Browsing Category: AI

EEG + AI assists drivers in manual and autonomous cars

Nissan’s Brain-to-Vehicle (B2V) technology will enable vehicles to interpret signals from a driver’s brain. The company describes two aspects of the system — prediction and detection, which depend on a driver wearing EEG electrodes: Predicton: By detecting, via the brain, that the driver is about to move, including turning the steering wheel or pushing the […]

Robots visualize actions, plan, with out human instruction

Sergey Levine and UC Berkeley colleagues have developed robotic learning technology that enables robots to visualize how different behaviors will affect the world around them, with out human instruction.  This ability to plan, in various scenarios,  could improve self-driving cars and robotic home assistants. Visual foresight allows robots to predict what their cameras will see if they perform […]

AI detects pneumonia from chest X-rays

Andrew Ng and Stanford colleagues used AI to detect pneumonia from x-rays with similar accuracy to trained radiologists.  The CheXNet model analyzed 112,200 frontal-view X-ray images of 30,805 unique patients released by the NIH (ChestX-ray14.) Deep Learning algorithms also detected14 diseases including fibrosis, hernias, and cell masses, with fewer false positives and negatives than NIH […]

AI detects bowel cancer in less than 1 second in small study

Yuichi Mori and Showa University colleagues haved used AI to identify bowel cancer by analyzing colonoscopy derived polyps in less than a second. The  system compares a magnified view of a colorectal polyp with 30,000 endocytoscopic images. The researchers claimed  86% accuracy, based on a study of 300 polyps. While further testing the technology, Mori said that […]

Machine learning improves breast cancer detection

MIT’s Regina Barzilay has used AI to improve breast cancer detection and diagnosis. Machine learning tools predict if a high-risk lesion identified on needle biopsy after a mammogram will upgrade to cancer at surgery, potentially eliminating unnecessary procedures. In current practice, when a mammogram detects a suspicious lesion, a needle biopsy is performed to determine if […]

Detecting dementia with automated speech analysis

WinterLight Labs is developing speech analyzing algorithms to detect and monitor dementia and aphasia.  A one minute speech sample is used to determine the lexical diversity, syntactic complexity, semantic content, and articulation associated with these conditions. Clinicians currently conduct similar tests by interviewing patients and writing their impressions on paper. The company believes that their […]

AI driven, music-triggered brain state therapy for pain, sleep, stress, gait

The Sync Project has developed a novel, music-based, non-pharmaceutical approach to treating pain, sleep, stress, and Parkinson’s gait issues. Recent studies showed Parkinson’s patients improved their gait when listening to a song with the right beat pattern, and post surgery patients used 1/3 the amount of self-administered morphine after listening to an hour of music. […]

Sensor, data, and AI-driven primary care

Forward has brought advanced technology to well-care. Patient/Members are integrated into the practice with a baseline  screening via body scans, blood and genetic tests.  They are then given consumer and medical wearables, which work with proprietary algorithms, for continuous monitoring (and access to data), personalized treatment, and emergency alerts. Physical exam rooms display all of the data […]

Machine learning tools predict heart failure

Declan O’Regan and MRC London Institute of Medical Sciences colleagues believe that AI can predict when pulmonary hypertension patients require more aggressive treatment to prevent death. In a recent study,  machine learning software automatically analyzed moving images of a patient’s heart, captured during an MRI. It then used  image processing to build a “virtual 3D heart”, […]