Machine Learning in Healthcare: Now for Everyone
Healthcare.ai is a community with education and open source technology tools focused on increasing the national adoption of machine learning in healthcare
Machine learning for healthcare just got a whole lot easier
The healthcare.ai packages are designed to streamline healthcare machine learning. They do this by including functionality specific to healthcare, as well as simplifying the workflow of creating and deploying models.
Learn more about machine learning via the healthcare.ai community by reading and subscribing to our weekly blogs, viewing our weekly YouTube live event broadcasts, and engaging our data science team with questions and answers via email or live events.
Learn and Engage with the Data Scientists Behind Healthcare.ai
Subscribe for Weekly Notifications
What has Healthcare.ai has been used to do?
- Drive $1M plus in annual savings realized by eliminating an outsourced service line reporting solution.
- Achieve 50% reduction in central line-associated blood stream infection (CLABSI) rates at a large academic medical center.
- Improve self-pay collections using intelligent workflows across more than 150K patients per month.
- Produce literature-beating models across readmissions, infection, and finance—helping clinicians and operations to prioritize resources.
What can I do with healthcare.ai?
- Create and compare models based on your data.
- Save and deploy a model.
- Perform risk-adjusted comparisons.
- Do trend analysis following Nelson rules.
- Improve sparse data via longitudinal imputation.
- Fill in missing data via imputation.
- Deploy a model to produce daily predictions.
- Write predictions back to a database.
- Learn what factors drive each prediction.
How is it tailored to healthcare?
- Longitudinal machine learning via mixed models.
- Longitudinal imputation.
- Risk-adjusted comparisons.
Our goal with this project is to expedite adoption of ML in healthcare by building pragmatic world class tools to help anyone with access to healthcare data.
You can help in many ways:
- Try out the packages and let us know what needs improvement!
- Check out our Github repos
How do I get started?
Healthcare.ai is available in packages for both R and Python, two of the most common languages used by data scientists. If you don’t previous experience with either language, we recommend the R package as it currently has more features and R is more newbie-friendly.
How does healthcare.ai focus on healthcare?Both packages differ from other machine learning packages in that they focus on data issues specific to healthcare. This means that we pay attention to longitudinal questions, offer an easy way to do risk-adjusted comparisons, and provide easy connections and deployment to databases.
Who is healthcare.ai designed for?While data scientists in healthcare will likely find these packages valuable, the audience healthcare.ai targets are those analysts, BI developers, and SQL developers that would love to create appropriate and accurate models with healthcare data.
tl;dr: Healthcare needs practical machine learning tools; the focus on deep learning and GPUs doesn’t help the average health system. Background Google just released a paper called “Scalable and accurate deep learning for electronic health records” that has received deserved acclaim in both the machine learning (ML) and healthcare communities. This research comes from the Google Brain group and isn’t their first foray into healthcare. See, for example, their impressive work in diabetic retinopathy. In fact, it’s now common for tech giants to wade into…
Last summer we discussed the simplified interface of the 1.0 CRAN release of healthcare.ai-R, and we’re now thrilled to demo new features related to clinician guidance in the 1.2 version. We’re calling this Patient Impact Predictor (PIP). Understanding an ML model This week we’d like to highlight new functionality that allows one to go a step beyond surfacing predictions to also surface targeted interventions. Risk scores are a great first step, but prescriptive guidance is where the results of machine learning (ML) may actually catch up to the…