LEARN FROM THESE YOUTUBE VIDEOS
... AND LEARN MORE FROM THESE ADDITIONAL VIDEOS
REVIEW THESE INFORMATIVE ARTICLES FROM 2017 – AND READ THOSE THAT INTEREST YOU
AI used to treat Bipolar Disorder in an app that could revolutionize medicine (AI/Psychiatry - 2017-06 - ScienceBlog)
David Fleck, an associate professor at the UC College of Medicine, and his co-authors used artificial intelligence called “genetic fuzzy trees” to predict how bipolar patients would respond to lithium. The best of 8 common models used in treating bipolar disorder predicted who would respond to lithium treatment with 75 percent accuracy. By comparison, the AI model was 100% accurate, and even predicted the actual reduction in manic symptoms after lithium treatment with 92% accuracy. Unlike other types of AI, fuzzy logic can describe in simple language why it made its choices. The model could help personalize medicine to individual patients, making health care both safer and more affordable. Fewer side-effects mean fewer hospital visits, less secondary medication, and better treatments.
Deep-learning Neural Network accurately forecasts onset of Alzheimer’s (AI/Alzheimer's - 2017-04 - MIT Technology Review)
South Korean researchers have developed a deep-learning neural network that can identify, with 81% accuracy, those likely to be diagnosed with Alzheimer’s in the next three years. The evidence continues to suggest that deep-learning machines can spot complex conditions earlier and more accurately than humans.
Machine Learning algorithm beats ACC-AHA heart attack risk guidelines by 7.6% (AI/Cardiology - 2017-04 - Engadget)
A team of researchers from the UK University of Nottingham has developed a machine-learning algorithm that can predict your likelihood of having a heart attack or stroke better than a doctor, using ACC/AHA guidelines. The neural network algorithm beat the guidelines by 7.6% while raising 1.6% fewer false alarms.
Google Deep Learning AI diagnoses cancer better than pathologists (AI/Pathology - 2017-03 - Int'l Business Times)
Google has been working on an advanced image-recognition system for several years, initially for the autonomous car project, now for cancer diagnosis. Recently the AI system was pitted against an experienced expert pathologist to examine slides in an unlimited time frame. While the human being achieved 73 percent accuracy, by the end of tweaking, GoogLeNet scored a smooth 89 percent accuracy.
REVIEW THESE INFORMATIVE ARTICLES FROM 2016 – AND READ THOSE THAT INTEREST YOU
Smart microscope detects blood infections with 93% accuracy (AI/Microbiology - 2016-12 - FutureScope)
Microbiologists from Harvard’s Beth Israel Deaconess Medical Center have developed a smart microscope that employs AI to accurately diagnose deadly blood infections. The microscope is enhanced with machine learning technology, and initial tests achieved 93% accuracy.
AI can detect bowel cancer in less than a second with 94% accuracy (AI/Radiology - 2016-10 - ZDNet)
Researchers from Showa University in Yokohama, Japan have built software that can detect bowel cancer in less than a second. In recently-conducted trials, the AI-powered system was able to spot colorectal adenomas — which are benign tumours that can evolve into cancer — from magnified endoscopic images. The images were matched against 30,000 others that were used for machine learning. The system analyzed more than 300 colorectal adenomas in 250 patients, taking less than a second to assess each magnified endoscopic image and determine the malignancy of the tumours with 94 percent accuracy.
AI reads mammograms with 99% accuracy (AI/Radiology - 2016-09 - Futurism)
A team from the Houston Methodist Research Institute has developed artificial intelligence software that analyzes mammograms for breast cancer with 99% accuracy. This could help keep women from undergoing unnecessary biopsies and would shield them from the agony of false positives.