[ad_1]
A team of US researchers has said that it should be tested in a wide range of populations as the deep learning models may fall short.
The findings should give rise to the question of how they are performing in the field of clinical performance. They are being deployed, observed by the Icahn School of Medicine at Mount Sinai School of Medicine.
A tool for the detection of pneumonia on chest X-rays. The results of this study are presented in the following table.
These findings suggest that the deep learning models may not perform as accurately as expected.
"Senior trained author Eric Oermann, MD, Instructor in Neurosurgery at the Icahn School of Medicine." Mount Sinai.
To reach this understanding, the researchers have identified pneumonia in 158,000 X-rays across three medical institutions – the National Institutes of Health, Mount Sinai Hospital and Indiana University Hospital.
In three out of five comparisons, the convolutional neural networks' (CNNs) performance in diagnosing diseases on X-rays from hospitals outside of its own network was significantly lower than that of the original health system.
However, CNNs were able to detect the hospital system when X-ray was acquired with a high-degree of accuracy, and cheated at their predictive task-based pneumonia at the training institution.
"If AI systems are to be used for medical diagnosis, they must be adapted to carefully consider clinical questions," explained Study's First Author John Zech .
–IANS
na / vm
(This story has been edited by Business Standard staff and is self-generated from a syndicated feed.)
[ad_2]
Source link
