There has been a growing demand for the development of validated data-driven decision support tools for the personalization of renal replacement therapy (RRT) initiation in intensive care unit (ICU) patients with acute kidney injury. Trials sequentially randomizing patients each day have never been conducted for RRT initiation. We used clinical data from routine care and trials to learn and validate optimal dynamic strategies for RRT initiation in the ICU.

We included participants from the MIMIC-III database for development and AKIKI and AKIKI2 (two randomized controlled trials on RRT timing) for validation. Participants were eligible if they were adult ICU patients with severe acute kidney injury, receiving invasive mechanical ventilation, catecholamine infusion, or both. We used a doubly-robust dynamic treatment regimen to learn when to start RRT after the occurrence of severe acute kidney injury given a patient's evolving characteristics—for three days in a row. The ‘crude strategy’ aimed to maximize hospital-free days at day 60 (HFD60). The ‘stringent strategy’ recommended initiating RRT only when there was evidence at the 0.05 threshold that a patient would benefit from initiation. For external validation, we evaluated the causal effects of implementing our learned strategies versus following current best practices on HFD60.

We included 3 748 patients in the development set (median age 69y [IQR 57– 79], 1 695 [45·2%] female), and 1 068 in the validation set (median age 67y [IQR 58–75], 344 [32·2%] female). Through external validation, we found that compared to current best practices, the crude and stringent strategies improved average HFD60 by 13.7 [95% CI -5.3– 35.7], and 14.9 [95% CI -3.2–39.2] days respectively. Figure 1A displays recommendations from the learned strategies. Figure 1B shows the discrepancies between current best practices and the crude strategy. Contrasted to best practices where 38% of patients initiated RRT within three days, we estimated that only 14% of patients would under the stringent strategy.

We developed a practical and interpretable dynamic decision support system for RRT initiation in the ICU. Implementing individualized strategies could improve the average number of days that ICU patients spend alive and outside the hospital. The stringent strategy entailed less frequent usage of RRT. This new individualized strategy could help save important health resources all the while reducing unnecessary treatment burdens.

Acute kidney injury, Renal replacement therapy, Personalized medicine, Causal inference, Reinforcement learning

Les auteurs n'ont pas précisé leurs éventuels liens d'intérêts.