- Health is a very complex sector that has been difficult to change.
- Transformation must address the need for more treatments, scalability, healthcare equity, cost, data privacy and AI in healthcare.
- For transformation to address these issues and be sustainable, healthcare must move from a pipeline business model to a platform-based model.
Health care around the world has struggled with unequal access and quality for decades. Although patients, providers and payers are all calling for change, the healthcare sector has largely resisted external disruptions.
Therefore, to drive transformation, we must first change our way of thinking. We need to move from the traditional, linear thinking of the pipeline service model to a platform approach, which brings together longitudinal medical, producer and consumer data to co-create a new healthcare paradigm that fundamentally changes the how we deliver health care and advance treatment.
To do this, I firmly believe it is the responsibility of health care providers like the Mayo Clinic and others – who every day balance the complex emotional and data-driven components of health care decision-making. healthcare with our patients – to work with complementary partners to lead patients – a transformation centered on access, cost and quality, but also scalability, equity, data privacy and the emerging role artificial intelligence (AI) in medicine. At Mayo Clinic, our new vehicle for healthcare transformation is the Mayo Clinic Platform, which can serve as a model for global healthcare transformation.
The unique architecture of a health platform
A health platform cannot be copied from other sectors. We must build the healthcare platform from the bottom up, and its architecture must reconcile seemingly contradictory terms – fully protecting patient data while enabling innovation through broad access to data.
The Mayo Clinic platform begins with a new digital foundation that is both flexible and highly secure. Our cloud-hosted platform – which hosts one of the largest sets of longitudinal clinical data in the world – uses certified and anonymized data in a federated learning model where, instead of sending data to tools , we reversed the process to bring the tools algorithm to the anonymized data (see Figure 1 below). This architecture creates a “glass wall” that allows external collaborators to access data to advance healthcare without the data ever leaving the platform, and therefore places patients and their privacy rights data first – a critical requirement for maintaining patient trust in a platform-enabled healthcare system.
Use platforms to innovate, increase access and advance knowledge
A healthcare platform supports the aggregation and harmonization of disparate clinical and non-clinical data, enabling us to care for more people, connect people and data to create new insights and transform healthcare by developing new, proven end-to-end algorithms and other innovative solutions to improve care.
In our own practice, physicians and researchers, in collaboration with external partners such as Google, nference, and others, have used vast data resources to develop algorithms that help predict and identify early cardiovascular disease, breast cancer, pancreatic cancer, neuromuscular diseases and anxiety/depression. with the aim of changing the course of the disease for individual patients. We also create other AI applications that reduce the burden of repetitive clinical and administrative tasks.
Looking ahead, we believe that the application of data, analytics and technology will improve, democratize and make healthcare more accessible and affordable for everyone. An example of this is our work with EKG AI algorithms. We believe that in the not too distant future and at very low cost, a smartwatch or other low cost single track device will run a number of AI algorithms and monitor people for 15-20 asymptomatic disorders . This will allow us to screen people on a large scale and identify the disease very early, so that we can intervene. Another example that can be scaled is an algorithm that reduces the time clinicians spend designing complex head and neck radiation therapy plans from 17 hours to one hour. Over the next few years, we anticipate that many more hospitals around the world will be able to diagnose, manage and prevent complex diseases through the flow of clinical knowledge from our platform.
Bringing the hospital to the patient
The shift from thinking about pipelines to thinking about platforms is also enabling the evolution of remote care – including home-to-hospital models – that we have relied on during the pandemic. It is estimated that 40% of providers will move 20% of hospital beds home for the next three years.
At the start of the COVID-19 pandemic, we launched Advanced Care at Home (ACH), which provides comprehensive hospital-level patient care at home with 24-hour availability from a Mayo Clinic provider and periodic information. home visits from a network of local health partners. Together with our partner, Medically Home, this initiative orchestrates all the elements necessary to support hospital care at home, combining technology, provider network and clinical expertise to meet the needs of each patient. With ACH, we have been able to cut readmissions in half, which means patients spend less time in our facilities and more time with their families and enjoying their lives. We are working with Kaiser Permanente and Medically Home to evolve this model of care and have established a broader Advanced Home Care Coalition to evolve it in a sustainable way. ACH will be just one part of the future healthcare experience that uses multiple data inputs to create seamless care transitions between digital and traditional in-person care.
Using Platforms to Improve Equity
There are legitimate concerns that using AI on datasets in a healthcare platform could exacerbate disparities. Conversely, the ethical and validated use of AI combined with platform thinking opens up equitable access to healthcare for many underserved populations around the world.
As part of the Mayo Clinic platform, we have established a process that validates every algorithm we develop and implement, ensuring it is fit for purpose. Together with US healthcare providers and cross-industry partners, we formed the Coalition of Health Care AI to develop guidelines that promote high-quality healthcare for all, through healthcare AI systems credible and transparent. One of the coalition’s deliverables is an algorithm labeling model that will describe the data used to develop each algorithm, its usefulness and its limitations for a given population – for example, an algorithm trained on data from only women may not be useful on men. The Data Labeling Project is designed to increase credibility, fairness and inclusivity by creating greater trust and transparency in AI algorithms and ensuring the end user knows they are suitable for the intended use (see Figure 2 below).
Moving from a pipeline to a platform holds great promise for transforming healthcare and providing the flexibilities needed to help us better manage the next inevitable health crisis. Over the past two years, we have demonstrated the potential, applicability, and scalability of platform thinking in healthcare. Now we need wide-scale adoption by governments, biotech, pharma, NGOs, and healthcare providers – with hurdles to prevent regression to pipeline thinking. Platform thinking will help us predict and prevent disease, facilitate hospital care for patients at home, and scale clinical knowledge to reach diverse people around the world. This is the future we are creating together now, as the platform revolution finally comes to healthcare.