People living with rare diseases are helping define and test technology built around their everyday needs, from an adjustable support glove to AI-assisted tools for gaming and managing medical records. The work shows how patient feedback can shape useful designs, while also exposing the distance between a promising prototype and something people can rely on day to day.
Watch Desk analysis
What happened
At an open-source innovation event in Hangzhou, developers and patients discussed projects based on specific needs, including medication reminders, tools for people with restricted vision and adaptations for physical disabilities. The Global Times describes one glove project that went through several redesigns after feedback on fit, ventilation, appearance and how much assistance users needed.
The article also describes Feng Jinyuan, a gamer with severely limited movement, using an AI platform to help build a customised on-screen gaming keyboard. He described the functions he wanted, tested the generated code and requested changes. He said the basic functions took about two days to develop; he later shared the code on GitHub.
Another project, for people with facioscapulohumeral muscular dystrophy, brings together health records and daily observations, extracts text from reports, arranges information on a disease timeline and produces a PDF summary for appointments. Its team says an AI question-and-answer feature draws on medical reference materials. A developer reportedly adapted the project’s code for people with haemophilia.
Why it matters
These examples make a useful case for involving the people who will use a tool in deciding what it should do. A design that works in a demonstration may still need changes for comfort, changing needs or ordinary tasks. Shared code can help another group get started, but it does not supply the time, expertise and testing needed to keep a project going.
The article also draws an important line between AI helping someone build or organise a tool and evidence that the tool is clinically effective. One project remains at the demonstration stage, with its team seeking help on medical-data requirements and public deployment. A well-targeted prototype is a beginning, not a health service.
Our read
The strongest idea here is not that AI can solve rare disease. It is that patients can help set the brief, test what gets built and say where it falls short. That is less glamorous than a grand unveiling, and far more likely to produce something a person can actually use.
For developers, the practical lesson is to involve users throughout design, not just at the testing stage. For everyone else, look for whether projects move beyond a one-off event: who maintains them, how they handle sensitive health information and whether users find them useful over time.
What to watch
- Whether the glove and other assistive designs receive continued development and testing with users.
- Whether the health-record project finds the expertise it needs to address medical-data requirements.
- Whether shared projects lead to tools that people can maintain and use in daily life.
Discussion spark: Should assistive technology projects be judged first by whether they solve a real user’s problem, or by whether they can meet the standards needed for wider deployment?
Sources and evidence
Watch Desk is operated by WittyWires as an independent cross-cutting AI news tracker. It does not speak for the organisations or people it covers.