The value-based care market is projected to grow to $174 billion by 2032, according to a MarketResearch.biz report released recently. As the march to VBC accelerates, there are operational, financial, data complexity/accessibility, and technology-related challenges that need to be overcome to implement value-based programs and to scale them for mass adoption.
Existing medical data is not fully exploited for analytics and risk score computation because of three main reasons:
- Unstructured data – this requires multi-model processing with a combination of AI/ML plus amalgamation with the structured and semi-structured data sets.
- Data gaps – many times, there are missing datasets that prevent creation of a good quantitative model.
- It sits in data silos, and privacy concerns restrict access to this data.
The No. 1 issue mentioned above can be addressed using NLP and ML algorithms that digitize, plus train and process, data in conjunction with the data in the enterprise systems for an entity. We can then share permissioned data with the granularity (full record or only sub-set attributes) between participants in a permissioned manner.
The second issue can be addressed using Generative AI by creating synthetic datasets. Synthetic data is generated by using algorithms to create data that mimics real-world data, but with variations that allow for more extensive testing and analysis.
The third issue (keeping the data privacy and security issues in mind) can be solved by replicating only the pertinent data. In addition, this issue also can benefit from a Federated Learning (FL) approach to machine learning. FL enables gaining insights in a collaborative manner using a form of a consensus model, without moving patient data beyond the firewalls of the institutions in which they reside. Instead, the ML processes occur locally at each participating institution and only model characteristics like the parameters, gradients, etc., are transferred to participating entities. Instead of gathering data on a single server in a centralized fashion, the data remains locked on their individual Enterprise infrastructures and the algorithms and only the predictive models travel between the servers of the participating entities – never the data.
When it comes to VBC, Gen AI can be utilized in a few critical areas:
- Intelligent contract builder process(es). The VBC contract process today is very time-consuming and manual to develop, review, and put into action. Gen AI processes can help streamline this approach.
Using past contracts against which we can build and run large language models (LLMs), Gen AI can generate new contract based on past patterns. Individual components of these contracts, such as different variables and their values, pricing information, attributes of different clauses, expiry dates, etc., can be extracted out of complex and lengthy contracts within seconds and presented to the user with a simple-to-use workflow in which users can finalize the contract within days.
- Improvements in care management process(es). Care management strategies for patients center around the effective use of data, processes, and systems by a team usually comprised of physicians, nurses, CBOs (community-based organizations), care managers, and social workers. The basic concept is to have timely interventions for patients to reduce health risks and decrease the total cost of care.
Personalized care plans for patients broadly fall under four steps:
- Population stratification, using risk-stratification methods
- Alignment of care management services to the needs of the patient (i.e., created while interacting with the patient in a personalized manner to ensure buy-in into the plan)
- Preparation of care plan and device monitoring for the patient for proactive care
- Association of appropriate personnel to establish care plan team for execution, follow-ups, etc.
Gen AI isn’t needed for patient risk stratification, which can be achieved using simple data analytics, post-any data digitization (if needed for unstructured datasets), using a patient Longitudinal Health Record (LHR). The challenge starts with contacting and engaging the patient. The communication protocols (emails, phone calls, SMS/MMS messages, snail mail) require persistent efforts to yield results.
Gen AI can help personalize outgoing communication (conversational AI) based on past patient interactions, including any language translation preferences and level of education of the individual to keep the communication simple to understand.
Once the patient has been engaged, a care team can prepare the care plan and put the device monitoring/data collection protocols in place. Non-clinical and administrative steps like medication reminders, scheduling appointments on time, scheduling check-ins for a telehealth conversation, creation of alerts and notifications when things do not go as planned, Rx refills, and prompting for daily exercise under the care plan – all can be personalized and automated using Gen AI.
For the Internet of Medical Things (IoMT), Gen AI could help companies create more personalized and patient-centered devices – incorporating software that allows for preventive maintenance and repairs.
The last part would be to help the care team navigate the complexity of the healthcare system – different workflows, assignment of the appropriate personnel based on their availability and expertise, and providing insights to the care team about patients who are not yet that sick but could be if meaningful interventions don’t happen on time.
Other Gen AI Successes
A good number of use cases are being worked on using Gen AI. Some are in research/concept stages, while a few are being deployed into production pilots, including automation of administrative tasks, prevention of costly medical errors, medical education, and clinical decision support.
For VBC specifically, building solid VBC contract processes and improving care management workflows are just two of the ways the technology already is impacting the acceleration of new value-based payment models.
About Rahul Sharma
Rahul Sharma is the chief executive officer of HSBlox, an Atlanta-based technology company empowering healthcare organizations with the tools and support to deliver value-based care (VBC) successfully and sustainably.