Electronic Health Record Data Can Predict Readmission in Children

HealthDay News — A new risk prediction model may identify infants and children at risk for hospital readmission, according to a study published online Nov. 11 in JAMA Network Open.

Denise M. Goodman, M.D., from Ann & Robert H. Lurie Children’s Hospital of Chicago, and colleagues developed and validated a tool identifying patients before hospital discharge who are at risk for subsequent readmission, applicable to all ages. The derivation set was based on 29,988 patients (48,019 hospitalizations).

The researchers found that among children aged 6 months and older with one or more prior hospitalizations within the last six months (recent admission), prior utilization, current or prior procedures indicative of severity of illness (transfusion, ventilation, or central venous catheter), commercial insurance, and prolonged length of stay (LOS) were associated with readmission. Among children aged older than 6 months with no prior hospitalizations in the last six months (new admission), procedures, prolonged LOS, and an emergency department visit in the past six months were associated with reduced readmission. Among children younger than 6 months (young infants), LOS, prior visits, and critical procedures were associated with readmission. The area under the receiver operating characteristics curve was 83.1 for the recent admission cohort, 76.1 for the new admission cohort, and 80.3 for the young infant cohort.

“These models may allow future improvements in tailored discharge preparedness to prevent high-risk readmissions,” the authors write.

Abstract/Full Text