蚂蚁论坛As president of the Mayo Clinic Platform, I lead a portfolio of new digital platform businesses focused on transforming health by leveraging artificial intelligence,the internet of things, and an ecosystem of partners for Mayo Clinic. This is made possible by an extraordinary team of people at Mayo and collaborators worldwide.This blog will document their story.

Friday, April 24, 2020

Reinventing Clinical Decision Support

In our latest book, Reinventing Clinical Decision Support: Data Analytics, Artificial Intelligence, and Diagnostic Reasoning, Paul Cerrato and I explore the promise of artificial intelligence and machine learning for improving clinicians’ ability to make more informed diagnostic and therapeutic decisions. Here’s an excerpt from Chapter 2:

“AI is a once-in-a-generation transformative technology. As such, expect its impact to be on the scale of the advent of electricity or the Internet,” says Jean-Claude Saghbini, Wolters Kluwer Health.(1)

“Artificial intelligence and machine learning are set to transform healthcare. From front line care delivery, including triage, clinical decision support and patient experience to back office operations, such as billing and revenue cycle, algorithms and emerging technologies are already proving their value,” according to a recent report from Healthcare Information Management Services Society (HIMSS). (1)

Both enthusiastic visions suggest that artificial intelligence (AI) and machine learning (ML) are poised to transform medicine and bring in an era of cost effective patient care. But these predictions have to be weighed against less optimistic views, including those that suggest AI will disrupt the workforce in healthcare and other industries, causing many to lose their jobs to soulless
algorithms and robots.

Israeli historian Yuval Noah Harari, for example, believes that: “For now, most of the skills that demand a combination between the cognitive and manual are beyond AI’s reach. Take medicine . . . ; if you compare a doctor with a nurse, it’s easier for AI to replace a doctor—who basically just analyzes data for diagnoses and suggests treatments. But replacing a nurse, who injects medications and bandages, is far more difficult. But this will change; we are really at the beginning of AI’s full potential.” (2)

There are futurists who are far more optimistic, however. They imagine a scenario in which every patient gets the same quality of care afforded presidents in affluent countries or billionaire CEOs at major technology companies. With the assistance of AI, machine learning, and massive databases, they envision a world in which we each have the electronic equivalent of a personal physician who has access to the very latest research, the best medical facilities that specialize in each individual’s health problems, access to cutting-edge data sets, predictive analytics, testing options, clinical trials currently enrolling new patients, and much more. For example, Alvin Rajkomar, MD; Jeffrey Dean, MD, of Google; and Isaac Kohane, MD, PhD, of Harvard Medical School, describe a possible future in which:

A 49-year-old patient takes a picture of a rash on his shoulder with a smartphone app that recommends an immediate appointment with a dermatologist. His insurance company automatically approves the direct referral, and the app schedules an appointment with an experienced nearby dermatologist in 2 days. This appointment is automatically cross-checked with the patient’s personal calendar. The dermatologist performs a biopsy of the lesion, and a pathologist reviews the computer-assisted diagnosis of stage I melanoma, which is then excised by the dermatologist.(3)

This scenario stands in stark contrast to the current state of affairs that often transpires in today’s broken healthcare ecosystem. As Rajkomar et al.3 point out, in today’s ecosystem, this patient is more likely to ignore his skin lesion for far too long; his primary care physician may misdiagnose the melanoma because of its atypical appearance, and the delay may result in a metastatic malignancy that requires systemic chemotherapy.

With such contrasting views, clinicians have to wonder: What precisely will the future look like? Our purpose in Chapter 2 is to explore the strengths and weaknesses of AI and ML and to help clinicians and technologists gain a realistic view of the near future—a future that promises to deliver more cost effective, more personalized care but also one that faces numerous challenges. We will explore basic terminology and concepts and discuss AI/Ml solutions in

a variety of medical specialties. In Chapter 3, we will outline the many challenges that stand in the way of the full implementation of these solutions. 

More details from Chapter 2 will appear in a subsequent blog. A full discussion of AI/ML is available in our book.


1. “AI and Machine Learning: What Cuts Hype from Reality.” Healthcare IT News. Retrieved on April 8, 2019.

2. Kaufman D. (2018, October 19). “Workers Beware: Algorithms Could Replace You—Someday.” The New York Times, p. F2.

3. Rajkomar, A., Dean, J., and Kohane, I. (2019). “Machine Learning in Medicine.” New England Journal of Medicine, vol. 380, pp. 1347–1354.

Saturday, April 18, 2020

A COVID update

I realize that my blog post frequency has diminished during COVID.   Writing time has been redirected to the national COVID-19 coalition and its 14 workgroups:

Modeling & Simulation
Health Systems and Clinical SME
Supply Chain
ICU and Mechanical Ventilation
COVID-19 Data Standardization (mCoVD = Minimal COVID-19 Viable Dataset)
Non-Pharmaceutical Interventions
Optimization of Clinical Therapeutics/Protocols
Data Storage and Source
Privacy Advisory
Contact Tracing

Below is a description of this week's highlights

a. Critical Shortages of Personal Protective Equipment (PPE)

Worked with international suppliers to deliver 580,000 FDA-certified respirators to New York City hospitals, working through Governor Cuomo’s procurement office.

Connected 100,000 FDA-certified respirators to Masks for America, a volunteer coalition of everyday Americans joining forces to deliver protective masks directly to frontline healthcare workers in COVID-19 hotspots.

Prepared guidelines, assisted purchases, and piloted novel solutions to decontaminate respirators so they can be reused multiple times, extending their lifecycle.

b. Implementing Social Policies

Launched a Non-Pharmaceutical Intervention  (NPI) dashboard that provides real-time tracking of state-wide NPI implementation.  As States begin relaxing NPIs, we’ll be able to see the impact. 

c. Achieving Data-Driven Clinical Care Outcomes

Coalition members, including numerous electronic health record vendors, are developing a minimal common data set for COVID-19.  This is now being used to research the outcomes of clinical outcomes on treatments, such as hydroxychloroquine, Remdesivir, and others.   We have designed a federated query approach so that any institution can participate in studies by running queries locally in their EHR. 

Supporting the rapid scale-up of telemedicine as part of a fully integrated healthcare delivery system.  With Mayo's help we are running multiple studies about the adoption of telemedicine during COVID.   See a starting set of best practices in the Resource Library

Detecting Dis/misinformation Related to COVID-19.   Dis/misinformation or outright fraud can affect patients' ability to understand and adhere to non-pharmaceutical interventions and, most importantly, their health.  A new dashboard will be published soon.

Supporting the Mayo Clinic-led national convalescent plasma trial, which is attracting thousands of health systems and patients.  We have worked closely with EHR vendors to develop order sets and a data analysis approach.

Supporting the Contact Tracing activities of Apple, Google, MIT and others with connections to the Association of State and Territory Health Officers, Bluetooth experts at Lincoln Labs, and leveraging an Amber alert like technology called Sara alert for infected patient followup. 

d. International Regulatory Standards and Comparison for N95 Respirators

Due to the shortage of N95 respirators in the U.S. during the pandemic, organizations are ordering similar respirators from international companies. We’ve listed what’s available from 7 countries and which products are FDA-authorized.  

e. Ventilator Training App

This multi-vendor library of training and product materials for medical professionals was created through a partnership of leading ventilator manufacturers and Allego, Inc. You’ll find free mobile access to video overviews, instruction manuals, and other training materials for equipment that is critical to treating patients suffering from COVID-19-related respiratory distress.   See

f. Coronavirus Scientific Literature Topic Browser

Researchers looking for COVID-19-related articles of clinical or scientific interest should try this interactive tool. The COVID-19 Open Research Dataset (CORD-19) is presented in several views, allowing users to quickly find clusters of papers on a desired topic. 

Sunday, March 22, 2020

Coming Together to Save Lives

The following is a post from the members of the COVID-19 Healthcare Coalition #C19Coalition co-chaired by  Dr. Jay Schnitzer, Chief Medical and Technology Officer at MITRE  @MITREcorp who directs initiatives in health/life sciences and Dr. John Halamka @jhalamka, President of Mayo Clinic Platform who leads a portfolio of platform businesses focused on transforming health.

Pandemics thrive in confusion.

Not because diseases like COVID-19 have intent, but because the lack of a focused response makes the spread of disease so much easier.

Pandemics stress our healthcare delivery system. We are now familiar with the generalized public health measures that help contain the spread of infectious disease including social distancing, hand washing, self-quarantine, cancellation of large public events, and school closures.    More targeted measures are needed and that requires coordination.

We need to leverage the strengths of the private sector. By bringing together healthcare organizations, technology companies, non-profits, academia, and startups we can leverage their unique strengths  for the benefit of all.

Over the past week, we've launched the Covid-19 Healthcare Coalition involving Amazon Web Services, Arcadia Health, athenahealth, Buoy Health, the CommonWell Health Alliance, HCA Healthcare, Intermountain Healthcare, LabCorp, Leavitt Partners, MassChallenge, Mayo Clinic, Microsoft, MITRE, Rush University System for Health, Salesforce, University of California Healthcare System and many others.

We've already begun focused efforts to increase COVID-19 testing capacity for the country, to coordinate early therapies, and to accelerate vaccine development.

We established guiding principles for the coalition:

1. Everyone participates for the benefit of those impacted by COVID-19

2. Everyone cooperates and openly seeks to assist each other when possible

3. Nobody will get paid. Bring your resources and no money will be exchanged

4. Verbal agreements will suffice to get us started

5. If you agree to these terms and conditions, you’re in

Our first task is to share learnings and encourage innovation across the coalition.

We’re moving fast to support technology and policy innovations.   MITRE, a national research and development center, is serving as program manager.

Pandemics thrive in confusion and wither against a united, clear-eyed attack.

Let’s shut down COVID-19 together.

Saturday, March 21, 2020

Unity Farm Sanctuary and COVID Planning

You might think a farm sanctuary doesn't need cyber-liability insurance (we do because we track social security numbers associated with donations).  You may not think that a Farm Sanctuary needs a comprehensive COVID plan.

We need a plan for five reasons
1.  We are a community gathering point for over 100 volunteers and hundreds of people taking enrichment classes including Yoga, Tai Chi, Meditation, Beekeeping, and Council on Aging activities.
2.  We are an employer with full time and part time workers
3.  We are accountable for the health of more than 250 creatures.   Without humans, these creatures would lack daily care
4.   As the economic impact of job losses reduces the ability of the community to support its animals, sanctuary services become increasingly important
5.   The community is looking to us for guidance

So what did we do?    Weeks ago, we realized that aggressive measures were needed.   We closed the farm sanctuary to the public.   We paused all classes.    We put the volunteer program on hold.    We began an aggressive disinfection/biological isolation protocol. 

At this point, only my wife and I plus 3 key employees come to the property.   Here is the email we sent to the community a few weeks ago

"My valued friends,
Effective immediately, Unity Farm Sanctuary is limiting access to the Sanctuary

Here's important background information

Currently, the vast majority of sanctuaries surveyed (on the two international sanctuary groups I belong to) have eliminated all volunteers and only have the smallest number of staff possible to run their sanctuaries. They all state that the owners and the core staff must stay as healthy as possible and limit their exposure. Most of us who run sanctuaries are most concerned too about feed supply-chain. Core staff will be focused on this this week.

If our core staff is sick, we will be in a VERY difficult place. (I am actually in a higher risk group from my own immune system - I am a breast cancer survivor, I have Graves Disease, I have had pneumonia in the past, I am very vulnerable to upper respiratory virus as a general rule, and I am nearing 60.)

Starting Monday, no volunteers will be onsite, no visitors, no tours, no classes. Staff will be pared down to the smallest group of core people we can manage. This will hold at minimum to April 6, and based on what I know from our connections through John's connections to experts, in our country you can expect at least an 8 week timeframe on groups, gatherings and interpersonal contact limits.

Please take social distancing seriously. I am restricting volunteers here so that I keep you healthy too. I want to hear that every single one of you is doing well and safe. I will be posting on newsletters, Instagram and FB as much as possible so that people do not feel disconnected.

Kathy Halamka"

And here is what we communicated to the staff

"Staff that is remaining on schedule will be following these precautions:
-All plastic and metal surfaces outside the house will be wiped down at noon and 7pm with bleach wipes.  Inside the Unity Meeting House we will focus on kitchen, bathroom, laundry room, and tables (handles, knobs, hayboxes, steering wheels,,,,)
-Staff should have no reason to go upstairs, so please stay on the first floor of the house so we do not need to wipedown the entire 2nd and 3rd floor as well.
-Wash hands thoroughly throughout your shift (and at home!)
-Keep distance between staff members (per CDC recommendations)
-If you or a family member are not feeling well or you believe you have come in contact with someone with COVID-19, stay home and self quarantine! (Let me know asap so we can find coverage)

In addition, we have been working hard to stock up on supplies (hay, grain, cleaning supplies)

Remember this is all temporary, and an effort to keep everyone healthy and safe so we can continue to care for our animal residents. If anyone has any questions please feel free to email, text, or call. "

The COVID pandemic will be filled with stories of amazing leadership and inspiration.    This once in century event effects all of us, even the citizens of Unity Farm Sanctuary.    We're doing our best to ensure every creature is comforted as we shelter in place.

Bringing Out the Best in Us

In the upcoming week you'll see numerous writings about national private sector efforts to enhance COVID response, communication, and collaboration.

As part of doing this work, one of my colleagues noted that the she's seen many recent examples of current events bringing out the best in people.     There's a willingness to help, a eagerness to volunteer, and a sense of belonging by banding together for a common cause.    Yes there are stories about hoarding toilet paper and purell, but those are minor distractions compared to the good things happening around us.

Here are examples of what I've seen in the past 24 hours.

1.  A major data analytics company focused on COVID modeling asked to collaborate with a major vaccine lab to accelerate development

2.  A group of competing companies aligned to create national policy requests that enable more virtual care

3.  Two competing big tech companies agreed to work together on helpful web-based resources for the country

4.  Big tech companies are offering expertise and credits for cloud resources

5.  An EHR company is working on a heat map showing orders placed for COVID testing as a proxy for virus spread

6.  An AI company is creating a map of national searches for COVID symptoms as a proxy for virus spread

7.  Many companies are offering free/reduced cost services in support of COVID response

8.  A non-profit recognized that we'll likely need a national vaccine registry linked by a nationwide patient matching strategy when a vaccine is available 12-18 months from now.    They will assemble a guiding coalition for that effort.

9.  A group of investigators is working on a trial of using convalescent plasma as a mechanism of conferring immunity. 

10.  A laboratory is seeking coronavirus positive blood to accelerate the development an easy to run, highly specific serology-based blood test

For all the anxiety we feel, it's clear that many people are working for the common good.    So if you're feeling that the future will be more Mad Max than Star Trek, realize that people around the world are working together to create the best possible outcome.

Working together, we can make a difference.

Saturday, March 7, 2020

What's a Platform Go Live?

As we plan our go-lives for the Mayo Clinic Platform, we recently discussed how best to measure what constitutes a go-live.

First, let's review what Platform thinking (technology, policy, people and process) can do for an organization.

*Facilitates collaborations and partnerships with external entities (i.e. participants on the Platform benefit from the presence of other participants)
*Connects assets (data, algorithms, expertise) with customers in ethical, privacy protecting ways
*Supports the development of ideas into products that may be licensed, spun out, or sold as services
*Has turnkey technology and policy approaches that empower innovators to incubate/accelerate their ideas with agility, such as assistance with validation/FDA clearance assessment or other common regulatory hurdles

Success can be measured in many ways - impact on patient care, the boldness of the innovation, value creation for all participants, public perception of the work, and time to market.  Value creation could be licensing, transactional revenue, or equity growth.

Different audiences may have different perceptions of go-lives.    While it would be tempting to conflate general availability (GA) of our Platform offerings with go-live, we believe that the Platform won't be live until an "active customer" or stakeholder actually uses what we have to offer.

With these ideas in mind, here are few straw definitions for the concept of go-live for the Mayo Platform businesses.

 1.  The Clinic Data Analytics Platform (CDAP) accelerates new insight discovery by enabling analysis of de-identified historical data stored within a secure cloud hosted container controlled by Mayo Clinic.     A reasonable definition of go live is that CDAP data and tools become available such that a customer runs a data analysis that yields new insights for that customer, for example discovering a potential path forward for COVID-19 care or treatment (the "active customer" criterion)

2.  The Home Hospital Platform enables high acuity care via telemetry, clinical care coordination, communication, supply chain, and record keeping.   A go-live occurs when a home hospital discharge occurs with a patient restored to health after management facilitated by Platform components hosted on Mayo Clinic Cloud.  (the "active patient" criterion)

3.  The Remote Diagnostic and Management Platform accepts a signal/data via a Mayo hosted orchestration engine, sends it to an algorithm/interpretation service, and a high quality diagnosis/interpretative result is returned to a customer, for which a payment is generated (the "active orchestration" criterion)

4.  We're thinking of developing some supportive functions such as FDA clearance services.  An approved FDA clearance would constitute a go live (the "demonstrated expertise" criterion).     The reason we are considering a standard function for FDA clearance as part of acceleration/incubation services is because of the significant complexity and expense of  FDA clearance:

a.       Regulatory Pathway Determination: $21-23K.  Takes about 2 months to complete
b.       Gap Analysis & QMS Implementation: $220K (800 hrs.) - $495K (1,800 hrs.), depending on results of Gap Analysis (how much needs to be done)
c.       FDA Pre-submission prep & meetings: $98K (354 hrs.)
d.       Complete FDA submission and clearance: $275-400K (1,000-1,200 hrs.)

A service that can pool experience, talent and technology to get synergies and scale to lower the unit cost and speed of FDA clearances would be a win for everyone.

5.   As we create our staffing model, we'll have functions that cross all new Platform businesses and dedicated roles in each business.   For example, across all businesses we'll have one team overseeing the communication plan and one team processing new business ideas/collaboration requests.     If a new proposal can be reviewed, analyzed, a go/no go decision made, and a new business launched, that would constitute a go-live of the function being open for business.    (the "process maturity" criterion)

In 2020, we're aiming for at least one go-live per quarter, celebrating the "ribbon cutting" of objectively measured Platform progress.   Next quarter, we'll launch the CDAP tool for Mayo internal users and begin processing our first queries for external customers.

To me, our most "pure Platform" go-live will be when we have a generalizable model for ingesting data, interpreting it with novel analytics/algorithms/services and returning a result within the workflow of the customer.    It's also one of the most challenging to assemble.    I'll be writing about our journey for that go-live throughout 2020.

Tuesday, February 25, 2020

What is the Architecture of a Modern Platform?

Platform businesses require technology that promotes interoperability and scalability.  For those who live in platform companies day-to-day, my thinking below may sound obvious, but for those who are thinking about a cloud journey, the list of technologies below may be helpful.

Storage and compute functionality in the cloud enables agility via "infrastructure as code" products such as Terraform.    Terraform enables virtual server spin up on demand within applications to provision and manage any cloud, infrastructure, or service.   Each cloud provider has strengths.    Customers like Google Cloud Platform because of BigQuery, which scales infinitely.  Customers like Amazon because of the tools like Comprehend Medical and Sagemaker.   Customers like Azure because of its integration with existing Microsoft components. 

Similarly, database functionality such as MySQL or PostgreSQL can be rapidly deployed using a front end service such as Google's SQL Cloud that makes it easy to set up, maintain, manage, and administer relational databases on Google Cloud Platform.

Kubernetes is an open-source container-orchestration system for automating application deployment, scaling, and management. It was originally designed by Google, and is now maintained by the Cloud Native Computing Foundation. 

For healthcare applications, it's clear that Fast Healthcare Interoperability Resources (FHIR) interfaces for inbound and outbound data exchange are the right approach to application/EHR integration.    Highly scalable FHIR services are available via HAPI FHIR on Smile CDR . Google Health's FHIR endpoint is also a good choice.

FHIR is best for exchanging summary data, as well as making EHR data available to an application more broadly.   For HL7 version 2, the Google Healthcare API supports a Minimal Lower Layer Protocol  (MLLP) entry point and a message repository (along with cloud publication/subscription notifications).

And of course, modern network security requires data be stored in encrypted form as well as in transit in encrypted form.  This simple idea will mitigate numerous security risks.

I recently met with well respected industry leaders and asked how Mayo Clinic can future proof its Platform  efforts.    I was told

"Ensure that infrastructure as code is used to deploy storage and compute.   Ensure relational databases can be deployed and managed on the cloud hosting platform.   Use Kubernetes to automate application deployment.  Embrace hosted FHIR and API management services."

As we evaluate new partnerships and collaborations, we do a technical deep dive to avoid locally hosted, siloed, and proprietary approaches, instead favoring a cloud native architecture using Terraform, Kubernetes, and FHIR.

As Wayne Gretzky taught us, you need to skate where the puck will be.    These cloud native architectures are clearly where the puck is going.