Jeffrey Eyestone is CognitiveScale’s Healthcare AI Advisor. In this role, Jeff works with Healthcare organizations (primarily providers/healthcare systems, payers and technology vendors) on their AI journey—from strategic insight into how to develop AI competencies and centers of excellence to more tactical development of AI roadmaps and delivery of AI solutions
Can you discuss why you believe AI is so important for the healthcare industry?
Massive amounts of complex, disparate and distributed data form the foundation for the underlying clinical, administrative and financial processes that drive healthcare. So, AI is now a core capability across the entire healthcare information technology value chain. Knowledge workers like clinicians and researchers are realizing significant improvements from AI — especially the “augmented intelligence” subset of AI.
AI in healthcare is a huge topic and there are many valuable use cases from sourcing data to deriving insights, from improving or automating processes to better patient engagement and the delivery of personalized care. Clinical outcomes are improving, efficiencies are driving cost savings, and there are many more use cases in the works that promise to drive value. The current global pandemic has put many more healthcare AI use cases in sharp focus, combining community and individual risk scores and insights with intelligent interventions, for example – all of which will improve healthcare systems all over the world well after we have beaten COVID-19.
How would you define augmented intelligence in a healthcare setting?
CognitiveScale focuses primarily on augmented intelligence. Some AI technology like robotic process automation (RPA) or chatbots seek to replace people with machines (much of the time, anyway). We are focused, primarily, on AI solutions that help healthcare organizations and staff work smarter and more efficiently. We are also focused on cognitive solutions— the more advanced subset of AI that has a learning or feedback loop—and often it is the “humans in the loop” that can provide the feedback for models to learn from. There are numerous examples of augmented intelligence in healthcare that are starting to deliver impressive results. For example, in radiology and pathology, clinicians are augmenting their ability to read images and make diagnoses with machine learning models, enabling earlier detection or more accurate diagnoses and lab results.
You’ve worked with both startups and large organizations that have implemented different AI strategies. What are some common mistakes that you’ve seen?
Just as cognitive AI solutions learn over time and mature, so has our understanding of the power of AI, and the pitfalls. The amount of time to get access to data—to prep the data—and then to train models on a census of data has usually taken longer than originally thought. Other mistakes relate to the operationalization and scale of AI solutions—assuming that a good model can easily be deployed and managed across a healthcare IT ecosystem, when the reality is that many AI models remain unused. But one of the most significant challenges in healthcare AI relates to trust: can models be trusted, are they biased, fair, explainable and accurate? Numerous headlines have shown that AI solutions can be biased in ways that will get the attention of regulators—or they might be black box solutions that earn skepticism from the providers whose intelligence they are supposed to be augmenting. This is the biggest challenge—and mistake—with healthcare AI that I am seeing lately.
What are your views on genomic profiling?
Genomic profiling is a subset of promising technologies designed to deliver personalized insight into a person, usually for the purpose of their healthcare (vs. genealogy, or occasionally we see stories about paternity disputes or even crime investigations leveraging this technology). Personalization is a major topic of healthcare AI use cases—how to better engage patients, or augment the intelligence of providers with more personalized and directed insights. Insomuch as genomic profiling can help deliver more personalization. And, as long as the data and use of it is trusted (unbiased, fair, explainable, accurate, etc.), then it will be an important component of personalized medicine—and a foundational element of hyper-personalized AI solutions that leverage genetic information.
Personalizing healthcare seems to be the wave of the future, in what ways do you see this having the most positive impact?
At CognitiveScale we are delivering personalized, predictive, prescriptive healthcare solutions. A couple of examples include intelligent interventions for care managers (clinical use case) and predicting service inquiries (administrative / operational use case). Intelligent intervention solutions deliver personalized inferences, predictions and risk scores (among other model outputs) that augment the work of those managing patients through a care management program. We are also leveraging these capabilities for public health authorities, provider and health plans trying to manage citizens/patients/members through the COVID-19 crisis. By predicting service inquiries, we are helping healthcare organizations know the moment a member or provider calls about claims, benefits, etc., the specific reason for the call and how to much more efficiently resolve it, thereby driving cost savings and impacting satisfaction and retention. There are many more healthcare AI use cases focused on personalized solutions. We could write a book on this topic alone.
Can you talk about the challenges of aggregating data from disparate sources such as EMR, ERPs, patient data, external data sources, etc, into one coherent data system?
Healthcare Information Technology (HCIT) is almost always an ecosystem: a distributed network of disparate systems. A common example is the personal health record (PHR)—the complete data set of a patient’s medical record. Even when a large healthcare system is on one homogenous hospital information system, their patients will likely have other caregivers, they may have insurance that is another source of data, and their lab and pharmacy data may well be spread across several clinics and companies. While there are standard transaction sets for healthcare data exchange, common data models for storing clinical data (and member, patient, customer and provider data schemas), healthcare AI solution vendors often need to be able to demonstrate how solutions can leverage multiple of these at one time—internal and external data, data connectivity, and data schemas. Obviously, the foundation of healthcare AI solutions is data. So, data aggregating capabilities must be a core competence of any healthcare AI provider.
What are some of the considerations that are needed with data traceability?
Data traceability is a component of some larger, pressing issues in healthcare AI. For one, data traceability is one of several issues related to privacy, data use, and data exchange. For instance, where is clinical data or personal health information (PHI) going and how is it being used? These issues relate to regulatory and legal aspects of healthcare data security and privacy. These issues, then, are a subset of ethical and trusted AI. Ethical AI would need to account for data use, privacy, regulations and legal aspects, etc., specifically addressing ethical use of data. Trusted AI includes aspects of explainability and data use as well.
You are an advisor with CognitiveScale, can you explain what CognitiveScale does and how you advise them?
CognitiveScale is a provider of AI software that helps organizations build, operationalize, and scale cognitive AI solutions; realize the value of AI across their organizations; and, manage trust. In Healthcare, we work for some of the largest payer and provider organizations in the country, on a wide range of AI use cases, including more recent work in areas like intelligent interventions related to the COVID-19 pandemic and how these solutions will then improve care management, service experience, and more, once we are past this crisis. As our lead healthcare subject matter expert, I help clients and partners more strategically in areas like building out robust AI roadmaps, and more tactically in areas like value realization and optimization. I am also working to help in areas such as product development (healthcare-specific features and capabilities of our platform, for example) and thought leadership with a focus in on the highest-value healthcare AI solutions (given the size of the opportunity).
Could you define for us what the biggest issues are with how AI sometimes operates as a black box, and potential solutions for the healthcare industry?
As I mentioned, trusted, ethical AI is a big challenge—and trust is largely due to the “black box” problem: a lack of explainability or visibility, and skepticism about issues like bias, fairness, accuracy and robustness. At CognitiveScale, our Certiai solution specifically addresses this challenge and helps clients with an AI Trust Index and its component parts (each with their own score and insights): bias, fairness, explainability, robustness and accuracy. Healthcare has had examples of biased models, or clinician skepticism with model output due to a lack of transparency or explainability. There are also regulatory requirements around privacy and data use, and the use of models to deliver fair or unbiased results—and these have made it into the news. We are working with a number of technology and risk management organizations to develop trusted ways to provide visibility and improve confidence in “black box” AI solutions.
What are some ways that we can reduce ER over saturation through predictive A.I?
ER avoidance is really a subset of care optimization and personalized healthcare—the right care at the right time. This may well involve emergency care, but many times it does not. The recent COVID-19 crisis highlights a useful example where care optimization. For example, the right care for a high risk patient in a high risk community might include clinician outreach, access to a testing center, or in some cases, emergency care. Patients, members, providers and payers all want the right level of care at the right time in this crisis so a combination of AI solutions are helping deliver insights such as community and patient risk scores, spread analysis, hospital utilization predictions, and personalized guidance for specific people, among other solutions. We rate the performance of our care management solutions against a number of performance metrics like improved outcomes including ER avoidance when appropriate.
Thank you for the interview, readers who wish to learn more may visit CognitiveScale.