Wearable Health Sensors and Diagnosis

Two men, Nick A. (left) and Nigel (right), sit at a white table, engaging in a lively and friendly conversation. Both wear checkered shirts and lavalier microphones, suggesting a filmed discussion or interview. Nick holds tissue samples in one hand and gestures animatedly, while Nigel smiles in response. Each has a white mug labeled with their name and a purple star logo. The background is a bright white, creating a clean and professional studio setting.
Resources

Wearable Health Sensors and Diagnosis

Sector: Diagnostics
Topic: Bio Break
YouTube video thumbnail

Wearable health sensors are becoming more capable as smartwatches and other devices continue to evolve. In this Bio Break episode, Nick and Nigel explore how a surprisingly small set of sensors could be used to identify a wide range of common health conditions. The conversation starts casually with a comparison between a simple Timex watch and modern smartwatches, but it quickly moves into deeper questions about sensing, diagnosis, and where wearables fit between wellness and medical devices.

How Wearable Health Sensors Are Expanding

As wearables become more advanced, they can sense more signals from the body. Nigel shares a long-standing interest in whether a limited number of sensors could diagnose many conditions. Rather than adding endless hardware, the idea focuses on selecting sensors that overlap across multiple use cases. This approach keeps systems simpler while still delivering meaningful insights.

Importantly, the discussion highlights the tension companies like Apple have faced when deciding whether a product is a wellness device or a regulated medical device. That distinction shapes how wearable health sensors are designed, validated, and positioned in the market.

Diagnosing Common Conditions with Fewer Sensors

Using a paper-based analysis, Nigel estimates that around 46 common conditions could be identified using just five sensors. These conditions tend to be ones with external or observable symptoms and may be chronic or episodic. Examples mentioned in the episode include pregnancy, common colds, asthma, and breathing difficulties.

Rather than chasing rare diagnoses, this model prioritizes conditions people experience frequently. As a result, wearable sensors can deliver more value without unnecessary complexity.

Finding the Core Sensor Set

Not every condition makes sense to include. Adding a sensor to capture only one or two extra diagnoses quickly becomes inefficient. Instead, the conversation points to a core group of sensors that form a nucleus. This nucleus provides the greatest overlap across many conditions, which is key for scalable wearable health sensors.

Reliability Still Matters

Despite all the potential of smart devices, the episode closes with a reminder that reliability is still valued. A simple watch may not diagnose conditions, but it works consistently. That contrast underscores the challenge for wearable diagnostics as they move closer to medical use.

Indirect ELISA explained with antibody model showing enzyme linked immunoassay detection

Nick and Nigel walk through how indirect ELISA works, why it uses two antibodies instead of one, and when this approach makes the most sense in real diagnostic workflows.

Smartwatch displaying heart rate and ECG-style waveform, illustrating the difference between wellness devices and medical devices in digital health regulation

Ariana Wilson and Mark Drlik break down medical vs wellness devices and explain why two products with identical hardware can fall into completely different regulatory categories.

Nick from StarFish Medical demonstrating antigen detection using a toy antibody model to explain how monoclonal antibodies bind antigens in ELISA diagnostics

Nick and Nigel break down the ELISA assay explained in simple, practical terms using everyday models.

Magnifying glass revealing cracks with the text “This gets missed,” illustrating hidden risks in medical device validation and real-world use.

Ariana Wilson sits down with Mark Drlik to unpack why reprocessing is often one of the hardest challenges engineers face during development.