Personalizing renal replacement therapy initiation in the intensive care unit: a reinforcement learning-based strategy with external validation on the AKIKI randomized controlled trials.

OBJECTIVE: The timely initiation of renal replacement therapy (RRT) for acute kidney injury (AKI) requires sequential decision-making tailored to individuals' evolving characteristics. To learn and validate optimal strategies for RRT initiation, we used reinforcement learning on clinical data from routine care and randomized controlled trials. MATERIALS AND METHODS: We used the MIMIC-III database for development and AKIKI trials for validation. Participants were adult ICU patients with severe AKI receiving mechanical ventilation or catecholamine infusion. We used a doubly robust estimator to learn when to start RRT after the occurrence of severe AKI for three days in a row. We developed a "crude strategy" maximizing the population-level hospital-free days at day 60 (HFD60) and a "stringent strategy" recommending RRT when there is significant evidence of benefit for an individual. For validation, we evaluated the causal effects of implementing our learned strategies versus following current best practices on HFD60. RESULTS: We included 3748 patients in the development set and 1068 in the validation set. Through external validation, the crude and stringent strategies yielded an average difference of 13.7 [95% CI -5.3 to 35.7] and 14.9 [95% CI -3.2 to 39.2] HFD60, respectively, compared to current best practices. The stringent strategy led to initiating RRT within 3 days in 14% of patients versus 38% under best practices. DISCUSSION: Implementing our strategies could improve the average number of days that ICU patients spend alive and outside the hospital while sparing RRT for many. CONCLUSION: We developed and validated a practical and interpretable dynamic decision support system for RRT initiation in the ICU.

Renal replacement therapy initiation strategies in comatose patients with severe acute kidney injury: a secondary analysis of a multicenter randomized controlled trial.

PURPOSE: The effect of renal replacement therapy (RRT) in comatose patients with acute kidney injury (AKI) remains unclear. We compared two RRT initiation strategies on the probability of awakening in comatose patients with severe AKI. METHODS: We conducted a post hoc analysis of a trial comparing two delayed RRT initiation strategies in patients with severe AKI. Patients were monitored until they had oliguria for more than 72 h and/or blood urea nitrogen higher than 112 mg/dL and then randomized to a delayed strategy (RRT initiated after randomization) or a more-delayed one (RRT initiated if complication occurred or when blood urea nitrogen exceeded 140 mg/dL). We included only comatose patients (Richmond Agitation-Sedation scale [RASS] < - 3), irrespective of sedation, at randomization. A multi-state model was built, defining five mutually exclusive states: death, coma (RASS < - 3), incomplete awakening (RASS [- 3; - 2]), awakening (RASS [- 1; + 1] two consecutive days), and agitation (RASS > + 1). Primary outcome was the transition from coma to awakening during 28 days after randomization. RESULTS: A total of 168 comatose patients (90 delayed and 78 more-delayed) underwent randomization. The transition intensity from coma to awakening was lower in the more-delayed group (hazard ratio [HR] = 0.36 [0.17-0.78]; p = 0.010). Time spent awake was 10.11 days [8.11-12.15] and 7.63 days [5.57-9.64] in the delayed and the more-delayed groups, respectively. Two sensitivity analyses were performed based on sedation status and sedation practices across centers, yielding comparable results. CONCLUSION: In comatose patients with severe AKI, a more-delayed RRT initiation strategy resulted in a lower chance of transitioning from coma to awakening.

Regional Practice Variation and Outcomes in the Standard Versus Accelerated Initiation of Renal Replacement Therapy in Acute Kidney Injury (STARRT-AKI) Trial: A Post Hoc Secondary Analysis.

OBJECTIVES: Among patients with severe acute kidney injury (AKI) admitted to the ICU in high-income countries, regional practice variations for fluid balance (FB) management, timing, and choice of renal replacement therapy (RRT) modality may be significant. DESIGN: Secondary post hoc analysis of the STandard vs. Accelerated initiation of Renal Replacement Therapy in Acute Kidney Injury (STARRT-AKI) trial (ClinicalTrials.gov number NCT02568722). SETTING: One hundred-fifty-three ICUs in 13 countries. PATIENTS: Altogether 2693 critically ill patients with AKI, of whom 994 were North American, 1143 European, and 556 from Australia and New Zealand (ANZ). INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Total mean FB to a maximum of 14 days was +7199 mL in North America, +5641 mL in Europe, and +2211 mL in ANZ (p < 0.001). The median time to RRT initiation among patients allocated to the standard strategy was longest in Europe compared with North America and ANZ (p < 0.001; p < 0.001). Continuous RRT was the initial RRT modality in 60.8% of patients in North America and 56.8% of patients in Europe, compared with 96.4% of patients in ANZ (p < 0.001). After adjustment for predefined baseline characteristics, compared with North American and European patients, those in ANZ were more likely to survive to ICU (p < 0.001) and hospital discharge (p < 0.001) and to 90 days (for ANZ vs. Europe: risk difference [RD], -11.3%; 95% CI, -17.7% to -4.8%; p < 0.001 and for ANZ vs. North America: RD, -10.3%; 95% CI, -17.5% to -3.1%; p = 0.007). CONCLUSIONS: Among STARRT-AKI trial centers, significant regional practice variation exists regarding FB, timing of initiation of RRT, and initial use of continuous RRT. After adjustment, such practice variation was associated with lower ICU and hospital stay and 90-day mortality among ANZ patients compared with other regions.

Initiation of continuous renal replacement therapy versus intermittent hemodialysis in critically ill patients with severe acute kidney injury: a secondary analysis of STARRT-AKI trial.

BACKGROUND: There is controversy regarding the optimal renal-replacement therapy (RRT) modality for critically ill patients with acute kidney injury (AKI). METHODS: We conducted a secondary analysis of the STandard versus Accelerated Renal Replacement Therapy in Acute Kidney Injury (STARRT-AKI) trial to compare outcomes among patients who initiated RRT with either continuous renal replacement therapy (CRRT) or intermittent hemodialysis (IHD). We generated a propensity score for the likelihood of receiving CRRT and used inverse probability of treatment with overlap-weighting to address baseline inter-group differences. The primary outcome was a composite of death or RRT dependence at 90-days after randomization. RESULTS: We identified 1590 trial participants who initially received CRRT and 606 who initially received IHD. The composite outcome of death or RRT dependence at 90-days occurred in 823 (51.8%) patients who commenced CRRT and 329 (54.3%) patients who commenced IHD (unadjusted odds ratio (OR) 0.90; 95% confidence interval (CI) 0.75-1.09). After balancing baseline characteristics with overlap weighting, initial receipt of CRRT was associated with a lower risk of death or RRT dependence at 90-days compared with initial receipt of IHD (OR 0.81; 95% CI 0.66-0.99). This association was predominantly driven by a lower risk of RRT dependence at 90-days (OR 0.61; 95% CI 0.39-0.94). CONCLUSIONS: In critically ill patients with severe AKI, initiation of CRRT, as compared to IHD, was associated with a significant reduction in the composite outcome of death or RRT dependence at 90-days.

Long-term outcomes after severe acute kidney injury in critically ill patients: the SALTO study.

BACKGROUND: The extent of the consequences of an episode of severe acute kidney injury (AKI) on long-term outcome of critically ill patients remain debated. We conducted a prospective follow-up of patients included in a large multicenter clinical trial of renal replacement therapy (RRT) initiation strategy during severe AKI (the Artificial Kidney Initiation in Kidney Injury, AKIKI) to investigate long-term survival, renal outcome and health related quality of life (HRQOL). We also assessed the influence of RRT initiation strategy on these outcomes. RESULTS: Follow-up of patients extended from 60 days to a median of 3.35 years [interquartile range (IQR), 1.89 to 4.09] after the end of initial study. Of the 619 patients included in the AKIKI trial, 316 survived after 60 days. The overall survival rate at 3 years from inclusion was 39.4% (95% CI 35.4 to 43.4). A total of 46 patients (on the 175 with available data on long-term kidney function) experienced worsening of renal function (WRF) at the time of follow-up [overall incidence of 26%, cumulative incidence at 4 years: 20.6% (CI 95% 13.0 to 28.3)]. Fifteen patients required chronic dialysis (5% of patients who survived after day 90). Among the 226 long-term survivors, 80 (35%) answered the EQ-5D questionnaire. The median index value reported was 0.67 (IQR 0.40 to 1.00) indicating a noticeable alteration of quality of life. Initiation strategy for RRT had no effect on any long-term outcome. CONCLUSION: Severe AKI in critically ill patients was associated with a high proportion of death within the first 2 months but less so during long-term follow-up. A quarter of long-term survivors experienced a WRF and suffered from a noticeable impairment of quality of life. Renal replacement therapy initiation strategy was not associated with mortality outcome.

Debate: Intermittent Hemodialysis versus Continuous Kidney Replacement Therapy in the Critically Ill Patient: The Choice Should Be Evidence Based.

Kidney replacement therapy (KRT) plays a major role in the treatment of severe AKI. Intermittent hemodialysis (HD) and continuous KRT (CKRT) are the main modalities in critically ill patients with AKI. CKRT is the preferred modality in many countries because of its alleged superiority on both hemodynamic tolerance and on kidney function recovery. In fact, randomized controlled trials (RCTs) comparing the two modalities have not shown any actual benefit of one technique over the other on mortality, hemodynamics, or kidney function recovery. Those RCTs were conducted more than 15 years ago. Major progress was eventually made leading to much lower mortality rates in recent studies than in previous studies. In addition, those RCTs included a noticeable proportion of patients who could have recovered without ever receiving KRT, as demonstrated by several recent studies. In the absence of evidence of clinical superiority of one KRT modality, the choice must be addressed not only regarding clinical outcome but also resources and logistics. Conclusions of health technology assessments and study reports were heterogeneous and conflicting concerning cost-effectiveness of intermittent HD versus CKRT. All these considerations justify a reevaluation of the issue in new RCTs that take into account recent knowledge on KRT initiation and management. Pending results of such study, the choice should be guided mainly by organizational considerations in each unit and without condemning any modality in the absence of proof.

Impact of renal replacement therapy strategy on beta-lactam plasma concentrations: the BETAKIKI study-an ancillary study of a randomized controlled trial.

BACKGROUND: Sepsis prognosis correlates with antibiotic adequacy at the early phase. This adequacy is dependent on antibacterial spectrum, bacterial resistance profile and antibiotic dosage. Optimal efficacy of beta-lactams mandates concentrations above the minimal inhibitory concentration (MIC) of the targeted bacteria for the longest time possible over the day. Septic acute kidney injury (AKI) is the most common AKI syndrome in ICU and often mandates renal replacement therapy (RRT) initiation. Both severe AKI and RRT may increase outside target antibiotic concentrations and ultimately alter patient's prognosis. PATIENTS AND METHODS: This is a secondary analysis of a randomized controlled trial that compared an early RRT initiation strategy with a delayed one in 620 critically ill patients undergoing severe AKI (defined by KDIGO 3). We compared beta-lactam trough concentrations between the two RRT initiation strategies. The primary outcome was the proportion of patients with sufficient trough plasma concentration of beta-lactams defined by trough concentration above 4 times the MIC. We hypothesized that early initiation of RRT could be associated with an insufficient antibiotic plasma trough concentration compared to patients allocated to the delayed strategy. RESULTS: One hundred and twelve patients were included: 53 in the early group and 59 in the delayed group. Eighty-three patients (74%) had septic shock on inclusion. Trough beta-lactam plasma concentration was above 4 times the MIC breakpoint in 80.4% (n = 90) of patients of the whole population, without differences between the early and the delayed groups (79.2% vs. 81.4%, respectively, p = 0.78). On multivariate analysis, the presence of septic shock and a higher mean arterial pressure were significantly associated with a greater probability of adequate antibiotic trough concentration [OR 3.95 (1.14;13.64), p = 0.029 and OR 1.05 (1.01;1.10), p = 0.013, respectively). Evolution of procalcitonin level and catecholamine-free days as well as mortality did not differ whether beta-lactam trough concentration was above 4 times the MIC or not. CONCLUSIONS: In this secondary analysis of a randomized controlled trial, renal replacement therapy initiation strategy did not significantly influence plasma trough concentrations of beta-lactams in ICU patients with severe AKI. Presence of septic shock on inclusion was the main variable associated with a sufficient beta-lactam concentration. TRIAL REGISTRATION: The AKIKI trial was registered on ClinicalTrials.gov (Identifier: NCT01932190) before the inclusion of the first patient.

Continuous renal replacement therapy versus intermittent hemodialysis as first modality for renal replacement therapy in severe acute kidney injury: a secondary analysis of AKIKI and IDEAL-ICU studies.

BACKGROUND: Intermittent hemodialysis (IHD) and continuous renal replacement therapy (CRRT) are the two main RRT modalities in patients with severe acute kidney injury (AKI). Meta-analyses conducted more than 10 years ago did not show survival difference between these two modalities. As the quality of RRT delivery has improved since then, we aimed to reassess whether the choice of IHD or CRRT as first modality affects survival of patients with severe AKI. METHODS: This is a secondary analysis of two multicenter randomized controlled trials (AKIKI and IDEAL-ICU) that compared an early RRT initiation strategy with a delayed one. We included patients allocated to the early strategy in order to emulate a trial where patients would have been randomized to receive either IHD or CRRT within twelve hours after the documentation of severe AKI. We determined each patient's modality group as the first RRT modality they received. The primary outcome was 60-day overall survival. We used two propensity score methods to balance the differences in baseline characteristics between groups and the primary analysis relied on inverse probability of treatment weighting. RESULTS: A total of 543 patients were included. Continuous RRT was the first modality in 269 patients and IHD in 274. Patients receiving CRRT had higher cardiovascular and total-SOFA scores. Inverse probability weighting allowed to adequately balance groups on all predefined confounders. The weighted Kaplan-Meier death rate at day 60 was 54·4% in the CRRT group and 46·5% in the IHD group (weighted HR 1·26, 95% CI 1·01-1·60). In a complementary analysis of less severely ill patients (SOFA score: 3-10), receiving IHD was associated with better day 60 survival compared to CRRT (weighted HR 1.82, 95% CI 1·01-3·28; p < 0.01). We found no evidence of a survival difference between the two RRT modalities in more severe patients. CONCLUSION: Compared to IHD, CRRT as first modality seemed to convey no benefit in terms of survival or of kidney recovery and might even have been associated with less favorable outcome in patients with lesser severity of disease. A prospective randomized non-inferiority trial should be implemented to solve the persistent conundrum of the optimal RRT technique.

Personalization of renal replacement therapy initiation: a secondary analysis of the AKIKI and IDEAL-ICU trials.

BACKGROUND: Trials comparing early and delayed strategies of renal replacement therapy in patients with severe acute kidney injury may have missed differences in survival as a result of mixing together patients at heterogeneous levels of risks. Our aim was to evaluate the heterogeneity of treatment effect on 60-day mortality from an early vs a delayed strategy across levels of risk for renal replacement therapy initiation under a delayed strategy. METHODS: We used data from the AKIKI, and IDEAL-ICU randomized controlled trials to develop a multivariable logistic regression model for renal replacement therapy initiation within 48 h after allocation to a delayed strategy. We then used an interaction with spline terms in a Cox model to estimate treatment effects across the predicted risks of RRT initiation. RESULTS: We analyzed data from 1107 patients (619 and 488 in the AKIKI and IDEAL-ICU trial respectively). In the pooled sample, we found evidence for heterogeneous treatment effects (P = 0.023). Patients at an intermediate-high risk of renal replacement therapy initiation within 48 h may have benefited from an early strategy (absolute risk difference, - 14%; 95% confidence interval, - 27% to - 1%). For other patients, we found no evidence of benefit from an early strategy of renal replacement therapy initiation but a trend for harm (absolute risk difference, 8%; 95% confidence interval, - 5% to 21% in patients at intermediate-low risk). CONCLUSIONS: We have identified a clinically sound heterogeneity of treatment effect of an early vs a delayed strategy of renal replacement therapy initiation that may reflect varying degrees of kidney demand-capacity mismatch.

Vascular access for renal replacement therapy among 459 critically ill patients: a pragmatic analysis of the randomized AKIKI trial.

BACKGROUND: Vascular access for renal replacement therapy (RRT) is routine question in the intensive care unit. Randomized trials comparing jugular and femoral sites have shown similar rate of nosocomial events and catheter dysfunction. However, recent prospective observational data on RRT catheters use are scarce. We aimed to assess the site of RRT catheter, the reasons for catheter replacement, and the complications according to site in a large population of critically ill patients with acute kidney injury. PATIENTS AND METHODS: We performed an ancillary study of the AKIKI study, a pragmatic randomized controlled trial, in which patients with severe acute kidney injury (KDIGO 3 classification) with invasive mechanical ventilation, catecholamine infusion or both were randomly assigned to either an early or a delayed RRT initiation strategy. The present study involved all patients who underwent at least one RRT session. Number of RRT catheters, insertion sites, factors potentially associated with the choice of insertion site, duration of catheter use, reason for catheter replacement, and complications were prospectively collected. RESULTS: Among the 619 patients included in AKIKI, 462 received RRT and 459 were finally included, with 598 RRT catheters. Femoral site was chosen preferentially (n = 319, 53%), followed by jugular (n = 256, 43%) and subclavian (n = 23, 4%). In multivariate analysis, continuous RRT modality was significantly associated with femoral site (OR = 2.33 (95% CI (1.34-4.07), p = 0.003) and higher weight with jugular site [88.9 vs 83.2 kg, OR = 0.99 (95% CI 0.98-1.00), p = 0.03]. Investigator site was also significantly associated with the choice of insertion site (p = 0.03). Cumulative incidence of catheter replacement did not differ between jugular and femoral site [sHR 0.90 (95% CI 0.64-1.25), p = 0.67]. Catheter dysfunction was the main reason for replacement (n = 47), followed by suspected infection (n = 29) which was actually seldom proven (n = 4). No mechanical complication (pneumothorax or hemothorax) occurred. CONCLUSION: Femoral site was preferentially used in this prospective study of RRT catheters in 31 French intensive care units. The choice of insertion site depended on investigating center habits, weight, RRT modality. A high incidence of catheter infection suspicion led to undue replacement.

Comparison of two delayed strategies for renal replacement therapy initiation for severe acute kidney injury (AKIKI 2): a multicentre, open-label, randomised, controlled trial.

BACKGROUND: Delaying renal replacement therapy (RRT) for some time in critically ill patients with severe acute kidney injury and no severe complication is safe and allows optimisation of the use of medical devices. Major uncertainty remains concerning the duration for which RRT can be postponed without risk. Our aim was to test the hypothesis that a more-delayed initiation strategy would result in more RRT-free days, compared with a delayed strategy. METHODS: This was an unmasked, multicentre, prospective, open-label, randomised, controlled trial done in 39 intensive care units in France. We monitored critically ill patients with severe acute kidney injury (defined as Kidney Disease: Improving Global Outcomes stage 3) until they had oliguria for more than 72 h or a blood urea nitrogen concentration higher than 112 mg/dL. Patients were then randomly assigned (1:1) to either a strategy (delayed strategy) in which RRT was started just after randomisation or to a more-delayed strategy. With the more-delayed strategy, RRT initiation was postponed until mandatory indication (noticeable hyperkalaemia or metabolic acidosis or pulmonary oedema) or until blood urea nitrogen concentration reached 140 mg/dL. The primary outcome was the number of days alive and free of RRT between randomisation and day 28 and was done in the intention-to-treat population. The study is registered with ClinicalTrial.gov, NCT03396757 and is completed. FINDINGS: Between May 7, 2018, and Oct 11, 2019, of 5336 patients assessed, 278 patients underwent randomisation; 137 were assigned to the delayed strategy and 141 to the more-delayed strategy. The number of complications potentially related to acute kidney injury or to RRT were similar between groups. The median number of RRT-free days was 12 days (IQR 0-25) in the delayed strategy and 10 days (IQR 0-24) in the more-delayed strategy (p=0·93). In a multivariable analysis, the hazard ratio for death at 60 days was 1·65 (95% CI 1·09-2·50, p=0·018) with the more-delayed versus the delayed strategy. The number of complications potentially related to acute kidney injury or renal replacement therapy did not differ between groups. INTERPRETATION: In severe acute kidney injury patients with oliguria for more than 72 h or blood urea nitrogen concentration higher than 112 mg/dL and no severe complication that would mandate immediate RRT, longer postponing of RRT initiation did not confer additional benefit and was associated with potential harm. FUNDING: Programme Hospitalier de Recherche Clinique.

Are bedside colonoscopies performed in intensive care unit really useful?

PURPOSE: Effectiveness of bedside Colonoscopies in Intensive Care Unit (CICU) might be limited by the poor quality of colonic preparation, and their feasibility. We sought to describe the indications and the profitability of CICU. METHODS: Retrospective, bicenter observational study (2004-2015) in unselected critically ill patients. We questioned the clinical profitability of CICU, according to its indications and preparation. RESULTS: One hundred and eleven CICU were performed in 84 patients (sex ratio 1.4, 49 M/35F; age 72.9 years [61.7-84.7]), for lower gastro-intestinal bleeding in 67 patients (LGIB, 60.3%) and for other causes in 44 (39.6%). The profitability was more frequent when CICU was performed for another reason than LGIB (75% vs 28.3%; p < 0.0001). Preparation was good in 47 procedures (42.3%) and allowed 33 complete CICU (29.7%). Fifty-six CICU (50.4%) were performed as a 2nd investigation after a contrast enhanced computed tomography. Three CICU were complicated by 3 hemodynamic and 2 respiratory failures, but none of them were fatal. CONCLUSIONS: CICU is clinically useful in half of cases, in the diagnostic and the therapeutic management of critically ill patients. Its profitability is close to scheduled colonoscopies and superior in non-lower gastro-intestinal bleeding indications.