Predicting acute kidney injury prognosis

Machine learning models for predicting acute kidney injury: a systematic review and critical appraisal

BACKGROUND

The number of studies applying machine learning (ML) to predict acute kidney injury (AKI) has grown steadily over the past decade. We assess and critically appraise the state of the art in ML models for AKI prediction, considering performance, methodological soundness, and applicability.

METHODS

We searched PubMed and ArXiv, extracted data, and critically appraised studies based on the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD), Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies (CHARMS), and Prediction Model Risk of Bias Assessment Tool (PROBAST) guidelines.

RESULTS

Forty-six studies from 3166 titles were included. Thirty-eight studies developed a model, five developed and externally validated one, and three studies externally validated one. Flexible ML methods were used more often than deep learning, although the latter was common with temporal variables and text as predictors. Predictive performance showed an area under receiver operating curves ranging from 0.49 to 0.99. Our critical appraisal identified a high risk of bias in 39 studies. Some studies lacked internal validation, whereas external validation and interpretability of results were rarely considered. Fifteen studies focused on AKI prediction in the intensive care setting, and the US-derived Medical Information Mart for Intensive Care (MIMIC) data set was commonly used. Reproducibility was limited as data and code were usually unavailable.

CONCLUSIONS

Flexible ML methods are popular for the prediction of AKI, although more complex models based on deep learning are emerging. Our critical appraisal identified a high risk of bias in most models: Studies should use calibration measures and external validation more often, improve model interpretability, and share data and code to improve reproducibility.

Predicting mortality in acute kidney injury patients undergoing continuous renal replacement therapy using a visualization model: A retrospective study

Background: Patients with severe acute kidney injury (AKI) require continuous renal replacement therapy (CRRT) when hemodynamically unstable. We aimed to identify prognostic factors and develop a nomogram that could predict mortality in patients with AKI undergoing CRRT. Methods: Data were extracted from the Dryad Digital Repository. We enrolled 1,002 participants and grouped them randomly into training (n = 670) and verification (n = 332) datasets based on a 2:1 proportion. Based on Cox proportional modeling of the training set, we created a web-based dynamic nomogram to estimate all-cause mortality. Results: The model incorporated phosphate, Charlson comorbidity index, body mass index, mean arterial pressure, levels of creatinine and albumin, and sequential organ failure assessment scores as independent predictive indicators. Model calibration and discrimination were satisfactory. In the training dataset, the area under the curves (AUCs) for estimating the 28-, 56-, and 84-day all-cause mortality were 0.779, 0.780, and 0.787, respectively. The model exhibited excellent calibration and discrimination in the validation dataset, with AUC values of 0.791, 0.778, and 0.806 for estimating 28-, 56-, and 84-day all-cause mortality, respectively. The calibration curves exhibited the consistency of the model between the two cohorts. To visualize the results, we created a web-based calculator. Conclusion: We created a web-based calculator for assessing fatality risk in patients with AKI receiving CRRT, which may help rationalize clinical decision-making and personalized therapy.

Characterizing chronological accumulation of comorbidities in healthy veterans: a computational approach

Understanding patient accumulation of comorbidities can facilitate healthcare strategy and personalized preventative care. We applied a directed network graph to electronic health record (EHR) data and characterized comorbidities in a cohort of healthy veterans undergoing screening colonoscopy. The Veterans Affairs Cooperative Studies Program #380 was a prospective longitudinal study of screening and surveillance colonoscopy. We identified initial instances of three-digit ICD-9 diagnoses for participants with at least 5 years of linked EHR history (October 1999 to December 2015). For diagnoses affecting at least 10% of patients, we calculated pairwise chronological relative risk (RR). iGraph was used to produce directed graphs of comorbidities with RR > 1, as well as summary statistics, key diseases, and communities. A directed graph based on 2210 patients visualized longitudinal development of comorbidities. Top hub (preceding) diseases included ischemic heart disease, inflammatory and toxic neuropathy, and diabetes. Top authority (subsequent) diagnoses were acute kidney failure and hypertensive chronic kidney failure. Four communities of correlated comorbidities were identified. Close analysis of top hub and authority diagnoses demonstrated known relationships, correlated sequelae, and novel hypotheses. Directed network graphs portray chronologic comorbidity relationships. We identified relationships between comorbid diagnoses in this aging veteran cohort. This may direct healthcare prioritization and personalized care.

Renal impairment assessment on adults living nearby a landfill: Early kidney dysfunction biomarkers linked to the environmental exposure to heavy metals

•

Health risk of the neighboring population of the Mbeubeuss landfill (Senegal).

•

Assessment of the impact of Cd/Pb exposure through dysfunction renal biomarkers.

•

Specific increases of a set of early dysfunction renal biomarkers in exposed subjects.

•

Glomerular and tubular dysfunction in exposed subjects.

The aim of this study was to assess the integrity and kidney overall functional capacity of subjects exposed to landfill emissions. Urine and blood levels of Pb and Cd, and several of the newly biomarkers of nephrotoxicity (Kim Injury Molecule 1 (KIM-1), alpha-1 Microglobulin (α1 M), beta-2 Microglobulin (β2 M), Cystatin-C (Cyst C), Clusterin, alpha-glutathione S-transferase (GSTα), pi-glutathione S-transferase (GSTπ), Tissue Inhibitor of Metalloproteinase-1 (TIMP1), Calbindin, Neutrophil Gelatinase-Associated Lipocalin (NGAL), Osteopontin (OPN), (Retinol Binding Protein(RBP), Liver-type Fatty Acid-Binding Protein (FABP-1), Trefoil Factor 3 (TFF3), Collagen VI) were measured in order to assess glomerular and tubule damage in adults living near a landfill.

Our results indicate glomerular dysfunction in exposed subjects, and supported evidence of necrosis of proximal and distal tubule epithelial cells as specific biomarkers began to appear in the urine.

Positive correlation by Pearson test were obtained between : blood Pb and B-OPN, B-Cyst C, Calbindin, U-KIM-1, TIMP1, U-OPN, and U-Clusterin; and also, between urinary Cd and TIMP1, B-Clusterin, U-OPN, FABP-1, Albumin, and U-Clusterin. The relation between biomarkers of Cd/Pb exposure and early effect biomarkers in this study clearly predicts the future risk of severe kidney injury in subjects living close to the landfill.

Biomarkers of acute kidney injury: the pathway from discovery to clinical adoption

Acute kidney injury (AKI) is a common complication of critical illnesses and has a significant impact on outcomes, including mortality and morbidities. Unfortunately, apart from prophylactic measures, no effective treatment for this syndrome is known. Therefore, early recognition of AKI not only can provide better opportunities for preventive interventions, but also opens many gates for research and development of effective therapeutic options. Over the last few years, several new AKI biomarkers have been discovered and validated to improve early detection, differential diagnosis, and differentiation of patients into risk groups for progressive renal failure, need for renal replacement therapy (RRT), or death. These novel AKI biomarkers complement serum creatinine (SCr) and urine output, which are the standard diagnostic tools for AKI detection. In this article, we review the available literature on characteristics of promising AKI biomarkers that are currently the focus of preclinical and clinical investigations. These biomarkers include neutrophil gelatinase-associated lipocalin (NGAL), kidney injury molecule 1 (KIM-1), liver-type fatty acid-binding protein, interleukin 18 (lL-18), insulin-like growth factor-binding protein 7, tissue inhibitor of metalloproteinase 2 (TIMP-2), calprotectin, urine angiotensinogen (AGT), and urine microRNA. We then describe the clinical performance of these biomarkers for diagnosis and prognostication. We also appraise each AKI biomarker's advantages and limitations as a tool for early AKI recognition and prediction of clinical outcomes after AKI. Finally, we review the current and future states of implementation of biomarkers in the clinical practice.