This is one outlet's own report from Forbes — the article as it was filed.
AIPROPX ReportForbes · 2h ago
AI Cognitive Health Startup Mantis Biotech Rethinks How Women Are Diagnosed
ForbesWomen AI Cognitive Health Startup Mantis Biotech Rethinks How Women Are Diagnosed By Geri Stengel ,
Forbes contributors publish independent expert analyses and insights. Geri Stengel writes about the success factors of women entrepreneurs. Follow Author Jul 31, 2026, 07:00am EDT --:-- / --:-- This voice experience is generated by AI. Learn more . This voice experience is generated by AI. Learn more . Summary Georgia Witchel's Mantis Biotech makes Parva, consumer software that reads how a person types and clicks to flag cognitive change relative to their own baseline, not a population average, largely built on men. The approach targets conditions that shift daily and disproportionately affect women: long COVID, ADHD, dementia, and perimenopause. Monthly appointments routinely miss these variations. Witchel, who built physics simulations to predict athletic injury before pivoting to cognitive care, argues that statistical AI fails at the individual level. Backed by $7.4 million led by Decibel, Parva reaches patients through ADHD, psychiatry, perimenopause, and neurology clinics. Pending FDA clearance, it flags risk rather than diagnosing, offering a continuous record where medicine was once measured by feel.
Robyn Schlicher spent years trying to measure her own mind. After a viral illness in 2020 left her with brain fog, memory gaps, and trouble reading, she tracked her decline the only way she could, by feel. “I was doing my best to assess changes in my mental state and cognitive ability qualitatively, based on how I felt, but it always seemed inaccurate and lacking,” she recalls.
That distance between what patients sense and what medicine can measure is the problem Georgia Witchel set out to close. Her company, Mantis Biotech, makes a consumer software product called Parva that quietly reads how a person types and clicks, then flags cognitive change against that person's own history . The bet underneath it is deceptively simple: The right yardstick is not you against the population, but you against yourself.
Cognitive care runs on a schedule that works against the biology it is meant to track. Witchel points out that treatment for conditions “like long COVID, dementia, perimenopausal syndrome is completely based on in-person appointments that will happen once a month at relatively random intervals.” A single monthly visit captures a mind at one arbitrary moment, then calls it a trend.
For women, that design flaw compounds. Symptoms shift with hormones and, as Witchel notes, “your emotions, your ability to self-regulate, is going to fluctuate with your hormones, with your monthly cycle.”
The stakes are not marginal. A 45-year-old woman carries a 1 in 5 lifetime risk of Alzheimer's, double the 1 in 10 a man faces. Women were also found 31% more likely to develop long COVID than men in the federal RECOVER study.
Most medical algorithms learn what “normal” looks like from large populations, and those populations were skewed toward males for decades. Parva throws that reference frame out. It installs on a laptop and reads passive signals—keystroke latency, mouse movement, how long attention lingers on a tab, how quickly someone answers a loved one—then stores them in a HIPAA-compliant database and weighs each day against the user's own earlier readings.
The shift reframes diagnosis itself. Take ADHD, widely missed in women because the criteria were built on boys. Witchel says Parva asks whether a woman improved against her own pattern, “rather than... the traditional method, which is just, do they fit into a traditional male pool as diagnosable as ADHD.”
Schlicher signed up on the spot. “Parva determined my baseline upon joining, and now I let it work in the background as I work, with no need for wearable or invasive devices,” she explains.
Notably, Witchel resists the women's health banner even as she builds squarely for it. She would rather treat these problems, in her words, “as like gaps in health, and women just like our lower baseline,” which is precisely why they stand to gain the most.
How Injury-Prediction Tech Became Cognitive Care
Witchel did not start in neurology. She built physics simulations to predict when bodies break, work that pulled her into professional sports because, as she puts it, “the number one buyer of a physical simulation of a human is someone who really, really cares if a human is going to get injured, and that is a pro athlete.”
Then she followed the misery to a bigger market. The total economic burden of dementia reached roughly $781 billion in 2025, while depression costs U.S. employers an estimated $187.8 billion a year.
Her technical wager is that pattern-matching AI flattens the very people who most need to be seen. “Statistical AI really breaks down at the individual level. It's really, really good at predicting populations,” she argues. The analogy she reaches for sticks: Ask an image model for a face, and “it'll give you a perfect human face. AI is very, very bad at doing uneven faces.”
Investors bought the thesis. Jon Sakoda of Decibel, who led the round, observes that “the next frontier will be models that understand each person as an individual. Mantis shows what's possible.”
Mantis has raised $7.4 million in funding, led by Decibel, with Y Combinator and Liquid 2 participating. The company straddles three young markets whose edges are still soft: digital biomarkers, forecast to reach $17.73 billion by 2031, according to Markets and Markets; behavioral biometrics, projected at $11.38 billion by 2031, according to Mordor Intelligence; and healthcare digital twins, headed toward $3.55 billion by 2030, according to AppInventiv.
Its nearest rivals cluster in digital biomarkers, among them Mindstrong, Altoida, and Evidation Health, though most chase a single signal or a single disease. For scale, the clinical digital-twin company Unlearn AI has raised more than $130 million, more than seventeen times Mantis's seed. Parva, meanwhi...
AIPROPX is an independent multi-source news index — we track, compare, and connect coverage from across the web into one place you won't find anywhere else.
