Two-week glucose sensor studies for gestational diabetes, read for the doctor
TL;DR Lilycurve gives pregnant women with gestational diabetes a licensed continuous glucose sensor for two weeks at a time, with a dietitian who reviews the readings and a short report for the obstetrician. Clinics order it, families pay, and the aim is fewer surprises late in pregnancy.
A 2024 meta-analysis of 117 Indian estimates put gestational diabetes at 13% of pregnancies, with urban rates above rural ones[1]. Diagnosis criteria differ across the country, so many women are labelled late or not at all[1].
After diagnosis, most women are told to prick a finger several times a day and keep a diary. How many manage that? Not many, and the readings they miss are usually the ones after meals, which is exactly when glucose peaks. HbA1c, the usual fallback, is less reliable in Indian women because anaemia and haemoglobin disorders are common[2]. Obstetricians in busy clinics see the diary for two minutes and must decide on diet changes, metformin or insulin with patchy data.
What it does, in regulatory terms: glucose monitoring with licensed sensors and decision support for the treating obstetrician. Lilycurve does not diagnose or prescribe. The sensors are approved medical devices, and the reporting software has to be checked against CDSCO's 2026 guidance on medical device software[3].
The obstetrician orders a 14-day study at diagnosis and, where needed, again around 32 weeks. A Lilycurve nurse fits the sensor at the clinic and teaches the phone app. A dietitian reviews the readings twice a week and calls the woman about meals that spike her. At day 14 the doctor gets a one-page summary - time in target range, post-meal peaks and the patterns behind them.
The seed pitched continuous monitoring of many biomarkers for everyone, and I reframed it. Glucose is the only biomarker with mature, licensed continuous sensors in India, and pregnancy is where trials show a clinical payoff, so Lilycurve starts there.
The woman uses it. Her family pays out of pocket, as with most pregnancy care in private clinics. The clinic or hospital is the channel, adding Lilycurve to its antenatal package and earning a share. I couldn't confirm an Indian sensor price from a primary source, so the study price has to be set after quotes from distributors.
The evidence firmed up in 2026. A meta-analysis of five trials found continuous monitoring halved the odds of an oversized baby compared with finger pricks[4]. A second review of 17 trials found fewer newborn intensive-care admissions with real-time sensors, while warning that the trials are small[5]. Flash sensors have also been tested in Indian children, so the devices are already in clinical use here[6].
There's no public figure for continuous monitoring in pregnancy in India. The narrow signal is the 13% prevalence[1], applied to the antenatal load of the private clinics you sign. Digital diabetes programmes already sell sensor-based programmes for adult diabetes[7], which shows families pay for sensors. Treat that as adjacent, not as your market.
One Indian digital diabetes programme uses sensors with coaching, but its site lists no pregnancy programme[7]. A wearables brand sells its sensor as a wellness product and says it is not meant for managing disease[8]. Hospital diabetes clinics fit sensors case by case. The gap is a pregnancy-only service that obstetricians can order with one form and read in one page.
| Difficulty | Moderate (43/100) |
| Starting capital | ₹55–95 L |
| Time to launch | 4–6 months |
Nothing here needs new hardware. The hard parts are clinical trust and staffing. Obstetricians have to believe the report and dietitians have to respond within a day, which sounds easy until you try to hire for it, and every sensor fitting needs a trained person at the clinic. Sensor supply and cost also sit with one or two global makers.
Yes. You use regulated sensors, and your report software may count as a device.
Building this outside India? The categories above usually have a local equivalent, so check with your own regulator.
AI must not change insulin or diet plans or tell a woman she has gestational diabetes. Lilycurve gives decision support, and the doctor decides.
Want to work out the AI layer for Lilycurve? Talk to Yash →
I think this is a good fit for a founder with a clinical partner in obstetrics and some experience running nurse or dietitian teams. If you're hoping to build a sensor then it's a poor fit. Prove one thing first - that obstetricians in three clinics order a second study for the same patient because the first one changed what they did.
Plan for roughly ₹55–95 L for sensors, software, staff and early operations.
Use CDSCO-licensed sensors, get a classification opinion on your report software and follow the Telemedicine Practice Guidelines and DPDP Act.
Yes. Check local device software rules and telehealth guidelines before launch. My advice is to run a small paid pilot with a few real customers before you commit the full budget.
The free Lilycurve validation kit has the line-by-line capital breakdown, the effort scoring, the device and data-protection checklist, a 14-day validation sprint with pass/fail targets, a 90-day launch plan, 10 interview questions for obstetricians and pregnant women, and 5 assumptions to test. Download the kit →
Thinking about building Lilycurve or something close to it? The make-or-break work is getting busy obstetricians to order the study and act on the report, and that's the kind of thing I help founders crack. If you need a hand, you know where to find me. Talk to Yash →
For illustration only. Names are fictional and ideas hypothetical; sourced facts are real but may be out of date. Nothing here is legal, financial or professional advice, and Yash Khatri is not personally liable for any use of it. Read the full disclaimer.