We so often speak of healthcare as an industry that we forget to think of healthcare as a purpose.
Globally and annually, trillions of dollars and data are wasted in the healthcare industry.
The total time we spend in a traditional medical setting getting checked for a potential disease accounts for only a tiny fraction of the total time we spend living our lives. Confining most of our healthcare needs to a traditional medical setting will always be fundamentally limiting. The vast majority of the time we spend living our lives is outside the traditional medical setting — a place that provides access to a significantly larger window to observe the signs of disease. However, thus far, we lack solutions to measure these signs.
Moreover, the traditional medical setting continues to rely on costly and invasive approaches that are also inaccessible to everyday consumers without a physician’s involvement. This often creates a barrier to accessibility, affordability and convenience, by requiring a physical intermediary (such as blood or tissue) to be measured in order to “mark” to a disease (known as biomarkers).
For example, Alzheimer’s disease biomarkers, which Bill Gates writes about in his Gates Notes blog, are expensive, invasive and under-accessible. They often require a spinal tap, where a thin needle is inserted into the lower back to collect cerebrospinal fluid to measure the fluid’s levels of tau and amyloid proteins as biomarkers.
Traditional healthcare has always done it this way, but can it be done better, faster, cheaper?
Diseases “express” themselves in non-molecular or digital ways, as well. Today, smartphones, smartwatches and other smart devices are acceleratingly entering our life settings and are embedded with multimodal sensors that can measure trillions of data points. These sensors actually have the ability to digitally measure certain signs of diseases in a far more scalable and accurate fashion.
At my company, we refer to these measurements as LIFEdata: learnable insights from expressions (and environment) data.
Advancements in the field of artificial intelligence (AI), which include machine learning and deep learning, provide us with the ability to analyze and process a massive number of variables, as well as explore their correlations with each other and with diseases. For applications in healthcare, this means understanding how expressions of a disease and environmental factors around life can be biomarked back to detecting or predicting a disease. In other words, LIFEdata can be processed using AI to statistically analyze how strongly it correlates with a disease and then converted into radically novel types of biomarkers: digital biomarkers.
What’s an example of LIFEdata or a digital biomarker?
Take a smartwatch that can now continuously measure heart rate — a type of LIFEdata. AI can process and analyze millions of retrospectively measured heart rate data points across a large population to determine specific changes in heart rate patterns that mark most accurately to a cardiovascular abnormality — making it a digital biomarker.
Users of heart rate measuring smartwatches (programmed with this digital biomarker algorithm) can then be notified in real time if they are developing a heart condition such as arrhythmia, and seek clinical intervention in a medical setting much earlier than they may have done otherwise.
The discovery of new digital biomarkers
Large companies in the tech industry are beginning to rapidly innovate in this space, especially given their expertise in AI. For instance, Apple partnered with Stanford Medicine to develop the Apple Heart Study, which uses the Apple Watch to study irregular heart rhythms of participants who can easily contribute to the research by simply downloading an app.
Verily, a subsidiary of Google, created the Study Watch to be used as part of a program that uses a proprietary smartwatch to “measure various physiological and contextual data through sensors.” Furthermore, it’s “intended to bring us one step closer to understanding health and diseases, and a future of proactive healthcare.”
And at my company, we are developing a mobile digital biomarker technology platform to digitally detect diseases in key areas, starting with neurology.
The types of digital biomarkers are abundant in variety and hold the promise of being digitally biomarkable to an array of diseases. Only once the right combination of LIFEdata is analyzed will we realize their tremendous value in healthcare — and the world has only just begun to scratch the surface.
Necessity is the mother of all invention
Advancements in technologies have been innovatively applied to many sectors, yielding radically new solutions to disrupt old problems, and healthcare should be no exception. Within healthcare, we are currently at a critical juncture wherein costs are rising (unsustainably) with little improvements in outcomes, necessitating technologically-driven innovations. The future of healthcare will need to produce solutions that measure signs of disease much more frequently, objectively and quantitatively (by computers) and much more accessibly, affordably and conveniently (for consumers).
Future innovations in this area will make us realize that we had been living in the dark about our own health for far too long.