Christopher T Smith.com
  • Home
  • About Me
  • Leadership
  • Reflections
  • Career Development Research
  • Neuroscience Research
  • Published Research
  • Press
  • Presentations
  • Job Search Resources
  • Funding Resources
  • Subscribe to Newsletter
  • Contact

Reflections Blog

Using Data Science and Artificial Intelligence to Improve Healthcare

9/30/2019

0 Comments

 
Data Analytics & Healthcare
Picture
This article originally appeared on the Health:Further blog on October 14, 2018.
It has been updated with current news and findings.
Data science is a buzzy term not only in the technology sector but in the wider culture as well. It has seeped into the common vernacular and promises increased insights and knowledge extracted from the vast quantity of data being generated every day.

The use of data science in healthcare is growing and artificial intelligence (AI) represents a huge business opportunity in the space. However, the potentially identifiable nature of health records and ethical concerns about how the data should be utilized and by whom makes working in this space a challenge.

The recent publication of work suggesting AI may be as good as clinicians in diagnosing disease further highlights the increased importance this technology will have in 21st Century healthcare.

I spoke with data scientists from 3 different healthcare companies on how their groups are using data to improve the quality and efficiency of healthcare.
Picture
axialHealthcare, Nashville, TN

Lindsey Clark, Ph.D., is Director of Data Science and Analytics at axialHealthcare in Nashville, TN. Since joining the company in 2015, Clark has watched axialHealthcare grow rapidly from 8 to more than 100 employees. Focusing on pain management and opioid care, axialHealthcare leverages medical, behavioral, and pharmacy claims data to drive improved patient care and financial savings for health insurers through technology-enabled capabilities.
In essence, axialHealthcare's goal is to understand which treatments are both effective and safe in the treatment of pain. Axial is also focused on determining if treatment approaches beyond potentially addictive opioids are viable for particular patients.

A big question at axialHealthcare is, “what does safe and effective pain management look like?” The answer seeks to ensure that 1) opioids are prescribed judiciously given their propensity for causing dependence and addiction and 2) that other pain reduction therapies are considered when warranted.
Picture
Clark emphasized the unique challenges of working with health information, including the critical need for data security and privacy as well as navigating the complex United States health system. The focus for most of U.S. healthcare is on what is reimbursable by either health insurers or Medicare/Medicaid (federal & state payers). Thus, every company trying to improve cost efficiency in healthcare must think about how their recommendations fit into the payers’ current reimbursement framework.

axialHealthcare has organized its Research and Development (R&D) group into data science and statistics/communication branches that communicate closely but have different functions. These teams work with the product team whose job is to think about the value they can extract from data insights and models to benefit customers. The R&D groups also provide support to the company’s clinical outreach team comprised of licensed clinical pharmacists and engagement specialists who work to change provider behavior and improve patient outcomes, which ultimately reduces costs on the healthcare system and protects insurers from spending on ineffective treatments.
Picture
axialHealthcare synthesizes a variety of data to improve patient care and drive savings for payers.
Most of the company’s data comes from insurance claims, but some is also gleaned from patient behavioral and electronic health record data. Although the team is always focused on new data-derived models of improved care and cost savings, it is critical for the data science team to align their projects with what the market needs.
Picture
“Insurers, our main clients, are very focused on short-term costs and so it’s often critical that our company frame the work in a way that indicates both short-term and long-term costs can be improved through data insights. Selling clients on the long-term cost savings can be difficult, especially if the short-term effects are increased costs to insurers,” according to Clark.

This point illustrates the challenge of providing solutions that are good for the business of healthcare and also for the health of patients.

Framing information in a way where payers can see the long-term savings generated from costly approaches in the short-term is critical to enacting meaningful, effective interventions.
Ultimately, the company hopes to collect its own data for two reasons: 1) access to data can be a challenge and 2) variables that may be of interest to the data science team aren’t always available in the data collected by a third party. Nevertheless, axialHealthcare’s current approach has proven effective for patients and payers.

Artificial Intelligence (AI) in Healthcare

At the 2018 Health:Further Festival held in Nashville, TN, I talked with two companies working to use artificial intelligence (AI) to improve healthcare.

Picture
Change Healthcare AI group, San Francisco, CA

Change Healthcare is the largest independent healthcare information technology company in the U.S., handling approximately 60% of medical claims. Alex Ermolaev is part of a growing AI team there. The goal of Change Healthcare’s AI group is to improve efficiency and add value on top of existing data management and analytics solutions.

See Alex's video on AI in Healthcare below.
Change Healthcare uses large, aggregated and de-identified claims, medical history, and treatment plan data from their databases to provide insights on how to increase the effectiveness of healthcare, particularly how to provide treatment that is more efficacious and economical. While Change has mostly claims data, Ermolaev said most of it is very extensive, often up to 400 pages per claim, so that meaning and insights can be extracted from the various doctor notes and other details from healthcare providers. Text from claims can be read and analyzed using natural language processing approaches to identify relevant information in the record.
Ermolaev, formerly at Nvidia, mentioned that most AI models can achieve very high accuracy (>95%) as long as the following 3 factors are available: 1) large amounts of data, 2) bigger/more complex models, 3) more computing power.

“The main limit to using AI in healthcare is the lack of large enough data sets,” according to Ermolaev. This shortage of data is not unexpected given the sensitivity of personal health information and the vast privacy protections in place. Thus, companies with access to the data have a great advantage when competing in the AI healthcare space.
Picture
As AI and predictive analytics grow in healthcare, Ermolaev believes we are moving from evidence-based healthcare, where treatment decisions are based on what’s been proven effective for the population in general, to intelligence-based care where a particular patient’s medical history informs more personalized treatment.
I was surprised to hear Ermolaev mention that genetic information (frequently promoted in academic circles as the key to precision medicine) is often not required to develop personalized insights. This highlights the fact that currently available medical history, behavioral, and symptom data is often adequate in creating dramatically more effective personalized treatment plans.

UPDATE:
Change Healthcare announced its Claims Life Cycle AI in February 2019, which seeks to reduce the number of denials for medical insurance claims processed by healthcare providers (see infographic).
Picture
Droice Labs, Brooklyn, NY

While at Health:Further, I also met with representatives from Droice Labs on Entrepreneur Alley at the 2018 Health:Further Festival, a showcase area where over 70 startup companies could meet with conference attendees.

Droice Labs brings the power of artificial intelligence to hospitals. The company’s technology provides personalized predictions of how a given treatment (e.g., a drug or a medical device) will perform for a given patient. This software solution is based on a combination of the latest medical research and learning algorithms, which together analyze how a treatment has performed on similar patients in the past by aggregating data from millions of patient records and treatment plans. This allows doctors to consider all of their options in real-time and choose the right treatment.
Picture
Picture
Droice labs uses a variety of patient datapoints to better understand individual differences in response to medical treatment.
Droice Labs has approximately 30 employees and works with providers, payers, pharma, and government clients to build applications that augment processes and improve workflows. The goal of this work is to improve the quality of care for patients while also decreasing the burden on physicians with the ultimate outcome of increasing the efficiency of the healthcare system.

The company has been around for just over 2.5 years. The founders of Droice have extensive backgrounds in technology and AI and take a “deep dive” approach to their projects, trying to understand the causation behind their insights and results. They then communicate these findings transparently to their clients.
The relatively small company has a very collaborative culture with employees from a variety of backgrounds—tech, healthcare (including clinicians), scientific research—that bring different but complementary perspectives to their work. “The company is structured to be very horizontal, an organizational setup that fosters the sharing of ideas among all individuals in the team,” according to Droice Labs Co-founder & CEO Mayur Saxena, Ph.D.

Speaking to M. Saxena and Co-founder & Chief Product Officer Harshit Saxena (no relation), it is clear Droice Labs has a growth-focused, startup-like culture with a hunger from employees to continue to innovate and do more. The company has a mission that appeals to young workers that want to work for a values-driven company. “One measure of success at Droice Labs is how many people we were able to impact by our work today,” says M. Saxena. “Do the insights we develop increase the well-being of an extra 1,000 people? How can we improve things to increase that impact?”
Picture
Both of the founders agree with a point mentioned on the main kickoff stage at the Health:Further Festival: healthcare touches everyone. When asked what got them into using their analytic skills in the healthcare space instead of a traditional technology company, M. Saxena emphasized the common human experience of healthcare: “my thought was, if I am going to consume it, I might as well work to improve it.” He went on to say that healthcare is full of great people that work tirelessly to improve human life and that the industry needs technology to enable healthcare workers to do their jobs more easily and effectively.

At companies like Droice Labs, Change Healthcare, and axialHealthcare, the approaches may differ but the goal is the same: to improve healthcare in the 21st Century through data and insights.

Read More
Artificial intelligence in healthcare: Past, present, and future
Artificial intelligence in healthcare
Applied data science in patient-centric healthcare


Additional Resources

Want to get into data science?
The Insight Data Science Fellowship program offers a fabulous training opportunity with demonstrated success in job placement afterwards.

NC State's Institute for Advanced Analytics offers a well-respected Master of Science in Analytics degree with excellent career outcomes for graduates.
0 Comments

NIH All of Us Research Program: A new standard in participant engagement and partnership

8/15/2019

0 Comments

 
Personalized Medicine
Picture
This article originally ran on the Health:Further Blog on July 2, 2018.
It has been updated with new content and findings. 


Precision medicine is a phrase often used in healthcare but not well understood, especially by the general public. What type of precision are we talking about? Precision medicine is an emerging approach to disease treatment and prevention that considers differences in people’s lifestyles, environments and biological makeup, including genes. When the Precision Medicine Initiative launched in 2015 it was promoted as a great leap forward in understanding the various factors that contribute to human health and disease in the United States (U.S.). Read the Precision Medicine Working Group Report here.

The project has since been branded the All of Us Research Program and that title could not be more fitting. The goal of the program is to recruit 1 million individuals who will volunteer to provide their biological and health information in the form of medical records, genetic samples, and lifestyle data that is both self-reported and obtained from wearables (FitBit-like devices).

All of Us Seeks to Represent & Engage a Diverse Population
The All of Us program participants are to reflect the diversity of individuals living in the U.S. and are being treated as partners in the study. This concept of partnership speaks to the idea of participant engagement, an area
Consuelo H. Wilkins, MD, MSCI, Executive Director of the Meharry-Vanderbilt Alliance and leader of the All of Us Research Program Engagement Core, knows quite a bit about.  Engagement differs from recruitment in that its goal is to involve participants in the design, implementation, and oversight of the research, not just to enroll them in a study. Engagement is also a 2-way line of communication where research plans are transformed based on the perspectives of all those involved in it: researchers and participants.
Picture
Leveraging Community Input
Another aspect of how the community provides useful feedback on the
All of Us program is in the form of community engagement studios, modeled on a similar program at Vanderbilt University. These engagement groups were held across the country and allowed individuals from the community to voice concerns or share their thoughts on various practices the program was planning to implement to recruit and interact with potential study participants. More than 70 studios were held in preparation for the nationwide rollout of All of Us on May 6, 2018.

Community Engagement Continues
The Engagement Core works closely with community partners across the U.S. to help host the community engagement studios in a manner that makes community members feel welcome. For example, the community organizations are asked for guidance on everything from the time of day the studio should be held to the location and what type of food should be ordered. There was one particularly memorable instance in Chicago where the Engagement Core staff had to bring a large amount of cash to purchase food at a cash-only restaurant recommended by an Asian community group. While a seemingly small thing, acts such as this engender trust between
All of Us and its community partners because the partners can see that their opinions are being used to guide not just food but research and policy choices made by the national program. Changes coming out of these community engagement studio sessions have included making the language in participant materials easier to understand (use of less jargon and complex terms) as well as providing a small amount of monetary compensation to All of Us participants. Many potential participants saw the compensation, even if it was small, as evidence they and their time was being valued. Such changes emerging out of these studios can have a major impact on study participation (see, for example) and the Engagement Core expects it to be the case for the All of Us
program as well.
Picture
Participant Engagement is Critical to the Success of All of Us
So far,
All of Us research participants have been “all in” to contribute to the program. Alecia Fair, DrPH, Research Assistant Professor with the Meharry-Vanderbilt Alliance, has been in the public health and health promotion/education field since 1992 and has never seen the degree of investment participants in the All of Us pilot program
have displayed since it began in 2016.

Individuals have strong motivations for volunteering as participants. Many have loved ones who are sick or died prematurely from disease and hope their contribution to the program as a participant, and also as a voice of participants, will make a difference in the health of others. Generating a high level of individual involvement, investment, and trust in participants is critical as they can volunteer as much or as little information as they want to the program. In order for deeper insights and knowledge to be gleaned from the program, participants will need to be willing to share information from their electronic medical record, genetics, wearable devices, and self-reported daily lifestyle choices.
The data collected in All of Us is not just for researchers. One important goal of the program is that all data collected from any participant will be provided back to the participant through useful insights. The Participant Technology Systems Center (PTSC) for All of Us is being administered by Vibrent Health, a  digital health technology company headquartered in Fairfax, Virginia.
Picture
The PTSC is responsible for innovating, developing and monitoring all participant-facing apps and technology systems used by All of Us (available across a variety of platforms: PC, iOS, Android). These systems enable study enrollment and data collection and, on the back end, data storage, organization, analysis, and curation—the full lifecycle of the participant’s involvement with the study. Vibrent Health provides a large-scale, cost-effective, mission-critical system to the program that needs around-the-clock support, a service they can provide that would be difficult for an academic institution to match.
The All of Us system has been designed by Vibrent to provide an overview of the study to potential participants as well as offer an interactive, informed consent process that allows for the opt-in or out of a variety of data collection processes. Importantly, the information is provided in the form of videos and text to make participant engagement and comprehension of the various data types the program seeks to collect clear. Knowledge of participants’ understanding of how their data will be collected, secured, and used is assessed via comprehension quizzes they must pass before being allowed to sign the consent forms.

Vibrent Health CEO Praduman Jain (PJ), spoke to the importance of returning value back to
All of Us participants, a value that is above and beyond their own health data. Using the company’s Research Platform, Vibrent will develop useful insights from the large and diverse sets of data provided by the All of Us participants, ultimately enabling researchers and clinicians to more precisely predict, prevent, and treat a variety of health conditions.
Picture
Picture
Picture
Picture
Integrating information on participants' environment, lifestyle, genomics, & behavior will be critical to understanding the complexities of human health.
Currently, as the research initiative gears up, Vibrent is in the data collection phase but hopes to soon amass the breadth and depth of data needed to develop meaningful insights through machine learning and other predictive analytics. The security and privacy of the participant information collected by Vibrent Health’s platform is of the utmost importance and various layers of encryption and de-identification of data are in place. In the end, Vibrent expects to develop novel and powerful predictive tools from this work that can be applied to the broader healthcare system in the U.S.

Only through the critical buy-in of participants will a program as ambitious as All of Us succeed. Now over 15 months since the launch of the program, All of Us has recruited nearly 25% of its targeted 1 million participants: 243,000+ at last count (as of August 13, 2019). And you can help them reach their goal (see link to participate)!

In the end, the All of Us program hopes to set a
precedent for how long-term, longitudinal, health and lifestyle research can take place in the 21st Century. No longer will participants in this type of research be passive subjects (often distrusting what is being done with their data) who provide (or don’t, or not truthfully) information and samples from which they never learn the insights obtained. Rather, participants will be partners in the research process, knowing their opinions and ideas matter and that their data is leading to new insights in which they are being informed.
In doing all this,
All of Us leadership expects participants will feel more engaged and empowered: willing to provide an unprecedented amount of health data with the knowledge that it will lead to discoveries that truly benefit All of Us.
Picture
UPDATES:
As of August 13, 2019: 180,000+ individuals have begun enrollment in the program with an excellent ethnic distribution: ~21% African American, ~18% Hispanic/Latino, & 47% Caucasian
80,000+ electronic health records and 188,000+ biosamples are currently in the system

The All of Us Research Hub has an online Data Browser to view publicly-available data:

https://databrowser.researchallofus.org/


For a Deeper Dive:
About the All of Use Research Program

New England Journal of Medicine special report on the project (published 8/15/19)

Want to take part?
Enroll in All of Us here:
https://www.joinallofus.org/en
Have questions about the program? See FAQs here.
Want to engage your community in the program? See resources here.

Read more about Engagement and the All of Us Program Here: 
https://catalyst.nejm.org/precision-medicine-initiative-everyone/


Vibrent Health’s Role in All of Us: 
https://www.vibrenthealth.com/knowledge-center/2018/05/vibrent-health-power-technology-history-making-us-research-program/
0 Comments

    Author

    A neuroscientist by training, I now work to improve the career readiness of graduate students and postdoctoral scholars.

      Subscribe to Reflections Newsletter

    Subscribe to Newsletter

    Archives

    December 2020
    November 2020
    October 2020
    September 2020
    August 2020
    July 2020
    June 2020
    May 2020
    March 2020
    February 2020
    January 2020
    December 2019
    November 2019
    September 2019
    August 2019
    July 2019
    May 2019
    April 2019

    Categories

    All
    Academic Job Search
    Artificial Intelligence
    Career Development
    Career Exploration
    Data Science
    Future Of Work
    International Concerns
    Life Advice
    Neuroscience
    NIH BEST Blog Rewind
    Opinion
    Personalized Medicine
    Scientific Workforce
    Welcome

    RSS Feed

Science

Career Development Research
​
Neuroscience Research


Publications

Writing

​Reflections Blog

Other Posts

Press, Resources, & Contact

Press                                                       Contact

Job Search Resources                Funding Resources

Subscribe to Reflections Newsletter 
© COPYRIGHT 2021. ALL RIGHTS RESERVED.