The ACCORD trial has yielded many findings that were contradictory to its original hypothesis.

Explorations on the patients' characteristics that modulate the treatment effect might help explain these findings.

The recent innovation in machine learning allow us to identify important modulators of treatment efficacy.

The results of such a study can help develop a more precise approach to allocating therapy.

To examine patient characteristics that may modulate the heterogeneous treatment effect of intensive systolic blood pressure control (SBP) and intensive glycemic control on incident heart failure (HF) risk in people with type 2 diabetes.

We analyzed 10,251 participants from the ACCORD glucose trial, and 4733 from the SBP sub-trial separately. We applied a robust machine-learning (ML) algorithm, namely the causal forest/causal tree analysis, to each trial to identify participants' characteristics that modulate the effectiveness of each trial intervention.

Diastolic blood pressure (DBP) was found to interact with intensive glycemic control and impact outcomes. An increased HF risk associated with intensive glycemic control (absolute risk change (ARC): 2.28 %, 95 % confidence interval (CI): 0.69 % to 3.90 %; relative risk (RR):1.57, 95 % CI: 1.15 to 2.20; P < 0.05) was observed in individuals with baseline DBP at the lowest tertile (45–69 mmHg), while no changes in HF risk associated with intensive glycemic control were observed in individuals with baseline DBP at the middle (70–79 mmHg) and the highest tertiles (80–100 mmHg). Liver function was identified as a modulator of intensive BP control, and baseline Alanine transaminase (ALT) level was a sensitive marker for the modulating effect. Only individuals with baseline ALT at the lowest tertile (8–19 mg/dl) benefited from the intensive BP control for HF prevention (ARC: −1.95 %, 95 % CI: −4.06 % to 0.11 %; RR:0.62. 95 % CI: 0.27 to 0.94; P < 0.05).

Our study is the first to observe and quantify the potential synergistic harmful effect when low DBP was combined with an intensive blood glucose intervention. Recognizing these may help clinicians develop a more precise approach to such treatments, thus increasing the efficiency and outcomes of diabetes treatments.

Cardiovascular disease

Heterogeneous treatment effect

The Action to Control Cardiovascular Risk in Diabetes Trial

The number needed to treat

Expected mean squared error

Nonalcoholic fatty liver disease

Type 2 diabetes

Machine learning

ACCORD trial

Heart failure hospitalization

Intensive blood glucose intervention

Diastolic blood pressure

© 2022 Elsevier Inc. All rights reserved.