News: AI-enabled monitoring may not reduce rehospitalizations in heart failure, study finds

Artificial intelligence (AI)-guided monitoring with clinician alerts appeared feasible in patients recently discharged after a hospital stay for heart failure (HF). It did not, however, reduce rehospitalizations or the composite of rehospitalizations, emergency visits, and death, a recent study published in JACC: Heart Failure found.

Researchers conducted a prospective, randomized, open-label study (LINK-HF2) at five United States Veterans Affairs (VA) medical centers to assess whether pairing AI-generated alerts with a structured clinician response plan was feasible for care after a hospital stay for HF. Adults being discharged after hospitalization for HF were enrolled, with the final analysis including 171 patients.

Patients wore a chest sensor patch for up to 90 days, with some randomly assigned to the intervention group and the rest to the control group. Only clinicians of those in the intervention group received AI alerts.

The patch tracked each patient’s heart rate, movement, and skin temperature. The AI set a personal baseline within 48 hours of discharge and raised an alert when readings deviated from baseline values. Clinicians contacted the patient and followed one of four response pathways, ranging from treatment adjustment to emergency department referral.

The risk for HF rehospitalization was found to not differ significantly between the intervention and control groups. The composite clinical endpoint of all-cause unplanned rehospitalizations, emergency department visits, and all-cause mortality also showed no significant difference between the groups.

In a post hoc analysis, the intervention group was found to have a lower rate of AI-detected physiologic instability than the control group, but the difference was not significant when death was treated as a competing risk.

Editor’s note: To read the full study, click here. To read additional coverage from Medpage Today, click here.