Health workers spend less time on paperwork and more on children, with vaccination records collected accurately.
Shifo Foundation wants a day when no child dies or suffers from preventable diseases, and needed reliable data on every child's registration and vaccinations to close the gaps in care.
What changed
What stood in the way.
- Its web application ran on an obsolete Python version, was slow and could not scale to the volume of data.
- Loading data from paper forms, which differ by country, and producing reports were manual and slow.
- 99%data accuracy, by the WHO data quality review toolkit (as reported)
- 60%less administration time for front-line health workers (as reported)
- 95%better data quality (as reported)
- 141,000+automated follow-ups (as reported)
What we built.
- A reworked Python application that uses less memory and runs faster, with pandas, NumPy, Redis, RQ and PostgreSQL.
- A reload module that moves scanned registration, vaccination and stock forms from Flexicapture into PostgreSQL, handling each country's forms.
- Reports in Excel instead of PDF, sent to government officials automatically.
- Python developers with 5+ years of experience added to Shifo's team for long-term support.
- Python
- pandas
- NumPy
- Redis
- RQ
- PostgreSQL
- Flexicapture
What this work shows about us.
The existing application was made faster and scalable instead of replaced, and Shifo kept its team's knowledge.
Paper forms from different countries reach one database and become reports officials receive automatically.
Want a faster vaccination data system like this? Tell us what you want to change. Our AI assistant, Ask Unthinkable, helps you define your requirements, then connects you with the right team.
Start your plan ↗If we built it today, with AI.
This work came before today's AI. If Shifo Foundation asked us now, this is what we would add, step by step.
An agent would remind each family when a child's next vaccine is due, in their language, and tell the health worker who has missed one. Health workers still decide every follow-up visit.
An agent would read each scanned registration form, flag fields that look wrong or missing and ask a person to check them before they reach the database. Staff confirm every correction.
Where this work fits.
- Hospitals & clinicsYour hospital is meant to deliver care without making patients wait.
- Records & imaging (EHR, PHR, PACS)Clinicians and patients find the record or image they need without asking twice.
- A Canadian health-tech startupPatients track their vitals, medicines, symptoms and mood in one app, and share their journey with their care team.
- A US-based global clinical research firmVaccine study participants report their side effects in an app, and can leave the study with their data fully removed.
Facts and figures from the project records; nothing added.
Want this for your business?
Tell us what you run or what you're building. Our AI assistant, Ask Unthinkable, helps you define your requirements, then connects you with a senior AI engineer.
Send us a note instead
An AI agent. This prototype uses prepared answers and sends nothing.
We use essential cookies to run this site. With your consent we also use analytics cookies to see which pages help. Privacy policy