Skip to content

IOMED Medical Language API

Today a very large number of patient records is produced in the healthcare system. Patient records are mostly in electronic format and written by health personnel. They describe symptoms, diagnosis, treatments and outcomes of the treatments, but they may also contain nursing narratives or daily notes.

These records are seldom reused, due to a lack of tools to process them adequately. There is a plethora of reasons to unlock and reuse the content of electronic patient records, since they contain valuable information about a vast number of patients.

IOMED's Medical Language API is a simple API allowing organizations, developers and researchers to extract and codify medical concepts from unstructured medical text in Spanish.


Currently we only support Spanish, with limited support for Catalan. If you would like to use this API in some other language, we would be interested in hearing from you.


This API allows you to easily extract medical concepts from unstructured text, allowing you to either analyze existing medical text, or build applications that automatically recognize medical concepts. Some common use cases are:

  • Feature extraction: use the output of the API to add new features to you Machine Learning models.
  • Data standarization: use our API to obtain codified information, reusable accross different information systems.
  • Hidden data mining: turn large amounts of medical text into something useful for analysis.
    • Obtain statistics on medications, symptoms, diseases, procedures...
    • Perform profiling and clusterization of patients, find risk groups, predict outcomes...
    • Automatically monitor patients or groups of patients.
  • Conversational interfaces: use the API as an out of the box Natural Language Understanding for medical topics.


Not just diagnostics

IOMED Medical Language API is able to retrieve a large variety of medically relevant concepts from medical text. It is not limited to diagnostics: you will be able to retrieve diseases, anatomical parts, substances, symptoms, diagnostic procedures, therapeutic procedures, population groups and more. Please find an exhaustive list here.



When a concept is found in medical text, its context is important: is the concept negated? does the disease belong to the patient, or to a relative?

IOMED Medical Language API is aware of the context, and will take it into account when structuring text. It is currently able to process negations and mentions of family history, and we are continuously working to add more context awareness. You can find technical information about it here.



We cannot unveil the meaning of the text by only looking at individual medical concepts. Rather, we have to understand how these concepts are related among them. In a sentence like "LDL 64 mg/dl", it is of little use to find "LDL" and "64 mg/dl" if you are not able to understand that the latter is a quantifier of the former. IOMED Medical Language API is able to find not only concepts, but also relations between concepts. Find more about it here.



The API includes a deep learning model to resolve homonyms: terms which are spelled the same way but have different meanings depending on the context.

In this case the context indicates that "gemelo" should is a "Group" (i.e. a person): gemelo_group While in this case it is a muscle: gemelo_anatomy

Help us improve the docs

Did you spot a mistake or came across any unclear explanation? We always appreciate suggestions. Send us an email.