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
- Breakthrough in AI protein structure and folding predictionon December 1, 2020 at 4:38 am
An artificial intelligence (AI) system called AlphaFold has been developed to effectively predict protein structures and folding.
- Google Reveals Major Hidden Weakness In Machine Learningon November 30, 2020 at 10:37 am
Deep learning algorithms are prone to a previously unknown problem, say a team of computer scientists at Google.
- Restoring Credibility Of Machine Learning Pipeline Output Through Blockchain Dataon November 27, 2020 at 6:34 pm
Challenges to the credibility of Machine Learning pipeline output. How the performance of such ML models are inherently compromised due to current practices. How such problems can be cured by using ...
- Boosting Weather Prediction with Machine Learningon November 25, 2020 at 5:39 am
WeatherBench is a data set compiled to serve as a standard for evaluating new approaches to artificial intelligence–driven weather forecasting.
- DXC Technology and Infinia ML Team Up to Bring Benefits of Advanced Machine Learning to Global Customerson November 24, 2020 at 1:15 pm
DXC will utilize Infinia ML machine learning capabilities across its Enterprise Technology Stack to automate document processing, boost performance of mission-critical IT systems, ...
- Machine learning uncovers missing info about ethnicity in population health data: Studyon November 18, 2020 at 12:52 pm
Machine learning can be used to fill a significant gap in Canadian public health data related to ethnicity and Aboriginal status, according to research published in PLOS ONE by a University of Alberta ...
- Machine learning-based prediction model may enable early diagnosis of opioid use disorderon November 18, 2020 at 7:33 am
Researchers have used machine learning, a type of artificial intelligence, to develop a prediction model for the early diagnosis of opioid use disorder.
- How Amazon Retail Systems Run Machine Learning Predictions with Apache Sparkon November 16, 2020 at 3:22 pm
For the machine learning (ML) framework for building our ... feature vector to NDList containing CSR data and convert output predictions of type NDList to Array[Array[Float]].
- Machine learning shows similar performance to traditional risk prediction modelson November 3, 2020 at 4:00 pm
Some studies claim that machine learning models can outperform traditional models, while others argue that they cannot provide explainable reasons behind their predictions, potentially leading to ...
via Bing News