The Mater Misericordiae University Hospital has become the first hospital in Ireland to use artificial intelligence (AI) across its radiology department in order to accelerate emergency care.
The Dublin hospital announced that, since it introduced the new software earlier this year, more than 15,600 patient scans have been analysed. Over 700 pathologies were correctly flagged by AI within two-three minutes of the scan being completed, with 500 intracranial haemorrhages and 200 pulmonary emboli being identified.
Mater consultant radiologist Prof Peter MacMahon, said, “our experiences have underscored the tangible benefits of AI, notably in expediting critical diagnoses and reducing turnaround times by rapidly flagging anomalies detected in scans.”
On out-patient scans, 50 pulmonary emboli were also flagged where the scans were being performed to assess other medical conditions. The overall accuracy of the software in real Irish clinical practice has been deemed to be highly sensitive and specific, with an accuracy rate of more than 90 per cent.
The screening platform, made by Aidoc, operates on an ‘always-on’ basis, meaning it is constantly running in the background in order to analyse medical imaging data, flag urgent findings, and highlight cases that should be prioritised and brought to the immediate attention of consultants.
Before being fully deployed across the radiology department, the software was trialled from April to August this year. It is now used alongside the work of radiologists at the hospital in emergency settings, ensuring that human scrutiny and verification remains at the centre of reading the scans.
The hospital has implemented AI assistance on CT pulmonary angiograms, incidental pulmonary embolism notification on CT scans, intracranial haemorrhage detection on CT head scans and fracture detection on cervical spine CT scans. It plans to trial further specialist AI tools, focusing on the analysis of bone and chest X-rays, in its emergency department early next year.
Source: Irish Medical Times