PCOS Is Dead. Meet PMOS, the Rename That Demands an AI Workup

More than 170 million women, 1 in 8 worldwide, are diagnosed with PCOS (polycystic ovary syndrome), now renamed PMOS (polyendocrine metabolic ovarian syndrome) as of this spring. The change took 14 years, 56 patient and professional organizations, and more than 22,000 survey responses to reach.

Researchers confirmed there is no real increase in abnormal ovarian cysts in the condition. The rename reflects that this is a whole-body metabolic and hormonal condition, not an ovarian one. Women with this condition carry a fourfold higher risk of type 2 diabetes before age 40 and a meaningfully higher cardiovascular burden. A name that puts metabolism first tells you where to point your attention from the first visit. 

Next step: Put metabolism at the center of the workup, and use AI to synthesize the larger data load each patient now generates.

PMOS remains a diagnosis of exclusion. You confirm it with at least two of these three findings:

A modern PMOS workup pulls labs, genetics, symptoms, and wearable streams into one view. You want to collect and synthesize the data before the patient walks in for their next appointment. Feed these inputs into a purpose-built clinical AI tool, or an AI-native EHR like Ultralight, and it lines up out-of-range markers and trends for you.

On the genetics, the evidence is real but still maturing. A 2025 genome review in Biomedicines found DENND1A, THADA, and MTNR1B variants showing signs of positive evolutionary selection, which hints at ancestral metabolic roles. A separate meta-analysis of 33 studies tied vitamin D receptor and ADIPOQ polymorphisms to risk. Use these as hypothesis-sharpeners, not verdicts. AI can pull the relevant variants out of a panel and line them up against the metabolic markers in front of you, but you still decide what it means for this patient.

The single most useful PMOS paper this year is a Nature Medicine study that grouped patients by pattern, with no preset categories, across nine clinical variables in 11,908 women and five international cohorts. It found four reproducible subtypes: 

This is the proof of concept for AI in PMOS. The same grouping logic, applied to your panel, moves you from one generic protocol to a subtype-matched plan. Ask your clinical AI tool which cluster a patient's labs resemble, then prescribe to that risk profile.

A single blood draw is one frame of a long film. Devices like the Mira analyzer give quantitative LH, E3G, PdG, and FSH from at-home urine wands, which matters because standard ovulation kits throw false positives in PMOS when baseline LH runs high. Overlay that hormone curve with continuous glucose monitor data and AI can show a patient, in their own numbers, how a glycemic spike tracks with a disrupted cycle. That single visual does more for adherence than a lecture ever will.

Feed daily wearable data (HRV, sleep, temperature) and symptom logs into a clinical AI model and it learns the patient's individual metabolic rhythm. The system flags an approaching cycle irregularity or an energy crash days before it happens, which gives you a window to adjust sleep, stress, or activity before the patient is already in it. For PMOS patients managing fatigue and cycle disruption, that early-warning capability is the difference between proactive and reactive care.

Patients now arrive with hormone reports, CGM exports, sleep data, and genetic files. That stack of files is data overload waiting to happen. Point an AI-native EHR like Ultralight at the incoming stream and have it draft a one-page pre-visit brief that surfaces the out-of-range markers and the trend lines. You spend the first two minutes acting on a synthesis instead of hunting for it. This is the same workflow we covered in the GLP-1 blindspot issue, now pointed at a different condition.

These tools give your patients structure between visits and hand you cleaner data at the next one. Recommend them as adjuncts, not replacements for your judgment.

Metabolic and glycemic insight. Levels or Signos pair a CGM with AI that scores meals and ties glucose swings to cravings and fatigue. For a condition driven by insulin resistance, that real-time feedback beats a generic low-carb handout.

Quantitative hormone mapping. The Mira analyzer confirms whether ovulation actually happened rather than guessing from a binary strip. A new startup to watch closely: Clair, a Stanford-founded continuous hormone wearable, is in beta now with hardware shipping later this year.

Recovery and autonomic tracking. The Oura Ring passively tracks temperature, sleep architecture, and heart rate variability as a stress proxy. Sleep apnea and elevated cortisol are common in this population, and recovery is part of the metabolic picture. The new Ring 5 also added GLP-1 management this year, which matters for the meaningful subset of PMOS patients now on these medications for insulin resistance.

At-home hormone and body-composition data. Eli Health is bringing daily saliva-based hormone monitoring into the home, with instant cortisol, progesterone, and testosterone tests. A smart scale from Withings gives patients a frictionless body-composition trend. Both feed the longitudinal record AI reads best.

One discipline carries over from our genomics issue. An AI tool is only as good as the model behind it and the data handling around it. A model can invent a confident lab summary or misread a scan, so treat every output as a draft you verify, not a result you sign. We walked through the failure modes worth watching in our piece on the red flags that your AI is working against you.

For anything that touches identifiable patient data, confirm three things first:

A general-purpose chatbot in its consumer form is not the place for identifiable labs or genetic files. A purpose-built clinical tool with HIPAA-compliant architecture is a different category. This is the line Ultralight was built on, an AI-native EHR made for functional, integrative, and longevity medicine. Know which one you are using.

You do not need to rebuild your practice. Pick one play and run it with five patients.

Option 1: Pull one patient's full PMOS panel and ask your clinical AI tool which of the four Nature Medicine subtypes their labs resemble. See if the matched risk profile changes your plan.

Option 2: Hand one patient Mira or a CGM app and ask them to bring their data to the next visit. You will get a real intake pattern instead of a vague recap.

Option 3: Point an AI summary at one patient's incoming files and have it draft a one-paragraph pre-visit brief. Time how much faster the visit starts.

The renaming is a three-year transition that finishes in the 2028 international guideline update. Your patients will hear "PMOS" from the news before they hear it from you. Being the clinician who already works the metabolic picture, and uses AI to keep up with it, is how you stay ahead.

Be a modern clinician with the help of Ultralight, the AI-native EHR built specifically for functional, integrative, and longevity medicine.

A $2M-per-year female longevity protocol just launched. Bryan Johnson announced his girlfriend Kate Tolo will become the most measured female in history, with endometriosis among the first conditions evaluated. Whatever you make of Johnson personally, the structural signal is worth tracking. Women's multi-system conditions (endometriosis, PMOS, perimenopause) are starting to generate the kind of large-scale data sets AI needs to be useful in them.

Clinical AI is consolidating from point solutions into operating systems. Two announcements landed in the same week. Longevitix launched June 8 with an AI platform that aggregates labs, wearables, intake forms, and notes into synthesized assessments for longevity and functional medicine. Three days later, Abridge announced a strategic investment from Eli Lilly and a foundation model co-developed with NVIDIA, expanding from clinical scribing into trial eligibility, billing, and insurance claims. Different segments, same thesis. The AI layer that synthesizes scattered clinical data is being built now.

Plasma biomarkers can now flag Alzheimer's risk in midlife. A new Lancet study from the CARDIA cohort found that 6% of adults aged 53 to 69 had elevated amyloid and tau plasma biomarkers, and these were associated with lower cognitive scores. The clinical implication: a blood test can flag patients at higher Alzheimer's risk decades before symptoms, with no PET scan or CSF tap required. For longevity clinicians, this is the kind of test that belongs in a midlife workup, especially for patients with the metabolic risk factors (insulin resistance, vascular disease) that overlap with PMOS.

Two tailwinds for metabolic and hormone-focused practices. A new Mayo Clinic Proceedings study found menopausal hormone therapy use dropped from 4.4% in 2007 to 1.7% in 2023, even among women 50-59 most likely to benefit. The undertreatment is now well-documented. Separately, new trial data confirms CGM significantly improves A1C in type 2 diabetes with benefits persisting after discontinuation. Both findings reinforce what functional, integrative, and longevity practices have been doing for years.

Upcoming Conferences & Events

Oct 8–10, A4M Women's Health Summit · San Antonio, TX ·  The best clinical education on hormone, metabolic, and midlife women's health you will see this year. The room to be in if you are growing the perimenopause and menopause side of your practice.

Oct 21–24, NAMS Annual Meeting · San Diego, CA  · The single most practice-changing meeting of the year for midlife women's health. Your protocols will look different after this one.

Nov 5–8, Eudēmonia Summit · West Palm Beach, FL ·  One of the most talked-about longevity gatherings in the U.S. Experientials, hands-on demos, and the best place to try the emerging frameworks your patients will ask you about next year. Ovation and Ultralight team will be there!

Nov 5-7 — Private Physicians Alliance Annual Meeting · St. Petersburg, FL The gathering for independent, cash-pay, and concierge physicians navigating practice independence. Practical and peer-driven. Ultralight will be there!

Nov 8-11 — American College of Lifestyle Medicine Conference · Orlando, FL Lifestyle medicine's main annual event — evidence-based approaches to behavior change, chronic disease, and healthspan. Growing overlap with the longevity medicine community.

Dec 11–13, A4M Longevity Fest · Las Vegas, NV  · The biggest longevity event in the U.S. The room spans clinicians, industry, founders, and the people building next year's platforms, and the connections from this one tend to compound through the rest of your year. Ultralight will be there!

Know of an event we should add? Reply and tell us.

PMOS asks you to treat the whole endocrine and metabolic system, and that means more data per patient than any chart review can hold in one head. AI makes the metabolic picture fast enough to read for every patient, not just the one in front of you today.

Pick one patient this week. Pull their panel, run it against the four subtypes, and find one thing worth acting on. Reply and tell us what you find. The best ideas in this newsletter come from clinicians doing the work.

— Sunita and Dr. G