InterSystems IntegratedML is an all-SQL machine learning (ML) module for InterSystems IRIS or IRIS for Health that: - Gives users the ability to create, train and deploy powerful models from simple SQL syntax without requiring data scientists. - Wraps "best of breed" open source and proprietary "AutoML" frameworks including DataRobot. - Focuses on easy deployment to IRIS, so you can easily add machine learning to your applications.
Diabetes can be discovered from some parameters well known to the medical community. In this way, in order to help the medical community and computerized systems, especially AI, the National Institute of Diabetes and Digestive and Kidney Diseases published a very useful dataset for training ML algorithms in the detection/prediction of diabetes. This publication can be found on the largest and best known data repository for ML, Kaggle at https://www.kaggle.com/datasets/mathchi/diabetes-data-set.
I've been playing with IntegratedML and have created a model and trained the model. When I try to use PREDICT or PROBABILITY statements in an SQL query, I get the following error:
[SQLCODE: <-400>:<Fatal error occurred>]
[%msg: <PREDICT execution error: ERROR #5002: ObjectScript error: <OBJECT DISPATCH>%LoadModel+31^%ML.AutoML.TrainedModel.1 *<class 'AttributeError'>: 'str' object has no attribute 'decode' - >]
Here's an example of the sequence of steps I've followed that lead to the error:
Prediction is a critical to the Maternal healthcare. The Health Dataset Application (https://openexchange.intersystems.com/package/Health-Dataset) has 10 real health datasets to predict the most important diseases and health problems, including Maternal Risk.
This article detail the steps to predict Maternal Risk using the InterSystems IRIS IntegratedML. This is a technology of InterSystems to do predictions using SQL Commnands! Great!
Have you tried the InterSystems learning platform lab for IRIS IntegratedML? In that lab you can train and test a model on a readmission dataset and be able to predict when a patient will be readmitted or not, or calculate its probability of being readmitted.
You can try it without any installation on your system, all you have to do is start a virtual lab environment (Zeppelin) and play it around!
The InterSystems IRIS IntegratedML feature is used to get predictions and probabilities using the AutoML technique. The AutoML is a Machine Learning technology used to select the better Machine Learning algorithm/model to predict status, numbers and general results based in the past data (data used to train the AutoML model). You don't need a Data Scientist, because the AutoML it will test the most common Machine Learning algorithms and select the better algorithm to you, based in the data features analysed. See more here, in this article.
https://www.youtube.com/embed/q8lC2a6eFgY [This is an embedded link, but you cannot view embedded content directly on the site because you have declined the cookies necessary to access it. To view embedded content, you would need to accept all cookies in your Cookies Settings]
I'd like to know if the VALIDATE MODEL statement in IntegratedML performs a cross validation (CV) procedure internally. If it doesn't, is there a ready to use method for CV?
Talking with a friend of mine, Machine Learning specialist @Renato Banzai, he brought one of the biggest challenges faced by companies nowadays: deploying ML/AI in live environments.
https://www.youtube.com/embed/BRyWD39Sado [This is an embedded link, but you cannot view embedded content directly on the site because you have declined the cookies necessary to access it. To view embedded content, you would need to accept all cookies in your Cookies Settings]
https://www.youtube.com/embed/f7A-wbNkIic [This is an embedded link, but you cannot view embedded content directly on the site because you have declined the cookies necessary to access it. To view embedded content, you would need to accept all cookies in your Cookies Settings]
Continued from the previous Part I ... In part I, we walked through traditional ML approaches on this Covid-19 dataset on Kaggle.
In this Part II, let's run the same data & task, in its simplest possible form, through IRIS integratedML which is a nice & sleek SQL interface for backend AutoML options. It uses the same environment.
Recently I noticed a Kaggle dataset for the prediction of whether a Covid-19 patient will be admitted to ICU. It is a spreadsheet of 1925 encounter records of 231 columns of vital signs and observations, with the last column of "ICU" being 1 for Yes or 0 for No. The task is to predict whether a patient will be admitted to ICU based on known data.
https://www.youtube.com/embed/KUjcpp5_a0w [This is an embedded link, but you cannot view embedded content directly on the site because you have declined the cookies necessary to access it. To view embedded content, you would need to accept all cookies in your Cookies Settings]
This is the second post of a series explaining how to create an end-to-end Machine Learning system.
Exploring Data
The Intersystem IRIS already has what we need to explore the data: an SQL Engine! For people who used to explore data in
csv or text files this could help to accelerate this step. Basically we explore all the data to understand the intersection
(joins) which should help to create a dataset prepared to be used by a machine learning algorithm.
https://www.youtube.com/embed/3-YSnFQnMLU [This is an embedded link, but you cannot view embedded content directly on the site because you have declined the cookies necessary to access it. To view embedded content, you would need to accept all cookies in your Cookies Settings]
Following up the previous part, it's time to take advantages for IntegratedML VALIDATION MODEL statement, to provide information in order to monitor your ML models. You can watch it in action here
https://www.youtube.com/embed/UowONCJzXVo [This is an embedded link, but you cannot view embedded content directly on the site because you have declined the cookies necessary to access it. To view embedded content, you would need to accept all cookies in your Cookies Settings]
By date
Open Exchange app
.png)