Patients experiencing pain and swelling in their limbs following an accident will often have X-Rays in the Emergency Department. The doctor will look at these X-rays for signs of a fracture and then treat the patient accordingly. The X-Ray specialist elsewhere in the hospital will also look at these X-Rays and write a report. However, this report may not be available until after the patient and doctor have both gone home. If the X-Ray specialist’s report identifies a fracture, other staff working in the Emergency Department will need to go back and double-check the patient’s records to make sure the fracture was picked up by the treating doctor and that the patient was appropriately treated.
The procedure for checking X-Ray reports and checking that the patient was appropriately treated is laborious and time consuming. Moreover, due to resourcing problems, it is often done days after the patient’s initial presentation to the Emergency Department. A more timely and efficient process is required.
The results of this study will ensure that patients have a safe, timely and efficient process for checking that their fractures are not missed.
Hassanzadeh, H., Nguyen, A., Karimi, S. and Chu, K., 2018. Transferability of artificial neural networks for clinical document classification across hospitals: a case study on abnormality detection from radiology reports. Journal of biomedical informatics, 85, pp.68-79.
Chu, K., Martin, S., Wagholikar, A., Zuccon, G., Nguyen, A., Keijzers, G., O'Dywer, J., Crilly, J., Philips, N. and Greenslade, J., 2013. Developing computer software to read limb X-rays reports. Emergency Medicine Australasia, 25.
Zuccon, G., Wagholikar, A.S., Nguyen, A.N., Butt, L., Chu, K., Martin, S. and Greenslade, J., 2013. Automatic classification of free-text radiology reports to identify limb fractures using machine learning and the snomed ct ontology. AMIA Summits on Translational Science Proceedings, 2013, p.300.
Wagholikar, A., Zuccon, G., Nguyen, A., Chu, K., Martin, S., Lai, K. and Greenslade, J., 2013. Automated classification of limb fractures from free-text radiology reports using a clinician-informed gazetteer methodology. The Australasian medical journal, 6(5), p.301.
Wagholikar, A.S., Lawley, M.J., Hansen, D.P. and Chu, K., 2011. Identifying symptom groups from Emergency Department presenting complaint free text using SNOMED CT. In AMIA Annual Symposium Proceedings (Vol. 2011, p. 1446). American Medical Informatics Association.
-Chu K. “Automated reconciliation of radiology reports & discharge summaries”, 2015 Australian e-Health Research Colloquium, 31 March 2015, Brisbane, Queensland, Australia
-Koopman, Bevan; Zuccon, Guido; Wagholikar, Amol; Chu, Kevin; O'Dwyer, John; Nguyen, Anthony. Automated Reconciliation of Radiology Reports and Discharge Summaries. In: AMIA; 14-18 November 2015; San Francisco. AMIA; 2015. 775-784.
A/Prof Kevin Chu
Dr James Lind
Dr Amol Walholikar
Prof Julia Crilly
Mr John O’Dwyer
Dr Natalie Phillips
A/Prof Jaimi Greenslade
Prof Gerben Keijzers
Dr Anthony Nguyen
Dr Michael Lawley