Crashing or Sliding into Sickness?
Breaking a bone is typically a discrete event. In Monday’s Tour De France Stage 3, sprinter Jasper Philipsen suffered a nasty crash that saw him carried away on a stretcher and out of this year’s race. In one moment, he was in full cry towards the line – the next, he was on the ground with a broken collarbone.
Perhaps fortunately, the big-name chronic conditions like heart disease, COPD, depression and kidney disease are not like that. These conditions typically develop over years as a gradual slide into sickness. The medical system, however, defines them in discrete terms: hypertension occurs when you hit a BP of 130/80; Stage II COPD occurs when your FEV1 slips from 80 to 79. This kind of classification is undoubtedly useful from a clinical perspective, as it triggers clinical action and justifies all-important reimbursement in a fee-for-service landscape. However, to change our system from reactive to proactive, we’re going to need to find better ways to see and treat disease more like a slide than a crash.
Helping AI to See the Slide
We’re living through the AI revolution of everything, but in diagnostics AI has mostly been confined to automating existing procedures. I argue that this is due to the types and quantities of data available to build models. If we want to unleash the power of AI for preventative medicine, we need a way to collect data about our bodies in all stages of sickness and health. Think of this analogy: if self-driving cars were trained only on ideal conditions and post-crash data, these systems would never learn the intermediate steps needed to avoid accidents in real-world driving. However, self-driving cars are peppered with sensors collecting thousands of data points each second. Humans aren’t – and existing tools to meaningfully measure physiology like MRI, ultrasound, and even blood tests can’t practically scale to meet this challenge, let alone do so in a cost-effective way.
Building Self-Driving Healthcare
At Skribe, we believe that advances in sensor technology have made it possible to measure clinically-actionable physiological signals using wearable devices – as long as they’re placed in the right location. We’re building tiny, battery-free sensor patches that can be placed directly over target organs to enable wearable sensing of whole-body health. We believe that measuring the ups and downs of organs like the heart, gut, brain, and more can create the types of data needed to train AI/ML models capable of making true leaps in preventative insights. However, healthcare is a complex beast and data alone won’t be enough. We’re looking beyond the technology build something that works for all stakeholders:
- Providers: inundating doctors with more data or opaque outputs from a black box algorithm won’t make their jobs any easier. We’re building our devices to detect the same metrics and be validated against gold-standard diagnostic devices that already fit established workflows.
- Patients: Wearable devices are only useful if they’re worn. Our enabling technology allows sensors to be comfortably placed anywhere and engages patients to be active participants in their own health journey.
- Payers: Healthcare spending is a major concern for everyone. We’re focused on building proof of better outcomes but also lower costs, demonstrating value to payers and increasing access for patients and people.
There’s a lot of talk about how healthcare is ripe for disruption, but we don’t think crashing against the system is the best way forward. We’re focused on creating technology that provides value today, while creating the tools for how we hope medicine will operate in the future. Unlike many other domains, so much meaningful information in healthcare is locked behind closed doors (often for good reason). By building tech that plugs into these systems from the start, we can leverage existing medical knowledge while at the same time augmenting it – creating change from the inside out. More than ever, the opportunity to change sick care into health care is now, and we’re excited to be part of the revolution.
Leave a Reply