Press Release: Australia’s HORIZON Machine Learning Platform in Deal to Crunch Data for the California Cancer Registry
- HORIZON has been chosen by California’s Public Health Institute (PHI) to extract and codify cancer data from pathology text reports for The California Cancer Registry (CCR) program.
- HORIZON platform will deliver a rich data set that can be used to inform public health policy, clinical procedures, patient health outcomes, and trends.
- The CCR is recognized as one of the leading cancer registries in the world, and has been the cornerstone of a substantial amount of research on cancer in the California population.
- HORIZON focuses on the 80% of “dark content” or unstructured text in clinical settings that existing big data analytics can’t read and analyse.
The leading Language Analytics and Big Text mining company Health Language Analytics (HLA) announced today that its machine learning platform HORIZON has been chosen by the Public Health Institute (PHI) to extract and codify cancer data from pathology text reports for The California Cancer Registry (CCR) program.
HLA is the U.S. subsidiary of Australian company Health Language Analytics (HLA) where HORIZON was developed.
PHI’s mission is to generate and promote research, leadership and partnerships to build capacity for strong public health policy, programs, systems and practices. This project aligns closely with PHI’s principles of using innovation and evidence-based public health to improve the health and outcomes for people with cancer.
The CCR is a program of the California Department of Public Health’s Chronic Disease Surveillance and Research Branch (CDSRB) (http://www.ccrcal.org).
The CCR is recognized as one of the leading cancer registries in the world, and has been the cornerstone of a substantial amount of research on cancer in the California population.
To date the CCR has collected detailed information on over 7 million cases of cancer among Californians diagnosed from 1988 forward, and more than 175,000 new cases are added annually.
The HORIZON platform will deliver a rich data set that can be used to inform public health policy, clinical procedures, patient health outcomes, and trends.
Horizon reads unstructured clinical text in such things as pathology reports, clinicians’ notes, radiology reports, discharge summaries etc., and converts idiosyncratic English into highly structured and coded clinical information.
This information is then consumed by analytic engines and any other applications the business requires.
HORIZON focuses on the 80% of “dark content” or unstructured text in clinical settings that existing big data analytics can’t read and analyse.
“This will be HORIZON’S biggest single project to date and the first U.S. contract,” said HLA CEO Professor Jon Patrick.
HLA is the region’s leading Clinical NLP company offering consulting and SaaS services from its machine learning technology platform HORIZON which beats the world’s best in accuracy, time and cost.
“The NLP market for healthcare and life sciences industry is projected to grow to USD 2.67 Billion from USD 1.10 Billion in 2015,” according to a recent analyst report by Research and Markets. [http://www.researchandmarkets.com/research/d969jt/natural_language]
“As healthcare organizations are looking for human-to-machine translation solutions to provide better access to important clinical data, the demand for NLP solutions are increasing at a high rate.
“The NLP market has been forecasted to have numerous opportunities for growth, such as the growing need for personalized medicine, need to raise disease awareness, and investment in the healthcare industry.
“The volume of content in the medical record is 80% text and so far no-one has been able to mine it for useful purposes. Big Data has actually only focused on 20% of the medical record. Our work in Big Text will enable the capability of Big Data to be effectively supercharged overnight to 100% and enable a vastly greater range of research projects along with massively increased scale.”
HLA, the U.S. subsidiary of Health Language Analytics (Australia), is leading the race to mine unstructured text in the health sector where it’s estimated 80% of text cannot currently be read or analysed easily or accurately.
The HLA technology directly impacts patient health, treatment discovery and company and institution finances, delivering results at one-tenth the cost of existing methods.
The HLA technology has emerged since Professor Patrick’s research team won the I2B2 NLP Challenge in 2009 and was ranked highly in other years. The Challenge was developed under the i2b2 funding provided by the USA Government to the Partners HealthCare System in Boston, Mass, led by Dr Isaac Kohane from Harvard Medical School with other Harvard affiliated hospitals and is the largest such challenge conducted worldwide.
HLA’s expertise includes:
- Natural Language Processing (NLP) of clinical texts
- Clinical Data Analytics
- Language Engineering Infrastructure
About Prof Jon Patrick
Prof. Patrick, was a national Science Prize Winner 2005 and the Chair of Language Technology at University of Sydney until 2012. He has more than 100 publications and 7 pending patents, and has built a technology team in Sydney that delivers text-mining services for some of Australia’s largest hospitals and cancer registries with 98% accuracy.