× Business
TelecomHealthcareDigital MarketingERPRetailMedia and EntertainmentOil and GasFood and BeveragesMarketing and AdvertisingBanking and InsuranceMetals and MiningLegalComplianceCryptocurrency
Big DataCloudIT ServiceSoftwareMobileSecurityNetworkingStorageCyber SecuritySAPData AnalysisloTBio TechQuality AssuranceEducationE-commerceGaming and VFXArtificial Intelligencescience-and-technology
Cisco DATABASE Google IBM Juniper Microsoft M2M Oracle Red hat Saas SYMANTEC
CEO ReviewCMO ReviewCFO ReviewCompany Review
Startups Opinion Yearbook Readers Speak Contact Us

Researchers Train AI to Spot Alzheimer Disease

siliconreview Researchers Train AI to Spot Alzheimer Disease

People haven’t found any proper cure for Alzheimer’s till now, only a few studies have revealed that people can keep the disease at bay by drinking more coffee. The only thing which can prevent it is by diagnosing it at an early stage.

In the latest development, few researchers from the USA have successfully trained an AI to stop the signs of the disease in brain scans up to six years before diagnosis would normally have been given.

The collective work of the researchers was published in the journal Radiology. The study conducted by a professor from the University of California, San-Francisco revealed a possible area of treatment where ML could work in tandem with the members of hospitals.

There are a few ways to diagnose the disease; one of them can be by studying the brain’s glucose level. Currently, glucose levels in brains tissues determine the result of PET scanning, but doctors may face challenges to carry out a diagnosis if the changes taking place inside the brain are delicate, because most of the times they are with a slowly-progressing disease like Alzheimer’s.

The researchers used around 2,000 scans to teach the algorithm. Each scanwere against scans that it had never seen before.  The accuracy level of in its first outing was 92 percent. But, the info that it collected from the test led to an accuracy level of 98 percent in the second test.

The new development will not be used for actual diagnosis of the disease soon but it may turn to be an effective tool for a doctor.