News: Augmented intelligence to predict 30-day mortality in patients with cancer, study shows

Leveraging socioeconomic and clinical data via augmented intelligence could predict 30-day mortality risks in patients with cancer, according to a study in Future Medicine.

In predicting patients’ end of life needs, providers can allow more time for hospice referrals, thus improving the patient’s quality of life and symptom management.

“In contrast, aggressive, life-sustaining end of life (EoL) care can conflict with patient preference and result in lower quality of life, family perceptions of poorer quality of care, and greater regret about treatment decisions. Earlier referral also represents an opportunity to transform cancer care by reducing the potential for unnecessary, toxic and expensive treatments at EoL,” the study authors wrote.

Currently, mortality prediction models only include clinical factors, meanwhile authors of the study say that the augmented intelligence tool includes sociodemographic and geographic factors that can identify patients at greater risk of short-term mortality.

Researchers concluded that the machine learning algorithm’s ability to identify patients with cancer at risk for 30-day mortality has the potential to improve outcomes for patients with reversible clinical factors. Additionally, the augmented intelligence system can prevent unnecessary and harmful care for those nearing EoL.

Editor’s note: The Future Medicine published study can be found here. The ACDIS CDI Journal edition on top CDI technologies can be found here.