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
- Integration of machine learning and genome-scale metabolic modeling identifies multi-omics biomarkers for radiation resistanceon May 11, 2021 at 5:56 am
Personalized prediction of tumor radiosensitivity would facilitate development of precision medicine workflows for cancer treatment. Here, the authors integrate machine learning and genome-scale ...
- High Danger of Defect: Machine learning model predicts potential disk failures in Google’s DCson May 10, 2021 at 7:31 am
Google has devised a machine learning (ML) model that predicts disk failures with 98 per cent accuracy. The idea is to reduce data recovery work when disks actually fail. According to a Google blog by ...
- Integrated Machine Learning and CT Angiography Helps Predict MACE: Studyon May 9, 2021 at 10:45 am
Coronary artery disease (CAD) is a leading cause of morbidity and mortality in the developed world. Previous studies have shown that coronary CT angiography (cCTA)-based risk scores can help ...
- Systematic misestimation of machine learning performance in neuroimaging studies of depressionon May 6, 2021 at 4:40 pm
We currently observe a disconcerting phenomenon in machine learning studies in psychiatry: While we would expect larger samples to yield better results due to the availability of more data, larger ...
- Machine Learning in Medicine Market by Manufacturers, Regions, Type and Application, Forecast To 2026 – Google, Bio Beats, Jvion, Lumiata, DreaMedon May 6, 2021 at 8:42 am
A recent research study on the global Machine Learning in Medicine market presented by Zeal Insider offers a detailed analysis of key market players, market revenue, market segments, share, and ...
- Advances in Machine Learning and Deep Neural Networkson May 5, 2021 at 7:38 am
We are currently experiencing the dawn of what is known as the fourth industrial revolution. At the center of this historical happening, as one of the key enabling technologies, lies a discipline that ...
- Top 5 Tips for Adopting Enterprise Machine Learningon May 4, 2021 at 9:21 am
So, what is machine learning? Simply put, machine learning is a subset of artificial intelligence in which computer algorithms learn from large datasets in order to make more accurate predictions over ...
- Machine learning for the prediction of pathologic pneumatosis intestinalis.on May 2, 2021 at 11:11 pm
The radiographic finding of pneumatosis intestinalis can indicate a spectrum of underlying processes ranging from a benign finding to a life-threatening condition. Although radiographic pneumatosis ...
- Membership inference attacks detect data used to train machine learning modelson April 29, 2021 at 12:21 am
In membership inference attacks, the adversary can work back from the machine learning algorithm to discover the training data used.
- Researchers develop new protocols to validate integrity of machine-learning modelson April 28, 2021 at 1:32 pm
Machine learning is widely used in various applications such as image recognition, autonomous vehicles and email filtering. Despite its success, concerns about the integrity and security of a model's ...
via Bing News