Gizmorama - August 29, 2018
I believe that artificial intelligence will either save humanity or end it. The first story seems to think the former. AI is being used to detect often-undetected cancer tumors. I'm all for it.
Learn about this and more interesting stories from the scientific community in today's issue.
Until Next Time,
P.S. Did you miss an issue? You can read every issue from the Gophercentral library of newsletters on our exhaustive archives page. Thousands of issues, all of your favorite publications in chronological order. You can read AND comment. Just click GopherArchives
*- Artificial intelligence detects often-undetected cancer tumors -*
Researchers have developed an artificial intelligence system to detect lung cancer on scans that radiologists fail to detect.
The AI method can notice specks of lung cancer with about 95 percent accuracy compared with 65 percent by radiologists, according to research conducted by the University of Central Florida's Computer Vision Research Center. The researchers published their findings in the Cornell University Library before the Medical Image Computing and Computer Assisted Intervention Society's conference next month in Granada, Spain.
Computed tomography, or CT, scans use computer-processed combinations of many X-ray measurements taken from different angles to produce cross-sectional images of specific areas of a scanned area.
"I believe this will have a very big impact," Ulas Bagci, an engineering assistant professor at UCF, said in a press release. "Lung cancer is the number one cancer killer in the United States and if detected in late stages, the survival rate is only 17 percent. By finding ways to help identify earlier, I think we can help increase survival rates."
The system is much like algorithms used in facial-recognition software that scan thousands of faces looking for a particular pattern for a match.
Researchers taught the system the technique by feeding it 1,000 CT scans from the National Institutes of Health, through a collaboration with the Mayo Clinic. They then tested their system on 888 chest CT scans.
"We used the brain as a model to create our system," said Rodney LaLonde, a doctoral candidate and captain of UCF's hockey team. "You know how connections between neurons in the brain strengthen during development and learn? We used that blueprint, if you will, to help our system understand how to look for patterns in the CT scans and teach itself how to find these tiny tumors."
The computer was taught how to ignore other tissue, nerves and masses.
The researchers plan to test the project into a hospital setting, then ideally put it on the market in two years.
"I think we all came here because we wanted to use our passion for engineering to make a difference and saving lives is a big impact," LaLonde said.
*- Paired technology easily monitors, detects atrial fibrillation -*
The advent of new technology -- pairing a mobile heart monitor and smart device app -- can detect atrial fibrillation in a more simplified manner, according to research.
Scienists studied the benefits of the smartphone monitor system, which is supported by an automated algorithm. Their findings, which were the first independent validation of the system in a clinical setting, compared it with simultaneous 12-lead ECGs and were published Tuesday in the journal HeartRhythm.
Atrial fibrillation, an irregular and often rapid heart rate, can increase the risk of stroke, heart failure and other heart-related complications.
"The ability to record your own rhythm strip and directly visualize it and share it with your physician was fictional up until a few years ago," lead investigator Dr. Khaldoun G. Tarakji, of the Cleveland Clinic Heart and Vascular Institute, said in a press release. "We live in an exciting era in which technology is evolving at an unprecedented pace."
Before the new technology, monitoring was cumbersome, limited in duration and invasive, and often required a trip to the doctor's office.
The Kardia Mobile Cardiac Monitor, which is manufactured by AliveCar, works by placing your fingers on two electrodes. It is hooked up to a smart device, enabling patients to record a 30-second rhythm strip. The KardiaMobile sells for $99, and a wearable device called KardiaBand costs $199.
For the study, researchers tested 52 patients with a median age of 68.
They ran the data from the devices through KMCM's automated rhythm analysis, which uses an algorithm specifically developed to detect AF. They compared it with the traditional 12-lead ECG recording analyzed by a doctor.
The researchers found the new technology had 96.6 percent sensitivity rate and 94.1 percent specificity for AF detection compared with physician-interpreted ECGs. Physician-interpreted KMCM recordings had 100 percent sensitivity and 89.2 percent specificity for AF detection compared with physician-interpreted ECGs,
The false negative detection rate was 3.4 percent although the automated system failed to classify some of the results as "Normal" or "Possible AF."
They found that the majority of these "unclassified" readings fell outside the predefined bounds for the algorithm -- less than 30 seconds in duration, the heart rate recorded was under 50 beats per minute or over 100 bpm, or that there was too much noise during the test.
"Given the predefined algorithm operating parameters and high rate of 'unclassified' recordings with resultant missed AF instances, this smartphone monitor's algorithm is not suited to be a replacement for physician analysis," Tarakji said. "However, given its highly accurate performance when able to provide an interpretation, it holds potential as an adjunct to clinical decision making."
Tarakji noted the new technology is beneficial but the products need to be thoroughly tested.
"As a medical community, we have a duty to test these products, assess their accuracy, and more importantly, examine their ability to change outcomes," he said. "Abundance of data could become noise if it does not come with guidance about proper management of the information. Our obligation through proper clinical studies is to provide guidance about the best use of these tools."
How to record a clean EKG with KardiaMobile from AliveCor on Vimeo.
Missed an Issue? Visit the Gizmorama Archives