AUG 31, 2019 6:09 PM PDT

AI Not Ready To Predict Acute Kidney Injury

WRITTEN BY: Amanda Mikyska

Image source: Siemens Healthineers

 

An international group of scientists from the U.S. and U.K. published new research in Nature about the effectiveness of AI in predicting Acute Kidney Injury (AKI).  

AKI is a blockage of waste that is a deadly complication for hospital patients.  Using AI, the researchers aimed to able to detect early signs of the condition before traditional methods.  Giving hospitals a way to detect symptoms earlier could save lives and prevent permanent damage.  

The group gathered data from 703,782 patients, all between the ages of 18 and 90, who had suffered some form of AKI.  First, the data was fed to algorithm, which learned the earliest signs of an impeding AKI.  Then the researchers reran the algorithm as a prediction method to see how early and accurately it could predict the kidney condition.  

Results show that the technology still needs some work, with prediction accuracy only reaching 90% in the most severe cases.  In less severe the prediction accuracy slipped to 55.8%, and the algorithm resulted in two falsely predictions for every correctly predicted occurrence.  

The technology has the potential to save hospitals time, and therefore save lives.  AI was able to predict severe cases 48 hours in advance of traditional tests, giving hospital staff critical time to prevent or minimize injury.  

AKI usually occurs in hospitals, following other major health procedures.  Injury is caused by a blockage of waste which leaves the kidneys unable to balance fluid in the body, and ultimately damages other organs.  AKI progresses within hours or days, and emergency action must be taken to avoid permanent damage or death.

 

Sources: Nature, National Kidney Foundation, MedicalExpress

About the Author
  • Amanda graduated from the University of Massachusetts Boston with a degree in Biology. After working in research on creating biochemicals from genetically engineered yeast, she started freelance science writing while traveling the world. Now, Amanda is a Lab Manager and Research Assistant at the the University of Central Florida, studying the molecular phylogeny of parasitic wasps. She writes about the latest research in Neuroscience, Genetics & Genomics, and Immunology. Interested in working on solutions for food/water security, sustainable fuel, and sustainable farming. Amanda is an avid skier, podcast listener, and has run two triathlons.
You May Also Like
APR 21, 2020
Drug Discovery & Development
Researchers Develop COVID-19 Nasal Spray Vaccine
APR 21, 2020
Researchers Develop COVID-19 Nasal Spray Vaccine
Researchers from the University of Waterloo in Canada are working on a DNA-based vaccine for COVID-19 that can be applie ...
MAY 17, 2020
Genetics & Genomics
How Non-Coding Genomic Regions Influence Autoimmune Disease
MAY 17, 2020
How Non-Coding Genomic Regions Influence Autoimmune Disease
Scientists have gained new insight into autoimmune and allergic disorders.
MAY 19, 2020
Drug Discovery & Development
COVID-19 Vaccine On Track for Late 2020
MAY 19, 2020
COVID-19 Vaccine On Track for Late 2020
Moderna, a biotechnology company based in Massachusetts, has released information on its vaccine against COVID-19 from i ...
JUN 18, 2020
Neuroscience
How Climate Change Worsened Zika Virus Defects
JUN 18, 2020
How Climate Change Worsened Zika Virus Defects
Image: Pixabay   In 2015 a massive outbreak of the Zika virus started in Brazil and spread across 33 countries. The ...
JUL 09, 2020
Immunology
Why COVID Herd Immunity Is Important but Impossible
JUL 09, 2020
Why COVID Herd Immunity Is Important but Impossible
The number of confirmed COVID-19 cases worldwide is steadily approaching 12 million. Meanwhile, despite accelerated time ...
JUL 13, 2020
Genetics & Genomics
New Therapeutic Targets For Lupus Are Identified
JUL 13, 2020
New Therapeutic Targets For Lupus Are Identified
Advances in computational and genetic technologies have enabled scientists to search the genome to look for places where ...
Loading Comments...