I recently participated in a conference on Artificial Intelligence (AI) in healthcare. It was the first onsite meeting after 900 days of the pandemic.
Here is a report from the front:
- AI has a way to go before it can substitute for physician judgment, intuition, creativity and empathy
- There seems to be an inherent conflict between using AI to standardize decisions compared to using it for mass customization. Efforts to develop customized care must be designed around a deep understanding of what happens at the ground level along the patient pathway and must incorporate patient engagement by focusing on such things as shared decision-making, definition of appointments, and self-management, all of which are elements of a “build-to-order” approach.
- When it comes to dissemination and implementation, culture eats strategy for lunch.
- The majority of the conversations had to do with the technical aspects and use cases for AI. A small amount was about how to get people in your organization to understand and use it.
- The goal is to empower clinical teams to collaborate with patient teams and that will take some work. Moving sick care to healthcare also requires changing a sprint mindset to a marathon relay race mindset with all the hazards and risks of dropped handoffs and referral and information management leaks.
- AI is a facilitating technology that cuts across many applications, use cases and intended uses in sick care. Some day we might be recruiting medical students, residents and other sick care workers using AI instead of those silly resumes.
- The value proposition of AI includes improving workflow and improving productivity
- AI requires large, clean data sets regardless of applications
- It will take a while to create trust in technology
- There needs to be transparency in data models
- There is a large repository of data from non-traditional sources that needs to be mined e.g social media sites, community based sites providing tests, like health clubs and health fairs, as well as post acute care facilities
- AI is enabling both the clinical and business models of value based care
- Cloud based AI is changing diagnostic imaging and pattern recognition which will change manpower dynamics
- There are potential opportunities in AI for quality outcome stratification, cost accounting and pricing of episodes of care, determining risk premiums and optimizing margins for a bundled priced procedure given geographic disparities in quality and cost.
- We are in the second era of AI that is based on deep learning v rules based algorithms
- Value based care requires care coordination, risk stratification, patient centricity and managing risk
- Machine learning is being used, like Moneyball, to pick startup winners and losers, with a dose of high touch.
- It is encouraging to see more and more doctors attending and speaking at these kinds of meetings and lending a much needed perspective and reality check to technologists and non-sick care entrepreneurs. There were few healthcare executives besides those who were invited to be on panels.
- Overcoming the barriers to AI in sick care have mostly to do with changing behavior and not dwelling on the technicalities, but, rather, focusing on the jobs that doctors need to get done.
- The costs of AI , particularly for small, independent practitioners, are often not affordable, particularly when bundled with crippling EMR expenses . Moore’s law has not yet impacted medicine
- The promise of using AI to get more done with less conflicts with the paradox of productivity
- Top of mind problems to be solved were how to increase revenuces, cut costs , fill the workforce pipelines and address burnout and behavioral health employee and patient problems with scarce resouces.
- Nurses, pharmacists, public health professionals and veterinarians were under represented
- Payers were scarce
- Patients were scarce
- Students, residents and clinicians were looking for ways to get side gigs, non-clinical careers and exit ramps if need be.
- 70% of AI applications are in radiology
- AI is migrating from shiny to standard, running in the background to power diverse remote care modalities
- Chronic disease management and behavioral health have replace infectious disease as the global care management challenges
- AI education and training in sickcare professional schools is still woefully absent but international sickcare professional schools are filling the gaps
- Process and workflow improvements are a necessary part of digital and AI transformation
At its core, AI is part of a sick care eco-nervous system “brain” that is designed to change how doctors and patients think, feel and act as part of continuous behavioral improvement. Outcomes are irrelevant without impact.
AI is another facilitating technology that is part and parcel of almost every aspect of sick care. Like other shiny new objects, it remains to be seen how much value it actually delivers on its promise. I look forward to future conferences where we will be discussing how, not if to use AI and comparing best practices and results, not fairy tales and comparing mine with yours.
Sign up here to get Human-Centered Change & Innovation Weekly delivered to your inbox every week.