I just realized I never finished this serie of articles!
In today's article, we'll take a look at the production process that extracts the ICD-10 diagnoses most similar to our text, so we can select the most appropriate option from our frontend.
Looking for diagnostic similarities:
From the screen that shows the diagnostic requests received in HL7 in our application, we can search for the ICD-10 diagnoses closest to the text entered by the professional.
Since the introduction of Embedded Python there has always been doubt about its performance compared to ObjectScript and on more than one occasion I have discussed this with
It is very common in the daily life of IRIS or Health Connect users that it is necessary to install new instances or update the ones they already have and in many cases it is not these same users who carry out the installation, but rather systems personnel who often do not take into account the particularities of the assignment of permissions necessary for the installation.
I have recently been deploying an IRIS for Health image on a Docker with a preconfigured Webgateway image and I have come across the problem of the SSL configurations that allow us to connect to the IRIS instance using HTTPS and going through our Webgateway.
Until now I had always deployed IRIS for Health with a Community license, which still has the Private Web Server installed, so I only needed to configure the Webgateway connection with the deployed IRIS instance:
Welcome to the third and final publication of our articles dedicated to the development of RAG applications based on LLM models. In this final article, we will see, based on our small example project, how we can find the most appropriate context for the question we want to send to our LLM model and for this we will make use of the vector search functionality included in IRIS.
I'm testing some functionalities about Foreign Tables and it works smoothly with PostgreSQL database, but I found out an issue with MySQL database, I followed the documentation:
In the previous article we presented the d[IA]gnosis application developed to support the coding of diagnoses in ICD-10. In this article we will see how InterSystems IRIS for Health provides us with the necessary tools for the generation of vectors from the ICD-10 code list using a pre-trained language model, its storage and the subsequent search for similarities on all these generated vectors.
With the introduction of vector data types and the Vector Search functionality in IRIS, a whole world of possibilities opens up for the development of applications and an example of these applications is the one that I recently saw published in a public contest by the Ministry of Health from Valencia in which they requested a tool to assist in ICD-10 coding using AI models.
How could we implement an application similar to the one requested? Let's see what we would need:
Finally and with a little delay, we conclude this series of articles about our Workflow Engine by showing an example of the connection that we could make from a mobile application.
Reviewing the different articles that I have published, I realized that I needed to explain a very practical functionality within our EMPI (Enterprise Master Patient Index) and it is none other than the notification of registrations and links to systems external to the EMPI.
In our previous article we presented the general concepts as well as the problem that we wanted to solve by using the task engine integrated in InterSystems IRIS, in today's article we will see how we configure an interoperability production to provide a solution.
Workflow Engine Configuration
First we are going to define the roles of the tasks that we are going to manage, in our example we are going to define two types:
For some time I have been planning to do some type of proof of concept with the Workflow functionality, which, like so many other functionalities present in IRIS, tends to go quite unnoticed by our clients (and for which I say mea culpa). That's why I decided a few days ago to develop an example of how to configure and exploit this functionality by connecting it with a user interface developed in Angular.
As you have seen in the latest community publications, InterSystems IRIS has included since version 2024.1 the possibility of including vector data types in its database and based on this type of data vector searches have been implemented. Well, these new features reminded me of the article I published a while ago that was based on facial recognition using Embedded Python.
We recently uploaded to OpenExchange a small application that I developed a while ago (and that @Jose-Tomas Salvador improved and refined) that I often use when I need to generate large volumes of HL7 messaging.
As most of you probably already know, since approximately the end of 2022 InterSystems IRIS included the columnar storage functionality to its database, well, in today's article we are going to put it to the test in comparison to the usual row storage.
We conclude this series of SMART On FHIR articles with Auth0 and InterSystems IRIS FHIR Repository by reviewing our application developed in Angular 16.
Let's remember what the architecture defined for our solution is like:
Our front-end application corresponds to the second column and as you can see it will be in charge of two things:
In the last article we presented the architecture of our SMART On FHIR project, so it's time to get down to business and start configuring all the elements that we are going to need.
We will first start with Auth0.
AUTH0 configuration
We will start by creating an Auth0 account with a valid email, once registered we will have to create our first application, and we will do it from the menu on the left:
Open Exchange app
All posts
.png)
.png)
