Finding Arthritis, Breast Cancer Diagnosis with Ultrasound, and Predicting Psychosis Among Cannabis Users
Artificial Intelligence in Health Care Weekly Roundup #11
“I believe that at the end of the century the use of words and general educated opinion will have altered so much that one will be able to speak of machines thinking without expecting to be contradicted.”
― Alan Turing, Computing machinery and intelligence
1) Predicting Arthritis from MRI
Arthritis is inflammation of the joints. With time, inflammation causes the cartilage of the joint to break down. Eventually, the cartilage wears away and bone is left rubbing on bone….ouch. Predicting the development of arthritis is a valuable tool that can be accomplished using MRI. These researchers evaluated the ability of a machine learning algorithm to classify in vivo magnetic resonance images of human articular cartilage for development of osteoarthritis. Their approach allowed for the successful detection of images that progress to arthritis with 75% accuracy.
2) Breast Cancer Diagnosis with Ultrasound
Ultrasound is one of the easiest, least invasive ways to understand what is happening inside the body. Unfortunately, the images produced with ultrasound are highly dependent on the person holding the ultrasound probe. Breast tumors are usually picked up on ultrasound but it can be challenging to know if the tumor is a dangerous cancer or a benign growth. Researchers in this study developed a machine learning based classifier to sort benign vs. malignant breast tumors using ultrasound with accuracy as high as 96.6%.
3) Predicting Psychosis Among Cannabis Users
With recent de-regulation of marijuana there has been significant press on the cannabis industry. Harms and benefits of marijuana have been widely debated and researched. However, little evidence is available on how to identify those individuals most at risk to experiencing the harmful effects of marijuana. Psychosis, is a rare but well known side-effect of weed, especially among the younger, susceptible population. These researchers have harnessed the power of machine learning to help identify people most at risk to developing a psychotic episode from puffing a joint.