A digital weight management platform that syncs patient weigh-ins in under a minute
Tizora built a digital weight management platform for a US health and wellness provider's gastric balloon program, used by more than 100,000 patients since 2018. Bluetooth scales sync weigh-ins automatically, and weight, sleep and exercise data are combined into one patient view. Patients get progress reports plus in-app chat and video with their care team, and every weigh-in reaches the patient record in under a minute.
What the platform changed for patients and care teams
What problem was the gastric balloon program facing?
After a gastric balloon procedure, success depends on what patients do day to day: staying active, tracking progress and keeping in touch with their care team. But weight was typed in by hand, activity data sat in different apps, and clinicians had little visibility between appointments.
The program didn't need another weight tracker. It needed a continuous feedback loop between patient data, patient behaviour and professional guidance.
- Weight tracked manually by patients
- Activity, sleep and exercise data spread across separate sources
- Limited visibility of patient progress for healthcare professionals
- Communication between patients and experts happened outside any shared record
How did Tizora build the weight management platform?
We engineered the system behind the screens. Bluetooth scales sync automatically, a normalization layer turns every data source into one patient model, reports turn data into progress, and Twilio adds chat and video. Structured data comes first, so AI can be added later without a rebuild.
Connect devices
Bluetooth scale sync replaces manual weight entry
Normalize data
Weight, activity, sleep and exercise combined into one patient model
Insight + care
Progress reports, trends, and in-app chat and video
Ready for AI
Structured data for personalization and risk scoring
How is the platform architected?
Cloud-based backend services run on AWS, AWS Lambda, Python and PostgreSQL. Core capabilities are separated into services that can evolve independently, and an integration and normalization layer turns data from Bluetooth scales and other health sources into one patient data model shared by the iOS and Android apps, progress reports and chat and video consultations.
The architecture leaves room for an intelligence layer above the data platform. Instead of delivering identical content to everyone, an AI personalization engine can determine what a patient should see next based on historical data, trends, patterns and risk signals, turning scheduled communication into context-aware engagement. It is the same idea behind our AI skin analysis feature, which matches each shopper to the right products.
The complexity of this project was not in building screens. It was in engineering the ecosystem behind those screens. The same engineering-first approach shaped our AI-ready patient management platform.
What does the platform do?
We transformed raw health data into visual reports, progress patterns, and a connected care loop.
What technology powers the platform?
Native iOS and Android patient apps and a React care-team dashboard sit on Python microservices running on AWS Lambda, with structured health data in PostgreSQL. Bluetooth scales sync weight automatically, and Twilio powers in-app chat and video consultations.
Mobile & web
Patient apps and the care-team view
iOS
Android
React
Hurdles
What made the project hard, and how was it solved?
The hard part wasn't the screens. It was keeping wearable devices connected so activity data had no gaps, and keeping times correct for patients in different time zones.
Bluetooth disconnects on wrist-worn trackers
In 2021 we paired wrist-worn devices over Bluetooth to track patients' activity during the weight-loss program. The Bluetooth module disconnected often, leaving gaps in activity data. We added a rapid retry loop that reconnects the device automatically after a drop. Tracking interruptions fell, and activity monitoring stayed continuous.
Sources that disagree on format and time
The app supported patients across multiple time zones, which complicated activity tracking, notifications and reporting. We stored every timestamp in UTC to keep records aligned across regions, then converted times to each patient's local time zone for notifications and reports.
Building a connected health or remote monitoring product? See how this architecture fits your devices and care workflows.
What results did the platform deliver?
Weigh-ins now reach the patient record in under a minute without typing, patients see all their health data in one place, and care-team reviews are faster. Weekly patient engagement also rose from 38% to 67%. These are operational results, not clinical outcomes.
| Metric | Before | to | After | Change |
|---|---|---|---|---|
| Weigh-ins entered by hand | 100% | <5% | −95 pts | |
| Weigh-in to patient record | Next manual entry | <1 min | Near real time | |
| Places a patient checks for health data | 3+ | 1 | One view | |
| Care-team review per patient | ~10 min | ~4 min | −60% | |
| Patient engagement (weekly active) | 38% | 67% | +29 pts |
Our coaches used to chase patients for weigh-ins. Now the data is just there, and our check-ins are about progress, not paperwork.
Lessons
What did we learn?
Normalize before you analyze
Devices report in different formats and frequencies, so normalization had to come before any progress reporting.
Remove the manual step
Bluetooth sync removed the manual entry that the old tracking depended on, and that is what made the data reliable.
Structure data now for AI later
One data model and independent services let personalization and risk scoring be added without a rebuild.
Will this work for your digital health program?
Typical timeline, team and what it connects to.
- Typical timeline
- 6–9 months to first release
- Team
- 1 solution architect, 3 software engineers, 1 frontend developer, 1 QA, 1 DevOps, 1 project manager
- Connects to
- Bluetooth scales, activity and sleep sources, Twilio chat and video
Yes, if your program depends on monitoring and supporting patients between visits. It fits gastric balloon, bariatric, weight-loss and lifestyle programs that need connected devices, progress reports and remote care in one app.
Digital weight management FAQs
Frequently asked questions
Patients step on a Bluetooth scale, and the reading syncs to the app and their record in under a minute, with no typing.
An integration and normalization layer converts each source's format, timestamps and frequency into one patient data model for weight, activity, sleep and exercise.
Yes. Real-time chat and video consultations, built with Twilio, run inside the app as part of the patient's program.
Not yet. It was built AI-ready: structured data and independent services make it possible to add personalized recommendations and risk scoring without rebuilding.
Disclosure
Client name withheld under a confidentiality agreement. This case study and its metrics were reviewed and approved by the client. Results reflect this client's data and measurement period and will vary; Results shown are operational, not clinical outcomes. Tizora built the platform to support the provider's HIPAA and GDPR obligations; responsibility for compliance rests with the provider. This case study describes software engineering work and is not medical advice. Screens shown use synthetic data.
Related healthcare case studies
Building a connected health or remote monitoring product?
Tell us about your devices, data and care workflows. In 30 minutes we'll suggest an architecture and a phased build plan.
