Utilization of Deep Learning for Subphenotype Identification in Sepsis-Associated Acute Kidney Injury

Predictive models of sepsis-associated acute kidney injury based on machine learning: a scoping review

BACKGROUND

With the development of artificial intelligence, the application of machine learning to develop predictive models for sepsis-associated acute kidney injury has made potential breakthroughs in early identification, grading, diagnosis, and prognosis determination.

METHODS

Here, we conducted a systematic search of the PubMed, Cochrane Library, Embase (Ovid), Web of Science, and Scopus databases on April 28, 2023, and screened relevant literature. Then, we comprehensively extracted relevant data related to machine learning algorithms, predictors, and predicted objectives. We subsequently performed a critical evaluation of research quality, data aggregation, and analyses.

RESULTS

We screened 25 studies on predictive models for sepsis-associated acute kidney injury from a total of originally identified 2898 studies. The most commonly used machine learning algorithm is traditional logistic regression, followed by eXtreme gradient boosting. We categorized these predictive models into early identification models (60%), prognostic prediction models (32%), and subtype identification models (8%) according to their predictive purpose. The five most commonly used predictors were serum creatinine levels, lactate levels, age, blood urea nitrogen concentration, and diabetes mellitus. In addition, a single data source, insufficient assessment of clinical utility, lack of model bias assessment, and hyperparameter adjustment may be the main reasons for the low quality of the current research.

CONCLUSIONS

However, studies on the nondeath prognostic outcomes, the long-term clinical outcomes, and the subtype identification models are insufficient. Additionally, the poor quality of the research and the insufficient practicality of the model are problems that need to be addressed urgently.

Reframing acute kidney injury as a pathophysiological continuum of disrupted renal excretory function

Surrogate measures of glomerular filtration rate (GFR) continue to serve as pivotal determinants of the incidence, severity, and management of acute kidney injury (AKI), as well as the primary reference point underpinning knowledge of its pathophysiology. However, several clinically important deficits in aspects of renal excretory function during AKI other than GFR decline, including acid-base regulation, electrolyte and water balance, and urinary concentrating capacity, can evade detection when diagnostic criteria are built around purely GFR-based assessments. The use of putative markers of tubular injury to detect "sub-clinical" AKI has been proposed to expand the definition and diagnostic criteria for AKI, but their diagnostic performance is curtailed by ambiguity with respect to their biological meaning and context specificity. Efforts to devise new holistic assessments of overall renal functional compromise in AKI would foster the capacity to better personalize patient care by replacing biomarker threshold-based diagnostic criteria with a shift to assessment of compromise along a pathophysiological continuum. The term AKI refers to a syndrome of sudden renal deterioration, the severity of which is classified by precise diagnostic criteria that have unquestionable utility in patient management as well as blatant limitations. Particularly, the absence of an explicit pathophysiological definition of AKI curtails further scientific development and clinical handling, entrapping the field within its present narrow GFR-based view. A refreshed approach based on a more holistic consideration of renal functional impairment in AKI as the basis for a new diagnostic concept that reaches beyond the boundaries imposed by the current GFR threshold-based classification of AKI, capturing broader aspects of pathogenesis, could enhance AKI prevention strategies and improve AKI patient outcome and prognosis.

Role of artificial intelligence in critical care nutrition support and research

Nutrition plays a key role in the comprehensive care of critically ill patients. Determining optimal nutrition strategy, however, remains a subject of intense debate. Artificial intelligence (AI) applications are becoming increasingly common in medicine, and specifically in critical care, driven by the data-rich environment of intensive care units. In this review, we will examine the evidence regarding the application of AI in critical care nutrition. As of now, the use of AI in critical care nutrition is relatively limited, with its primary emphasis on malnutrition screening and tolerance of enteral nutrition. Despite the current scarcity of evidence, the potential for AI for more personalized nutrition management for critically ill patients is substantial. This stems from the ability of AI to integrate multiple data streams reflecting patients' changing needs while addressing inherent heterogeneity. The application of AI in critical care nutrition holds promise for optimizing patient outcomes through tailored and adaptive nutrition interventions. A successful implementation of AI, however, necessitates a multidisciplinary approach, coupled with careful consideration of challenges related to data management, financial aspects, and patient privacy.

Fine-grained subphenotypes in acute kidney injury populations based on deep clustering: Derivation and interpretation

BACKGROUND

Acute kidney injury (AKI) is associated with increased mortality in critically ill patients. Due to differences in the etiology and pathophysiological mechanism, the current AKI criteria put it an embarrassment to evaluate clinical therapy and prognosis.

OBJECTIVE

We aimed to identify subphenotypes based on routinely collected clinical data to expose the unique pathophysiologic patterns.

METHODS

A retrospective study was conducted based on the Medical Information Mart for Intensive Care IV (MIMIC-IV) and the eICU Collaborative Research Database (eICU-CRD), and a deep clustering approach was conducted to derive subphenotypes. We conducted further analysis to uncover the underlying clinical patterns and interpret the subphenotype derivation.

RESULTS

We studied 14,189 and 19,382 patients with AKI within 48 h of ICU admission in the two datasets, respectively. Through our approach, we identified seven distinct AKI subphenotypes with mortality heterogeneity in each cohort. These subphenotypes displayed significant variations in demographics, comorbidities, levels of laboratory measurements, and survival patterns. Notably, the subphenotypes could not be effectively characterized using the Kidney Disease: Improving Global Outcomes (KDIGO) criteria alone. Therefore, we uncovered the unique underlying characteristics of each subphenotype through model-based interpretation. To assess the usability of the subphenotypes, we conducted an evaluation, which yielded a micro-Area Under the Receiver Operating Characteristic (AUROC) of 0.81 in the single-center cohort and 0.83 in the multi-center cohort within 48-hour of admission.

CONCLUSION

We derived highly characteristic, interpretable, and usable AKI subphenotypes that exhibited superior prognostic values.

The Road to Precision Medicine for Acute Kidney Injury

OBJECTIVES

Acute kidney injury (AKI) is a common form of organ dysfunction in the ICU. AKI is associated with adverse short- and long-term outcomes, including high mortality rates, which have not measurably improved over the past decade. This review summarizes the available literature examining the evidence of the need for precision medicine in AKI in critical illness, highlights the current evidence for heterogeneity in the field of AKI, discusses the progress made in advancing precision in AKI, and provides a roadmap for studying precision-guided care in AKI.

DATA SOURCES

Medical literature regarding topics relevant to precision medicine in AKI, including AKI definitions, epidemiology, and outcomes, novel AKI biomarkers, studies of electronic health records (EHRs), clinical trial design, and observational studies of kidney biopsies in patients with AKI.

STUDY SELECTION

English language observational studies, randomized clinical trials, reviews, professional society recommendations, and guidelines on areas related to precision medicine in AKI.

DATA EXTRACTION

Relevant study results, statements, and guidelines were qualitatively assessed and narratively synthesized.

DATA SYNTHESIS

We synthesized relevant study results, professional society recommendations, and guidelines in this discussion.

CONCLUSIONS

AKI is a syndrome that encompasses a wide range of underlying pathologies, and this heterogeneity has hindered the development of novel therapeutics for AKI. Wide-ranging efforts to improve precision in AKI have included the validation of novel biomarkers of AKI, leveraging EHRs for disease classification, and phenotyping of tubular secretory clearance. Ongoing efforts such as the Kidney Precision Medicine Project, identifying subphenotypes in AKI, and optimizing clinical trials and endpoints all have great promise in advancing precision medicine in AKI.

An overview of circulating and urinary biomarkers capable of predicting the transition of acute kidney injury to chronic kidney disease

INTRODUCTION

Acute kidney injury (AKI) defined by a substantial decrease in kidney function within hours to days and is often irreversible with higher risk to chronic kidney disease (CKD) transition.

AREAS COVERED

The authors discuss the diagnostic and predictive utilities of serum and urinary biomarkers on AKI and on the risk of AKI-to-CKD progression. The authors focus on the relevant literature covering evidence of circulating and urinary biomarkers' capability to predict the transition of AKI to CKD.

EXPERT OPINION

Based on the different modalities of serum and urinary biomarkers, multiple biomarker panel seems to be potentially useful to distinguish between various types of AKI, to detect the severity and the risk of AKI progression, to predict the clinical outcome and evaluate response to the therapy. Serum/urinary neutrophil gelatinase-associated lipocalin (NGAL), serum/urinary uromodulin, serum extracellular high mobility group box-1 (HMGB-1), serum cystatin C and urinary liver-type fatty acid-binding protein (L-FABP) were the most effective in the prediction of AKI-to-CKD transition regardless of etiology and the presence of critical state in patients. The current clinical evidence on the risk assessments of AKI progression is mainly based on the utility of combination of functional, injury and stress biomarkers, mainly NGAL, L-FABP, HMGB-1 and cystatin C.

[Recent developments in acute kidney injury : Definition, biomarkers, subphenotypes, and management]

Acute kidney injury (AKI) is a common problem in critically ill patients and is associated with increased morbidity and mortality. Since 2012, AKI has been defined according to the KDIGO (Kidney Disease Improving Global Outcome) guidelines. As some biomarkers are now available that can provide useful clinical information, a new definition including a new stage 1S has been proposed by an expert group of the Acute Disease Quality Initiative (ADQI). At this stage, classic AKI criteria are not yet met, but biomarkers are already positive defining subclinical AKI. This stage 1S is associated with a worse patient outcome, regardless of the biomarker chosen. The PrevAKI and PrevAKI-Multicenter trial also showed that risk stratification with a biomarker and implementation of the KDIGO bundle (in the high-risk group) can reduce the rate of moderate and severe AKI. In the absence of a successful clinical trial, conservative management remains the primary focus of treatment. This mainly involves optimization of hemodynamics and an individualized (restrictive) fluid management. The STARRT-AKI trial has shown that there is no benefit from accelerated initiation of renal replacement therapy. However, delaying too long might be associated with potential harm, as shown in the AKIKI2 study. Prospective studies are needed to determine whether artificial intelligence will play a role in AKI in the future, helping to guide treatment decisions and improve outcomes.

Machine learning derived serum creatinine trajectories in acute kidney injury in critically ill patients with sepsis

BACKGROUND

Current classification for acute kidney injury (AKI) in critically ill patients with sepsis relies only on its severity-measured by maximum creatinine which overlooks inherent complexities and longitudinal evaluation of this heterogenous syndrome. The role of classification of AKI based on early creatinine trajectories is unclear.

METHODS

This retrospective study identified patients with Sepsis-3 who developed AKI within 48-h of intensive care unit admission using Medical Information Mart for Intensive Care-IV database. We used latent class mixed modelling to identify early creatinine trajectory-based classes of AKI in critically ill patients with sepsis. Our primary outcome was development of acute kidney disease (AKD). Secondary outcomes were composite of AKD or all-cause in-hospital mortality by day 7, and AKD or all-cause in-hospital mortality by hospital discharge. We used multivariable regression to assess impact of creatinine trajectory-based classification on outcomes, and eICU database for external validation.

RESULTS

Among 4197 patients with AKI in critically ill patients with sepsis, we identified eight creatinine trajectory-based classes with distinct characteristics. Compared to the class with transient AKI, the class that showed severe AKI with mild improvement but persistence had highest adjusted risks for developing AKD (OR 5.16; 95% CI 2.87-9.24) and composite 7-day outcome (HR 4.51; 95% CI 2.69-7.56). The class that demonstrated late mild AKI with persistence and worsening had highest risks for developing composite hospital discharge outcome (HR 2.04; 95% CI 1.41-2.94). These associations were similar on external validation.

CONCLUSIONS

These 8 classes of AKI in critically ill patients with sepsis, stratified by early creatinine trajectories, were good predictors for key outcomes in patients with AKI in critically ill patients with sepsis independent of their AKI staging.

[Artificial intelligence and acute kidney injury]

Digitalization is increasingly finding its way into intensive care units and with it artificial intelligence (AI) for critically ill patients. One promising area for the use of AI is in the field of acute kidney injury (AKI). The use of AI is primarily focused on the prediction of AKI, but further approaches are also being used to classify existing AKI into different phenotypes. Different AI models are used for prediction. The area under the receiver operating characteristic curve values (AUROC) achieved with these models vary and are influenced by several factors, such as the prediction time and the definition of AKI. Most models have an AUROC between 0.650 and 0.900, with lower values for predictions further into the future and when applying Acute Kidney Injury Network (AKIN) instead of KDIGO criteria. Classification into phenotypes already makes it possible to categorize patients into groups with different risks of mortality or requirement of renal replacement therapy (RRT), but the etiologies or therapeutic consequences derived from this are still lacking. However, all the models suffer from AI-specific shortcomings. The use of large databases does not make it possible to promptly include recent changes in therapy and the implementation of new biomarkers in a relevant proportion. For this reason, serum creatinine and urinary output, with their known limitations, dominate current AI models for prediction impairing the performance of the current models. On the other hand, the increasingly complex models no longer allow physicians to understand the basis on which the warning of a threatening AKI is calculated and subsequent initiation of therapy should take place. The successful use of AIs in routine clinical practice will be highly determined by the trust of the physicians in the systems and overcoming the aforementioned weaknesses. However, the clinician will remain irreplaceable as the decisive authority for critically ill patients by combining measurable and nonmeasurable parameters.

Sepsis-associated acute kidney injury: recent advances in enrichment strategies, sub-phenotyping and clinical trials

Acute kidney injury (AKI) often complicates sepsis and is associated with high morbidity and mortality. In recent years, several important clinical trials have improved our understanding of sepsis-associated AKI (SA-AKI) and impacted clinical care. Advances in sub-phenotyping of sepsis and AKI and clinical trial design offer unprecedented opportunities to fill gaps in knowledge and generate better evidence for improving the outcome of critically ill patients with SA-AKI. In this manuscript, we review the recent literature of clinical trials in sepsis with focus on studies that explore SA-AKI as a primary or secondary outcome. We discuss lessons learned and potential opportunities to improve the design of clinical trials and generate actionable evidence in future research. We specifically discuss the role of enrichment strategies to target populations that are most likely to derive benefit and the importance of patient-centered clinical trial endpoints and appropriate trial designs with the aim to provide guidance in designing future trials.

A novel method leveraging time series data to improve subphenotyping and application in critically ill patients with COVID-19

Computational subphenotyping, a data-driven approach to understanding disease subtypes, is a prominent topic in medical research. Numerous ongoing studies are dedicated to developing advanced computational subphenotyping methods for cross-sectional data. However, the potential of time-series data has been underexplored until now. Here, we propose a Multivariate Levenshtein Distance (MLD) that can account for address correlation in multiple discrete features over time-series data. Our algorithm has two distinct components: it integrates an optimal threshold score to enhance the sensitivity in discriminating between pairs of instances, and the MLD itself. We have applied the proposed distance metrics on the k-means clustering algorithm to derive temporal subphenotypes from time-series data of biomarkers and treatment administrations from 1039 critically ill patients with COVID-19 and compare its effectiveness to standard methods. In conclusion, the Multivariate Levenshtein Distance metric is a novel method to quantify the distance from multiple discrete features over time-series data and demonstrates superior clustering performance among competing time-series distance metrics.

Chinese experts' consensus on the application of intensive care big data

The development of intensive care medicine is inseparable from the diversified monitoring data. Intensive care medicine has been closely integrated with data since its birth. Critical care research requires an integrative approach that embraces the complexity of critical illness and the computational technology and algorithms that can make it possible. Considering the need of standardization of application of big data in intensive care, Intensive Care Medicine Branch of China Health Information and Health Care Big Data Society, Standard Committee has convened expert group, secretary group and the external audit expert group to formulate Chinese Experts' Consensus on the Application of Intensive Care Big Data (2022). This consensus makes 29 recommendations on the following five parts: Concept of intensive care big data, Important scientific issues, Standards and principles of database, Methodology in solving big data problems, Clinical application and safety consideration of intensive care big data. The consensus group believes this consensus is the starting step of application big data in the field of intensive care. More explorations and big data based retrospective research should be carried out in order to enhance safety and reliability of big data based models of critical care field.

Sepsis-associated acute kidney injury-treatment standard

Sepsis is a host's deleterious response to infection, which could lead to life-threatening organ dysfunction. Sepsis-associated acute kidney injury (SA-AKI) is the most frequent organ dysfunction and is associated with increased morbidity and mortality. Sepsis contributes to ≈50% of all AKI in critically ill adult patients. A growing body of evidence has unveiled key aspects of the clinical risk factors, pathobiology, response to treatment and elements of renal recovery that have advanced our ability to detect, prevent and treat SA-AKI. Despite these advancements, SA-AKI remains a critical clinical condition and a major health burden, and further studies are needed to diminish the short and long-term consequences of SA-AKI. We review the current treatment standards and discuss novel developments in the pathophysiology, diagnosis, outcome prediction and management of SA-AKI.

Unsupervised clustering identifies sub-phenotypes and reveals novel outcome predictors in patients with dialysis-requiring sepsis-associated acute kidney injury

INTRODUCTION

Heterogeneity exists in sepsis-associated acute kidney injury (SA-AKI). This study aimed to perform unsupervised consensus clustering in critically ill patients with dialysis-requiring SA-AKI.

PATIENTS AND METHODS

This prospective observational cohort study included all septic patients, defined by the Sepsis-3 criteria, with dialysis-requiring SA-AKI in surgical intensive care units in Taiwan between 2009 and 2018. We employed unsupervised consensus clustering based on 23 clinical variables upon initializing renal replacement therapy. Multivariate-adjusted Cox regression models and Fine-Gray sub-distribution hazard models were built to test associations between cluster memberships with mortality and being free of dialysis at 90 days after hospital discharge, respectively.

RESULTS

Consensus clustering among 999 enrolled patients identified three sub-phenotypes characterized with distinct clinical manifestations upon renal replacement therapy initiation (n = 352, 396 and 251 in cluster 1, 2 and 3, respectively). They were followed for a median of 48 (interquartile range 9.5-128.5) days. Phenotypic cluster 1, featured by younger age, lower Charlson Comorbidity Index, higher baseline estimated glomerular filtration rate but with higher severity of acute illness was associated with an increased risk of death (adjusted hazard ratio of 3.05 [95% CI, 2.35-3.97]) and less probability to become free of dialysis (adjusted sub-distribution hazard ratio of 0.55 [95% CI, 0.38-0.8]) than cluster 3. By examining distinct features of the sub-phenotypes, we discovered that pre-dialysis hyperlactatemia ≥3.3 mmol/L was an independent outcome predictor. A clinical model developed to determine high-risk sub-phenotype 1 in this cohort (C-static 0.99) can identify a sub-phenotype with high in-hospital mortality risk (adjusted hazard ratio of 1.48 [95% CI, 1.25-1.74]) in another independent multi-centre SA-AKI cohort.

CONCLUSIONS

Our data-driven approach suggests sub-phenotypes with clinical relevance in dialysis-requiring SA-AKI and serves an outcome predictor. This strategy represents further development toward precision medicine in the definition of high-risk sub-phenotype in patients with SA-AKI.Key messagesUnsupervised consensus clustering can identify sub-phenotypes of patients with SA-AKI and provide a risk prediction.Examining the features of patient heterogeneity contributes to the discovery of serum lactate levels ≥ 3.3 mmol/L upon initializing RRT as an independent outcome predictor.This data-driven approach can be useful for prognostication and lead to a better understanding of therapeutic strategies in heterogeneous clinical syndromes.

Machine Learning Predicts Acute Kidney Injury in Hospitalized Patients with Sickle Cell Disease

INTRODUCTION

Acute kidney injury (AKI) is common among hospitalized patients with sickle cell disease (SCD) and contributes to increased morbidity and mortality. Early identification and management of AKI is essential to preventing poor outcomes. We aimed to predict AKI earlier in patients with SCD using a machine-learning model that utilized continuous minute-by-minute physiological data.

METHODS

A total of6,278 adult SCD patient encounters were admitted to inpatient units across five regional hospitals in Memphis, TN, over 3 years, from July 2017 to December 2020. From these, 1,178 patients were selected after filtering for data availability. AKI was identified in 82 (7%) patient encounters, using the 2012 Kidney Disease Improving Global Outcomes (KDIGO) criteria. The remaining 1,096 encounters served as controls. Features derived from five physiological data streams, heart rate, respiratory rate, and blood pressure (systolic, diastolic, and mean), captured every minute from bedside monitors were used. An XGBoost classifier was used for classification.

RESULTS

Our model accurately predicted AKI up to 12 h before onset with an area under the receiver operator curve (AUROC) of 0.91 (95% CI [0.89-0.93]) and up to 48 h before AKI with an AUROC of 0.82 (95% CI [0.80-0.83]). Patients with AKI were more likely to be female (64.6%) and have history of hypertension, pulmonary hypertension, chronic kidney disease, and pneumonia than the control group.

CONCLUSION

XGBoost accurately predicted AKI as early as 12 h before onset in hospitalized SCD patients and may enable the development of innovative prevention strategies.

Biomarker Enrichment in Sepsis-Associated Acute Kidney Injury: Finding High-Risk Patients in the Intensive Care Unit

BACKGROUND

Sepsis-associated acute kidney injury (AKI) is a leading comorbidity in admissions to the intensive care unit. While a gold standard definition exists, it remains imperfect and does not allow for the timely identification of patients in the setting of critical illness. This review will discuss the use of biochemical and electronic biomarkers to allow for prognostic and predictive enrichment of patients with sepsis-associated AKI over and above the use of serum creatinine and urine output.

SUMMARY

Current data suggest that several biomarkers are capable of identifying patients with sepsis at risk for the development of severe AKI and other associated morbidity. This review discusses these data and these biomarkers in the setting of sub-phenotyping and endotyping sepsis-associated AKI. While not all these tests are widely available and some require further validation, in the near future we anticipate several new tools to help nephrologists and other providers better care for patients with sepsis-associated AKI.

KEY MESSAGES

Predictive and prognostic enrichment using both traditional biomarkers and novel biomarkers in the setting of sepsis can identify subsets of patients with either similar outcomes or similar pathophysiology, respectively. Novel biomarkers can identify kidney injury in patients without consensus definition AKI (e.g., changes in creatinine or urine output) and can predict other adverse outcomes (e.g., severe consensus definition AKI, inpatient mortality). Finally, emerging artificial intelligence and machine learning-derived risk models are able to predict sepsis-associated AKI in critically ill patients using advanced learning techniques and several laboratory and vital sign measurements.

An integrated machine learning predictive scheme for longitudinal laboratory data to evaluate the factors determining renal function changes in patients with different chronic kidney disease stages

Background and objectives

Chronic kidney disease (CKD) is a global health concern. This study aims to identify key factors associated with renal function changes using the proposed machine learning and important variable selection (ML&IVS) scheme on longitudinal laboratory data. The goal is to predict changes in the estimated glomerular filtration rate (eGFR) in a cohort of patients with CKD stages 3-5.

Design

A retrospective cohort study.

Setting and participants

A total of 710 outpatients who presented with stable nondialysis-dependent CKD stages 3-5 at the Shin-Kong Wu Ho-Su Memorial Hospital Medical Center from 2016 to 2021.

Methods

This study analyzed trimonthly laboratory data including 47 indicators. The proposed scheme used stochastic gradient boosting, multivariate adaptive regression splines, random forest, eXtreme gradient boosting, and light gradient boosting machine algorithms to evaluate the important factors for predicting the results of the fourth eGFR examination, especially in patients with CKD stage 3 and those with CKD stages 4-5, with or without diabetes mellitus (DM).

Main outcome measurement

Subsequent eGFR level after three consecutive laboratory data assessments.

Results

Our ML&IVS scheme demonstrated superior predictive capabilities and identified significant factors contributing to renal function changes in various CKD groups. The latest levels of eGFR, blood urea nitrogen (BUN), proteinuria, sodium, and systolic blood pressure as well as mean levels of eGFR, BUN, proteinuria, and triglyceride were the top 10 significantly important factors for predicting the subsequent eGFR level in patients with CKD stages 3-5. In individuals with DM, the latest levels of BUN and proteinuria, mean levels of phosphate and proteinuria, and variations in diastolic blood pressure levels emerged as important factors for predicting the decline of renal function. In individuals without DM, all phosphate patterns and latest albumin levels were found to be key factors in the advanced CKD group. Moreover, proteinuria was identified as an important factor in the CKD stage 3 group without DM and CKD stages 4-5 group with DM.

Conclusion

The proposed scheme highlighted factors associated with renal function changes in different CKD conditions, offering valuable insights to physicians for raising awareness about renal function changes.

The application of artificial intelligence in the management of sepsis

Sepsis is a complex and heterogeneous syndrome that remains a serious challenge to healthcare worldwide. Patients afflicted by severe sepsis or septic shock are customarily placed under intensive care unit (ICU) supervision, where a multitude of apparatus is poised to produce high-granularity data. This reservoir of high-quality data forms the cornerstone for the integration of AI into clinical practice. However, existing reviews currently lack the inclusion of the latest advancements. This review examines the evolving integration of artificial intelligence (AI) in sepsis management. Applications of artificial intelligence include early detection, subtyping analysis, precise treatment and prognosis assessment. AI-driven early warning systems provide enhanced recognition and intervention capabilities, while profiling analyzes elucidate distinct sepsis manifestations for targeted therapy. Precision medicine harnesses the potential of artificial intelligence for pathogen identification, antibiotic selection, and fluid optimization. In conclusion, the seamless amalgamation of artificial intelligence into the domain of sepsis management heralds a transformative shift, ushering in novel prospects to elevate diagnostic precision, therapeutic efficacy, and prognostic acumen. As AI technologies develop, their impact on shaping the future of sepsis care warrants ongoing research and thoughtful implementation.

Leveraging Data Science and Novel Technologies to Develop and Implement Precision Medicine Strategies in Critical Care

Precision medicine aims to identify treatments that are most likely to result in favorable outcomes for subgroups of patients with similar clinical and biological characteristics. The gaps for the development and implementation of precision medicine strategies in the critical care setting are many, but the advent of data science and multi-omics approaches, combined with the rich data ecosystem in the intensive care unit, offer unprecedented opportunities to realize the promise of precision critical care. In this article, the authors review the data-driven and technology-based approaches being leveraged to discover and implement precision medicine strategies in the critical care setting.

Deep learning on electronic medical records identifies distinct subphenotypes of diabetic kidney disease driven by genetic variations in the Rho pathway

Kidney disease affects 50% of all diabetic patients; however, prediction of disease progression has been challenging due to inherent disease heterogeneity. We use deep learning to identify novel genetic signatures prognostically associated with outcomes. Using autoencoders and unsupervised clustering of electronic health record data on 1,372 diabetic kidney disease patients, we establish two clusters with differential prevalence of end-stage kidney disease. Exome-wide associations identify a novel variant in ARHGEF18, a Rho guanine exchange factor specifically expressed in glomeruli. Overexpression of ARHGEF18 in human podocytes leads to impairments in focal adhesion architecture, cytoskeletal dynamics, cellular motility, and RhoA/Rac1 activation. Mutant GEF18 is resistant to ubiquitin mediated degradation leading to pathologically increased protein levels. Our findings uncover the first known disease-causing genetic variant that affects protein stability of a cytoskeletal regulator through impaired degradation, a potentially novel class of expression quantitative trait loci that can be therapeutically targeted.

Integrated Analysis of Blood and Urine Biomarkers to Identify Acute Kidney Injury Subphenotypes and Associations With Long-term Outcomes

RATIONALE & OBJECTIVE

Acute kidney injury (AKI) is a heterogeneous clinical syndrome with varying causes, pathophysiology, and outcomes. We incorporated plasma and urine biomarker measurements to identify AKI subgroups (subphenotypes) more tightly linked to underlying pathophysiology and long-term clinical outcomes.

STUDY DESIGN

Multicenter cohort study.

SETTING & PARTICIPANTS

769 hospitalized adults with AKI matched with 769 without AKI, enrolled from December 2009 to February 2015 in the ASSESS-AKI Study.

PREDICTORS

29 clinical, plasma, and urinary biomarker parameters used to identify AKI subphenotypes.

OUTCOME

Composite of major adverse kidney events (MAKE) with a median follow-up period of 4.7 years.

ANALYTICAL APPROACH

Latent class analysis (LCA) and k-means clustering were applied to 29 clinical, plasma, and urinary biomarker parameters. Associations between AKI subphenotypes and MAKE were analyzed using Kaplan-Meier curves and Cox proportional hazard models.

RESULTS

Among 769 AKI patients both LCA and k-means identified 2 distinct AKI subphenotypes (classes 1 and 2). The long-term risk for MAKE was higher with class 2 (adjusted HR, 1.41 [95% CI, 1.08-1.84]; P=0.01) compared with class 1, adjusting for demographics, hospital level factors, and KDIGO stage of AKI. The higher risk of MAKE among class 2 was explained by a higher risk of long-term chronic kidney disease progression and dialysis. The top variables that were different between classes 1 and 2 included plasma and urinary biomarkers of inflammation and epithelial cell injury; serum creatinine ranked 20th out of the 29 variables for differentiating classes.

LIMITATIONS

A replication cohort with simultaneously collected blood and urine sampling in hospitalized adults with AKI and long-term outcomes was unavailable.

CONCLUSIONS

We identify 2 molecularly distinct AKI subphenotypes with differing risk of long-term outcomes, independent of the current criteria to risk stratify AKI. Future identification of AKI subphenotypes may facilitate linking therapies to underlying pathophysiology to prevent long-term sequalae after AKI.

PLAIN-LANGUAGE SUMMARY

Acute kidney injury (AKI) occurs commonly in hospitalized patients and is associated with high morbidity and mortality. The AKI definition lumps many different types of AKI together, but subgroups of AKI may be more tightly linked to the underlying biology and clinical outcomes. We used 29 different clinical, blood, and urinary biomarkers and applied 2 different statistical algorithms to identify AKI subtypes and their association with long-term outcomes. Both clustering algorithms identified 2 AKI subtypes with different risk of chronic kidney disease, independent of the serum creatinine concentrations (the current gold standard to determine severity of AKI). Identification of AKI subtypes may facilitate linking therapies to underlying biology to prevent long-term consequences after AKI.

Precision management of acute kidney injury in the intensive care unit: current state of the art

Acute kidney injury (AKI) is a prototypical example of a common syndrome in critical illness defined by consensus. The consensus definition for AKI, traditionally defined using only serum creatinine and urine output, was needed to standardize the description for epidemiology and to harmonize eligibility for clinical trials. However, AKI is not a simple disease, but rather a complex and multi-factorial syndrome characterized by a wide spectrum of pathobiology. AKI is now recognized to be comprised of numerous sub-phenotypes that can be discriminated through shared features such as etiology, prognosis, or common pathobiological mechanisms of injury and damage. The characterization of sub-phenotypes can serve to enable prognostic enrichment (i.e., identify subsets of patients more likely to share an outcome of interest) and predictive enrichment (identify subsets of patients more likely to respond favorably to a given therapy). Existing and emerging biomarkers will aid in discriminating sub-phenotypes of AKI, facilitate expansion of diagnostic criteria, and be leveraged to realize personalized approaches to management, particularly for recognizing treatment-responsive mechanisms (i.e., endotypes) and targets for intervention (i.e., treatable traits). Specific biomarkers (e.g., serum renin; olfactomedin 4 (OLFM4); interleukin (IL)-9) may further enable identification of pathobiological mechanisms to serve as treatment targets. However, even non-specific biomarkers of kidney injury (e.g., neutrophil gelatinase-associated lipocalin, NGAL; [tissue inhibitor of metalloproteinases 2, TIMP2]·[insulin like growth factor binding protein 7, IGFBP7]; kidney injury molecule 1, KIM-1) can direct greater precision management for specific sub-phenotypes of AKI. This review will summarize these evolving concepts and recent innovations in precision medicine approaches to the syndrome of AKI in critical illness, along with providing examples of how they can be leveraged to guide patient care.

Characteristics of Kidney Transplant Recipients with Prolonged Pre-Transplant Dialysis Duration as Identified by Machine Learning Consensus Clustering: Pathway to Personalized Care

Longer pre-transplant dialysis duration is known to be associated with worse post-transplant outcomes. Our study aimed to cluster kidney transplant recipients with prolonged dialysis duration before transplant using an unsupervised machine learning approach to better assess heterogeneity within this cohort. We performed consensus cluster analysis based on recipient-, donor-, and transplant-related characteristics in 5092 kidney transplant recipients who had been on dialysis ≥ 10 years prior to transplant in the OPTN/UNOS database from 2010 to 2019. We characterized each assigned cluster and compared the posttransplant outcomes. Overall, the majority of patients with ≥10 years of dialysis duration were black (52%) or Hispanic (25%), with only a small number (17.6%) being moderately sensitized. Within this cohort, three clinically distinct clusters were identified. Cluster 1 patients were younger, non-diabetic and non-sensitized, had a lower body mass index (BMI) and received a kidney transplant from younger donors. Cluster 2 recipients were older, unsensitized and had a higher BMI; they received kidney transplant from older donors. Cluster 3 recipients were more likely to be female with a higher PRA. Compared to cluster 1, cluster 2 had lower 5-year death-censored graft (HR 1.40; 95% CI 1.16-1.71) and patient survival (HR 2.98; 95% CI 2.43-3.68). Clusters 1 and 3 had comparable death-censored graft and patient survival. Unsupervised machine learning was used to characterize kidney transplant recipients with prolonged pre-transplant dialysis into three clinically distinct clusters with variable but good post-transplant outcomes. Despite a dialysis duration ≥ 10 years, excellent outcomes were observed in most recipients, including those with moderate sensitization. A disproportionate number of minority recipients were observed within this cohort, suggesting multifactorial delays in accessing kidney transplantation.

Joint Modeling of Clinical and Biomarker Data in Acute Kidney Injury Defines Unique Subphenotypes with Differing Outcomes

BACKGROUND

AKI is a heterogeneous syndrome. Current subphenotyping approaches have only used limited laboratory data to understand a much more complex condition.

METHODS

We focused on patients with AKI from the Assessment, Serial Evaluation, and Subsequent Sequelae in AKI (ASSESS-AKI). We used hierarchical clustering with Ward linkage on biomarkers of inflammation, injury, and repair/health. We then evaluated clinical differences between subphenotypes and examined their associations with cardiorenal events and death using Cox proportional hazard models.

RESULTS

We included 748 patients with AKI: 543 (73%) of them had AKI stage 1, 112 (15%) had AKI stage 2, and 93 (12%) had AKI stage 3. The mean age (±SD) was 64 (13) years; 508 (68%) were men; and the median follow-up was 4.7 (Q1: 2.9, Q3: 5.7) years. Patients with AKI subphenotype 1 ( N =181) had the highest kidney injury molecule (KIM-1) and troponin T levels. Subphenotype 2 ( N =250) had the highest levels of uromodulin. AKI subphenotype 3 ( N =159) comprised patients with markedly high pro-brain natriuretic peptide and plasma tumor necrosis factor receptor-1 and -2 and low concentrations of KIM-1 and neutrophil gelatinase-associated lipocalin. Finally, patients with subphenotype 4 ( N =158) predominantly had sepsis-AKI and the highest levels of vascular/kidney inflammation (YKL-40, MCP-1) and injury (neutrophil gelatinase-associated lipocalin, KIM-1). AKI subphenotypes 3 and 4 were independently associated with a higher risk of death compared with subphenotype 2 and had adjusted hazard ratios of 2.9 (95% confidence interval, 1.8 to 4.6) and 1.6 (95% confidence interval, 1.01 to 2.6, P = 0.04), respectively. Subphenotype 3 was also independently associated with a three-fold risk of CKD and cardiovascular events.

CONCLUSIONS

We discovered four AKI subphenotypes with differing clinical features and biomarker profiles that are associated with longitudinal clinical outcomes.

Identifying acute kidney injury subphenotypes using an outcome-driven deep-learning approach

OBJECTIVE

Acute kidney injury (AKI), a common condition on the intensive-care unit (ICU), is characterized by an abrupt decrease in kidney function within a few hours or days, leading to kidney failure or damage. Although AKI is associated with poor outcomes, current guidelines overlook the heterogeneity among patients with this condition. Identification of AKI subphenotypes could enable targeted interventions and a deeper understanding of the injury's pathophysiology. While previous approaches based on unsupervised representation learning have been used to identify AKI subphenotypes, these methods cannot assess time series or disease severity.

METHODS

In this study, we developed a data- and outcome-driven deep-learning (DL) approach to identify and analyze AKI subphenotypes with prognostic and therapeutic implications. Specifically, we developed a supervised long short-term memory (LSTM) autoencoder (AE) with the aim of extracting representation from time-series EHR data that were intricately correlated with mortality. Then, subphenotypes were identified via application of K-means.

RESULTS

In two publicly available datasets, three distinct clusters were identified, characterized by mortality rates of 11.3%, 17.3%, and 96.2% in one dataset and 4.6%, 12.1%, and 54.6% in the other. Further analysis demonstrated that AKI subphenotypes identified by our proposed approach were statistically significant on several clinical characteristics and outcomes.

CONCLUSION

In this study, our proposed approach could successfully cluster the AKI population in ICU settings into 3 distinct subphenotypes. Thus, such approach could potentially improve outcomes of AKI patients in the ICU, with better risk assessment and potentially better personalized treatment.

Machine learning for the prediction of all-cause mortality in patients with sepsis-associated acute kidney injury during hospitalization

Background

Sepsis-associated acute kidney injury (S-AKI) is considered to be associated with high morbidity and mortality, a commonly accepted model to predict mortality is urged consequently. This study used a machine learning model to identify vital variables associated with mortality in S-AKI patients in the hospital and predict the risk of death in the hospital. We hope that this model can help identify high-risk patients early and reasonably allocate medical resources in the intensive care unit (ICU).

Methods

A total of 16,154 S-AKI patients from the Medical Information Mart for Intensive Care IV database were examined as the training set (80%) and the validation set (20%). Variables (129 in total) were collected, including basic patient information, diagnosis, clinical data, and medication records. We developed and validated machine learning models using 11 different algorithms and selected the one that performed the best. Afterward, recursive feature elimination was used to select key variables. Different indicators were used to compare the prediction performance of each model. The SHapley Additive exPlanations package was applied to interpret the best machine learning model in a web tool for clinicians to use. Finally, we collected clinical data of S-AKI patients from two hospitals for external validation.

Results

In this study, 15 critical variables were finally selected, namely, urine output, maximum blood urea nitrogen, rate of injection of norepinephrine, maximum anion gap, maximum creatinine, maximum red blood cell volume distribution width, minimum international normalized ratio, maximum heart rate, maximum temperature, maximum respiratory rate, minimum fraction of inspired O2, minimum creatinine, minimum Glasgow Coma Scale, and diagnosis of diabetes and stroke. The categorical boosting algorithm model presented significantly better predictive performance [receiver operating characteristic (ROC): 0.83] than other models [accuracy (ACC): 75%, Youden index: 50%, sensitivity: 75%, specificity: 75%, F1 score: 0.56, positive predictive value (PPV): 44%, and negative predictive value (NPV): 92%]. External validation data from two hospitals in China were also well validated (ROC: 0.75).

Conclusions

After selecting 15 crucial variables, a machine learning-based model for predicting the mortality of S-AKI patients was successfully established and the CatBoost model demonstrated best predictive performance.

IDENTIFICATION OF SUBPHENOTYPES OF SEPSIS-ASSOCIATED LIVER DYSFUNCTION USING CLUSTER ANALYSIS

ABSTRACT

Objectives: We attempted to identify and validate the subphenotypes of sepsis-associated liver dysfunction (SALD) using routine clinical information. Design: This article is a retrospective observational cohort study. Setting: We used the Medical Information Mart for Intensive Care IV database and the eICU Collaborative Research Database. Patients: We included adult patients (age ≥18 years) who developed SALD within the first 48 hours of intensive care unit (ICU) admission. We excluded patients who died or were discharged from the ICU within the first 48 hours of admission. Patients with abnormal liver function before ICU admission were also excluded. Measurements and Main Results: Patients in the MIMIC-IV 1.0 database served as a derivation cohort. Patients in the eICU database were used as validation cohort. We identified four subphenotypes of SALD (subphenotype α, β, γ, δ) using K-means cluster analysis in 5234 patients in derivation cohort. The baseline characteristics and clinical outcomes were compared between the phenotypes using one-way analysis of variance/Kruskal-Wallis test and the χ 2 test. Moreover, we used line charts to illustrate the trend of liver function parameters over 14 days after ICU admission. Subphenotype α (n = 1,055) was the most severe cluster, characterized by shock with multiple organ dysfunction (MODS) group. Subphenotype β (n = 1,179) had the highest median bilirubin level and the highest proportion of patients with underlying liver disease and coexisting coagulopathy (increased bilirubin group). Subphenotype γ (n = 1,661) was the cluster with the highest mean age and had the highest proportion of patients with chronic kidney disease (aged group). Subphenotype δ (n = 1,683) had the lowest 28-day and in-hospital mortality (mild group). The characteristics of clusters in the validation cohort were similar to those in the derivation cohort. In addition, we were surprised to find that GGT levels in subphenotype δ were significantly higher than in other subphenotypes, showing a different pattern from bilirubin. Conclusions: We identified four subphenotypes of SALD that presented with different clinical features and outcomes. These results can provide a valuable reference for understanding the clinical characteristics and associated outcomes to improve the management of patients with SALD in the ICU.

Sepsis-associated acute kidney injury: consensus report of the 28th Acute Disease Quality Initiative workgroup

Sepsis-associated acute kidney injury (SA-AKI) is common in critically ill patients and is strongly associated with adverse outcomes, including an increased risk of chronic kidney disease, cardiovascular events and death. The pathophysiology of SA-AKI remains elusive, although microcirculatory dysfunction, cellular metabolic reprogramming and dysregulated inflammatory responses have been implicated in preclinical studies. SA-AKI is best defined as the occurrence of AKI within 7 days of sepsis onset (diagnosed according to Kidney Disease Improving Global Outcome criteria and Sepsis 3 criteria, respectively). Improving outcomes in SA-AKI is challenging, as patients can present with either clinical or subclinical AKI. Early identification of patients at risk of AKI, or at risk of progressing to severe and/or persistent AKI, is crucial to the timely initiation of adequate supportive measures, including limiting further insults to the kidney. Accordingly, the discovery of biomarkers associated with AKI that can aid in early diagnosis is an area of intensive investigation. Additionally, high-quality evidence on best-practice care of patients with AKI, sepsis and SA-AKI has continued to accrue. Although specific therapeutic options are limited, several clinical trials have evaluated the use of care bundles and extracorporeal techniques as potential therapeutic approaches. Here we provide graded recommendations for managing SA-AKI and highlight priorities for future research.

Research frontiers and trends in the application of artificial intelligence to sepsis: A bibliometric analysis

Background

With the increasing interest of academics in the application of artificial intelligence to sepsis, thousands of papers on this field had been published in the past few decades. It is difficult for researchers to understand the themes and latest research frontiers in this field from a multi-dimensional perspective. Consequently, the purpose of this study is to analyze the relevant literature in the application of artificial intelligence to sepsis through bibliometrics software, so as to better understand the development status, study the core hotspots and future development trends of this field.

Methods

We collected relevant publications in the application of artificial intelligence to sepsis from the Web of Science Core Collection in 2000 to 2021. The type of publication was limited to articles and reviews, and language was limited to English. Research cooperation network, journals, cited references, keywords in this field were visually analyzed by using CiteSpace, VOSviewer, and COOC software.

Results

A total of 8,481 publications in the application of artificial intelligence to sepsis between 2000 and 2021 were included, involving 8,132 articles and 349 reviews. Over the past 22 years, the annual number of publications had gradually increased exponentially. The USA was the most productive country, followed by China. Harvard University, Schuetz, Philipp, and Intensive Care Medicine were the most productive institution, author, and journal, respectively. Vincent, Jl and Critical Care Medicine were the most cited author and cited journal, respectively. Several conclusions can be drawn from the analysis of the cited references, including the following: screening and identification of sepsis biomarkers, treatment and related complications of sepsis, and precise treatment of sepsis. Moreover, there were a spike in searches relating to machine learning, antibiotic resistance and accuracy based on burst detection analysis.

Conclusion

This study conducted a comprehensive and objective analysis of the publications on the application of artificial intelligence in sepsis. It can be predicted that precise treatment of sepsis through machine learning technology is still research hotspot in this field.

Federated Learning in Health care Using Structured Medical Data

The success of machine learning-based studies is largely subjected to accessing a large amount of data. However, accessing such data is typically not feasible within a single health system/hospital. Although multicenter studies are the most effective way to access a vast amount of data, sharing data outside the institutes involves legal, business, and technical challenges. Federated learning (FL) is a newly proposed machine learning framework for multicenter studies, tackling data-sharing issues across participant institutes. The promise of FL is simple. FL facilitates multicenter studies without losing data access control and allows the construction of a global model by aggregating local models trained from participant institutes. This article reviewed recently published studies that utilized FL in clinical studies with structured medical data. In addition, challenges and open questions in FL in clinical studies with structured medical data were discussed.

Identification of spinal tuberculosis subphenotypes using routine clinical data: a study based on unsupervised machine learning

OBJECTIVE

The identification of spinal tuberculosis subphenotypes is an integral component of precision medicine. However, we lack proper study models to identify subphenotypes in patients with spinal tuberculosis. Here we identified possible subphenotypes of spinal tuberculosis and compared their clinical results.

METHODS

A total of 422 patients with spinal tuberculosis who received surgical treatment were enrolled. Clustering analysis was performed using the K-means clustering algorithm and the routinely available clinical data collected from patients within 24 h after admission. Finally, the differences in clinical characteristics, surgical efficacy, and postoperative complications among the subphenotypes were compared.

RESULTS

Two subphenotypes of spinal tuberculosis were identified. Laboratory examination results revealed that the levels of more than one inflammatory index in cluster 2 were higher than those in cluster 1. In terms of disease severity, Cluster 2 showed a higher Oswestry Disability Index (ODI), a higher visual analysis scale (VAS) score, and a lower Japanese Orthopedic Association (JOA) score. In addition, in terms of postoperative outcomes, cluster 2 patients were more prone to complications, especially wound infections, and had a longer hospital stay.

CONCLUSION

K-means clustering analysis based on conventional available clinical data can rapidly identify two subtypes of spinal tuberculosis with different clinical results. We believe this finding will help clinicians to rapidly and easily identify the subtypes of spinal tuberculosis at the bedside and become the cornerstone of individualized treatment strategies.

Predicting Risk Factors of Acute Kidney Injury in the First 7 Days after Admission: Analysis of a Group of Critically Ill Patients

Background

Acute kidney injury (AKI) is a common complication in critically ill patients. Some predictive models have been reported, but the conclusions are controversial. The aim of this study was the formation of nomograms to predict risk factors for AKI in critically ill patients within the first 7 days after admission to the intensive care unit (ICU).

Methods

Data were extracted from the Medical Information Mart for Intensive Care- (MIMIC-) III database. The random forest method was used to fill in the missing values, and least absolute shrinkage and selection operator (Lasso) regression analysis was performed to screen for possible risk factors.

Results

A total of 561 patients were enrolled. Complication with AKI is significantly associated with a longer length of stay (LOS). For all patients, the predictors contained in the prediction nomogram included hypertension, coronary artery disease (CAD), cardiopulmonary bypass (CPB), coronary artery bypass grafting (CABG), Simplified Acute Physiology Score II (SAPS II), central venous pressure (CVP) measured for the first time after admission, and maximum and minimum mean artery pressure (MAP). The model showed good discrimination (C - index = 0.818, 95% CI: 0.779-0.857). In the subgroup of patients with well-controlled blood glucose levels, the significant predictors included hypertension, CABG, CPB, SAPS II, and maximum and minimum MAP. Good discrimination was also present before (C - index = 0.785, 95% CI: 0.736-0.834) and after adjustment (adjusted C - index = 0.770).

Conclusion

Hypertension, CAD, CPB, CABG, SAPS II, CVP measured for the first time after admission, and maximum and minimum MAP were independent risk factors for AKI in critically ill patients.

KIT-LSTM: Knowledge-guided Time-aware LSTM for Continuous Clinical Risk Prediction

Rapid accumulation of temporal Electronic Health Record (EHR) data and recent advances in deep learning have shown high potential in precisely and timely predicting patients' risks using AI. However, most existing risk prediction approaches ignore the complex asynchronous and irregular problems in real-world EHR data. This paper proposes a novel approach called Knowledge-guIded Time-aware LSTM (KIT-LSTM) for continuous mortality predictions using EHR. KIT-LSTM extends LSTM with two time-aware gates and a knowledge-aware gate to better model EHR and interprets results. Experiments on real-world data for patients with acute kidney injury with dialysis (AKI-D) demonstrate that KIT-LSTM performs better than the state-of-the-art methods for predicting patients' risk trajectories and model interpretation. KIT-LSTM can better support timely decision-making for clinicians.

Subphenotypes of acute kidney injury in children

PURPOSE OF REVIEW

The purpose of this review is to describe acute kidney injury (AKI) phenotypes in children.

RECENT FINDINGS

AKI is a heterogenous disease that imposes significant morbidity and mortality on critically ill and noncritically ill patients across the age spectrum. As our understanding of AKI and its association with outcomes has improved, it is becoming increasingly apparent that there are distinct AKI subphenotypes that vary by cause or associated conditions. We have also learned that severity, duration, and repeated episodes of AKI impact outcomes, and that integration of novel urinary biomarkers of tubular injury can also reveal unique subphenotypes of AKI that may not be otherwise readily apparent.

SUMMARY

Studies that further delineate these unique AKI subphenotypes are needed to better understand the impact of AKI in children. Further delineation of these phenotypes has both prognostic and therapeutic implications.

Opportunities in digital health and electronic health records for acute kidney injury care

PURPOSE OF REVIEW

The field of digital health is evolving rapidly with applications relevant to the prediction, detection and management of acute kidney injury (AKI). This review will summarize recent publications in these areas.

RECENT FINDINGS

Machine learning (ML) approaches have been applied predominantly for AKI prediction, but also to identify patients with AKI at higher risk of adverse outcomes, and to discriminate different subgroups (subphenotypes) of AKI. There have been multiple publications in this area, but a smaller number of ML models have robust external validation or the ability to run in real-time in clinical systems. Recent studies of AKI alerting systems and clinical decision support systems continue to demonstrate variable results, which is likely to result from differences in local context and implementation strategies. In the design of AKI alerting systems, choice of baseline creatinine has a strong effect on performance of AKI detection algorithms.

SUMMARY

Further research is required to overcome barriers to the validation and implementation of ML models for AKI care. Simpler electronic systems within the electronic medical record can lead to improved care in some but not all settings, and careful consideration of local context and implementation strategy is recommended.

Subphenotypes of acute kidney injury in adults

PURPOSE OF REVIEW

Acute kidney injury is a heterogeneous syndrome and as such is associated with multiple predisposing conditions and causes all of which affect outcomes. Such heterogeneity may conceal the potential benefit of therapies when generally applied to patients with acute kidney injury (AKI). The discovery of pathophysiology-based subphenotypes could be of benefit in allocating current and future therapies to specific groups.

RECENT FINDINGS

Clinical subphenotypes group patients into categories according to predisposing factors, disease severity, and trajectory. These may be helpful in assessing patient outcomes. Analyses of existing databases have revealed biological subphenotypes that are characterized by levels of biomarkers indicative of hyperinflammation and endothelial injury. Patients with increased levels of these biomarkers display higher mortality rates compared with those with lower levels and there is potential that this group might respond differently to therapies. However, challenges remain in the validation, generalizability, and application of these subphenotypes.

SUMMARY

Subphenotyping may help reduce heterogeneity under the umbrella term of acute kidney injury. Despite challenges remain, the identification of AKI subphenotypes has opened the potential of AKI research focused on better targeted therapies.

Machine learning for risk stratification in kidney disease

PURPOSE OF REVIEW

Risk stratification for chronic kidney is becoming increasingly important as a clinical tool for both treatment and prevention measures. The goal of this review is to identify how machine learning tools contribute and facilitate risk stratification in the clinical setting.

RECENT FINDINGS

The two key machine learning paradigms to predictively stratify kidney disease risk are genomics-based and electronic health record based approaches. These methods can provide both quantitative information such as relative risk and qualitative information such as characterizing risk by subphenotype.

SUMMARY

The four key methods to stratify chronic kidney disease risk are genomics, multiomics, supervised and unsupervised machine learning methods. Polygenic risk scores utilize whole genome sequencing data to generate an individual's relative risk compared with the population. Multiomic methods integrate information from multiple biomarkers to generate trajectories and prognostic different outcomes. Supervised machine learning methods can directly utilize the growing compendia of electronic health records such as laboratory results and notes to generate direct risk predictions, while unsupervised machine learning methods can cluster individuals with chronic kidney disease into subphenotypes with differing approaches to care.

Biomarkers for the Prediction and Judgement of Sepsis and Sepsis Complications: A Step towards precision medicine?

Sepsis and septic shock are a major public health concern and are still associated with high rates of morbidity and mortality. Whilst there is growing understanding of different phenotypes and endotypes of sepsis, all too often treatment strategies still only employ a “one-size-fits-all” approach. Biomarkers offer a unique opportunity to close this gap to more precise treatment approaches by providing insight into clinically hidden, yet complex, pathophysiology, or by individualizing treatment pathways. Predicting and evaluating systemic inflammation, sepsis or septic shock are essential to improve outcomes for these patients. Besides opportunities to improve patient care, employing biomarkers offers a unique opportunity to improve clinical research in patients with sepsis. The high rate of negative clinical trials in this field may partly be explained by a high degree of heterogeneity in patient cohorts and a lack of understanding of specific endotypes or phenotypes. Moving forward, biomarkers can support the selection of more homogeneous cohorts, thereby potentially improving study conditions of clinical trials. This may finally pave the way to a precision medicine approach to sepsis, septic shock and complication of sepsis in the future.

Artificial Intelligence in Acute Kidney Injury Prediction

The use of artificial intelligence (AI) in nephrology and its associated clinical research is growing. Recent years have seen increased interest in utilizing AI to predict the development of hospital-based acute kidney injury (AKI). Several AI techniques have been employed to improve the ability to detect AKI across a variety of hospitalized settings. This review discusses the evolutions of AKI risk prediction discussing the static risk assessment models of yesteryear as well as the more recent trend toward AI and advanced learning techniques. We discuss the relative improvement in AKI detection as well as the relative dearth of data around the clinical implementation and patient outcomes using these models. The use of AI for AKI detection and clinical care is in its infancy, and this review describes how we arrived at our current position and hints at the promise of the future.

Recent Advances and Future Perspectives in the Use of Machine Learning and Mathematical Models in Nephrology

We reviewed some of the latest advancements in the use of mathematical models in nephrology. We looked over 2 distinct categories of mathematical models that are widely used in biological research and pointed out some of their strengths and weaknesses when applied to health care, especially in the context of nephrology. A mechanistic dynamical system allows the representation of causal relations among the system variables but with a more complex and longer development/implementation phase. Artificial intelligence/machine learning provides predictive tools that allow identifying correlative patterns in large data sets, but they are usually harder-to-interpret black boxes. Chronic kidney disease (CKD), a major worldwide health problem, generates copious quantities of data that can be leveraged by choice of the appropriate model; also, there is a large number of dialysis parameters that need to be determined at every treatment session that can benefit from predictive mechanistic models. Following important steps in the use of mathematical methods in medical science might be in the intersection of seemingly antagonistic frameworks, by leveraging the strength of each to provide better care.

Machine Learning for Acute Kidney Injury Prediction in the Intensive Care Unit

Machine learning is the field of artificial intelligence in which computers are trained to make predictions or to identify patterns in data through complex mathematical algorithms. It has great potential in critical care to predict outcomes, such as acute kidney injury, and can be used for prognosis and to suggest management strategies. Machine learning can also be used as a research tool to advance our clinical and biochemical understanding of acute kidney injury. In this review, we introduce basic concepts in machine learning and review recent research in each of these domains.

Application of Machine Learning for Clinical Subphenotype Identification in Sepsis

INTRODUCTION

Sepsis is a heterogeneous clinical syndrome. Identification of sepsis subphenotypes could lead to allowing more precise therapy. However, there is a lack of models to identify the subphenotypes in such patients. Thus, we aimed to identify possible subphenotypes and compare the clinical outcomes for subphenotypes in a large sepsis cohort.

METHODS

This machine learning-based, cluster analysis was performed using the Medical Information Mart in Intensive Care (MIMIC)-IV database. We enrolled all adult (> 18 years old) patients diagnosed with sepsis in the first 24 h after intensive care unit (ICU) admission. K-means cluster analysis was performed to identify the number of classes. Multivariable logistic regression models were used to estimate the association between sepsis subphenotypes and in-hospital mortality.

RESULTS

A total of 8817 participants with sepsis were enrolled. The median age was 66.8 (IQR, 55.9-77.1) years, and 38.1% (3361/8817) were female. Two subphenotypes resulted in optimal separation including 11 routinely available clinical variables obtained during the first 24 h after ICU admission. Participants in subphenotype B showed higher levels of lactate, glucose and creatinine, white blood cell count, sodium and heart rate and lower body temperature, platelet count, systolic blood pressure, hemoglobin and PaO₂/FiO₂ ratio. In addition, the in-hospital mortality in patients with subphenotype B was significantly higher than that in subphenotype A (29.4% vs. 8.5%, P < 0.001). The difference was still significant after adjustment for potential covariates (adjusted OR 2.214; 95% CI 1.780-2.754, P < 0.001).

CONCLUSIONS

Two sepsis subphenotypes with different clinical outcomes could be rapidly identified using the K-means clustering analysis based on routinely available clinical data. This finding may help clinicians to identify the subphenotype rapidly at the bedside.

Subphenotypes in acute kidney injury: a narrative review

Acute kidney injury (AKI) is a frequently encountered syndrome especially among the critically ill. Current diagnosis of AKI is based on acute deterioration of kidney function, indicated by an increase in creatinine and/or reduced urine output. However, this syndromic definition encompasses a wide variety of distinct clinical features, varying pathophysiology, etiology and risk factors, and finally very different short- and long-term outcomes. Lumping all AKI together may conceal unique pathophysiologic processes specific to certain AKI populations, and discovering these AKI subphenotypes might help to develop targeted therapies tackling unique pathophysiological processes. In this review, we discuss the concept of AKI subphenotypes, current knowledge regarding both clinical and biomarker-driven subphenotypes, interplay with AKI subphenotypes and other ICU syndromes, and potential future and clinical implications.

Supervised Pretraining through Contrastive Categorical Positive Samplings to Improve COVID-19 Mortality Prediction

Clinical EHR data is naturally heterogeneous, where it contains abundant sub-phenotype. Such diversity creates challenges for outcome prediction using a machine learning model since it leads to high intra-class variance. To address this issue, we propose a supervised pre-training model with a unique embedded k-nearest-neighbor positive sampling strategy. We demonstrate the enhanced performance value of this framework theoretically and show that it yields highly competitive experimental results in predicting patient mortality in real-world COVID-19 EHR data with a total of over 7,000 patients admitted to a large, urban health system. Our method achieves a better AUROC prediction score of 0.872, which outperforms the alternative pre-training models and traditional machine learning methods. Additionally, our method performs much better when the training data size is small (345 training instances).

Distinct Subtyping of Successful Weaning from Acute Kidney Injury Requiring Renal Replacement Therapy by Consensus Clustering in Critically Ill Patients

Background: Clinical decisions regarding the appropriate timing of weaning off renal replacement therapy (RRT) in critically ill patients are complex and multifactorial. The aim of the current study was to identify which critical patients with acute kidney injury (AKI) may be more likely to be successfully weaned off RRT using consensus cluster analysis. Methods: In this study, critically ill patients who received RRT at three multicenter referral hospitals at several timepoints from August 2016 to July 2018 were enrolled. An unsupervised consensus clustering algorithm was used to identify distinct phenotypes. The outcomes of interest were the ability to wean off RTT and 90-day mortality. Results: A total of 124 patients with AKI requiring RRT (AKI-RRT) were enrolled. The 90-day mortality rate was 30.7% (38/124), and 49.2% (61/124) of the patients were successfully weaned off RRT for over 90 days. The consensus clustering algorithm identified three clusters from a total of 45 features. The three clusters had distinct features and could be separated according to the combination of urinary neutrophil gelatinase-associated lipocalin to creatinine ratio (uNGAL/Cr), Sequential Organ Failure Assessment (SOFA) score, and estimated glomerular filtration rate at the time of weaning off RRT. uNGAL/Cr (hazard ratio [HR] 2.43, 95% confidence interval [CI]: 1.36–4.33) and clustering phenotype (cluster 1 vs. 3, HR 2.7, 95% CI: 1.11–6.57; cluster 2 vs. 3, HR 44.5, 95% CI: 11.92–166.39) could predict 90-day mortality or re-dialysis. Conclusions: Almost half of the critical patients with AKI-RRT could wean off dialysis for over 90 days. Urinary NGAL/Cr and distinct clustering phenotypes could predict 90-day mortality or re-dialysis.

Multi-Omics Techniques Make it Possible to Analyze Sepsis-Associated Acute Kidney Injury Comprehensively

Sepsis-associated acute kidney injury (SA-AKI) is a common complication in critically ill patients with high morbidity and mortality. SA-AKI varies considerably in disease presentation, progression, and response to treatment, highlighting the heterogeneity of the underlying biological mechanisms. In this review, we briefly describe the pathophysiology of SA-AKI, biomarkers, reference databases, and available omics techniques. Advances in omics technology allow for comprehensive analysis of SA-AKI, and the integration of multiple omics provides an opportunity to understand the information flow behind the disease. These approaches will drive a shift in current paradigms for the prevention, diagnosis, and staging and provide the renal community with significant advances in precision medicine in SA-AKI analysis.

The Pathophysiology of Sepsis-Associated AKI

Sepsis-associated AKI is a life-threatening complication that is associated with high morbidity and mortality in patients who are critically ill. Although it is clear early supportive interventions in sepsis reduce mortality, it is less clear that they prevent or ameliorate sepsis-associated AKI. This is likely because specific mechanisms underlying AKI attributable to sepsis are not fully understood. Understanding these mechanisms will form the foundation for the development of strategies for early diagnosis and treatment of sepsis-associated AKI. Here, we summarize recent laboratory and clinical studies, focusing on critical factors in the pathophysiology of sepsis-associated AKI: microcirculatory dysfunction, inflammation, NOD-like receptor protein 3 inflammasome, microRNAs, extracellular vesicles, autophagy and efferocytosis, inflammatory reflex pathway, vitamin D, and metabolic reprogramming. Lastly, identifying these molecular targets and defining clinical subphenotypes will permit precision approaches in the prevention and treatment of sepsis-associated AKI.