By COLIN LAWLOR
A patient attends a regular primary care appointment. The nurse goes over the usual checklist: temperature, blood pressure, pulse, weight, and sometimes pulse oximetry. Sleep probably won’t come. If so, it will be a side note, and if the patient says “not very well,” what often follows is a look of sympathy and the familiar advice to relax a little before going to bed.
This is, more or less, what sleep looks like in the most common diagnostic interaction in American medicine. Don’t worry, it’s not much, if anything better in any other country. The other vital signs get numbers, while sleep is small talk. Calling this a minor gap is meaningless.
What the evidence says
Sleep is among the strongest physiological and behavioral predictors we have for chronic diseases, cognitive decline, mental health outcomes, and burnout.
Stanford work recently showed that just one night of sleep data (certainly from a hospital sleep lab), processed by a basic model called SleepFM, could pinpoint elevated risk across 130 disease categories with high precision. The results on that list are not trivial and include all-cause mortality, dementia, myocardial infarction, and heart failure.
TO general review 2025 that brought together 29 systematic reviews found bidirectional physiologically mediated links between sleep and depression, anxiety, and a long catalog of cardiometabolic conditions.
And researchers at Washington State University published what, so far, is the longest objective description of sleep in chronic insomnia. Eight weeks of continuous at-home measurements pointed out something doctors have struggled to capture for years: night-to-night changes in sleep efficiency, sleep latency, and intermittent wakefulness are critical to this condition. Sleep diaries and overnight laboratory studies still did not account for that pattern.
The clinical rationale for measuring sleep is established, but what remains unclear is whether medicine intends to behave as if it believes its own evidence.
Look at the current configuration. Obstructive sleep apnea affects about 960 million people worldwide, and up to 80 percent of moderate to severe cases have not yet been diagnosed. Chronic insomnia affects more than 800 million people worldwide. Both disorders lead to costly and common downstream consequences, including cardiovascular disease, depression, car accidents, work-related injuries, dementia, and more. Both can be treated. However, routine primary care usually does not detect either.
The American College of Physicians has recommended coCognitive behavioral therapy for insomnia. as a first-line treatment since 2016. Still, most people with chronic insomnia never receive CBT-I, in part because they are never identified in the first place. Doctors cannot treat what they do not discover and often do not even ask the questions that might arise.
The void that consumer technology filled
Talk to working professionals, parents of young children, perimenopausal women, older adults, teens, just about anyone, and sleep will come back quickly. People know it’s important. They’ve read about it, they monitor it with a watch, they take it to their doctor. And increasingly, when the clinical system has nowhere to put that concern, it looks elsewhere.
After more than 16 years in sleep science and health technology, the biggest change I have seen is the change in what patients do when medicine leaves a void.
Consumer technology entered the space that healthcare left open. People measure their sleep, sometimes well, sometimes poorly, through wearable devices, phone apps, and bedside devices. Apple, Google, and the consumer market in general have helped make sleep seem “accountable,” something worth paying attention to. That is real progress.
But the next step is where things break down. If a patient sees a consistent decline in deep sleep reported by their watch over six months, there is typically no clinical pathway for that signal. Most primary care offices are not designed to receive it. Doctors usually have little training to interpret it. Insurers are rarely willing to pay for the time and work required to investigate it.
The data is available, but what is missing is the machinery that converts data into knowledge and attention.
Therefore, patients end up doing the interpretation themselves, usually with mixed results and often surrounded by wellness content ranging from thoughtful to careless. That gap is not a consumption problem. It is medical in nature.
What medicine should do
This case is more practical than it seems. You don’t have to swallow the whole world of wearable devices to take sleep seriously. You need to do four concrete things.
First, incorporate validated sleep measurement into routine primary care, along with other vital signs. At the population scale, tools for smartphone-based measurements, clinical-grade bedside sensors, and standardized wearable data aggregation already exist and have been compared to polysomnography. Science is not the bottleneck. Reimbursement, workflow and training are.
Second, routinely screen for the three most common and least diagnosed sleep disorders: obstructive sleep apnea, chronic insomnia, and restless legs syndrome, especially in groups where prevalence is high. Primary care is an obvious place for this, but so are obesity medicine, cardiology, endocrinology, mental health, and women’s health. None of these areas do so reliably today.
Third, create a referral and treatment pathway that works. When sleep measurement points to a clinical problem, there has to be a place for the patient to go. That means more sleep medication capacity, broader access to CBT-I, and closer collaboration between sleep specialists and the rest of the care team. Right now, the route often passes through too few sleep labs and even fewer sleep physicians or behavioral sleep clinicians, leaving patients waiting or never being seen. Capacity needs to be expanded.
Fourth, treat the sleep data that people already collect as legitimate data. Tens of millions of Americans track their sleep every night. Data quality varies and interpretation is often uncertain, yes. Still, the signal becomes much clearer when validated measurements and clinical context are added. This is made easier thanks to high-quality harmonization tools. When a patient comes to an appointment with months of self-collected data, they are doing work that the system has not formally asked anyone to do. Medicine should take this seriously.
Science is sufficiently advanced. What remains is the operational work of separating the wheat from the chaff, creating workflows, advocating for reimbursement, training physicians, expanding capacity, and treating sleep with the same seriousness we have given other vital signs for a century.
The dream is also an obvious entry point into a broader question. How should medicine harness the power of continuous physiological signals in daily care? Sleep is increasingly easier to measure, has profound consequences, is personally felt, and has one of the widest gaps between what we know and what we do.
If the healthcare system can’t figure out how to measure and respond to sleep—something universal, intuitive to patients, and backed by indisputable evidence—then the broader promise of preventive medicine driven by physiological data seems shaky. We can no longer argue about whether sleep is important. We can no longer prove that technology can measure it. The question that remains is simpler and more difficult: is medicine willing to treat sleep as the vital sign that it is?
This one has been “sleeping” for quite some time.
Colin Lawlor is the founder and CEO of Sleep.aiwhere he has spent over a decade developing validated sleep measurement and intelligence technologies.
