtube.com/watch?v=OVBZTDREg7c

• Oracle: From Overload to Impact

– Healthcare executives say collecting & managing more business information today than 2 years ago A erage increase 85% per ear – Average increase 85% per year

• Frost & Sullivan: US Hospital Health Data Analytics

Market – 2011 10% of US hospitals use data analytic tools – 2016 50% of US hospitals will use data analytic tools

Big Data

Viktor Mayer-Schonberger & Kenneth Cukier, 2013

• To analyze & understand the world we used to test

hypotheses driven by theories

• Big data discards theories & causality for

correlations

• Univ of Ontario premature baby studies
• 1,260 data points per second
• Diagnose infections 24 hours before apparent
• Very constant vital signs indicate impending

infection

Algorithms Mine Public Data

• Atul Butte combined data from 130 studies of

gene activity levels in diabetic & healthy tissue

• Butte identified new gene associate with Type 2

g yp DM because stood out in 78/130 studies

• Algorithm looking for drugs & diseases that had
• pposing effects on gene expression

– Cimetidine for lung adenocarcinomas – Topiramate for Chrohn’s Disease

5

Algorithms Mine Public Data

• Russ Altman used algorithms to mine

Stanford Translational Research Integrated Database Environment & FDA adverse event reports database

• Patients taking SSRI antidepressants and

thiazide are at increased risk for long QT syndrome, a serious cardiac arrhythmia

Big Data for Cancer Care

Ron Winslow, WSJ, March 27, 2013

• ASCO
• Database of hundreds of thousands of patients
• Prototype has collected 100,000 breast cancer

yp , patients from 27 groups who have different EMRs

• “Recognition that big data is imperative for the

future of medicine” Lynn Etheredge

• Less than 5% of adult cancer patients participate

in randomized clinical trials

Big Data

Viktor Mayer-Schonberger & Kenneth Cukier, 2013

• Datafication of acts of living
• Zeo large database of sleep patterns
• Asthmapolis sensor to inhaler that tracks
• Asthmapolis sensor to inhaler that tracks

location via GPS identifies environmental triggers

• Fitbit and Jawbone
• iTrem monitors Parkinson’s tremors almost

as well as the tri-axial accelerometer used in specialized office medical equipment

Big Data

Viktor Mayer-Schonberger & Kenneth Cukier, 2013

• Paralyzing privacy

– Notice and consent – Consent for secondary uses impossible – Anonymization does not work

• AOL 2006 20 million search from 657,000 users:

NY Times user number 4417749 as Thelma Arnold (“My goodness, it’s my whole personal life. I had no idea somebody was looking over my shoulder”)

• Netflix Prize 100 million rental records from

500,000 users. Mother and closeted lesbian in Midwest was reidentified

Big Data

Viktor Mayer-Schonberger & Kenneth Cukier, 2013

• Dictatorship of Data

– Relying on numbers when they are far more fallible than we think – Robert McNamara’s body count numbers in Viet Nam – Michael Eisen tried to buy The Making of a Fly on Amazon in April 2011. Two established sellers offering the book for $1,730,045 and $2,198,177. Two week escalation to a peak of $23,698,655.93 on April 18 – Unsupervised algorithms priced the books for the two sellers.

The Hidden Biases of Big Data

http://blogs.hbr.org/cs/2013/04/the_hidden_biases_in_big_data.html

• Big Data vs. Data with Depth
• “With enough data, the numbers speak for themselves.”

Chris Anderson Can n mbers act all speak for themsel es? Sadl the

• Can numbers actually speak for themselves? Sadly, they

can't. Data and data sets are not objective; they are creations of human design. We give numbers their voice, draw inferences from them, and define their meaning through our interpretations.

• Hidden biases in both the collection and analysis stages

6

The Hidden Biases of Big Data

http://blogs.hbr.org/cs/2013/04/the_hidden_biases_in_big_data.html

• Boston’s StreetBump smartphone app

– 20,000 potholes a year need to be patched – Poor areas have less cell phones, less service Poor areas have less cell phones, less service

• Hurricane Sandy 20 million tweets +

4square

– Grocery shopping day before – Night life peaked day after – Illusion Manhattan was hub of disaster

Digital Medicine of Present & Future

• Predict and Prevent
• Health is a state of complete physical,

mental and social well-being and not mental, and social well being and not merely absence of disease

• Patient story is essential for development of

personal metrics which will be unique to each individual

• Pathologist sadly becomes less important