Artificial intelligence system developed by researchers quickly diagnoses and classifies brain haemorrhages, providing the basis of its decisions from relatively small image datasets.
"Some critics suggest that Machine Learning (ML) algorithms cannot be used in clinical practice because the algorithms do not provide justification for their decisions," said co-lead author Sehyo Yune from the Massachusetts General Hospital (MGH) in the US.
Bleeding (Hemorrhagic) Diathesis
Bleeding diathesis is a severe condition characterized by an increased tendency of the body to bleed.
Advertisement
‘The new model system is an accurate in detecting and classifying intracranial haemorrhages.’
Tweet it Now
To train the system, the research team began with 904 head CT scans, each consisting of around 40 individual images that were labelled by a team of five neuroradiologists as to whether they depicted one of the five haemorrhage subtypes, based on the location within the brain, or no haemorrhage.
To improve the accuracy of this deep-learning system, the team built in steps mimicking the way radiologists analyse images, suggested the study published in the journal Nature Biomedical Engineering.
![Artificial intelligence in Healthcare]( "Artificial intelligence in Healthcare")
Artificial intelligence (AI) in healthcare is the discipline using data intensive computer based solutions to improve patient care and outcome.
Once the model system was created, the team tested it on two separate sets of CT scans -- a retrospective set taken before the system was developed, consisting of 100 scans with and 100 without intracranial haemorrhage, and a prospective set of 79 scans with and 117 without haemorrhage, taken after the model was created.
In its analysis of the prospective set, it proved to be even better than non-expert human readers, they added.
Source: IANS
Artificial intelligence in Healthcare
Artificial intelligence (AI) in healthcare is the discipline using data intensive computer based solutions to improve patient care and outcome.
Advertisement
Once the model system was created, the team tested it on two separate sets of CT scans -- a retrospective set taken before the system was developed, consisting of 100 scans with and 100 without intracranial haemorrhage, and a prospective set of 79 scans with and 117 without haemorrhage, taken after the model was created.
In its analysis of the prospective set, it proved to be even better than non-expert human readers, they added.
Source: IANS
Blood Type O Could be a Potential Risk Factor for Hemorrhage
Blood type O was associated with high death rates in severe trauma patients, shows study.
Advertisement
Artificial Intelligence Helps Victims of Abuse to Disclose Traumatic TestimonyArtificial intelligence could be valuable tool to help young victims disclose traumatic testimony, said study. | Advertisement
|
Advertisement
Recommended Reading
Latest News on IT in Healthcare
Although the body can often heal minor injuries on its own, this is not always the case for more serious wounds such as cuts, burns, and scrapes.
The expanding AI market in healthcare reflects the demand for new solutions that can enhance patient engagement and reduce healthcare costs.
Artificial intelligence helps doctors gain fresh insights from the data generated by the healthcare system leading to more effective diagnosis and treatment.
The newly discovered AI-based tool has the potential to enhance diagnosis of patients with brain tumors.
Although medical implants can be life-changing, the immune system often perceives them as foreign objects.