Data analytics

Program
A case study on the challenges and opportunities in the Australian hospital sector

In the presentation Peter will present a case study on the challenges and opportunities in the Australian hospital sector. The question to be answered was…. "Can I cost and analyse medication at a patient and dose level?" And like most things in healthcare, a deceptively easy question has required considerable thought, effort and collaboration along the way. The approach and solution has meaningful insights for hospital administration, clinicians, researchers and anyone else trying to make a difference through better use of healthcare data.

Dr Peter Cronin Co-founder,  Prospection

Dr Peter Cronin is the co-founder of leading analytics company Prospection. Peter combines 15 years of clinical experience with business and technology expertise, and is passionate about driving meaningful innovation in the healthcare sector. Prospection is unique blend of clinical, technology and commercial capabilities and is recognised for the development of analytics platforms and consulting solutions with their commercial, research and hospital clients.


Automatic Coding and content extraction from imaging reports for cancer registries

Automation of the process of discovering cancer reports at a radiology service is a precursor to delivery and extraction of content from imaging reports from services distributed across the country.
A pipeline technology was built for the Victorian and NSW Cancer Registries as five automated stages to deliver cancer reports to the Registries and then extract the required content. Stage one is a classifier that is located at each imaging service. All their daily reports were computationally filtered for reportable cancers, which were forwarded to the registry. Stage two is a Report Purpose document classifier. Stage three classified the reports for 15 tumour streams. The fourth stage was data extraction of specified material and the fifth stage was an inference engine that inferred the staging values from the extracted content. The sensitivity and specificity of the tumour classifier was 98.5 and 95.0% respectively, tested on a held out set. This classifier used both a statistical language model and rules system.

Prof Jon Patrick CEO, Health Language Analytics

Jon Patrick healed the chair of Information Systems at the Univeristy of Sydney from 1998 to 2004 and then moved the Chair of Language Technology. In 2005 he won the national Eureka Science prize for his work in natural language processing. He has conducted extensive research on the use of language technology in Intensive Care, Pathology and Radiology departments, and in information systems research in emergency medicine and oncology. In 2012 he left the University of Sydney to pursue his interests in R&D consulting in Health IT and NLP and is the CEO for the companies Health Language Analytics (HLA) and Innovative Clinical Information Management Systems (iCIMS).

Registration Fees
This event is free for HISA member and $25.00 for non-members. Please register via the above link to confirm your attendance. 

Proudly Supported By