In a 12-question, 5000-word interview, we get the views of Chat GPT-4 on how CMS may be promoting or retarding the adotion of impactful uses of artificial intelligence in healthcare.
The interview includes an AI-generated summary at top.
- I have clipped the whole interview (which would equal a 30-minute webinar) into this long blog.
- I have also clipped the whole interview in an open access Google doc, which some readers may prefer.
- For the official 22-page white paper version,
- For a two-minute video overview:
The interview is entirely unedited except for minor wordsmithing of the summary. The title and subtitle are AI-generated. The two-minute video overview is from an AI script.
Thanks to Richard Coda Design for design and graphics. Thanks to Galileo and Plato for the idea of presenting books in dialog format.
____
Summary (AI generated)
This interview between Dr Bruce Quinn and GPT-4 discusses
various aspects of AI in healthcare, including its applications, challenges,
and the roles of different stakeholders. AI has the potential to revolutionize
healthcare by improving diagnostics, treatment planning, patient monitoring,
and workflow efficiency. Radiology and pathology have been particularly
impacted by AI, with innovations that were previously impossible without AI
technology.
However, the adoption of AI in healthcare faces challenges, particularly in the Medicare
reimbursement system. The current reimbursement models, such as the Medicare
RVU payment system, may not account for the unique costs and benefits
associated with AI technologies. This can create financial barriers for
healthcare providers and organizations, limiting the integration of AI-driven
solutions.
The interview explores strategies for engaging with policymakers, focusing on
simplifying the message, quantifying the impact of AI, and connecting the issue
to broader public health goals. Collaboration with various stakeholders,
including healthcare providers, AI developers, professional organizations, and
patient advocacy groups, is crucial for driving meaningful change in reimbursement
policies and fostering a supportive environment for AI adoption in healthcare.
Also discussed: the roles of organizations like the American Medical Association, the National
Institutes of Health (NIH), and the Centers for Medicare & Medicaid Services
(CMS) in promoting AI in healthcare. Cross-agency collaborations between the
NIH and CMS, as well as efforts to address ethical considerations and integrate
AI into medical education, can contribute to the successful integration of AI
into the healthcare system.
The take-home lesson is that AI has the potential to significantly improve patient care and
outcomes, but its impact largely depends on addressing financial, regulatory,
and technical barriers. Collaborative efforts among stakeholders are essential
to promote AI adoption in healthcare and ensure its benefits are fully
realized.
Q1. What activities, programs, or policies is the Medicare
agency using to Promote or to reimburse for uses of artificial intelligence in
healthcare?
Q2. Are there any major features of Medicare payment policy
that are barriers to expanded use of AI in healthcare?
Q3. How does the cost architecture of the Medicare RVU
payment system discourage use of AI?
Q4. Is the American Medical Association doing much to
encourage use of true AI (not just telemedicine) in US healthcare?
Q5. What are the most impactful uses of AI in radiology?
Q6. What are the most impactful applications of AI in
pathology? Focus on things that require AI and we’re not possible without it.
Q7. What is the NIH doing to encourage breakthroughs in AI
that will improve healthcare in new ways?
Q8. Are there AI focused collaborations between NIH and
CMS?
Q9. Help me compare two things. (1) There is a well known
problem that biopharmas, especially new venture funded ones, have difficulty
getting good ROI for novel antibiotics and may even go bankrupt after FDA
approval. (2) Similarly, I am concerned that healthcare coding and coverage and
reimbursement is lacking for breakthrough or out of the box AI innovations, and
limiting progress in healthcare. Can you comment ?
Q10. I would like to
focus on your point which begins, “for breakthrough AI innovations in
healthcare…” How would you explain the problem to a senior CMS policymaker who
has limited knowledge about AI in healthcare? How would you help him understand
the problem, prioritize the problem, and engage in solutions?
Q11. Let’s assume you have been meeting with the senior CMS
policymaker, and your presentation has covered these five points. He seems a
little disengaged and you are concerned that he won’t do much once the meeting
is over. What would you do next? Would you focus on this person, or seek higher
level meetings, or turn to other government bodies, what is missing?
Q12. Your help is excellent. I find that higher level
policymakers should take a broader view of public health goals, yet, they are
farther from details like coding or RVU rules where the problems for
reimbursements lie. How can we overcome this dilemma?
Q13. Can
you provide a single summary (200-300 words) of our discussion.
########
Q1. What activities, programs, or
policies is the Medicare agency using to Promote or to reimburse for uses of
artificial intelligence in healthcare?
As of my knowledge cutoff date in September 2021, the Centers for
Medicare & Medicaid Services (CMS) had already started exploring ways to
incorporate artificial intelligence (AI) into healthcare programs and policies.
While there may have been developments since then, the following are some
notable examples of AI integration within the Medicare system up to 2021:
- Virtual
Care: CMS expanded telehealth services
during the COVID-19 pandemic, which included remote patient monitoring and
virtual consultations. AI plays a significant role in these services by
assisting with diagnostics, patient triage, and care management.
- AI
Health Outcomes Challenge:
CMS, in collaboration with the American Academy of Family Physicians and
the Laura and John Arnold Foundation, launched the AI Health Outcomes
Challenge. This initiative aimed to accelerate the development and
adoption of AI-driven solutions to predict patient outcomes and improve
care quality.
- Chronic
Care Management (CCM): CMS has recognized
the potential of AI-driven remote monitoring and care management tools to
improve the management of chronic conditions. They have introduced
reimbursement codes for remote patient monitoring, allowing healthcare
providers to bill Medicare for these services.
- Fraud,
Waste, and Abuse Detection:
CMS has started using AI and machine learning algorithms to detect
patterns of fraud, waste, and abuse in the Medicare system. This can help
identify and prevent inappropriate billing practices and protect the
program's integrity.
- Electronic
Health Records (EHRs): CMS has been
promoting the use of EHRs and interoperability to improve care
coordination and reduce errors. AI-powered tools can analyze large amounts
of data from EHRs to identify patterns and trends that can inform better
clinical decision-making.
- Quality
Payment Program (QPP): The QPP focuses on
improving the quality of care and encouraging the adoption of innovative
technologies, including AI. The Merit-based Incentive Payment System
(MIPS) and Advanced Alternative Payment Models (APMs) within the QPP
financially reward healthcare providers for using technology to improve
patient outcomes.
It is essential to note that the Medicare landscape is continually
evolving, and CMS may have implemented new programs or policies since September
2021. It is recommended to visit the CMS website or consult with healthcare
experts for the most up-to-date information on AI integration in the Medicare
system.
Q2. Are there any major features of
Medicare payment policy that are barriers to expanded use of AI in healthcare?
There are several aspects of Medicare payment policy that can act as barriers
to the expanded use of AI in healthcare. Some of these include:
- Fee-for-service
reimbursement model: Medicare's
traditional fee-for-service (FFS) reimbursement model might not adequately
incentivize the adoption of AI technologies, as it mainly focuses on the
quantity of services provided rather than the quality or efficiency of
care. This system may not provide appropriate incentives for healthcare
providers to invest in AI solutions that could improve patient outcomes
and reduce costs.
- Limited
coverage and reimbursement:
Medicare's coverage and reimbursement policies for AI-driven technologies
are still in the early stages of development. Many AI-based tools and
services might not yet have established billing codes or specific
reimbursement pathways, making it challenging for healthcare providers to
adopt these innovations due to financial uncertainty.
- Regulatory
and approval processes: The development and
adoption of AI technologies in healthcare can be slowed down by lengthy
regulatory and approval processes. In the United States, AI-driven medical
devices and software must be approved by the Food and Drug Administration
(FDA) before they can be reimbursed by Medicare. This can result in delays
and added costs for innovators and healthcare providers.
- Data
privacy and security concerns:
Medicare payment policies need to address data privacy and security
concerns related to AI technologies. As AI systems often rely on large
datasets, including sensitive patient information, there is an increased
risk of data breaches and misuse of information. These concerns can slow
down the adoption of AI in healthcare.
- Fragmentation
of care: The Medicare system is
fragmented, with various parts (Part A, Part B, Part C, and Part D)
catering to different healthcare needs. This fragmentation can make it
challenging to coordinate and integrate AI-driven solutions across
different parts of the system.
- Lack
of standardized data and interoperability: AI systems require standardized, high-quality, and
interoperable data to function effectively. However, the lack of
standardized data formats and interoperability between electronic health
record (EHR) systems can hinder the adoption of AI in healthcare.
To overcome these barriers and encourage the adoption of AI in healthcare,
Medicare payment policies should focus on creating incentives for providers to
invest in innovative technologies, streamlining regulatory and approval
processes, and addressing data privacy and security concerns. Additionally,
fostering collaboration between various stakeholders, including healthcare
providers, payers, technology developers, and regulatory agencies, can further
help accelerate AI's integration into the healthcare system.
Q3. How does the cost architecture of
the Medicare RVU payment system discourage use of AI?
The Medicare Relative Value Unit (RVU) payment system is based on the
Resource-Based Relative Value Scale (RBRVS), which assigns a relative value to
each medical service or procedure. This value is determined based on three
components: Physician Work RVUs, Practice Expense RVUs, and Malpractice RVUs.
The total RVUs are then multiplied by a monetary conversion factor to determine
the payment amount for a specific service or procedure.
The RVU payment system can discourage the use of AI in healthcare in the
following ways:
- Limited
incentives for innovation:
The RVU payment system mainly focuses on compensating healthcare providers
for their time and expertise, practice expenses, and malpractice costs. It
may not account for the potential benefits of adopting AI technologies,
such as improved patient outcomes, reduced costs, or increased efficiency.
This lack of incentives for innovation can discourage healthcare providers
from investing in AI solutions.
- Inadequate
reimbursement for AI-driven services:
The current RVU payment system may not adequately reimburse AI-driven
services, as it is not explicitly designed to account for the unique costs
and benefits associated with AI technologies. This can result in
healthcare providers being hesitant to adopt AI solutions due to financial
concerns.
- Fee-for-service
model: The RVU payment system is a
fee-for-service model, which rewards providers based on the volume of
services rendered rather than the quality or effectiveness of care. This
model may not create incentives for healthcare providers to adopt
AI-driven solutions that could improve care quality, as they may not be
directly rewarded for the improved outcomes resulting from the use of AI.
- Slow
to adapt: The RVU payment system may be
slow to adapt to new technologies, such as AI, as it requires updates to
incorporate new billing codes and reimbursement pathways for AI-driven
services. This slow adaptation process can hinder the integration of AI
into the healthcare system.
- Lack
of specific billing codes:
AI-driven services may not have specific billing codes within the RVU
payment system. Without well-defined billing codes, healthcare providers
may face difficulties in receiving reimbursement for these services,
discouraging their adoption.
To encourage the use of AI in healthcare, the Medicare RVU payment system
needs to evolve and adapt to the unique costs and benefits associated with AI
technologies. This could involve developing new billing codes and reimbursement
pathways, as well as creating incentives for healthcare providers to invest in
AI-driven solutions that can improve patient outcomes and reduce healthcare
costs.
Very good.
Thank you! I'm glad you found the information helpful. If you have any
more questions or need further assistance, please don't hesitate to ask.
Q4. Is the American Medical
Association doing much to encourage use of true AI (not just telemedicine) in
US healthcare?
The American Medical Association (AMA) has shown interest in promoting
the responsible adoption of AI in healthcare to improve patient care and
outcomes. Although the AMA's efforts are not limited to true AI, they have
taken several initiatives to encourage the use of AI and related technologies
in the US healthcare system:
- AI
policy development: The AMA has been
working on developing policy recommendations related to AI in healthcare.
In 2018, the AMA adopted a new policy that provided a broad framework for
AI's role in healthcare, focusing on ensuring that AI-driven tools are
safe, effective, and evidence-based, while prioritizing patient interests
and addressing liability concerns.
- Ethical
guidelines: The AMA has emphasized the
importance of developing and implementing ethical guidelines for AI in
healthcare. They encourage AI developers, healthcare providers, and other
stakeholders to follow ethical principles, such as transparency,
accountability, privacy, and fairness, when designing and using AI
systems.
- Education
and training: The AMA recognizes the need for
medical professionals to be well-equipped to integrate AI into their
practice. They support education and training efforts that can help
physicians and other healthcare providers understand AI's potential
benefits, limitations, and ethical considerations.
- Collaboration
with other organizations:
The AMA has been involved in collaborative efforts with other
organizations to promote the responsible use of AI in healthcare. For
example, they have partnered with organizations like the American Heart
Association (AHA) to develop certification programs for AI-driven digital
health tools, aiming to establish standardized criteria for evaluating
these technologies.
- Advocacy
for research and development:
The AMA has been advocating for increased research and development in AI
for healthcare applications. They support federal efforts to fund AI
research and encourage collaboration between the public and private
sectors to drive innovation in this field.
- Participation
in AI-focused events: AMA representatives
have participated in various AI-focused conferences, workshops, and panel
discussions, contributing their insights and promoting discussions around
AI's role in healthcare.
While the AMA's efforts may not be exclusively focused on true AI, they
play an essential role in shaping the landscape for AI adoption in healthcare.
By developing policies, ethical guidelines, and educational resources, the AMA
is working to ensure that AI-driven technologies are responsibly integrated
into the US healthcare system to improve patient care and outcomes.
What are the most impactful uses of AI
in radiology?
AI has made significant strides in radiology, leading to various
impactful applications that can improve diagnostic accuracy, efficiency, and
patient outcomes. Some of the most notable uses of AI in radiology include:
- Image
analysis and interpretation:
AI algorithms, particularly deep learning techniques like convolutional
neural networks (CNNs), can automatically analyze medical images (e.g.,
X-rays, MRIs, CT scans) to detect and classify abnormalities, such as
tumors, fractures, or lung nodules. These algorithms can achieve high
accuracy and sometimes even surpass human radiologists in certain tasks,
resulting in faster and more reliable diagnoses.
- Computer-aided
detection and diagnosis (CAD):
AI-powered CAD systems can assist radiologists by flagging potential
abnormalities and providing diagnostic suggestions. By serving as a
"second opinion," these systems can help reduce diagnostic
errors, improve the consistency of interpretations, and alleviate the
workload for radiologists.
- Automated
measurements and quantification:
AI algorithms can automatically measure and quantify various imaging
features, such as the size, shape, and volume of tumors or other
structures. This can help radiologists monitor disease progression, assess
treatment response, and provide more accurate prognoses for patients.
- Radiation
dose optimization: AI can help optimize
radiation doses in imaging procedures, ensuring that patients receive the
minimum necessary dose while maintaining image quality. This can reduce
patients' exposure to ionizing radiation and minimize potential risks
associated with radiation exposure.
- Image
reconstruction and enhancement:
AI techniques can help improve the quality of medical images by reducing
noise, correcting artifacts, and enhancing image resolution. This can lead
to better visualization of anatomical structures and pathological
findings, enabling more accurate diagnoses.
- Workflow
optimization: AI can streamline radiology
workflows by automating tasks like image sorting, prioritization, and
report generation. By identifying urgent or critical cases and
prioritizing them for review, AI can help radiologists focus on the most
important cases, thereby reducing turnaround times and improving patient outcomes.
- Predictive
analytics: AI can analyze large datasets of
radiological images and associated clinical data to identify patterns and
correlations that can inform clinical decision-making. These insights can
help radiologists predict disease progression, treatment response, and
patient outcomes more accurately.
These impactful AI applications in radiology have the potential to
revolutionize the field by improving diagnostic accuracy, reducing human
errors, enhancing efficiency, and ultimately leading to better patient care and
outcomes.
Q6. What are the most impactful
applications of AI in pathology? Focus on things that require AI and we’re not
possible without it.
AI, particularly deep learning techniques, has shown great potential in
the field of pathology, enabling the development of various impactful
applications that were not previously possible without it. Some of the most
significant AI applications in pathology include:
- Digital
pathology and whole-slide image analysis: AI-powered algorithms can analyze digitized
whole-slide histopathology images at high resolution to detect and
classify various features, such as cancerous cells, tissue architecture,
and biomarkers. The ability to efficiently and accurately analyze
large-scale, high-resolution images is a task that was not feasible
without AI, given the substantial amount of data involved and the level of
detail required.
- Computer-aided
diagnosis and prognosis:
AI algorithms can assist pathologists in making more accurate and
consistent diagnoses by identifying and quantifying specific features in
histopathological samples. These algorithms can also predict patient
outcomes, such as the likelihood of cancer recurrence or metastasis, based
on the analysis of complex patterns within the tissue samples that may be
challenging for human pathologists to discern.
- Personalized
medicine and treatment planning:
AI can analyze large amounts of data from pathological samples, including genetic,
molecular, and imaging data, to identify patterns and correlations that
can inform personalized treatment plans. By considering the unique
characteristics of a patient's tumor or disease, AI can help pathologists
and oncologists recommend the most effective therapies tailored to
individual patients.
- Biomarker
discovery and validation:
AI can efficiently analyze large datasets to identify potential biomarkers
associated with specific diseases or treatment responses. This process can
help researchers discover new diagnostic, prognostic, or predictive
biomarkers that were previously hidden in the vast amount of data, leading
to new insights and breakthroughs in disease understanding and treatment.
- Computational
pathology and multi-modal data integration: AI can integrate and analyze multi-modal data, such
as histopathology images, radiology images, genomic data, and clinical
information, to provide a more comprehensive understanding of diseases.
This integrative approach was not possible without AI, as it requires the
efficient processing and analysis of vast and heterogeneous datasets to
generate meaningful insights.
These AI applications in pathology have the potential to revolutionize
the field by enhancing diagnostic accuracy, enabling personalized medicine, and
uncovering new biomarkers, ultimately leading to better patient care and
outcomes. The ability of AI to process and analyze large-scale, complex data
has opened up new possibilities in pathology that were not feasible without its
advanced capabilities.
Q7. What is the NIH doing to encourage
breakthroughs in AI that will improve healthcare in new ways?
The National Institutes of Health (NIH) has been actively involved in
fostering research and innovation in AI to improve healthcare. The agency has
undertaken several initiatives to promote breakthroughs in AI that can lead to
better healthcare outcomes, such as:
- Funding
AI research: The NIH provides funding
opportunities for researchers focused on AI and its applications in
healthcare through various grants and programs. These funding
opportunities support AI-related projects across a wide range of areas,
including diagnostics, therapeutics, medical imaging, and genomics.
- Collaborations
and partnerships: The NIH collaborates
with other government agencies, academic institutions, and private
organizations to promote AI research in healthcare. These collaborations
help to facilitate knowledge exchange, share resources, and accelerate the
development of AI-driven solutions for healthcare.
- Initiatives
for data sharing and accessibility:
The NIH supports initiatives that promote data sharing and accessibility
for AI research, such as the National Library of Medicine's National Center
for Biotechnology Information (NCBI) and the National Cancer Institute's
Cancer Imaging Archive (TCIA). These resources provide researchers with
access to large-scale datasets that are critical for developing and
validating AI algorithms.
- AI-focused
workshops and conferences:
The NIH organizes and participates in AI-focused workshops, conferences,
and panel discussions to share insights, promote discussions, and identify
new research directions in AI for healthcare.
- Training
and educational programs:
The NIH supports training and educational programs aimed at developing the
next generation of AI researchers and healthcare professionals. These
programs help to build a skilled workforce capable of harnessing AI's
potential to improve healthcare.
- Strategic
Roadmap for AI in Biomedical Research:
In 2021, the NIH released a strategic roadmap that outlines the agency's
vision for AI in biomedical research. The roadmap identifies key
priorities and strategies for promoting AI research and applications in
healthcare, such as fostering interdisciplinary collaboration, addressing
data challenges, and ensuring the ethical development and use of AI.
These initiatives by the NIH demonstrate a commitment to advancing AI
research and innovation in healthcare. By providing funding, promoting
collaborations, and supporting data sharing and training initiatives, the NIH
is actively working to encourage breakthroughs in AI that can lead to improved
healthcare outcomes.
Q8. Are there AI focused
collaborations between NIH and CMS?
While there might not be any direct AI-focused collaborations between the
National Institutes of Health (NIH) and the Centers for Medicare & Medicaid
Services (CMS), these agencies work together in certain areas where AI plays a
crucial role. The primary goal of these collaborations is to improve healthcare
outcomes, reduce costs, and promote the adoption of innovative technologies,
including AI. Some indirect collaborations include:
- Data
sharing initiatives: Both the NIH and CMS
have taken steps to make healthcare data more accessible to researchers
and developers. By promoting data sharing and the use of standardized data
formats, these agencies can help AI researchers access the datasets they
need to develop and validate AI-driven solutions for healthcare.
- Quality
improvement programs: CMS runs various
quality improvement programs aimed at enhancing patient care and reducing
costs in the Medicare and Medicaid systems. Some of these programs, such
as the Quality Payment Program (QPP), encourage healthcare providers to
adopt innovative technologies, including AI, to improve patient care. The
NIH, through its research and support for AI in healthcare, can indirectly
contribute to these quality improvement efforts.
- Interagency
collaborations: Both the NIH and CMS participate
in interagency collaborations that involve AI in healthcare. For example,
they may work together in initiatives led by the Office of the National
Coordinator for Health Information Technology (ONC), which focuses on
promoting the adoption of health IT and fostering innovation in
healthcare. In this context, both agencies may contribute to AI-related
discussions, policy development, and research directions.
- Support
for AI research and development:
While the NIH primarily funds and promotes AI research in healthcare, CMS
can play a role in adopting AI-driven solutions through reimbursement
policies and coverage decisions. By working together, both agencies can
create an environment that encourages the development, validation, and
integration of AI in healthcare systems.
Although there might not be direct AI-focused collaborations between the
NIH and CMS, these agencies play complementary roles in promoting AI research
and adoption in healthcare. Their joint efforts can help foster a supportive
environment for AI-driven innovations, ultimately improving patient care and
outcomes.
Q9. Help me compare two things. (1)
There is a well known problem that biopharmas, especially new venture funded
ones, have difficulty getting good ROI for novel antibiotics and may even go
bankrupt after FDA approval. (2) Similarly, I am concerned that healthcare
coding and coverage and reimbursement is lacking for breakthrough or out of the
box AI innovations, and limiting progress in healthcare. Can you comment ?
Certainly, both situations involve challenges related to market dynamics
and financial incentives, which can hinder the development and adoption of
novel solutions in their respective fields. Let's compare the two scenarios:
- Difficulty
in achieving ROI for novel antibiotics:
- The
development of new antibiotics is costly and time-consuming. However, the
return on investment (ROI) for these drugs tends to be lower compared to
other therapeutic areas, such as oncology or rare diseases. This is
because antibiotics are typically prescribed for short durations and are
often saved as a last resort to avoid the development of antibiotic
resistance.
- Moreover,
generic antibiotics are widely available at low prices, making it
difficult for novel antibiotics to compete in the market.
- This
financial disincentive has led to a decline in antibiotic research and
development, as biopharmaceutical companies, particularly new
venture-funded ones, may struggle to recoup their investments or even go
bankrupt after FDA approval.
- Limited
coding, coverage, and reimbursement for breakthrough AI innovations in
healthcare:
- Healthcare
coding, coverage, and reimbursement systems, such as the Medicare RVU
payment system, can be slow to adapt to new technologies like AI, leading
to inadequate reimbursement for AI-driven services.
- The
current reimbursement models may not account for the unique costs and
benefits associated with AI technologies, and there may be a lack of
specific billing codes for AI-driven services.
- This
situation can create financial barriers for healthcare providers and
organizations to adopt breakthrough AI innovations, as they may not
receive sufficient reimbursement to cover the costs and justify their
investments.
In both scenarios, the lack of appropriate financial incentives and
market dynamics can limit the development and adoption of novel solutions. To
address these challenges, it is essential to create a supportive environment
that fosters innovation and provides appropriate financial incentives:
- For
novel antibiotics, this could involve
implementing new reimbursement models, such as subscription-based or
value-based pricing, offering incentives for antibiotic R&D, and
providing regulatory support to expedite the development and approval
process.
- For
breakthrough AI innovations in healthcare, this could involve updating reimbursement systems to
account for the unique costs and benefits of AI technologies, creating new
billing codes for AI-driven services, and incentivizing healthcare
providers to invest in AI-driven solutions that can improve patient care
and outcomes.
By addressing these financial barriers and aligning incentives, it is
possible to encourage the development and adoption of novel antibiotics and
breakthrough AI innovations in healthcare, ultimately leading to better patient
care and outcomes.
Q10.
I would like to focus on your point which begins, “for breakthrough AI
innovations in healthcare…” How would you explain the problem to a senior CMS
policymaker who has limited knowledge about AI in healthcare? How would you
help him understand the problem, prioritize the problem, and engage in
solutions?
When explaining the problem of limited coding, coverage, and
reimbursement for breakthrough AI innovations in healthcare to a senior CMS
policymaker with limited knowledge about AI in healthcare, it's essential to
convey the information in a clear and concise manner. Here's a suggested
approach:
- Introduce
AI in healthcare: Begin by briefly
explaining what AI is and how it has the potential to revolutionize
healthcare by enhancing diagnostics, treatment planning, patient
monitoring, and workflow efficiency. Highlight a few key examples of AI
applications that have demonstrated success in improving patient outcomes
and reducing costs.
- Explain
the problem: Describe how the current coding,
coverage, and reimbursement systems may not account for the unique costs
and benefits associated with AI technologies. Explain that healthcare
providers and organizations may be hesitant to adopt AI-driven solutions
if they cannot receive sufficient reimbursement to cover the costs and
justify their investments. Emphasize that this situation can limit the
adoption of AI innovations in healthcare, which in turn may hinder
improvements in patient care and outcomes.
- Discuss
the importance of prioritizing the problem: Help the policymaker understand that addressing this
issue is essential for promoting AI-driven healthcare innovations, which
have the potential to significantly improve patient care, reduce
healthcare costs, and increase efficiency. Emphasize that, as AI
technology continues to advance, it is critical to create a supportive
environment that fosters its adoption in healthcare systems.
- Engage
in solutions: Suggest potential solutions to
the problem, such as: a. Updating reimbursement systems to account for the
unique costs and benefits of AI technologies, which could involve
exploring alternative payment models, like value-based or bundled
payments. b. Developing new billing codes specifically for AI-driven
services, ensuring that providers can receive appropriate reimbursement
for AI-enabled care. c. Collaborating with stakeholders, including AI
developers, healthcare providers, and professional organizations, to
develop guidelines and standards for the integration of AI in healthcare.
d. Encouraging pilot programs and studies to evaluate the real-world
impact of AI innovations on patient outcomes and healthcare costs,
providing evidence to support future reimbursement decisions.
- Offer
support and collaboration: Offer
your expertise and knowledge in AI in healthcare to help the policymaker
navigate this complex issue. Suggest working together to explore
solutions, gather input from stakeholders, and develop policy
recommendations that can help create a supportive environment for AI
adoption in healthcare systems.
By explaining the problem clearly and emphasizing the potential benefits
of addressing it, you can help the senior CMS policymaker understand the
importance of tackling this issue and engaging in solutions that promote the
adoption of AI innovations in healthcare.
Q11. Let’s assume you have been
meeting with the senior CMS policymaker, and your presentation has covered
these five points. He seems a little disengaged and you are concerned that he
won’t do much once the meeting is over. What would you do next? Would you focus
on this person, or seek higher level meetings, or turn to other government
bodies, what is missing?
If the senior CMS policymaker seems disengaged and you are concerned
about the potential lack of follow-up, you can take several additional steps to
ensure the issue remains on the agenda and gains momentum. Here are some
suggestions:
- Recap
and address concerns: Before ending the
meeting, briefly recap the main points discussed and emphasize the urgency
of addressing the issue. Ask the policymaker if they have any concerns or
questions that you could address, and make sure to clarify any
misunderstandings or provide additional information as needed.
- Offer
follow-up materials: Provide the
policymaker with follow-up materials, such as a one-page summary of the
key points, relevant research articles, or case studies that demonstrate
the impact of AI in healthcare. This information can help reinforce the
importance of the issue and serve as a reference for future discussions.
- Establish
a follow-up plan: Suggest scheduling a
follow-up meeting or call to discuss progress and any updates on the
issue. This can help keep the momentum going and demonstrate your
commitment to addressing the problem.
- Engage
other stakeholders: Consider reaching
out to other stakeholders within CMS, such as other policymakers, program
managers, or department heads who might have a vested interest in AI
adoption in healthcare. Share your concerns and insights with them and
explore potential collaboration opportunities.
- Seek
higher-level meetings: If you believe that
your message is not being effectively communicated or prioritized,
consider requesting a meeting with higher-level officials within CMS or
the Department of Health and Human Services (HHS). Present your case to
them and emphasize the importance of addressing the issue for the future
of healthcare.
- Collaborate
with external organizations:
Partner with professional organizations, AI developers, healthcare
providers, and patient advocacy groups to build a coalition that can raise
awareness of the issue and advocate for policy changes. By working
together, you can create a stronger and more unified voice in support of
AI adoption in healthcare.
- Engage
with other government bodies:
Explore opportunities to collaborate with other government agencies that
have an interest in AI and healthcare, such as the NIH, the FDA, or the
ONC. By working together, you can leverage their expertise and resources
to address the issue and promote the development and adoption of AI
innovations in healthcare.
By taking these additional steps, you can increase the likelihood that
the issue of limited coding, coverage, and reimbursement for breakthrough AI
innovations in healthcare remains on the agenda and gains the attention it
deserves. Building support from various stakeholders and keeping the
conversation going are crucial to driving meaningful change in policy and
practice.
Q12. Your help is excellent. I find
that higher level policymakers should take a broader view of public health
goals, yet, they are farther from details like coding or RVU rules where the
problems for reimbursements lie. How can we overcome this dilemma?
To overcome the dilemma of higher-level policymakers having a broader
view of public health goals while being farther from the details like coding or
RVU rules, you can take the following steps to bridge the gap and effectively
communicate the importance of addressing reimbursement challenges for AI-driven
healthcare solutions:
- Simplify
the message: Translate complex issues related
to coding and RVU rules into simpler, more relatable messages that
emphasize the impact on patient care, healthcare costs, and overall public
health goals. Use clear language and focus on the broader implications of
addressing reimbursement challenges for AI adoption in healthcare.
- Quantify
the impact: Present data and real-world
examples that quantify the potential impact of AI innovations on patient
outcomes, cost savings, and healthcare efficiency. Use compelling
statistics and case studies to demonstrate the value of investing in
AI-driven solutions and the risks of not addressing reimbursement
challenges.
- Connect
to broader policy goals:
Link the issue of AI reimbursement to broader public health goals, such as
improving patient outcomes, reducing healthcare disparities, and promoting
the adoption of innovative technologies. Explain how addressing
reimbursement challenges for AI can contribute to these larger objectives
and align with the policymakers' priorities.
- Develop
targeted policy recommendations:
Develop specific, actionable policy recommendations that can address the
reimbursement challenges for AI-driven healthcare solutions. By presenting
clear and feasible solutions, you can help policymakers understand how
changes in coding and RVU rules can lead to better healthcare outcomes
without getting lost in the technical details.
- Build
a coalition of support:
Engage with various stakeholders, including AI developers, healthcare
providers, professional organizations, and patient advocacy groups, to
create a unified voice advocating for policy changes. A strong coalition
can help communicate the importance of the issue to policymakers at
various levels and increase the likelihood of driving meaningful change.
- Encourage
cross-functional collaboration:
Facilitate collaboration between policymakers who focus on broader public
health goals and those who are more involved in the technical aspects of
healthcare reimbursement. Encourage cross-functional discussions and
working groups that can bridge the gap between the high-level goals and
the specific coding or RVU rules.
- Ongoing
communication and education:
Maintain an ongoing dialogue with policymakers to keep them informed about
advancements in AI, the impact of AI-driven healthcare solutions, and the
evolving challenges related to reimbursement. Provide educational
resources, host workshops, or organize briefings to ensure they stay
informed and engaged in the issue.
By simplifying the message, connecting the issue to broader policy goals,
and facilitating collaboration and communication, you can help higher-level
policymakers understand the importance of addressing reimbursement challenges
for AI-driven healthcare solutions and encourage them to take action to support
innovation in the field.
Q13.
Thank you. Considering the whole range of 12 questions we have discussed
above, do you have any concluding comments for me? Is there anything I should
have asked you, but didn't?
Over
the course of our discussion, we have covered various aspects of AI in
healthcare, including its applications in radiology and pathology, the role of
the American Medical Association, NIH and CMS collaborations, and the
challenges related to Medicare reimbursement for AI-driven services. We have
also explored strategies for engaging policymakers and driving meaningful
change in this area.
As a
concluding comment, I would like to emphasize that AI has the potential to
revolutionize healthcare, but its adoption and impact largely depend on
creating a supportive environment that addresses the financial, regulatory, and
technical barriers to its integration. In this context, it is crucial to
work collaboratively with various stakeholders, including policymakers,
healthcare providers, AI developers, and professional organizations, to ensure
that AI-driven innovations can effectively contribute to improving patient care
and outcomes.
As for
any questions that were not asked, you might consider exploring the
following topics in future discussions:
- Ethical
considerations related to AI in healthcare,
such as privacy, data security, and algorithmic bias.
- The
role of AI in addressing healthcare disparities and promoting
equitable access to care.
- How
AI can be integrated into medical education and training to prepare
healthcare professionals for the future.
These
additional areas of inquiry can provide further insights into the broader
implications of AI adoption in healthcare and help guide your efforts to
address the challenges and opportunities associated with this rapidly evolving
technology.
##
Bonus link. GPT4 also provided a 90 second script for a teaser video promoting this white paper interview. Here.
Bonus link. You may have heard GPT can help you with Excel functions or other computer tasks . I posted some of my own Q&A in this area in a Google Doc.
