We believe you look at the solution every day in your smart devices, starting with the multimodal sensors your smartphone. We spend less than 1% of our time in a traditional “medical setting” and expect the medical data generated there to lead to enhanced outcomes. Meanwhile, the “life setting” provides access to something the medical setting does not — that other 99% observable window of time. Moreover, the traditional medical setting continues to rely on costly and invasive approaches that are inaccessible to everyday consumers without a clinician’s involvement. This often creates a barrier by requiring a physical intermediary (such as blood or tissue) to measure and mark signs to a disease – known as biomarkers.
In short, yes!
The traditional medical setting continues to rely on costly and invasive approaches that are also inaccessible to everyday consumers without a physician's involvement.
Our healthcare system uses biomarkers to measure our health. Today, these biomarkers are overwhelmingly molecular (blood) in nature. In fact, according to the CDC, 70% of medical decision-making about our health is based on molecular biomarkers.
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 signs 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.
Today, smartphones, smartwatches and other smart devices are acceleratingly entering our life setting 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.
BioTrillion internally calls this life data: Learnable Insights From Expressions (or Environment) data.
Advancements in the field of 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 learn about 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 – life data – can be “marked” back to detecting or predicting a disease. In other words, life data can be processed using AI to analyze how strongly it correlates with a disease and then converted into radically novel types of biomarkers: digital biomarkers.
Algorithms analyze life data much like a physician would, but can augment a physician’s abilities – better, faster, and cheaper. At BioTrillion, we are developing a health technology platform called BioEngine4D™ to achieve this by generating novel life data and aggregating medical data, then analyzing the data together to digitally detect developing diseases.
We believe digital biomarkers will one day overtake molecular biomarkers in healthcare.
Risk factors can indicate the future likeliness of a disease.Biomarkers can detect the current existence of a disease.
Life data — learnable insights from expressions (or environment) data — can become a digital biomarker when a relationship is established between a health-related measure and a disease's detection, diagnosis, or response to a drug.
Digital biomarkers are device-generated physiological and behavioral data points generated from digital smart devices that can be used to detect or predict certain health diseases and outcomes.
Take a smartwatch that can now continuously measure heart rate – a type of life data. 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.
Prospectively, 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 types of life data we have yet to generate are abundant in variety and hold the promise of being digitally biomarkable to a vast array of diseases. Only once the right combination of life data is analyzed will we realize their tremendous value in healthcare – and the world has only just begun to scratch the surface.
BioTrillion is developing a mobile digital biomarker technology platform to digitally detect diseases in key areas.
A great example of a digital biomarker for cardiovascular health is heart rate. According to Harvard Health, “when it comes to your heart rate, it's a bit like the speed of your car. What you want is not too fast, not too slow, and not too erratic... And unless something unusual is going on, you're likely completely unaware of what your heart is doing.” Today, millions and soon to be billions of people can now digitally measure their heart rate from a smartwatch.
Digital biomarkers offer a host of advantages to measure our health — affordability, accessibility, frequency, and scalability — over molecular biomarkers that are confined to clinical settings. However, it also takes into consideration a crucial component of our health, via the often undermeasured time dimension: physiologic processes. Nonetheless, our current healthcare system still lacks these primary digital biomarkers, and we believe the healthcare industry has only begun to scratch the surface in identifying them. There exists tremendous potential to innovate new technologies that can measure and produce insights from the features that live in the world of millimeters and milliseconds. Particularly so considering the rapid pace of hardware advancements we all enjoy in our smartphone cameras, with annually improving resolutions and frame rates.
We humans have developed innovative technologies to observe both ends of these scales in different ways. At the macro scale, innovations in optical hardware, such as cameras equipped with AI-based computer vision software, can automate processes that otherwise require manual human intervention, such as self-driving cars. At the micro scale, the same AI technology can enable us with the ability to see and measure the size of cancer cells in a tissue biopsy. However, what about the middle, or what might be referred to as the “milli scale” — the scale at which we humans can technically see, but usually do not perceive?
Did you know that there is a difference between seeing and perceiving? In fact, there is valuable visual information that occurs every day, in front of your very eyes, that you “see” yet do not “perceive.” We humans have developed innovative technologies to enable applications at both ends of the macro and micro visual scales in different ways. However, what about the middle, or what might be referred to as the “milli scale” — the scale at which we humans can technically see, but usually do not perceive, and certainly don't remember?
Many developing diseases express their features as life data in a dynamic pattern of progression that can be better detected through more accessible and frequent anatomic and physiologic digital measures.
The milli scale can be further broken down by dimensions: space or time (spatial millimeters or temporal milliseconds). And we believe a treasure of health information remains trapped at the milli scales features, particularly in the milli temporal dimension, and we are on a mission to unlock these life data features into digital biomarkers for health insights.
Think of the majority of medical biomarkers you've experienced: most are measures of static/spatial features. While informative, physiologic data rarely get measured in the clinical setting and these milli temporal features provide the additional dimension of time-series data that will unlock insights into the body's health function. And, most digital biomarkers are inherently time-series.
Yes! And therein lies the opportunity and arbitrage.
In healthcare, the eyes and face are a classic example of the milli scale’s potential, but where there remains a dearth of health innovation. For example, consider the human eye. There is spatial information that we can see, such as the millimeter size of a pupil (or hand tremor frequency), that can provide insights into one’s emotional state. There is also temporal information, such as the millisecond time it takes for a pupil to constrict when stimulated by light (or hand movement time), that can provide insights into one’s neurologic function. There exists tremendous potential to innovate new technologies that can measure and produce insights from the features that live in the world of millimeters and milliseconds. Particularly so considering the rapid pace of hardware advancements we all enjoy in our smartphone cameras, with annually improving resolutions and frame rates.
Today, the smartphone represents a computational extension of 3 billion humans – that naturally intersects with one's eyes and face over 100x / day. Smartphone sensors (especially optical) represent one of the most underleveraged modalities applied to Consumer Health. The smartphone industry is looking for that next “killer application” – with a more compelling value proposition to upgrade to better cameras – than just photography or FaceID.
BioTrillion believes that "killer app" is Health. Innovating at this intersection will unlock: earlier disease detection and accelerated drug development – scalable to Anyone, Anytime, Anywhere.
Artificial intelligence allows us to develop detective and predictive models which make medical sense of the various input variables generated from and around life in order to understand how they relate to one’s health. In other words, AI facilitates the transformation of life data into digital biomarkers for diseases. Better disease measures, via digital biomarkers, present benefits for every constituent in the healthcare industry and society as a whole.
Consumer healthcare has been undergoing a seismic shift. Over the past few years, the "consumerization" of healthcare has accelerated dramatically. The seeds of the revolution began in the disease prevention phase, with wellness gadgets such as Fitbits and accessories that measure disease prevention wellness metrics, such as steps or activity. However, these measures lack meaningful insights into detecting whether a disease has originated. Across sectors, technology has yielded innovative solutions to satisfy consumers' desires for convenience and independence, and healthcare should be no exception. We believe future consumer healthcare innovations will evolve from disease prevention to disease detection -- outside of the medical setting.
Hundreds of engineers, years of R&D, and hundreds of millions of dollars were invested into the Apple Watch 6's ECG and SpO2. This was a major validating tailwind for BioTrillion and the market we’ve been predicting for next-gen healthcare: digitally detecting developing diseases.
Evolution has spent thousands of years developing the human body as the most complex machine ever engineered.
Biological systems can be broken down into an engineering science, such as Bioengineering, but understanding that complexity is fundamentally limited by the human brain itself. Biology is too complex, non-linear, and interconnected to reverse engineer by human minds alone.
Ironically, we now require human-engineered machines, computers, to reverse engineer the human body.
BioTrillion was architected from Day 1 for mass scale-from-synergies. Rather than start with a Disease and innovate a physical device to measure its Signs, BioTrillion flips this paradigm by starting with the Signs of Disease that 1B people can already measure, right now.
Across industries, novel technologies applied to traditional domains have yielded entirely new opportunities to solve old problems in new ways. Within healthcare, we are currently at a critical juncture wherein costs are rising – unsustainably – with little improvements in outcomes, necessitating radical, technologically-driven innovations. We believe the future of healthcare will require solutions oriented around accessibility, affordability, continuity, timeliness, and data-driven outcomes. Solutions that — in retrospect — will make us realize that we have been “in the dark” about our health 99% of the time.
We need to empower individuals with enhanced healthcare abilities, by providing access to better disease detection solutions and by facilitating accelerations in the drug development process. Advances in technology have amplified our individual capabilities in many ways, and healthcare should be no exception.
After all, no one will have a greater interest in your health than you.