CLEVELAND, OH — A team of Cleveland Clinic researchers has published a new study titled “Novel Machine Learning Can Predict Acute Asthma Exacerbation.” As the title implies, the study focused on the use of Machine Learning, or ML, for patients with asthma with outpatient data taken from patients’ electronic health records, also known as EHR.
Findings from the study show that ML can be used to predict a non-severe asthma exacerbation, an asthma-related ED visit, or hospitalization. This means that with the use of ML, predicting when an acute asthma exacerbation might occur will be much easier. Clinicians can simply check the patient’s EHR to do so.
“In application,” says Joe Zein, MD, Ph.D., a pulmonologist in the Respiratory Institute and the study’s first author, “this means the ML algorithm could interface with patients’ EHR, interpret their unique demographic information, clinical data, and biomarkers and make a prediction about the probability of an asthma episode within a certain time frame.”
So, to put it simply, the use of ML in medicine can benefit both the patient and the physician as it collects the patient’s data more efficiently and thoroughly, making it easier to keep track of what’s going on (and going to happen) in your body.
Dr. Zein and his colleagues took to exploring the viability of ML in this context since previous studies with traditional statistical modeling and known disease risk factors did not perform optimally. Even though ML is increasingly being used in medicine, no other studies have investigated the risk of an asthma episode using ML and outpatient data taken from patients’ electronic health records.
Findings from this study did not surprise Dr. Zein, as he already asserted that ML has excellent potential in medicine, especially in the delivery of personalized care. ML handles large data sets and missing values much better than the classic statistical modeling, thus, it is more predictive due to its capacity to leverage real-world data.
So, essentially, ML algorithms are designed to make predictions models that are more accurate than classic statistics.
“We are pleased that our findings demonstrate that ML can be used to build decision-making tools in the clinical management of asthmatic patients,” he says. “ML is effective in aiding with the integration of big data, but the physician provides judgment rooted in clinical context and experience,” he says. “Both are extremely important.”