Documentation
Platform API
FAQ

FAQ

Bots and text analysis

  • Yes. You can build a symptom checker chatbot using Infermedica’s Platform API. That said, it would have significant limitations that one built using our Engine API might not have. If you’re interested in building a chatbot, contact us to get a better understanding of which technology would be right for you.

  • Yes. You can build a symptom checking chatbot using Infermedica’s Platform API. That said, perhaps one built using our Engine API would offer more options. For a better understanding of which technology would be right for your chatbot, contact us.

Technical

  • Infermedica Platform API is a language-independent, standard web service that can be easily integrated with any existing HTTP client using virtually all of the popular programming languages and frameworks.

  • The API can return several types of questions. For the most up-to-date list, please refer to our Navigating Question Flows section in the documentation.

  • If you are getting error 403 in response to your API call, it’s most likely because you have exceeded your monthly limit of API requests.

    Learn more about Infermedica Platform API errors by clicking the link. If that doesn’t help, please contact us.

  • Yes, it is possible. For a full guide, please refer to our Navigating Question Flows section.

  • This is not available directly in the current API version, but you could compute BMI on your side and add one of the corresponding BMI-related risk factors to the evidence about the current case.

    There are two such risk factors:

    • p_6 – BMI below 19
    • p_7 – BMI over 30

    If the computed value of the person’s BMI exceeds 30, add "p_7": "present". If the value is lower than 19, add "p_6": "present". If the value falls within the healthy range (19 < BMI < 30), it’s best to add both of these risk factors as absent to prevent the API from asking about BMI.

  • This is due to security measures. For all API calls containing less than three reported observations, the list of conditions will be limited to a single condition. For all calls with more than two observations (either present or absent), the API will return the full ranking of relevant conditions.

    In all real life situations, you will want to collect more than two pieces of evidence (e.g. two symptoms, two answers). Given that, we believe this API behavior is not a limitation for any proper application.

(Former) Engine API users

  • Yes, the Platform API still uses endpoints although the flexibility isn’t as great as with Engine API. This is offset by faster and smoother processes overall. For a list of the endpoints used in Platform API, visit our Medical Knowledge section.

  • You can still do this to an extent. That said, the configurability is a bit more limited with Platform API to increase ease of use and the speed of implementation. For more information about the differences between Platform and Engine API, visit our Platform API vs Engine API section.

  • The speed and ease of use are two very large advantages as you no longer need to have the extensive backend knowledge sometimes needed for highly configured implementations. For more information on this topic, visit our Platform API vs Engine API section.

  • We have several frontend options including a UI kit and our own frontend that can be purchased. Also, it’s worth noting that while you don’t need extensive backend knowledge, you still have to know how to use endpoints and properly connect the frontend with the backend. For more information about this, contact us.