8 new hospital applications for machine learning: AWS Textract, an algorithm predicting ICU outcomes & more

Here are eight studies and product launches from the month of May that demonstrate the many uses of machine learning artificial intelligence in clinical settings:

1. Amazon Web Services' Textract service uses machine learning to extract information from any document, including hospital claims, patient forms and more.

2. An algorithm developed at the University of Copenhagen analyzes an intensive care unit patient's long-term disease history to better predict their chances of survival.

3. Franklin, Tenn.-based AI company Digital Reasoning created a machine learning system that analyzes written radiology reports to identify potentially cancerous lung nodules.

4. Researchers from the University of Michigan trained a predictive model to identify how patients with Crohn's disease will respond to long-term usage of the popular treatment ustekinumab.

5. An algorithm developed at the University of California was able to classify amyloid plaques in close-up images of brain tissue with a level of accuracy equal to that of a human neuropathologist.

6. A study presented at the International Conference on Nuclear Cardiology and Cardiac CT described a machine learning tool with the ability to predict a patient's risk of developing a potentially lethal arrhythmia after experiencing heart failure.

7. The LogitBoost algorithm can predict death and heart attack with more than 90 percent accuracy by analyzing cardiac imaging data.

8. A machine learning system called ARTICA significantly outperformed cardiologists in determining whether further cardiac imaging tests are unnecessary for patients with stable chest pain.

More articles about AI:
Facial recognition tech can be used to monitor ICU patient safety
Most oncologists expect AI to improve patient outcomes in coming years, report finds: 3 notes
IBM Watson Health's clinical support in cancer care proven by multiple studies

© Copyright ASC COMMUNICATIONS 2020. Interested in LINKING to or REPRINTING this content? View our policies by clicking here.


Featured Content

Featured Webinars

Featured Whitepapers