When it comes to remote sensing, we need to understand the basic science before we go to the bedside to start seeing patients.
When it comes to remote sensing, we need to understand the basic science before we go to the bedside to start seeing patients. Here's what will be on the test:
1. Afferent limb problems: These are issues that involve the data that is derived and sent to the next step, the central processing station. For example, how do we know that the scale measuring your weight at home is actually accurate? How do I know that the person standing on the scale is actually the patient? How can we protect the data that is being sent from intruders or third party intermediaries?
2. Central processing problems: These are problems with how, when, and where all this data is processed, stored, analyzed, and displayed to create actionable information and generate a valuable efferent signal. For example, should the data be analyzed by a machine, a non-medical professional or someone else? How? How do we prevent “alert fatigue,” i.e. not sending so many false positive signals that users ignore the real emergencies?
3. Efferent limb problems: These are problems that involve who gets the information and what they are expected to do with it. For example, should the patient get the alerts or the doctor? What are the tools we offer to patients to change their health and wellness behavior and will they work? How do we get doctors to adopt these new technologies and use the information to prescribe interventions that will measurably reduce per capita costs, improve health outcomes, and improve the patient experience?
We are still beginning to understand the embryology of remote sensing and what makes patients tick is more important than what makes your iWatch tick.
The future of wearables, in my opinion, looks something like this:
1. Better, cheaper, faster transcutaneous sensors measuring multiple analytes.
2. A better interface between the doctor and the data.
3. Better decision support to interpret the data at the point of service.
4. Verizoncare that integrates media, data, social media, search, and communications.
5. Data scientists as part of the care team.
6. Secure data and information.
7. Creating data science jobs that have yet to be invented.
9. DIY medicine.
10. Migrating sick care to disease prevention, crowd-sourced epidemiology, and disease management linked to payment.
Wearables—devices used to create actionable information at the point of care, are coming soon. Connecting to your sneakers is so 2015.