A study has found that machine learning can be used to help improve the accuracy of the diagnosis in lung diseases, by utilising algorithms that can learn from and perform predictive data analysis. The team at the University of Leuven developed an algorithm process in addition to the routine lung function parameters and clinical variables of smoking history, body mass index (BMI) and age.
Based on the pattern of both the clinical and lung function data, the algorithm makes a suggestion for the most likely diagnosis. “We have demonstrated that AI can provide us with a more accurate diagnosis. The algorithm can simulate the complex reasoning that a clinician uses to give their diagnosis, but in a more standardised and objective way so it removes any bias,” said Wim Janssens from the University of Leuven.
Currently, clinicians rely on analysing the results using population-based parameters. But with AI-based solutions, the machine can observe a combination of patterns at one time to help produce a more accurate diagnosis. “The benefit of this method is a more accurate and automated interpretation of pulmonary function tests and, thus, better disease detection,” added Marko Topalovic, also from University of Leuven.
In this new study, researchers included data from 968 people who were undergoing complete lung function testing for the first time. All participants received a first clinical diagnosis based on lung function tests and all other necessary additional tests (such as CT scans, electrocardiogram, etc.). The final diagnosis was validated by the consensus of the large group of expert clinicians.
“Not only can this help non-experienced clinicians but also has many benefits for healthcare overall as it could decrease the number of redundant additional tests clinicians are taking to confirm the diagnosis,” Topalovic noted.
This article was re-published from tech2