Machine algorithm uses 85 variables to calculate risk in individuals Formulas used by humans include a handful of variables and have modest accuracy
By repeatedly analysing 85 variables in 950 patients with known six-year outcomes, an algorithm “learned” how imaging data interacts. It then identified patterns correlating the variables to death and heart attack with more than 90% accuracy.
Machine learning, the modern bedrock of artificial intelligence (AI), is used every day. Google’s search engine, face recognition on smartphones, self-driving cars, Netflix and Spotify recommendation systems all use machine learning algorithms to adapt to the individual user.
Study author Dr Luis Eduardo Juarez-Orozco, of the Turku PET Centre, Finland, said: “These advances are far beyond what has been done in medicine, where we need to be cautious about how we evaluate risk and outcomes. We have the data but we are not using it to its full potential yet.”
Doctors use risk scores to make treatment decisions. But these scores are based on just a handful of variables and often have modest accuracy in individual patients. Through repetition and adjustment, machine learning can exploit large amounts of data and identify complex patterns that may not be evident to humans.
Dr Juarez-Orozco explained: “Humans have a very hard time thinking further than three dimensions (a cube) or four dimensions (a cube through time). The moment we jump into the fifth dimension we’re lost. Our study shows that very high dimensional patterns are more useful than single dimensional patterns to predict outcomes in individuals and for that we need machine learning.”
The study enrolled 950 patients with chest pain who underwent the centre’s usual protocol to look for coronary artery disease. A coronary computed tomography angiography (CCTA) scan yielded 58 pieces of data on presence of coronary plaque, vessel narrowing, and calcification. Those with scans suggestive of disease underwent a positron emission tomography (PET) scan which produced 17 variables on blood flow. Ten clinical variables were obtained from medical records including sex, age, smoking and diabetes.
During an average six-year follow-up there were 24 heart attacks and 49 deaths from any cause. The 85 variables were entered into a machine learning algorithm called LogitBoost, which analysed them over and over again until it found the best structure to predict who had a heart attack or died.
Dr Juarez-Orozco said: “The algorithm progressively learns from the data and after numerous rounds of analyses, it figures out the high dimensional patterns that should be used to efficiently identify patients who have the event. The result is a score of individual risk.”
The predictive performance using the ten clinical variables alone (similar to current clinical practice) was modest, with an area under the curve (AUC) of 0.65 (where 1.0 is a perfect test and 0.5 is a random result). When PET data were added, AUC increased to 0.69. The predictive performance increased significantly (p=0.005) when CCTA data were added to clinical and PET data, giving an AUC 0.82 and more than 90% accuracy.
Dr Juarez-Orozco said: “Doctors already collect a lot of information about patients – for example those with chest pain. We found that machine learning can integrate these data and accurately predict individual risk. This should allow us to personalise treatment and ultimately lead to better outcomes for patients.”
The Latest on: Machine learning predictions
via Google News
The Latest on: Machine learning predictions
Machine Learning may help capture fusion energy on Earth
on May 19, 2019 at 3:56 am
A team of researchers in the US have used Machine Learning (ML) to rapidly control plasma that ... The trained model accurately reproduced predictions of the behaviour of the energetic particles ... […]
Predicting Hospitalization: Machine Learning Models On The Rise
on May 18, 2019 at 10:12 pm
Individually and collectively, these are adding to the rapidly rising healthcare costs. It seems emerging machine learning models could offer a much earlier prediction of which patients will develop ... […]
Machine learning speeds modeling of experiments aimed at capturing fusion energy on Earth
on May 17, 2019 at 12:07 pm
Machine learning (ML), a form of artificial intelligence ... The trained model accurately reproduces predictions of the behavior of the energetic particles produced by powerful neutral beam ... […]
Machine Learning Accurately Predicts Australian Wheat Yield Months Before Harvest
on May 17, 2019 at 8:33 am
“We tested various machine-learning approaches and integrated large-scale climate and satellite data to come up with a reliable and accurate prediction of wheat production for the whole of Australia,” ... […]
Cyclica Announces the Integration of the POEM Machine Learning Predictive Engine in their Ligand Express® Platform
on May 17, 2019 at 7:19 am
has announced the addition of a machine learning predictive engine called POEM to its Ligand Express ® platform. POEM has been applied to the prediction of ADMET (Absorption, Distribution ... […]
Can Machine Learning And AI Head Off Heart Attacks And Strokes?
on May 17, 2019 at 2:40 am
which happens every 40 seconds in the U.S. Machine learning and artificial intelligence more broadly could help reduce strokes and heart attacks by analyzing patient data to spot trends and make ... […]
How Artificial Intelligence and Machine Learning are Transforming Data Centers
on May 16, 2019 at 2:21 pm
You’ve seen the analysts’ predictions that as much as a third of data centers that fail to employ some form of machine learning in their management portfolios, will cease to be competitive by the end ... […]
Qindom Cracks the Code for Real Estate Prediction with Quantum Machine Learning
on May 16, 2019 at 9:40 am
TORONTO, May 16, 2019 /PRNewswire/ - Qindom, the Toronto-based Quantum Machine Learning (QML) start-up, is shifting conventional pricing practices in Real Estate business. Qindom's proprietary AI ... […]
Machine learning, practically speaking
on May 9, 2019 at 6:59 am
Within the AI field, many projects involve machine learning (ML), in which a computer can learn iteratively from data and make predictions 1. Basic ideas of ML architectures have been around for ... […]
BitterSweet: Building machine learning models for predicting the bitter and sweet taste of small molecules
on May 9, 2019 at 2:11 am
Towards these goals, our study provides a structured compilation of bitter, sweet and tasteless molecules and state-of-the-art machine learning models for bitter-sweet taste prediction (BitterSweet). ... […]
via Bing News