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
GE Introduces New Analytics to Advance Electric Grid Operations
on June 16, 2019 at 8:17 pm
GE (NYSE: GE) announced the availability of three new grid analytics that combine domain expertise with artificial intelligence (AI) and machine learning (ML ... helps reduce outage restoration time, ... […]
New machine-learning method more precisely quantifies a known indicator for psychosis
on June 14, 2019 at 6:34 am
Wolff's lab focuses on language semantics and machine learning to predict decision-making and mental health. "Our finding is novel and adds to the evidence showing the potential for using machine ... […]
Africa: What Is the Value Proposition of Machine Learning?
on June 14, 2019 at 1:35 am
Machine learning is transforming the way consumers ... Facebook uses AI to predict your content preference and pushes that to the top of your feed. By simple voice instruction, Siri helps iPhone ... […]
The whisper of schizophrenia: Machine learning finds 'sound' words predict psychosis
on June 13, 2019 at 8:08 am
Automated analysis of the two language variables -- more frequent use of words associated with sound and speaking with low semantic density, or vagueness -- can predict whether an at-risk person will ... […]
A machine learning approach to predicting psychosis using semantic density and latent content analysis
on June 13, 2019 at 2:06 am
Subtle features in people’s everyday language may harbor the signs of future mental illness. Machine learning offers an approach for the rapid and accurate extraction of these signs. Here we ... […]
How Bringing Machine Learning Into Marketing Improves Business Results
on June 12, 2019 at 7:54 am
With machine learning I can. In marketing, a lot of time is spent processing and enriching data, predicting customer activity, and then personalizing content based on those predictions — which can all ... […]
Straight Talk On Artificial Intelligence, Machine Learning And How They Can Help Your Business
on June 12, 2019 at 5:24 am
Using machine learning to transform a manual data entry process or AI to accurately predict a sale or retain a valued member of a team make up what in my experience offer the most return on investment ... […]
Marketing Benefits of AI and Machine Learning
on June 11, 2019 at 6:39 am
Predictive analytics and forecasting is a crucial part of big data and machine learning for marketing. Demand forecasting has already been a focus of marketers, using trend analysis and purchase ... […]
Machine Learning, Risk Scores Help Predict Hospital Readmissions
on June 11, 2019 at 6:38 am
June 11, 2019 - Researchers at the University of Maryland Medical System (UMMS) have developed a machine learning model that creates risk scores to help clinicians identify which patients are at ... […]
Transit city navigation app seeks to solve bad public transit ETAs with machine learning
on June 11, 2019 at 6:18 am
Transit, a company that has spent its entire life trying to make it easier to get around cities, is unveiling a new machine learning-powered estimated time of arrival prediction feature to help ... […]
via Bing News