A model developed using artificial intelligence (AI) is better at predicting risk of death in patients with heart disease than models designed by medical experts, a new study from the Francis Crick Institute shows.
The study, published in PLOS One, adds to the growing evidence that AI could revolutionise healthcare in the UK and beyond. So far, the emphasis has been on the potential of AI to help diagnose and treat various diseases, but these new findings suggest it could also help predict the likelihood of patients dying too.
“It won’t be long before doctors are routinely using these sorts of tools in the clinic to make better diagnoses and prognoses, which can help them decide the best ways to care for their patients,” says Andrew Steele, first author of the paper, who carried out the project in the Crick’s Bioinformatics and Computational Biology Laboratory.
“Doctors already use computer-based tools to work out whether a patient is at risk of heart disease, and machine-learning will allow more accurate models to be developed for a wider range of conditions.”
The model was designed using the electronic health data of over 80,000 patients, collected as part of routine care, and available for researchers on the CALIBER platform.
Scientists at the Crick, working collaboratively with colleagues at the Farr Institute of Health Informatics Research and University College London Hospitals NHS Foundation Trust, wanted to see if they could create a model for coronary artery disease – the leading cause of death in the UK – that outperforms experts using self-taught machine learning techniques.
Coronary artery disease develops when the major blood vessels that supply the heart with blood, oxygen and nutrients become damaged, or narrowed by fatty deposits. Eventually restricted blood flow to the heart can lead to chest pain and shortness of breath, while a complete blockage can cause a heart attack.
An expert-constructed prognostic model for coronary artery disease which this work was compared against made predictions based on 27 variables chosen by medical experts, such as age, gender and chest pains. By contrast, the Crick team got their AI algorithms to train themselves, searching for patterns and picking the most relevant variables from a set of 600.
Not only did the new data-driven model beat expert-designed models at predicting patient mortality, but it also identified new variables that doctors hadn’t thought of.
“Along with factors like age and whether or not a patient smoked, our models pulled out a home visit from their GP as a good predictor of patient mortality,” says Andrew. “Home visits are not something a cardiologist might say is important in the biology of heart disease, but perhaps a good indication that the patient is too unwell to make it to the doctor themselves, and a useful variable to help the model make accurate predictions.”
This study was a proof-of-principle to compare expert-designed models to machine learning approaches, but a similar model could be implemented in the clinic in the not too distant future.
“Machine learning is a hugely powerful tool in medicine and has the ability to revolutionise how we deliver care to patients over the next few years,” says Andrew.
The Latest on: Machine learning predictions
via Google News
The Latest on: Machine learning predictions
- New twist in artificial intelligence could enhance the prediction of fusion disruptionson February 27, 2020 at 6:34 am
The method enables the deep learning form of AI machine learning to predict disruptions directly from raw ... that house the reactions. Accurate predictions that lead to avoidance of disruptions will ...
- Data Science Institute team wins Facebook award to enhance machine learningon February 26, 2020 at 10:11 am
"Today's machine-learning models are limited as they are primarily trained only for making the best predictions," says Asaf Cidon, an assistant professor of electrical engineering and computer science ...
- Predictions for 2030 by people shaping the worldon February 26, 2020 at 4:22 am
Erik Brynjolfsson, director, MIT Initiative on the Digital Economy (USA) Machine learning has advanced tremendously over the past decade, yet US productivity growth has fallen by 50% since 2004. It’s ...
- GeoAI: A prescription for COVID-19 predictionon February 25, 2020 at 12:28 pm
things that are further apart,” Geraghty said. “You can take that idea -- we call it spatial autocorrelation -- and use that to make predictions and to see patterns and trends geographically over ...
- SwRI’s Motion Prediction Algorithms Enhance Safety Features for Automated Vehicleson February 24, 2020 at 4:17 pm
Machine vision system predicts pedestrian movements with convolutional neural network Southwest Research Institute, a leading innovator of machine learning technologies, has developed a motion ...
- Obviously AI Rolls Out First Natural Language-Powered Machine Learning Platform for Predicting Outcomes from Any Dataon February 24, 2020 at 3:14 pm
No-Code Machine Learning Platform makes data science effortless by enabling anyone to run predictions and analytics using natural language questions BERKELEY, CA / ACCESSWIRE / February 19, 2020 / ...
- Macular Ganglion Cell-Inner Plexiform Layer Thickness Prediction from Red-free Fundus Photography using Hybrid Deep Learning Modelon February 24, 2020 at 7:54 am
Hence, mGCIPL thickness prediction could be made based on the peripapillary area rather than on ... The feature vector extracted from the CNN was inputted to train the SVM regression model. SVM is a ...
- Machine Learning Analysis for Quantitative Discrimination of Dried Blood Dropletson February 24, 2020 at 7:02 am
We found that when our machine learning algorithm, which optimises a statistical model combining Principal Component Analysis (PCA) as an unsupervised learning method and Linear Discriminant Analysis ...
- The 7 malignant myths of machine learningon February 23, 2020 at 11:47 am
The biggest obstacle to unleashing the power of enterprise artificial intelligence (AI) and machine learning (ML) isn’t a lack of data scientists – it ... Reality: Use ML for more than predictions and ...
- Cisco adds 5G and machine learning to IoT monitoring platformon February 20, 2020 at 10:02 am
What's the next logical step for an IoT Control Center operating at scale across 3G and 4G with 160M SIMs under management and 60 million connected cars? Adding 5G to the mix. Vikas Butaney, vice ...
via Bing News