Multi-perspective predictive modeling for acute kidney injury in general hospital populations using electronic medical records

Abstract Objectives Acute kidney injury (AKI) in hospitalized patients puts them at much higher risk for developing future health problems such as chronic kidney disease, stroke, and heart disease. Accurate AKI prediction would allow timely prevention and intervention. However, current AKI prediction researches pay less attention to model building strategies that meet complex clinical application scenario. This study aims to build and evaluate AKI prediction models from multiple perspectives that reflect different clinical applications. Materials and Methods A retrospective cohort of 76 957 encounters and relevant clinical variables were extracted from a tertiary care, academic hospital electronic medical record (EMR) system between November 2007 and December 2016. Five machine learning methods were used to build prediction models. Prediction tasks from 4 clinical perspectives with different modeling and evaluation strategies were designed to build and evaluate the models. Results Experimental analysis of the AKI prediction models built from 4 different clinical perspectives suggest a realistic prediction performance in cross-validated area under the curve ranging from 0.720 to 0.764. Discussion Results show that models built at admission is effective for predicting AKI events in the next day; models built using data with a fixed lead time to AKI onset is still effective in the dynamic clinical application scenario in which each patient’s lead time to AKI onset is different. Conclusion To our best knowledge, this is the first systematic study to explore multiple clinical perspectives in building predictive models for AKI in the general inpatient population to reflect real performance in clinical application.

Download Full-text

Prediction Scores for Acute Kidney Injury following Adult Cardiac Surgery

10.21203/rs.3.rs-88293/v1 ◽

2020 ◽

Author(s):

Yu Tian ◽

Wei Zhao ◽

Yuefu Wang ◽

Chunrong Wang ◽

Xiaolin Diao ◽

...

Keyword(s):

Acute Kidney Injury ◽

Cardiac Surgery ◽

Prediction Model ◽

Prediction Models ◽

Area Under The Curve ◽

Kidney Injury ◽

Scoring Systems ◽

Multivariable Logistic Regression Analysis ◽

Derivation Cohort ◽

Associated Risk Factors

Abstract Background In the development of scoring systems for acute kidney injury (AKI) following cardiac surgery, previous investigations have primarily and solely attached importance to preoperative associated risk factors without any consideration for surgery-derived physiopathology. We sought to internally derive and then validate risk score systems using pre- and intraoperative variables to predict the occurrence of any-stage (stage 1-3) and stage-3 AKI within 7 days.Methods Patients undergoing cardiac surgery from Jan 1, 2012, to Jan 1, 2019, were enrolled in our retrospective study. The clinical data were divided into a derivation cohort (n= 43799) and a validation cohort (n= 14600). Multivariable logistic regression analysis was used to develop the prediction models.Results The overall prevalence of any-stage and stage-3 AKI after cardiac surgery was 34.3% and 1.7%, respectively. Any-stage AKI prediction-model discrimination measured by the area under the curve (AUC) was acceptable (AUC = 0.69, 95% CI: 0.68, 0.69), and the prediction model calibration measured by the Hosmer-Lemshow test was good (P = 0.95). The stage-3 AKI prediction model had an AUC of 0.84 (95% CI 0.83, 0.85) and good calibration according to the Hosmer-Lemshow test (P = 0.73).Conclusions Using pre- and intraoperative data, we developed two scoring systems for any-stage AKI and stage-3 AKI in a cardiac surgery population. These scoring systems can potentially be adopted clinically in the field of AKI recognition and therapeutic intervention.

Download Full-text

A nomogram incorporating functional and tubular damage biomarkers to predict the risk of acute kidney injury for septic patients

BMC Nephrology ◽

10.1186/s12882-021-02388-w ◽

2021 ◽

Vol 22 (1) ◽

Author(s):

Jianchao Ma ◽

Yujun Deng ◽

Haiyan Lao ◽

Xin Ouyang ◽

Silin Liang ◽

...

Keyword(s):

Acute Kidney Injury ◽

Clinical Utility ◽

Prediction Models ◽

Validation Cohort ◽

Tertiary Care ◽

Kidney Injury ◽

Apache Ii Score ◽

Tubular Damage ◽

Care Hospital ◽

Icu Admission

Abstract Background Combining tubular damage and functional biomarkers may improve prediction precision of acute kidney injury (AKI). Serum cystatin C (sCysC) represents functional damage of kidney, while urinary N-acetyl-β-D-glucosaminidase (uNAG) is considered as a tubular damage biomarker. So far, there is no nomogram containing this combination to predict AKI in septic cohort. We aimed to compare the performance of AKI prediction models with or without incorporating these two biomarkers and develop an effective nomogram for septic patients in intensive care unit (ICU). Methods This was a prospective study conducted in the mixed medical-surgical ICU of a tertiary care hospital. Adults with sepsis were enrolled. The patients were divided into development and validation cohorts in chronological order of ICU admission. A logistic regression model for AKI prediction was first constructed in the development cohort. The contribution of the biomarkers (sCysC, uNAG) to this model for AKI prediction was assessed with the area under the receiver operator characteristic curve (AUC), continuous net reclassification index (cNRI), and incremental discrimination improvement (IDI). Then nomogram was established based on the model with the best performance. This nomogram was validated in the validation cohort in terms of discrimination and calibration. The decision curve analysis (DCA) was performed to evaluate the nomogram’s clinical utility. Results Of 358 enrolled patients, 232 were in the development cohort (69 AKI), while 126 in the validation cohort (52 AKI). The first clinical model included the APACHE II score, serum creatinine, and vasopressor used at ICU admission. Adding sCysC and uNAG to this model improved the AUC to 0.831. Furthermore, incorporating them significantly improved risk reclassification over the predictive model alone, with cNRI (0.575) and IDI (0.085). A nomogram was then established based on the new model including sCysC and uNAG. Application of this nomogram in the validation cohort yielded fair discrimination with an AUC of 0.784 and good calibration. The DCA revealed good clinical utility of this nomogram. Conclusions A nomogram that incorporates functional marker (sCysC) and tubular damage marker (uNAG), together with routine clinical factors may be a useful prognostic tool for individualized prediction of AKI in septic patients.

Download Full-text

A simple nomogram to predict contrast-induced acute kidney injury in patients with congestive heart failure undergoing coronary angiography

European Heart Journal ◽

10.1093/ehjci/ehaa946.2554 ◽

2020 ◽

Vol 41 (Supplement_2) ◽

Author(s):

L Lei ◽

Y He ◽

Z Guo ◽

B Liu ◽

J Liu ◽

...

Keyword(s):

Heart Failure ◽

Congestive Heart Failure ◽

Acute Kidney Injury ◽

Coronary Angiography ◽

Prediction Models ◽

Validation Cohort ◽

Kidney Injury ◽

Class Ii ◽

Functional Class ◽

Killip Class

Abstract Background Patients with congestive heart failure (CHF) are vulnerable to contrast-induced acute kidney injury (CI-AKI), but few prediction models are currently available. Objectives We aimed to establish a simple nomogram for CI-AKI risk assessment for patients with CHF undergoing coronary angiography. Methods A total of 1876 consecutive patients with CHF (defined as New York Heart Association functional class II-IV or Killip class II-IV) were enrolled and randomly (2:1) assigned to a development cohort and a validation cohort. The endpoint was CI-AKI defined as serum creatinine elevation of ≥0.3 mg/dL or 50% from baseline within the first 48–72 hours following the procedure. Predictors for the nomogram were selected by multivariable logistic regression with a stepwise approach. The discriminative power was assessed using the area under the receiver operating characteristic (ROC) curve and was compared with the classic Mehran score in the validation cohort. Calibration was assessed using the Hosmer–Lemeshow test and 1000 bootstrap samples. Results The incidence of CI-AKI was 9.06% (n=170) in the total sample, 8.64% (n=109) in the development cohort and 9.92% (n=61) in the validation cohort (p=0.367). The simple nomogram including four predictors (age, intra-aortic balloon pump, acute myocardial infarction and chronic kidney disease) demonstrated a similar predictive power as the Mehran score (area under the curve: 0.80 vs 0.75, p=0.061), as well as a well-fitted calibration curve. Conclusions The present simple nomogram including four predictors is a simple and reliable tool to identify CHF patients at risk of CI-AKI, whereas further external validations are needed. Figure 1 Funding Acknowledgement Type of funding source: None

Download Full-text

P0614URINARY EXOSOMAL MICRORNA-21 AS A MARKER OF SCRUB TYPHUS-ASSOCIATED ACUTE KIDNEY INJURY

Nephrology Dialysis Transplantation ◽

10.1093/ndt/gfaa142.p0614 ◽

2020 ◽

Vol 35 (Supplement_3) ◽

Author(s):

In O Sun ◽

Kwang Young Lee ◽

A Young Cho

Keyword(s):

Acute Kidney Injury ◽

Kidney Disease ◽

Scrub Typhus ◽

Area Under The Curve ◽

Kidney Injury ◽

Diagnostic Value ◽

Cross Sectional Study ◽

Total Leukocyte Count ◽

Cross Sectional ◽

Exosomal Mirna

Abstract Background and Aims Urinary microRNA (miRNA)-21 is reported to be a biomarker for detection of acute kidney injury (AKI). Analysis of urinary exsome may serve as a novel diagnostic approach in kidney disease. The aim of this study is to investigate the clinical significance of urinary exosomal miRNA-21 for AKI in patients with scrub typhus. Method In a cross-sectional study, we collected 138 urine samples at the time of admission from 145 patients with scrub typhus. For 25 patients with scrub typhus-associated AKI and 25 age, sex-matched scrub typhus patient without AKI, we measured miRNA-21 in urinary exosomal fraction and compared diagnostic value in predictiong AKI. Results Compared with patients in the non-AKI group, patients in the AKI group were more likely to have one or more comorbidity such as diabetes (50% vs. 5%, P<0.01) and chronic kidney disease (8% vs. 0%, P<0.01). Total leukocyte count were higher in patients with AKI than in those without AKI (10.40 × 103/ mL vs. 6.40 × 103/mL, P<0.01). The levels of urinary miRNA-21 were higher in the AKI group than in the non-AKI group. Urinary exosomal miRNA-21 levels correlated directly with serum neutrophil gelatinase-associated lipocalin values and total leukocyte counts and inversely with estimated glomerular filtration rate. The receiver operator characteristics curve analysis for urinary exosomal miRNA-21 showed good discriminative power for the diagnosis of scrub typhus-associated AKI, with area under the curve value of 0.907. Conclusion Urinary exosomal miRNA-21 could be a surrogate markers for the diagnosis of scrub typhus–associated AKI.

Download Full-text

Neutrophil gelatinase-associated lipocalin as a biomarker for acute kidney injury in children after cardiac surgery

Paediatrica Indonesiana ◽

10.14238/pi56.4.2016.230-7 ◽

2016 ◽

Vol 56 (4) ◽

pp. 230

Author(s):

Meta Herdiana Hanindita ◽

Riskky Vitria Prasetyo ◽

Ninik Asmaningsih Soemyarso ◽

I Ketut Alit Utamayasa ◽

Paul Tahalele

Keyword(s):

Acute Kidney Injury ◽

Cardiac Surgery ◽

Creatinine Clearance ◽

Sensitivity And Specificity ◽

Area Under The Curve ◽

Kidney Injury ◽

Schwartz Formula ◽

Neutrophil Gelatinase Associated Lipocalin ◽

Plasma Ngal ◽

Neutrophil Gelatinase

Background Acute kidney injury (AKI) is still diagnosed by measuring the estimated creatinine clearance (eCCl), despite the fact that it may not change until 50% or more of kidney function has been lost. AKI after cardiac surgery is related to prolonged intensive care, decreased quality of life, and increased long term mortality. Neutrophil gelatinase-associated lipocalin (NGAL) represents an early biomarker of AKI, which may be useful for assessing AKI in cardiac patients.Objective To determine the validity of urinary and plasma NGAL as biomarkers for AKI in children after cardiac surgery.Methods Subjects were children who underwent cardiac surgery in Dr. Soetomo Hospital, Surabaya, Indonesia from August 2013 to January 2014. Serial urine and blood samples were analyzed for NGAL before surgery, as well as at 2h, 4h, 12h, and 24h after surgery. The AKI was established based on pRIFLE criteria. Estimated creatinine clearance (eCCl) was calculated from the estimated glomerular filtration rate (eGFR), according to age by the traditional Schwartz formula. Serum creatinine was assayed by the Jaffe method before surgery, as well as at 12h, 24h, 48h, and 72h after surgery.Results Of 20 subjects, 5 developed AKI. Urinary and plasma NGAL increased markedly at 2h postoperatively, as compared to eGFR which showed a rise at 12-48 h after cardiac surgery. Analysis of 2h post-operative urinary NGAL at a cut off value of 11.270ng/mL yielded an area under the curve (AUC) of 1.00 (95%CI 2.63 to 12.13), with sensitivity and specificity of 100% each for AKI. In addition, 2h post-operative plasma NGAL at a cut off value of 8.385 ng/mL yielded an AUC of 1.00 (95%CI 3.71 to 12.15) with sensitivity and specificity of 100% each for AKI.Conclusion Urinary and plasma NGAL are valid as early biomarkers for AKI in children after cardiac surgery.

Download Full-text

Preoperative Albuminuria and Intraoperative Chloride Load: Predictors of Acute Kidney Injury Following Major Abdominal Surgery

Journal of Clinical Medicine ◽

10.3390/jcm7110431 ◽

2018 ◽

Vol 7 (11) ◽

pp. 431 ◽

Cited By ~ 5

Author(s):

Diamantina Marouli ◽

Kostas Stylianou ◽

Eleftherios Papadakis ◽

Nikolaos Kroustalakis ◽

Stavroula Kolyvaki ◽

...

Keyword(s):

Risk Factors ◽

Acute Kidney Injury ◽

Abdominal Surgery ◽

Care Center ◽

Chronic Kidney Disease Stage ◽

Tertiary Care ◽

Kidney Injury ◽

Major Abdominal Surgery ◽

Disease Stage ◽

Postoperative Aki

Background: Postoperative Acute Kidney Injury (AKI) is a common and serious complication associated with significant morbidity and mortality. While several pre- and intra-operative risk factors for AKI have been recognized in cardiac surgery patients, relatively few data are available regarding the incidence and risk factors for perioperative AKI in other surgical operations. The aim of the present study was to determine the risk factors for perioperative AKI in patients undergoing major abdominal surgery. Methods: This was a prospective, observational study of patients undergoing major abdominal surgery in a tertiary care center. Postoperative AKI was diagnosed according to the Acute Kidney Injury Network criteria within 48 h after surgery. Patients with chronic kidney disease stage IV or V were excluded. Logistic regression analysis was used to evaluate the association between perioperative factors and the risk of developing postoperative AKI. Results: Eleven out of 61 patients developed postoperative AKI. Four intra-operative variables were identified as predictors of AKI: intra-operative blood loss (p = 0.002), transfusion of fresh frozen plasma (p = 0.004) and red blood cells (p = 0.038), as well as high chloride load (p = 0.033, cut-off value > 500 mEq). Multivariate analysis demonstrated an independent association between AKI development and preoperative albuminuria, defined as a urinary Albumin to Creatinine ratio ≥ 30 mg·g−1 (OR = 6.88, 95% CI: 1.43–33.04, p = 0.016) as well as perioperative chloride load > 500 mEq (OR = 6.87, 95% CI: 1.46–32.4, p = 0.015). Conclusion: Preoperative albuminuria, as well as a high intraoperative chloride load, were identified as predictors of postoperative AKI in patients undergoing major abdominal surgery.

Download Full-text

Prediction models for acute kidney injury in patients with gastrointestinal cancers: a real-world study based on Bayesian networks

Renal Failure ◽

10.1080/0886022x.2020.1810068 ◽

2020 ◽

Vol 42 (1) ◽

pp. 869-876

Author(s):

Yang Li ◽

Xiaohong Chen ◽

Ziyan Shen ◽

Yimei Wang ◽

Jiachang Hu ◽

...

Keyword(s):

Acute Kidney Injury ◽

Bayesian Networks ◽

Real World ◽

Prediction Models ◽

Kidney Injury ◽

Gastrointestinal Cancers

Download Full-text

Acute Kidney Injury in Pediatric Acute Respiratory Distress Syndrome

Journal of Intensive Care Medicine ◽

10.1177/0885066620944042 ◽

2020 ◽

pp. 088506662094404

Author(s):

Shubhi Kaushik ◽

Sindy Villacres ◽

Ruth Eisenberg ◽

Shivanand S. Medar

Keyword(s):

Acute Kidney Injury ◽

Acute Respiratory Distress Syndrome ◽

Respiratory Distress Syndrome ◽

Respiratory Distress ◽

Distress Syndrome ◽

Invasive Mechanical Ventilation ◽

Tertiary Care ◽

Kidney Injury ◽

Oxygenation Index ◽

Significant Difference

Objectives: To describe the incidence of and risk factors for acute kidney injury (AKI) in children with acute respiratory distress syndrome (ARDS) and study the effect of AKI on patient outcomes. Design: A single-center retrospective study. Setting: A tertiary care children’s hospital. Patients: All patients less than 18 years of age who received invasive mechanical ventilation (MV) and developed ARDS between July 2010 and July 2013 were included. Acute kidney injury was defined using p-RIFLE (risk, injury, failure, loss, and end-stage renal disease) criteria. Interventions: None. Measurements and Main Results: One hundred fifteen children met the criteria and were included in the study. Seventy-four children (74/115, 64%) developed AKI. The severity of AKI was risk in 34 (46%) of 74, injury in 19 (26%) of 74, and failure in 21 (28%) of 74. The presence of AKI was associated with lower Pao 2 to Fio 2 (P/F) ratio ( P = .007), need for inotropes ( P = .003), need for diuretics ( P = .004), higher oxygenation index ( P = .03), higher positive end-expiratory pressure (PEEP; P = .01), higher mean airway pressure ( P = .008), and higher Fio 2 requirement ( P = .03). Only PEEP and P/F ratios were significantly associated with AKI in the unadjusted logistic regression model. Patients with AKI had a significantly longer duration of hospital stay, although there was no significant difference in the intensive care unit stay, duration of MV, and mortality. Recovery of AKI occurred in 68% of the patients. A multivariable model including PEEP, P/F ratio, weight, need for inotropes, and need for diuretics had a better receiver operating characteristic (ROC) curve with an AUC of 0.75 compared to the ROC curves for PEEP only and P/F ratio only for the prediction of AKI. Conclusions: Patients with ARDS have high rates of AKI, and its presence is associated with increased morbidity and mortality.

Download Full-text

MO1031FROM MARCELLO MALPIGHI THROUGH JEAN REDMAN OLIVER AND JOSEP TRUETA: A CONTINUING CONTRIBUTION TO THE “BLACK BOX” CLINICAL PREDICTION MODELS IN NEPHROLOGY

Nephrology Dialysis Transplantation ◽

10.1093/ndt/gfab105.003 ◽

2021 ◽

Vol 36 (Supplement_1) ◽

Author(s):

Enrico Favaro ◽

Roberta Lazzarin ◽

Daniela Cremasco ◽

Erika Pierobon ◽

Marta Guizzo ◽

...

Keyword(s):

Machine Learning ◽

Acute Kidney Injury ◽

Prediction Models ◽

Kidney Diseases ◽

Kidney Injury ◽

Black Box ◽

Renal Physiology ◽

Clinical Prediction ◽

Renal Circulation ◽

Clinical Prediction Models

Abstract Background and Aims The modern development of the black box approach in clinical nephrology is inconceivable without a logical theory of renal function and a comprehension of anatomical architecture of the kidney, in health and disease: this is the undisputed contribution offered by Malpighi, Oliver and Trueta starting from the seventeenth century. The machine learning model for the prediction of acute kidney injury, progression of renal failure and tubulointerstitial nephritis is a good example of how different knowledge about kidney are an indispensable tool for the interpretation of model itself. Method Historical data were collected from literature, textbooks, encyclopedias, scientific periodicals and laboratory experimental data concerning these three authors. Results The Italian Marcello Malpighi (1628-1694), born in Crevalcore near Bologna, was Professor of anatomy at Bologna, Pisa and Messina. The historic description of the pulmonary capillaries was made in his second epistle to Borelli published in 1661 and intitled De pulmonibus, by means of the frog as “the microscope of nature” (Fig. 1). It is the first description of capillaries in any circulation. William Harvey in De motu cordis in 1628 (year of publication the same of date of birth of Italian anatomist!) could not see the capillary vessels. This thriumphant discovery will serve for the next reconnaissance of characteristic renal rete mirabile.in the corpuscle of Malpighi, lying within the capsule of Bowman. Jean Redman Oliver (1889-1976), a pathologist born and raised in Northern California, was able to bridge the gap between the nephron and collecting system through meticulous dissections, hand drawn illustrations and experiments which underpin our current understanding of renal anatomy and physiology. In the skillful lecture “When is the kidney not a kidney?” (1949) Oliver summarizes his far-sighted vision on renal physiology and disease in the following sentence: the Kidney in health, if you will, but the Nephrons in disease. Because, the “nephron” like the “kidney” is an abstraction that must be qualified in terms of its various parts, its cellular components and the molecular mechanisms involved in each discrete activity (Fig. 2). The Catalan surgeon Josep Trueta I Raspall (1897-1977) was born in the Poblenou neighborhood of Barcelona. His impact of pioneering and visionary contribution to the changes in renal circulation for the pathogenesis of acute kidney injury was pivotal for history of renal physiology. “The kidney has two potential circulatory circulations. Blood may pass either almost exclusively through one or other of two pathways, or to a varying degree through both”. (Studies of the Renal Circulation, published in 1947). Now this diversion of blood from cortex to the less resistant medullary circulation is known with the eponym Trueta shunt. Conclusion The black box approach to the kidney diseases should be considered by practitioners as a further tool to help to inform model update in many clinical setting. The number of machine learning clinical prediction models being published is rising, as new fields of application are being explored in medicine (Fig. 3). A challenge in the clinical nephrology is to explore the “kidney machine” during each therapeutic diagnostic procedure. Always, the intriguing relationship between the set of nephrological syndromes and kidney diseases cannot disregard the precious notions the specific organization of kidney microcirculation, fruit of many scientific contributions of the work by Malpighi, Oliver and Trueta (Fig. 3).

Download Full-text