Unsupervised machine learning can assign older adult patients to low, moderate, or high prediagnosis symptom severity categories, allowing healthcare providers to identify patients at risk for hospitalization or death even before initiating treatment, researchers reported in JAMA Network Open.
The researchers used the algorithm to sort patient-reported symptom data from 706 older adults who had participated in a National Cancer Institute clinical trial. The patients reported varying severity pretreatment symptoms such as fatigue, insomnia, memory problems, and headaches.
Patients who were categorized with moderate to severe symptoms were more likely to have unplanned hospitalization and poorer overall survival but not more toxic effects from treatment, the researchers reported. Their risks were higher if they had a greater number of severe symptoms before treatment and were diagnosed with more aggressive cancers (e.g., pancreatic).
“Our findings reinforce the importance of routine symptom assessment prior to treatment initiation as a best practice standard,” the researchers wrote. “Machine learning may be used to guide the development of risk stratification tools with the potential to assist clinicians in identifying older adults with a high risk of adverse outcomes.”
Learn how ONS members are using team-based symptom assessment approaches to inform patient care and optimize outcomes.