Researchers from the University of Utah have developed a model that can anticipate the deterioration of asthma in children. According to a Lung Disease News report, researchers reported development of the first machine learning models able to predict signs of asthma deterioration in children 1 week prior to exacerbation. In this research study, the research team utilized weekly a method based on a self-monitoring tool for asthma called the Asthma Symptom Tracker.

The new approach was validated on a total of 210 children recruited during hospitalization, and the participants were assessed for a period of more than 2 years in a total of 2,912 weekly evaluations. The Lung Disease News report notes that during this period, data were gathered then combined with other criteria like patient attributes and environmental variables such as carbon monoxide, sulfur dioxide, temperature, relative humidity, precipitation, and tree pollen count, among others.

The results of the study suggest that the developed model was 73.8% sensitive, 71.8% accurate, and 71.4% specific in predicting occurrence of deterioration of asthma in children 1 week before incidence.

Overall, the findings highlight the promising usefulness of the developed model in predicting asthma attacks in children 1 week before the occurrence, and the success rate is around 75%. The researchers did identify, however, key potential parameters that could improve the model. The Lung Disease News report indicates if the model is integrated into an electronic device in the future, it may allow for a real-time self-monitoring system to record early signs of asthma deterioration, which would reduce exacerbations and improve the well being of patients.

Source: Lung Disease News