Machine learning has come of age in public health reporting according to researchers from the Regenstrief Institute and Indiana University School of Informatics and Computing at Indiana University-Purdue University Indianapolis. They have found that existing algorithms and open source machine learning tools were as good as, or better than, human reviewers in detecting cancer cases using data from free-text pathology reports. The computerized approach was also faster and less resource intensive in comparison to human counterparts.
Every state in the United States requires cancer cases to be reported to statewide cancer registries for disease tracking, identification of at-risk populations, and recognition of unusual trends or clusters. Typically, however, busy health care providers submit cancer reports to equally busy public health departments months into the course of a patient’s treatment rather than at the time of initial diagnosis.
This information can be difficult for health officials to interpret, which can further delay health department action, when action is needed. The Regenstrief Institute and IU researchers have demonstrated that machine learning can greatly facilitate the process, by automatically and quickly extracting crucial meaning from plaintext, also known as free-text, pathology reports, and using them for decision-making.
“Towards Better Public Health Reporting Using Existing Off the Shelf Approaches: A Comparison of Alternative Cancer Detection Approaches Using Plaintext Medical Data and Non-dictionary Based Feature Selection” is published in the April 2016 issue of the Journal of Biomedical Informatics.
“We think that its no longer necessary for humans to spend time reviewing text reports to determine if cancer is present or not,” said study senior author Shaun Grannis, M.D., M.S., interim director of the Regenstrief Center of Biomedical Informatics. “We have come to the point in time that technology can handle this. A human’s time is better spent helping other humans by providing them with better clinical care.”
“A lot of the work that we will be doing in informatics in the next few years will be focused on how we can benefit from machine learning and artificial intelligence. Everything — physician practices, health care systems, health information exchanges, insurers, as well as public health departments — are awash in oceans of data. How can we hope to make sense of this deluge of data? Humans can’t do it — but computers can.”
Dr. Grannis, a Regenstrief Institute investigator and an associate professor of family medicine at the IU School of Medicine, is the architect of the Regenstrief syndromic surveillance detector for communicable diseases and led the technical implementation of Indiana’s Public Health Emergency Surveillance System – one of the nation’s largest. Studies over the past decade have shown that this system detects outbreaks of communicable diseases seven to nine days earlier and finds four times as many cases as human reporting while providing more complete data.
“What’s also interesting is that our efforts show significant potential for use in underserved nations, where a majority of clinical data is collected in the form of unstructured free text,” said study first author Suranga N. Kasthurirathne, a doctoral student at School of Informatics and Computing at IUPUI. “Also, in addition to cancer detection, our approach can be adopted for a wide range of other conditions as well.”
The researchers sampled 7,000 free-text pathology reports from over 30 hospitals that participate in the Indiana Health Information Exchange and used open source tools, classification algorithms, and varying feature selection approaches to predict if a report was positive or negative for cancer. The results indicated that a fully automated review yielded results similar or better than those of trained human reviewers, saving both time and money.
“Machine learning can now support ideas and concepts that we have been aware of for decades, such as a basic understanding of medical terms,” said Dr. Grannis. “We found that artificial intelligence was as least as accurate as humans in identifying cancer cases from free-text clinical data. For example the computer ‘learned’ that the word ‘sheet’ or ‘sheets’ signified cancer as ‘sheet’ or ‘sheets of cells’ are used in pathology reports to indicate malignancy.
“This is not an advance in ideas, it’s a major infrastructure advance — we have the technology, we have the data, we have the software from which we saw accurate, rapid review of vast amounts of data without human oversight or supervision.”
The Latest on: Machine learning
via Google News
The Latest on: Machine learning
- Develop a Basic Understanding of Machine Learning With These Courseson November 13, 2020 at 5:15 am
In the first course, you'll walk through the fundamental theoretical concepts of machine learning and artificial intelligence. You'll get familiar with the terms used in the industry, understand the ...
- KeyBank Battles Push-Payment Fraud With Machine Learning, Other Tacticson November 13, 2020 at 5:00 am
The Digital Fraud Tracker explores the threat of APP fraud and the use of data analytics and pattern recognition to identify and counter digital schemes.
- Australia Post using machine learning to tell you when to expect a deliveryon November 13, 2020 at 12:42 am
It will give customers a two-hour window for when a delivery will arrive, although it has mapped it down to plus or minus 15 minutes.
- Machine learning for making machines: Applying visual search to mechanical partson November 12, 2020 at 1:15 pm
Computer vision researchers use machine learning to train computers in visually recognizing objects – but very few apply machine learning to mechanical parts such as gearboxes, bearings, brakes, ...
- How Amazon Retail Systems Run Machine Learning Predictions with Apache Sparkon November 12, 2020 at 8:54 am
Amazon Retail systems uses Apache Spark with Deep Java Library (DJL) to build propensity models to drive customer experience.
- How Amazon Personalizes Customer Experiences with Machine Learningon November 12, 2020 at 8:13 am
This blog explores how Amazon’s retail systems run machine learning predictions with Apache Spark using Deep Java Library.
- Fivetran Extends Integration With Databricks, Accelerating SQL Analytics, Data Science and Machine-Learning Applicationson November 12, 2020 at 3:01 am
Fivetran, the leading provider of automated data integration, today announced advancements in its integration with Databricks, the Data and AI Company, extending the companies’ strategic partnership ...
- AI research finds a ‘compute divide’ concentrates power and accelerates inequality in the era of deep learningon November 11, 2020 at 4:25 pm
Big Tech and elite universities are working together more often, accelerating inequality and crowding out lower-tier universities.
- Amazon beefs up machine learning in Alexa to predict ‘latent goals’ that aren’t directly expressedon November 11, 2020 at 8:24 am
Alexa is getting smarter. Amazon's voice assistant in the U.S. can now predict "latent goals," or potential requests that a user doesn't explicitly ask. In the example above, when a user asks for ...
- Sorting out viruses with machine learningon November 11, 2020 at 6:17 am
The ongoing global pandemic has created an urgent need for rapid tests that can diagnose the presence of the SARS-CoV-2 virus, the pathogen that causes COVID-19, and distinguish it from other ...
via Bing News