Personalized acute kidney injury treatment.

PURPOSE OF REVIEW: Acute kidney injury (AKI) is a complex syndrome that might be induced by different causes and is associated with an increased morbidity and mortality. Therefore, it is a very heterogeneous syndrome and establishing a "one size fits all" treatment approach might not work. This review aims to examine the potential of personalized treatment strategies for AKI. RECENT FINDINGS: The traditional diagnosis of AKI is based on changes of serum creatinine and urine output, but these two functional biomarkers have several limitations. Recent research identified different AKI phenotypes based on clinical features, biomarkers, and pathophysiological pathways. Biomarkers, such as Cystatin C, NGAL, TIMP2∗IGFBP7, CCL14, and DKK-3, have shown promise in predicting AKI development, renal recovery, and prognosis. Biomarker-guided interventions, such as the implementation of the KDIGO bundle, have demonstrated an improvement in renal outcomes in specific patient groups. SUMMARY: A personalized approach to AKI treatment as well as research is becoming increasingly important as it allows the identification of distinct AKI phenotypes and the potential for targeted interventions. By utilizing biomarkers and clinical features, physicians might be able to stratify patients into subphenotypes, enabling more individualized treatment strategies. This review highlights the potential of personalized AKI treatment, emphasizing the need for further research and large-scale clinical trials to validate the efficacy of these approaches.

Evaluation of Proenkephalin A 119-159 for liberation from renal replacement therapy: an external, multicenter pilot study in critically ill patients with acute kidney injury.

INTRODUCTION: Recent evidence suggests an association of plasma Proenkephalin A 119-159 (penKid) with early and successful liberation from continuous renal replacement therapy (CRRT) in critically ill patients with acute kidney injury. However, these exploratory results are derived from a monocentric trial and therefore require external validation in a multicenter cohort. METHODS: Data and plasma samples from the "Effect of Regional Citrate Anticoagulation versus Systemic Heparin Anticoagulation During Continuous Kidney Replacement Therapy on Dialysis Filter Life Span and Mortality Among Critically Ill Patients With Acute Kidney Injury-A Randomized Clinical Trial" (RICH Trial) were used for this validation study. PenKid was measured in all plasma samples available at CRRT initiation and at day 3 of CRRT. Patients were categorized into low and high penKid groups with a cutoff at 100 pmol/l. Competing-risk time-to-event analyses were performed. Competing risk endpoints were successful and unsuccessful liberation from CRRT, the latter meaning death or initiation of a new RRT within one week of discontinuation of primary CRRT. Then penKid was compared to urinary output. RESULTS: Low pre-CRRT penKid levels at CRRT initiation were not associated with early and successful liberation from CRRT compared to patients with high pre-CRRT penKid levels [subdistribution hazard ratio (sHR) 1.01, 95% CI 0.73-1.40, p = 0.945]. However, the landmark analysis on day 3 of ongoing CRRT demonstrated an association between low penKid levels and successful liberation from CRRT (sHR 2.35, 95% CI 1.45-3.81, p < 0.001) and an association between high penKid levels and unsuccessful liberation (sHR 0.46, 95% CI 0.26-0.80, p = 0.007). High daily urinary output (> 436 ml/d) was even stronger associated with successful liberation (sHR 2.91, 95% CI 1.80-4.73, p < 0.001) compared to penKid. DISCUSSION: This study suggests that penKid may be a competent biomarker to monitor the recovery of kidney function during CRRT. This is in line with previous findings and investigated this concept in a multicenter cohort. Again, low penKid was associated with early and successful CRRT liberation, but was outperformed by high daily urinary output. The findings of this study now warrant further evaluation in prospective studies or a randomized controlled trial. Trial registration The RICH Trial was registered at clinicaltrials.gov: NCT02669589. Registered 01 February 2016.

Implementation of Nephroprotective Measures to Prevent Acute Kidney Injury in Septic Patients: A Retrospective Cohort Study.

BACKGROUND: Sepsis remains the leading cause of mortality in critically ill patients, and mortality is increased when acute kidney injury (AKI) occurs. The Kidney Disease: Improving Global Outcomes (KDIGO) guideline recommends the implementation of supportive measures in patients at high risk for AKI. However, it remains unclear to what extent these nephroprotective measures are implemented in daily clinical practice in critically ill patients, especially those with high-risk exposures such as sepsis. METHODS: We analyzed the Medical Information Mart for Intensive Care IV (MIMIC-IV) database to identify septic patients with and without AKI. The primary outcome of interest was the adherence to the KDIGO bundle consisting of avoidance of nephrotoxic agents, implementation of a functional hemodynamic monitoring, optimization of perfusion pressure and volume status, close monitoring of renal function, avoidance of hyperglycemia, and avoidance of radiocontrast agents. Secondary outcomes included the development of AKI, progression of AKI, the use of renal replacement therapy (RRT), mortality, and a composite end point consisting of progression of AKI and mortality within 7 days. RESULTS: Our analysis included 34,679 patients with sepsis with 1.6% receiving the complete bundle (10% received 5, 42.3% 4, 35.4% 3, and 9.8% 2 bundle components). In 56.4%, nephrotoxic agents were avoided, and hemodynamic optimization was reached in 86.5%. Secondary end points were improved in patients with bundle adherence. Avoidance of nephrotoxic drugs and optimization of hemodynamics were significantly associated with lower rates of AKI and improved patient outcomes, including 30-day mortality. CONCLUSIONS: Implementation of the KDIGO bundle is poor in patients with sepsis but may be associated with improved outcomes.

Proenkephalin A 119-159 predicts early and successful liberation from renal replacement therapy in critically ill patients with acute kidney injury: a post hoc analysis of the ELAIN trial.

BACKGROUND: Renal replacement therapy (RRT) remains the key rescue therapy for critically ill patients with severe acute kidney injury (AKI). However, there are currently no tools available to predict successful liberation from RRT. Biomarkers may allow for risk stratification and individualization of treatment strategies. Proenkephalin A 119-159 (penKid) has been suggested as a promising marker of kidney function in the context of AKI, but has not yet been evaluated for RRT liberation in critically ill patients with AKI. METHODS: This post hoc analysis included 210 patients from the randomized clinical ELAIN trial and penKid levels were measured in the blood of these patients. Competing risk time-to-event analyses were performed for pre-RRT penKid at initiation of RRT and in a landmark analysis at day 3 after initiation of RRT. Competing risk endpoints were successful liberation from RRT or death without prior liberation from RRT. RESULTS: Low pre-RRT penKid levels (penKid ≤ 89 pmol/l) at RRT initiation were associated with early and successful liberation from RRT compared to patients with high pre-RRT penKid levels (subdistribution hazard ratio (sHR) 1.83, 95%CI 1.26-2.67, p = 0.002, estimated 28d-cumulative incidence function (28d-CIF) of successful liberation from RRT 61% vs. 45%, p = 0.022). This association persisted in the landmark analysis on day 3 of RRT (sHR 1.78, 95%CI 1.17-2.71, p = 0.007, 28d-CIF of successful liberation from RRT 67% vs. 47%, p = 0.018). For both time points, no difference in the competing event of death was detected. CONCLUSIONS: In critically ill patients with RRT-dependent AKI, plasma penKid appears to be a useful biomarker for the prediction of shorter duration and successful liberation from RRT and may allow an individualized approach to guide strategies of RRT liberation in critically ill patients with RRT-dependent AKI. TRIAL REGISTRATION: The ELAIN trial was prospectively registered at the German Clinical Trial Registry (Identifier: DRKS00004367) on 28th of May 2013.

Second trimester fetal thymus size in association to preterm birth.

OBJECTIVES: The aim of this study was to compare the second trimester thymus-thorax-ratio (TTR) between fetuses born preterm (study group) and those born after 37 weeks of gestation were completed (control group). METHODS: This study was conducted as a retrospective evaluation of the ultrasound images of 492 fetuses in the three vessel view. The TTR was defined as the quotient of a.p. thymus diameter and a.p. thoracic diameter. RESULTS: Fetuses that were preterm showed larger TTR (p<0.001) the second trimester than those born after 37 weeks of gestation were completed. The sensitivity of a binary classifier based on TTR for predicting preterm birth (PTB) was 0.792 and the specificity 0.552. CONCLUSIONS: In our study, fetuses affected by PTB showed enlarged thymus size. These findings led us to hypothesize, that inflammation and immunomodulatory processes are altered early in pregnancies affected by PTB. However, TTR alone is not able to predict PTB.

DeepTSE: A Time-Sensitive Deep Embedding of ICU Data for Patient Modeling and Missing Data Imputation.

Missing data is a common problem in the intensive care unit as a variety of factors contribute to incomplete data collection in this clinical setting. This missing data has a significant impact on the accuracy and validity of statistical analyses and prognostic models. Several imputation methods can be used to estimate the missing values based on the available data. Although simple imputations with mean or median generate reasonable results in terms of mean absolute error, they do not account for the currentness of the data. Furthermore, heterogeneous time span of data records adds to this complexity, especially in high-frequency intensive care unit datasets. Therefore, we present DeepTSE, a deep model that is able to cope with both, missing data and heterogeneous time spans. We achieved promising results on the MIMIC-IV dataset that can compete with and even outperform established imputation methods.

Biomarker-guided intervention to prevent acute kidney injury after major surgery (BigpAK-2 trial): study protocol for an international, prospective, randomised controlled multicentre trial.

INTRODUCTION: Previous studies demonstrated that the implementation of the Kidney Disease Improving Global Outcomes (KDIGO) guideline-based bundle, consisting of different supportive measures in patients at high risk for acute kidney injury (AKI), might reduce rate and severity of AKI after surgery. However, the effects of the care bundle in broader population of patients undergoing surgery require confirmation. METHODS AND ANALYSIS: The BigpAK-2 trial is an international, randomised, controlled, multicentre trial. The trial aims to enrol 1302 patients undergoing major surgery who are subsequently admitted to the intensive care or high dependency unit and are at high-risk for postoperative AKI as identified by urinary biomarkers (tissue inhibitor of metalloproteinases 2*insulin like growth factor binding protein 7 (TIMP-2)*IGFBP7)). Eligible patients will be randomised to receive either standard of care (control) or a KDIGO-based AKI care bundle (intervention). The primary endpoint is the incidence of moderate or severe AKI (stage 2 or 3) within 72 hours after surgery, according to the KDIGO 2012 criteria. Secondary endpoints include adherence to the KDIGO care bundle, occurrence and severity of any stage of AKI, change in biomarker values during 12 hours after initial measurement of (TIMP-2)*(IGFBP7), number of free days of mechanical ventilation and vasopressors, need for renal replacement therapy (RRT), duration of RRT, renal recovery, 30-day and 60-day mortality, intensive care unit length-of-stay and hospital length-of-stay and major adverse kidney events. An add-on study will investigate blood and urine samples from recruited patients for immunological functions and kidney damage. ETHICS AND DISSEMINATION: The BigpAK-2 trial was approved by the Ethics Committee of the Medical Faculty of the University of Münster and subsequently by the corresponding Ethics Committee of the participating sites. A study amendment was approved subsequently. In the UK, the trial was adopted as an NIHR portfolio study. Results will be disseminated widely and published in peer-reviewed journals, presented at conferences and will guide patient care and further research. TRIAL REGISTRATION NUMBER: NCT04647396.

Exponential growth of systematic reviews assessing artificial intelligence studies in medicine: challenges and opportunities.

The evidence-based medicine (EBM) movement is stepping up its efforts to assess medical artificial intelligence (AI) and data science studies. Since 2017, there has been a marked increase in the number of published systematic reviews that assess medical AI studies. Increasingly, data from observational studies are used in systematic reviews of medical AI studies. Assessment of risk of bias is especially important in medical AI studies to detect possible "AI bias".

Prediction of Acute Kidney Injury in the Intensive Care Unit: Preliminary Findings in a European Open Access Database.

Acute kidney injury (AKI) is a common complication in critically ill patients and is associated with long-term complications and an increased mortality. This work presents preliminary findings from the first freely available European intensive care database released by Amsterdam UMC. A machine learning (ML) model was developed to predict AKI in the intensive care unit 12 hours before the actual event. Main features of the model included medications and hemodynamic parameters. Our models perform with an accuracy of 81.8% on moderate to severe AKI and 79.8% on all AKI patients. Those results can compete with models reported in the literature and introduce an ML model for AKI based on European patient data.