CHICAGO — A randomized trial at the University of Chicago, conducted from March 2019 to August 2024, found that early nephrology consultations triggered by real-time machine-learning risk scores did not reduce acute kidney injury or improve secondary outcomes. The trial randomized 180 hospitalized patients who did not have baseline acute kidney injury but triggered an Electronic Signal to Prevent AKI (ESTOP-AKI) score greater than 0.01.

The median patient age was 62.5 years. Men comprised 56.7% of participants, while 52.8% were white and 41.1% were Black. The adjusted mean difference in 7-day serum creatinine was 0.04 mg/dL for the early consultation group and -0.03 mg/dL for the usual care group, with a P-value of 0.30 for the difference between the groups.

In the early consultation group, 42% of patients developed Kidney Disease: Improving Global Outcomes (KDIGO) stage 1 or higher acute kidney injury, compared to 36% in the usual care group. The P-value for this difference was 0.47. For KDIGO stage 2 or higher acute kidney injury, 19% of patients in the early consultation group developed it, versus 13% in the usual care group, with a P-value of 0.28.

The intervention also did not show an effect on secondary endpoints, including acute kidney injury severity, hospital length of stay, inpatient mortality, or 90-day outcomes. There were 121 early nephrology consultations with 270 recommendations in the intervention group, compared to 19 usual care consultations with 36 recommendations in the control group.

Recommendations for changing patients' diet were made in 28.9% of the intervention group and 13.9% of the usual care group. Recommendations for stopping medications occurred in 20.7% of the intervention group and 16.7% of the usual care group, while recommendations for changing medication doses occurred in 11.9% and 11.1%, respectively. The automated nephrology consultation included an in-person assessment covering volume status, kidney perfusion, drug dosing, electrolytes, nutrition, and diagnostic testing.

Regarding adherence, recommendations for medication dosage and discontinuation, diuretics or fluids, and vasopressors were completely followed in 68% of cases in the usual care arm, but only in 41% of cases in the intervention arm. The findings were framed as traditional, non-mandatory consultation notes rather than direct orders, and primary teams were not obligated to follow the recommendations in the intervention group.

Jay L. Koyner, MD, said in a publication, "It is possible that this low uptake of early consultative recommendations contributed to the trial outcome." He added, "It is not clear if stopping exposure to a nephrotoxin or dose reducing a medication before there is evidence of [serum creatinine]-based AKI improves outcomes."