Deep-learning-based real-time prediction of acute kidney injury outperforms human predictive performance

Attention to early stages: predicting acute kidney injury in a post cardiosurgical ICU setting using an inclusive time-to-event model

BACKGROUND

Acute kidney injury (AKI) is a critical complication in intensive care units (ICUs) that is known to have multifaceted impacts. However, as AKI is often detected too late, early prediction is crucial for timely intervention.

METHODS

We used an attention-based time-to-event model to estimate the risk of a patient's first AKI incidence in a post-cardiosurgical ICU setting, irrespective of commonly employed limitations such as focusing on severe stages (2 & 3). Pre-, intra-, and postoperative data from 8564 adult patients were included, and AKI was defined by adhering to the full Kidney Disease: Improving Global Outcomes (KDIGO) definition. Models were primarily evaluated using the concordance index (CI).

RESULTS

70.4 % of patients developed AKI, with stage 1 being the most frequent initial stage (88.1 %). The attention-based network outperformed our baseline model, achieving CIs of 0.80, 0.72, and 0.69 for ranking event risks up to 6, 12, and 24 h prior to the onset. In terms of converting the task to a classification problem for literature comparison, we obtained areas under the receiver operator characteristic curve (auROCs) of 0.82-0.73. Performance improved for severe AKIs only, yielding CIs of 0.92, 0.85, and 0.75, and auROCs ranging between 0.94 and 0.78.

CONCLUSION

We demonstrated the importance of early-stage AKI predictions and presented a novel approach to achieve this. Under similar assumptions, our results showed improvement and approached outcomes comparable to the literature. While practical validation is pending, we are confident that our approach proves useful in assisting physicians to prevent AKI development.

Machine learning based finite element analysis for personalized prediction of pressure injury risk in patients with spinal cord injury

BACKGROUND AND OBJECTIVE

Patients with spinal cord injury (SCI), are prone to pressure injury (PI) in the soft tissues of buttocks. Early prediction of PI holds the potential to reduce the occurrence and progression of PI. This study proposes a machine learning model to predict soft tissue stress/strain and evaluate PI risk in SCI patients.

METHODS

Based on the standard database from parametric models of buttock, the biomechanical response of soft tissues and risk factors affecting PI were analyzed. A comprehensive assessment of multiple machine-learning methods was performed to predict the risk of PI, the selected optimal model is explained locally and globally using Shapley additive explanations (SHAP).

RESULTS

The proposed hybrid model for predicting PI consists of a backpropagation neural network and Extreme Gradient Boosting, performed the coefficient of determination (R2) of 0.977.

CONCLUSION

The model exhibits accurate performance which may be considered as the ideal method for predicting PI. Furthermore, it can be used with other health-monitoring equipment to improve the quality of patients with SCI or other dysfunctional diseases.

Machine Learning to Assist in Managing Acute Kidney Injury in General Wards: Multicenter Retrospective Study

BACKGROUND

Most artificial intelligence-based research on acute kidney injury (AKI) prediction has focused on intensive care unit settings, limiting their generalizability to general wards. The lack of standardized AKI definitions and reliance on intensive care units further hinder the clinical applicability of these models.

OBJECTIVE

This study aims to develop and validate a machine learning-based framework to assist in managing AKI and acute kidney disease (AKD) in general ward patients, using a refined operational definition of AKI to improve predictive performance and clinical relevance.

METHODS

This retrospective multicenter cohort study analyzed electronic health record data from 3 hospitals in South Korea. AKI and AKD were defined using a refined version of the Kidney Disease: Improving Global Outcomes criteria, which included adjustments to baseline serum creatinine estimation and a stricter minimum increase threshold to reduce misclassification due to transient fluctuations. The primary outcome was the development of machine learning models for early prediction of AKI (within 3 days before onset) and AKD (nonrecovery within 7 days after AKI).

RESULTS

The final analysis included 135,068 patients. A total of 7658 (8%) patients in the internal cohort and 2898 (7.3%) patients in the external cohort developed AKI. Among the 5429 patients in the internal cohort and 1998 patients in the external cohort for whom AKD progression could be assessed, 896 (16.5%) patients and 287 (14.4%) patients, respectively, progressed to AKD. Using the refined criteria, 2898 cases of AKI were identified, whereas applying the standard Kidney Disease: Improving Global Outcomes criteria resulted in the identification of 5407 cases. Among the 2509 patients who were not classified as having AKI under the refined criteria, 2242 had a baseline serum creatinine level below 0.6 mg/dL, while the remaining 267 experienced a decrease in serum creatinine before the onset of AKI. The final selected early prediction model for AKI achieved an area under the receiver operating characteristic curve of 0.9053 in the internal cohort and 0.8860 in the external cohort. The early prediction model for AKD achieved an area under the receiver operating characteristic curve of 0.8202 in the internal cohort and 0.7833 in the external cohort.

CONCLUSIONS

The proposed machine learning framework successfully predicted AKI and AKD in general ward patients with high accuracy. The refined AKI definition significantly reduced the classification of patients with transient serum creatinine fluctuations as AKI cases compared to the previous criteria. These findings suggest that integrating this machine learning framework into hospital workflows could enable earlier interventions, optimize resource allocation, and improve patient outcomes.

A bibliometric analysis of perioperative medicine and artificial intelligence

BACKGROUND

Artificial intelligence holds the potential to transform perioperative medicine by leveraging complex datasets to predict risks and optimise patient management in response to rising surgical volumes and patient complexity.

AIM

This bibliometric analysis aims to analyse trends, contributions, collaborations and research hotspots in artificial intelligence and perioperative medicine.

METHODS

A Scopus search on 11 October 2024 identified articles on artificial intelligence in perioperative medicine. Relevant peer-reviewed studies were screened by two reviewers, with a third resolving discrepancies. Data were analysed using VOSviewer, Biblioshiny and Microsoft Excel.

RESULTS

A total of 240 articles were included; 84% of articles were published after 2018, indicating rapid recent growth. The United States, China and Italy led contributions. Single-country publications comprised 76.6% of the dataset, reflecting limited international collaboration. Key research areas included perioperative risk prediction, intraoperative monitoring, blood management and echocardiography.

CONCLUSION

Artificial intelligence in perioperative medicine is rapidly advancing but requires increased international collaboration to fully realise its potential.

EMR-LIP: A lightweight framework for standardizing the preprocessing of longitudinal irregular data in electronic medical records

OBJECTIVE

Longitudinal data from Electronic Medical Records (EMRs) are increasingly utilized to construct predictive models for various clinical tasks, offering enhanced insights into patient health. However, significant discrepancies exist in preprocessing the irregular and intricate EMR data across studies due to the absence of universally accepted tools and standardization methods. This study introduces the Electronic Medical Record Longitudinal Irregular Data Preprocessing (EMR-LIP) framework, a lightweight approach for optimizing the preprocessing of longitudinal, irregular EMR data, aiming to enhance research efficiency, consistency, reproducibility, and comparability.

MATERIALS AND METHODS

EMR-LIP modularizes the preprocessing of longitudinal irregular EMR data, offering tools with a low level of encapsulation. Compared to other pipelines, EMR-LIP categorizes variables in a more granular manner, designing specific preprocessing techniques for each type. To demonstrate its versatility, EMR-LIP was applied in an empirical study to two public EMR databases, MIMIC-IV and eICU-CRD. Data processed with EMR-LIP was then used to test several renowned deep learning models on a range of commonly used benchmark tasks.

RESULTS

In both the MIMIC-IV and eICU-CRD databases, models based on EMR-LIP showed superior baseline performance compared to previous studies. Interestingly, using data preprocessed by EMR-LIP, traditional models such as LSTM and GRU outperformed more complex models, achieving an AUROC of up to 0.94 for in-hospital death prediction. Additionally, models based on EMR-LIP showed stable performance across various resampling intervals and exhibited better fairness in performance across different ethnic groups.

CONCLUSION

EMR-LIP streamlines the preprocessing of irregular longitudinal EMR data, offering an end-to-end solution for model-ready data creation, and has been open-sourced for collaborative refinement by the research community.

pyAKI-An open source solution to automated acute kidney injury classification

OBJECTIVE

Acute kidney injury (AKI) is a frequent complication in critically ill patients, affecting up to 50% of patients in the intensive care units. The lack of standardized and open-source tools for applying the Kidney Disease Improving Global Outcomes (KDIGO) criteria to time series, requires researchers to implement classification algorithms of their own which is resource intensive and might impact study quality by introducing different interpretations of edge cases. This project introduces pyAKI, an open-source pipeline addressing this gap by providing a comprehensive solution for consistent KDIGO criteria implementation.

MATERIALS AND METHODS

The pyAKI pipeline was developed and validated using a subset of the Medical Information Mart for Intensive Care (MIMIC)-IV database, a commonly used database in critical care research. We constructed a standardized data model in order to ensure reproducibility. PyAKI implements the Kidney Disease: Improving Global Outcomes (KDIGO) guideline on AKI diagnosis. After implementation of the diagnostic algorithm, using both serum creatinine and urinary output data, pyAKI was tested on a subset of patients and diagnostic accuracy was compared in a comparative analysis against annotations by physicians.

RESULTS

Validation against expert annotations demonstrated pyAKI's robust performance in implementing KDIGO criteria. Comparative analysis revealed its ability to surpass the quality of human labels with an accuracy of 1.0 in all categories.

DISCUSSION

The pyAKI pipeline is the first open-source solution for implementing KDIGO criteria in time series data. It provides a standardized data model and a comprehensive solution for consistent AKI classification in research applications for clinicians and data scientists working with AKI data. The pipeline's high accuracy make it a valuable tool for clinical research and decision support systems.

CONCLUSION

This work introduces pyAKI as an open-source solution for implementing the KDIGO criteria for AKI diagnosis using time series data with high accuracy and performance.

Advances in critical care nephrology through artificial intelligence

PURPOSE OF REVIEW

This review explores the transformative advancement, potential application, and impact of artificial intelligence (AI), particularly machine learning (ML) and large language models (LLMs), on critical care nephrology.

RECENT FINDINGS

AI algorithms have demonstrated the ability to enhance early detection, improve risk prediction, personalize treatment strategies, and support clinical decision-making processes in acute kidney injury (AKI) management. ML models can predict AKI up to 24-48 h before changes in serum creatinine levels, and AI has the potential to identify AKI sub-phenotypes with distinct clinical characteristics and outcomes for targeted interventions. LLMs and generative AI offer opportunities for automated clinical note generation and provide valuable patient education materials, empowering patients to understand their condition and treatment options better. To fully capitalize on its potential in critical care nephrology, it is essential to confront the limitations and challenges of AI implementation, including issues of data quality, ethical considerations, and the necessity for rigorous validation.

SUMMARY

The integration of AI in critical care nephrology has the potential to revolutionize the management of AKI and continuous renal replacement therapy. While AI holds immense promise for improving patient outcomes, its successful implementation requires ongoing training, education, and collaboration among nephrologists, intensivists, and AI experts.

Development and validation of a predictive model for acute kidney injury in patients with ureterolithiasis

OBJECTIVES

This study aims to identify risk factors for acute kidney injury (AKI) in patients with ureterolithiasis and to develop a predictive model for early AKI detection in this population.

METHODS

A retrospective analysis was conducted on data from 1,016 patients with ureterolithiasis who presented to our outpatient emergency department between January 2021 and December 2022. Using multifactorial logistic regression, we identified independent risk factors for AKI and constructed a nomogram to predict AKI risk. The predictive model's efficacy was assessed through the area under the ROC curve, calibration curves, Hosmer-Lemeshow (HL) test, and decision curve analysis (DCA).

RESULTS

AKI was diagnosed in 18.7% of the patients. Independent risk factors identified included age, fever, diabetes, hyperuricemia, bilateral calculi, functional solitary kidney, self-medication, and prehospital delay. The nomogram demonstrated excellent discriminatory capabilities, with AUCs of 0.818 (95% CI, 0.775-0.861) for the modeling set and 0.782 (95% CI, 0.708-0.856) for the validation set. Both calibration curve and HL test results confirmed strong concordance between the model's predictions and actual observations. DCA highlighted the model's significant clinical utility.

CONCLUSIONS

The predictive model developed in this study provides clinicians with a valuable tool for early identification and management of patients at high risk for AKI, thereby potentially enhancing patient outcomes.

Exploring the role of Artificial Intelligence in Acute Kidney Injury management: a comprehensive review and future research agenda

This study reviews the studies utilizing Artificial Intelligence (AI) and AI-driven tools and methods in managing Acute Kidney Injury (AKI). It categorizes the studies according to medical specialties, analyses the gaps in the existing research, and identifies opportunities for future research directions. PRISMA guidelines were adopted using the three most common databases (PubMed, Scopus, and EBSCO), which resulted in 27 eligible studies, published between 2012 and 2023. The study showed significant heterogeneity in the design of the models, with variations in clinical settings, patient characteristics, cohort regions, and statistical methods. Most models were developed for AKI in hospitalized patients, particularly those undergoing surgery or in intensive care units. Compact models with a subset of significant predictors were deemed more clinically applicable than full models with all predictors. The findings suggest that AI tools, such as machine learning (ML) algorithms, have high prediction capabilities despite the dynamic and complex association among the influencing factors and AKI. Based on these findings and the recognized need for broader inclusivity, future studies should consider adopting a more inclusive approach by incorporating diverse healthcare settings, including resource-limited or developing countries. This inclusivity will lead to a more holistic understanding of AKI management challenges and facilitate the development of adaptable and universally applicable AI-driven solutions. Additionally, further investigations should focus on refining AI models to enhance their accuracy and interpretability, promoting seamless integration and implementation of AI-based tools in real-world clinical practice. Addressing these key aspects will elevate the effectiveness and impact of AI-driven approaches in managing AKI.

Study protocol for a consortium linking health medical records, biospecimens, and biosignals in Korean patients with acute kidney injury (LINKA cohort)

Background

Acute kidney injury (AKI) may transition into acute kidney disease (AKD) or chronic kidney disease (CKD), leading to subacute and chronic deterioration, respectively. Despite extensive research on AKI, a significant gap exists in understanding the specific biomarkers and development of individualized treatments prior to progression to AKD and CKD.

Methods

As a consortium linking health medical records, biospecimens, and biosignals, eight Korean tertiary hospitals participated in the establishment of a retrospective and prospective cohort, each comprising approximately 1,500 patients with AKI receiving continuous kidney replacement therapy (CKRT). Other information included AKI-related information, CKRT prescriptions, and patient outcomes. Follow-up timeframes were set at baseline, 1 week, 3 months, and 1 year after the initiation of CKRT. Human biospecimens will be collected from the prospective cohort. An artificial intelligence model was developed using the retrospective cohort to predict the prognosis of AKD and its subsequent sequelae and to formulate patient-individualized treatments, with validation planned in a prospective cohort. Follow-up studies are scheduled to identify biomarkers related to outcomes using biospecimens. Finally, based on the results and literature review, decision-making on the prevention and management of diseases, as well as the development of treatment guidelines, are being planned.

Conclusion

This study will provide scientific evidence on clinical insights and appropriate management targets for AKI and AKD, which will form the basis for relevant treatment guidelines. Additionally, these findings may facilitate a more personalized approach to patient care, enabling clinicians to tailor treatments based on individual biomarker profiles and predictive models.

Integrating multi-task and cost-sensitive learning for predicting mortality risk of chronic diseases in the elderly using real-world data

BACKGROUND AND OBJECTIVE

Real-world data encompass population diversity, enabling insights into chronic disease mortality risk among the elderly. Deep learning excels on large datasets, offering promise for real-world data. However, current models focus on single diseases, neglecting comorbidities prevalent in patients. Moreover, mortality is infrequent compared to illness, causing extreme class imbalance that impedes reliable prediction. We aim to develop a deep learning framework that accurately forecasts mortality risk from real-world data by addressing comorbidities and class imbalance.

METHODS

We integrated multi-task and cost-sensitive learning, developing an enhanced deep neural network architecture that extends multi-task learning to predict mortality risk across multiple chronic diseases. Each patient cohort with a chronic disease was assigned to a separate task, with shared lower-level parameters capturing inter-disease complexities through distinct top-level networks. Cost-sensitive functions were incorporated to ensure learning of positive class characteristics for each task and achieve accurate prediction of the risk of death from multiple chronic diseases.

RESULTS

Our study covers 15 prevalent chronic diseases and is experimented with real-world data from 482,145 patients (including 9,516 deaths) in Shenzhen, China. The proposed model is compared with six models including three machine learning models: logistic regression, XGBoost, and CatBoost, and three state-of-the-art deep learning models: 1D-CNN, TabNet, and Saint. The experimental results show that, compared with the other compared algorithms, MTL-CSDNN has better prediction results on the test set (ACC=0.99, REC=0.99, PRAUC=0.97, MCC=0.98, G-means = 0.98).

CONCLUSIONS

Our method provides valuable insights into leveraging real-world data for precise multi-disease mortality risk prediction, offering potential applications in optimizing chronic disease management, enhancing well-being, and reducing healthcare costs for the elderly population.

Machine learning approaches toward an understanding of acute kidney injury: current trends and future directions

Acute kidney injury (AKI) is a significant health challenge associated with adverse patient outcomes and substantial economic burdens. Many authors have sought to prevent and predict AKI. Here, we comprehensively review recent advances in the use of artificial intelligence (AI) to predict AKI, and the associated challenges. Although AI may detect AKI early and predict prognosis, integration of AI-based systems into clinical practice remains challenging. It is difficult to identify AKI patients using retrospective data; information preprocessing and the limitations of existing models pose problems. It is essential to embrace standardized labeling criteria and to form international multi-institutional collaborations that foster high-quality data collection. Additionally, existing constraints on the deployment of evolving AI technologies in real-world healthcare settings and enhancement of the reliabilities of AI outputs are crucial. Such efforts will improve the clinical applicability, performance, and reliability of AKI Clinical Support Systems, ultimately enhancing patient prognoses.

Recommendations for Performance Evaluation of Machine Learning in Pathology: A Concept Paper From the College of American Pathologists

CONTEXT.—

Machine learning applications in the pathology clinical domain are emerging rapidly. As decision support systems continue to mature, laboratories will increasingly need guidance to evaluate their performance in clinical practice. Currently there are no formal guidelines to assist pathology laboratories in verification and/or validation of such systems. These recommendations are being proposed for the evaluation of machine learning systems in the clinical practice of pathology.

OBJECTIVE.—

To propose recommendations for performance evaluation of in vitro diagnostic tests on patient samples that incorporate machine learning as part of the preanalytical, analytical, or postanalytical phases of the laboratory workflow. Topics described include considerations for machine learning model evaluation including risk assessment, predeployment requirements, data sourcing and curation, verification and validation, change control management, human-computer interaction, practitioner training, and competency evaluation.

DATA SOURCES.—

An expert panel performed a review of the literature, Clinical and Laboratory Standards Institute guidance, and laboratory and government regulatory frameworks.

CONCLUSIONS.—

Review of the literature and existing documents enabled the development of proposed recommendations. This white paper pertains to performance evaluation of machine learning systems intended to be implemented for clinical patient testing. Further studies with real-world clinical data are encouraged to support these proposed recommendations. Performance evaluation of machine learning models is critical to verification and/or validation of in vitro diagnostic tests using machine learning intended for clinical practice.

Using machine learning to predict the risk of short-term and long-term death in acute kidney injury patients after commencing CRRT

BACKGROUND

The mortality rate and prognosis of short-term and long-term acute kidney injury (AKI) patients who undergo continuous renal replacement therapy (CRRT) are different. Setting up risk stratification tools for both short-term and long-term deaths is highly important for clinicians.

METHOD

A total of 1535 AKI patients receiving CRRT were included in this study, with 1144 from the training set (the Dryad database) and 391 from the validation set (MIMIC IV database). A model for predicting mortality within 10 and 90 days was built using nine different machine learning (ML) algorithms. AUROC, F1-score, accuracy, sensitivity, specificity, precision, and calibration curves were used to assess the predictive performance of various ML models.

RESULTS

A total of 420 (31.1%) deaths occurred within 10 days, and 1080 (68.8%) deaths occurred within 90 days. The random forest (RF) model performed best in both predicting 10-day (AUROC: 0.80, 95% CI: 0.74-0.84; accuracy: 0.72, 95% CI: 0.67-0.76; F1-score: 0.59) and 90-day mortality (AUROC: 0.78, 95% CI: 0.73-0.83; accuracy: 0.73, 95% CI: 0.69-0.78; F1-score: 0.80). The importance of the feature shows that SOFA scores are rated as the most important risk factor for both 10-day and 90-day mortality.

CONCLUSION

Our study, utilizing multiple machine learning models, estimates the risk of short-term and long-term mortality among AKI patients who commence CRRT. The results demonstrated that the prognostic factors for short-term and long-term mortality are different. The RF model has the best prediction performance and has valuable potential for clinical application.

Time Series AI Model for Acute Kidney Injury Detection Based on a Multicenter Distributed Research Network: Development and Verification Study

Background

Acute kidney injury (AKI) is a marker of clinical deterioration and renal toxicity. While there are many studies offering prediction models for the early detection of AKI, those predicting AKI occurrence using distributed research network (DRN)-based time series data are rare.

Objective

In this study, we aimed to detect the early occurrence of AKI by applying an interpretable long short-term memory (LSTM)-based model to hospital electronic health record (EHR)-based time series data in patients who took nephrotoxic drugs using a DRN.

Methods

We conducted a multi-institutional retrospective cohort study of data from 6 hospitals using a DRN. For each institution, a patient-based data set was constructed using 5 drugs for AKI, and an interpretable multivariable LSTM (IMV-LSTM) model was used for training. This study used propensity score matching to mitigate differences in demographics and clinical characteristics. Additionally, the temporal attention values of the AKI prediction model's contribution variables were demonstrated for each institution and drug, with differences in highly important feature distributions between the case and control data confirmed using 1-way ANOVA.

Results

This study analyzed 8643 and 31,012 patients with and without AKI, respectively, across 6 hospitals. When analyzing the distribution of AKI onset, vancomycin showed an earlier onset (median 12, IQR 5-25 days), and acyclovir was the slowest compared to the other drugs (median 23, IQR 10-41 days). Our temporal deep learning model for AKI prediction performed well for most drugs. Acyclovir had the highest average area under the receiver operating characteristic curve score per drug (0.94), followed by acetaminophen (0.93), vancomycin (0.92), naproxen (0.90), and celecoxib (0.89). Based on the temporal attention values of the variables in the AKI prediction model, verified lymphocytes and calcvancomycin ium had the highest attention, whereas lymphocytes, albumin, and hemoglobin tended to decrease over time, and urine pH and prothrombin time tended to increase.

Conclusions

Early surveillance of AKI outbreaks can be achieved by applying an IMV-LSTM based on time series data through an EHR-based DRN. This approach can help identify risk factors and enable early detection of adverse drug reactions when prescribing drugs that cause renal toxicity before AKI occurs.

Artificial intelligence and machine learning's role in sepsis-associated acute kidney injury

Sepsis-associated acute kidney injury (SA-AKI) is a serious complication in critically ill patients, resulting in higher mortality, morbidity, and cost. The intricate pathophysiology of SA-AKI requires vigilant clinical monitoring and appropriate, prompt intervention. While traditional statistical analyses have identified severe risk factors for SA-AKI, the results have been inconsistent across studies. This has led to growing interest in leveraging artificial intelligence (AI) and machine learning (ML) to predict SA-AKI better. ML can uncover complex patterns beyond human discernment by analyzing vast datasets. Supervised learning models like XGBoost and RNN-LSTM have proven remarkably accurate at predicting SA-AKI onset and subsequent mortality, often surpassing traditional risk scores. Meanwhile, unsupervised learning reveals clinically relevant sub-phenotypes among diverse SA-AKI patients, enabling more tailored care. In addition, it potentially optimizes sepsis treatment to prevent SA-AKI through continual refinement based on patient outcomes. However, utilizing AI/ML presents ethical and practical challenges regarding data privacy, algorithmic biases, and regulatory compliance. AI/ML allows early risk detection, personalized management, optimal treatment strategies, and collaborative learning for SA-AKI management. Future directions include real-time patient monitoring, simulated data generation, and predictive algorithms for timely interventions. However, a smooth transition to clinical practice demands continuous model enhancements and rigorous regulatory oversight. In this article, we outlined the conventional methods used to address SA-AKI and explore how AI and ML can be applied to diagnose and manage SA-AKI, highlighting their potential to revolutionize SA-AKI care.

Development and External Validation of a Multidimensional Deep Learning Model to Dynamically Predict Kidney Outcomes in IgA Nephropathy

Key Points

A dynamic model predicts IgA nephropathy prognosis based on deep learning. Longitudinal clinical data and deep learning improve predictive accuracy and interpretability in GN.

Background

Accurately predicting kidney outcomes in IgA nephropathy is crucial for clinical decision making. Insufficient use of longitudinal data in previous studies has limited the accuracy and interpretability of prediction models for failing to reflect the chronic nature of IgA nephropathy. The aim of this study was to establish a multivariable dynamic deep learning model using comprehensive longitudinal data for the prediction of kidney outcomes in IgA nephropathy.

Methods

In this retrospective cohort study of 2056 patients with IgA nephropathy from 18 kidney centers, a total of 28,317 data points were collected by the sliding window method. Among them, 15,462 windows in a single center were randomly assigned to training (80%) and validation (20%) sets and 8797 windows in 18 kidney centers were assigned to an independent test set. Interpretable multivariable long short-term memory, a deep learning model, was implemented to predict kidney outcomes (kidney failure or 50% decline in kidney function) based on time-invariant variables measured at biopsy and time-variant variables measured during follow-up. Risk performance was evaluated using the Kaplan–Meier analysis and C-statistic. Trajectory analysis was performed to assess the various trends of clinical variables during follow-up.

Results

The model achieved a higher C-statistic (0.93; 95% confidence interval, 0.92 to 0.95) on the test set than the machine learning prediction model that we developed in a previous study using only baseline information (C-statistic, 0.84; 95% confidence interval, 0.80 to 0.88). The Kaplan–Meier analysis showed that groups with lower predicted risks from the full model survived longer than groups with higher risks. Time-variant variables demonstrated higher importance scores than time-invariant variables. Within time-variant variables, more recent measurements showed higher importance scores. Further interpretation showed that certain trajectory groups of time-variant variables such as serum creatinine and urine protein were associated with elevated risks of adverse outcomes.

Conclusions

In IgA nephropathy, a deep learning model can be used to accurately and dynamically predict kidney prognosis based on longitudinal data, and time-variant variables show strong ability to predict kidney outcomes.

A simple machine learning model for the prediction of acute kidney injury following noncardiac surgery in geriatric patients: a prospective cohort study

BACKGROUND

Surgery in geriatric patients often poses risk of major postoperative complications. Acute kidney injury (AKI) is a common complication following noncardiac surgery and is associated with increased mortality. Early identification of geriatric patients at high risk of AKI could facilitate preventive measures and improve patient prognosis. This study used machine learning methods to identify important features and predict AKI following noncardiac surgery in geriatric patients.

METHODS

The data for this study were obtained from a prospective cohort. Patients aged ≥ 65 years who received noncardiac surgery from June 2019 to December 2021 were enrolled. Data were split into training set (from June 2019 to March 2021) and internal validation set (from April 2021 to December 2021) by time. The least absolute shrinkage and selection operator (LASSO) regularization algorithm and the random forest recursive feature elimination algorithm (RF-RFE) were used to screen important predictors. Models were trained through extreme gradient boosting (XGBoost), random forest, and LASSO. The SHapley Additive exPlanations (SHAP) package was used to interpret the machine learning model.

RESULTS

The training set included 6753 geriatric patients. Of these, 250 (3.70%) patients developed AKI. The XGBoost model with RF-RFE selected features outperformed other models with an area under the precision-recall curve (AUPRC) of 0.505 (95% confidence interval [CI]: 0.369-0.626) and an area under the receiver operating characteristic curve (AUROC) of 0.806 (95%CI: 0.733-0.875). The model incorporated ten predictors, including operation site and hypertension. The internal validation set included 3808 geriatric patients, and 96 (2.52%) patients developed AKI. The model maintained good predictive performance with an AUPRC of 0.431 (95%CI: 0.331-0.524) and an AUROC of 0.845 (95%CI: 0.796-0.888) in the internal validation.

CONCLUSIONS

This study developed a simple machine learning model and a web calculator for predicting AKI following noncardiac surgery in geriatric patients. This model may be a valuable tool for guiding preventive measures and improving patient prognosis.

TRIAL REGISTRATION

The protocol of this study was approved by the Committee of Ethics from West China Hospital of Sichuan University (2019-473) with a waiver of informed consent and registered at www.chictr.org.cn (ChiCTR1900025160, 15/08/2019).

Anesthetic Management Recommendations Using a Machine Learning Algorithm to Reduce the Risk of Acute Kidney Injury After Cardiac Surgeries

Background

Open heart surgeries are a common surgical approach among patients with heart disease. Acute kidney injury (AKI) is one of the most common postoperative complications following cardiac surgeries, with an average incidence of 6 - 10%. Additionally, AKI has a mortality rate of 5 - 10%. One of the challenges of cardiac surgeries is selecting the appropriate anesthetic approaches to reduce the risk of AKI.

Objectives

This study presents a machine learning-based method that consists of two regression models. These models can inform the anesthesiologist about the risk of AKI resulting from the improper selection of anesthetic parameters.

Methods

In this cohort study, the medical records of 998 patients who underwent cardiac surgery were collected. The proposed method includes two regression models. The first regression model recommends optimal anesthesia parameters to minimize the risk of AKI. The second model provides the anesthesiologist with the safest margin for deciding on anesthetic parameters during surgery, including cardiopulmonary bypass (CPB) time, anesthesia time, crystalloid dose, diuretic dose, and transfusion of packed red cells (PC) and fresh frozen plasma (FFP). Using this method, the specialist can evaluate the anesthetic parameters and assess the potential AKI risk. Additionally, the proposed method can also provide the treatment team with anesthetic parameters that carry the lowest risk of AKI.

Results

This method was evaluated using data from 526 patients who suffered from postoperative AKI (AKI+) and 472 who did not suffer any injury (AKI-). The accuracy of the proposed method is 80.6%. Additionally, the evaluation of the proposed method by three experienced cardiac anesthesiologists shows a high correlation between the results of the proposed method and the opinions of the anesthesiologists.

Conclusions

The results indicated that the outputs of the proposed models and the designed software could help reduce the risk of postoperative AKI.

Forecasting acute kidney injury and resource utilization in ICU patients using longitudinal, multimodal models

BACKGROUND

Advances in artificial intelligence (AI) have realized the potential of revolutionizing healthcare, such as predicting disease progression via longitudinal inspection of Electronic Health Records (EHRs) and lab tests from patients admitted to Intensive Care Units (ICU). Although substantial literature exists addressing broad subjects, including the prediction of mortality, length-of-stay, and readmission, studies focusing on forecasting Acute Kidney Injury (AKI), specifically dialysis anticipation like Continuous Renal Replacement Therapy (CRRT) are scarce. The technicality of how to implement AI remains elusive.

OBJECTIVE

This study aims to elucidate the important factors and methods that are required to develop effective predictive models of AKI and CRRT for patients admitted to ICU, using EHRs in the Medical Information Mart for Intensive Care (MIMIC) database.

METHODS

We conducted a comprehensive comparative analysis of established predictive models, considering both time-series measurements and clinical notes from MIMIC-IV databases. Subsequently, we proposed a novel multi-modal model which integrates embeddings of top-performing unimodal models, including Long Short-Term Memory (LSTM) and BioMedBERT, and leverages both unstructured clinical notes and structured time series measurements derived from EHRs to enable the early prediction of AKI and CRRT.

RESULTS

Our multimodal model achieved a lead time of at least 12 h ahead of clinical manifestation, with an Area Under the Receiver Operating Characteristic Curve (AUROC) of 0.888 for AKI and 0.997 for CRRT, as well as an Area Under the Precision Recall Curve (AUPRC) of 0.727 for AKI and 0.840 for CRRT, respectively, which significantly outperformed the baseline models. Additionally, we performed a SHapley Additive exPlanation (SHAP) analysis using the expected gradients algorithm, which highlighted important, previously underappreciated predictive features for AKI and CRRT.

CONCLUSION

Our study revealed the importance and the technicality of applying longitudinal, multimodal modeling to improve early prediction of AKI and CRRT, offering insights for timely interventions. The performance and interpretability of our model indicate its potential for further assessment towards clinical applications, to ultimately optimize AKI management and enhance patient outcomes.

Real-time sports injury monitoring system based on the deep learning algorithm

In response to the low real-time performance and accuracy of traditional sports injury monitoring, this article conducts research on a real-time injury monitoring system using the SVM model as an example. Video detection is performed to capture human movements, followed by human joint detection. Polynomial fitting analysis is used to extract joint motion patterns, and the average of training data is calculated as a reference point. The raw data is then normalized to adjust position and direction, and dimensionality reduction is achieved through singular value decomposition to enhance processing efficiency and model training speed. A support vector machine classifier is used to classify and identify the processed data. The experimental section monitors sports injuries and investigates the accuracy of the system's monitoring. Compared to mainstream models such as Random Forest and Naive Bayes, the SVM utilized demonstrates good performance in accuracy, sensitivity, and specificity, reaching 94.2%, 92.5%, and 96.0% respectively.

Machine learning in cardiac surgery: a narrative review

Background and Objective

Machine learning (ML) is increasingly being utilized to provide data driven solutions to challenges in medicine. Within the field of cardiac surgery, ML methods have been employed as risk stratification tools to predict a variety of operative outcomes. However, the clinical utility of ML in this domain is unclear. The aim of this review is to provide an overview of ML in cardiac surgery, particularly with regards to its utility in predictive analytics and implications for use in clinical decision support.

Methods

We performed a narrative review of relevant articles indexed in PubMed since 2000 using the MeSH terms "Machine Learning", "Supervised Machine Learning", "Deep Learning", or "Artificial Intelligence" and "Cardiovascular Surgery" or "Thoracic Surgery".

Key Content and Findings

ML methods have been widely used to generate pre-operative risk profiles, consistently resulting in the accurate prediction of clinical outcomes in cardiac surgery. However, improvement in predictive performance over traditional risk metrics has proven modest and current applications in the clinical setting remain limited.

Conclusions

Studies utilizing high volume, multidimensional data such as that derived from electronic health record (EHR) data appear to best demonstrate the advantages of ML methods. Models trained on post cardiac surgery intensive care unit data demonstrate excellent predictive performance and may provide greater clinical utility if incorporated as clinical decision support tools. Further development of ML models and their integration into EHR's may result in dynamic clinical decision support strategies capable of informing clinical care and improving outcomes in cardiac surgery.

Interpretable machine learning-based individual analysis of acute kidney injury in immune checkpoint inhibitor therapy

BACKGROUND

Acute kidney injury (AKI) is a critical complication of immune checkpoint inhibitor therapy. Since the etiology of AKI in patients undergoing cancer therapy varies, clarifying underlying causes in individual cases is critical for optimal cancer treatment. Although it is essential to individually analyze immune checkpoint inhibitor-treated patients for underlying pathologies for each AKI episode, these analyses have not been realized. Herein, we aimed to individually clarify the underlying causes of AKI in immune checkpoint inhibitor-treated patients using a new clustering approach with Shapley Additive exPlanations (SHAP).

METHODS

We developed a gradient-boosting decision tree-based machine learning model continuously predicting AKI within 7 days, using the medical records of 616 immune checkpoint inhibitor-treated patients. The temporal changes in individual predictive reasoning in AKI prediction models represented the key features contributing to each AKI prediction and clustered AKI patients based on the features with high predictive contribution quantified in time series by SHAP. We searched for common clinical backgrounds of AKI patients in each cluster, compared with annotation by three nephrologists.

RESULTS

One hundred and twelve patients (18.2%) had at least one AKI episode. They were clustered per the key feature, and their SHAP value patterns, and the nephrologists assessed the clusters' clinical relevance. Receiver operating characteristic analysis revealed that the area under the curve was 0.880. Patients with AKI were categorized into four clusters with significant prognostic differences (p = 0.010). The leading causes of AKI for each cluster, such as hypovolemia, drug-related, and cancer cachexia, were all clinically interpretable, which conventional approaches cannot obtain.

CONCLUSION

Our results suggest that the clustering method of individual predictive reasoning in machine learning models can be applied to infer clinically critical factors for developing each episode of AKI among patients with multiple AKI risk factors, such as immune checkpoint inhibitor-treated patients.

Public and patient perspectives on the use of clinical and administrative health data to identify and contact people at risk of future illness-The case of chronic kidney disease

For decades, researchers have used linkable administrative health data for evaluating the health care system, subject to local privacy legislation. In Ontario, Canada, the relevant privacy legislation permits some organizations (prescribed entities) to conduct this kind of research but is silent on their ability to identify and contact individuals in those datasets. Following consultation with the Office of the Information and Privacy Commissioner of Ontario, we developed a pilot study to identify and contact by mail a sample of people at high risk for kidney failure within the next 2 years, based on laboratory and administrative data from provincial datasets held by ICES, to ensure they receive needed kidney care. Before proceeding, we conducted six focus groups to understand the acceptability to the public and people living with chronic kidney disease of direct mail outreach to people at high risk of developing kidney failure. While virtually all participants indicated they would likely participate in the study, most felt strongly that the message should come directly from their primary care provider or whoever ordered the laboratory tests, rather than from an unknown organization. If this is not possible, they felt the health care provider should be made aware of the concern related to their kidney health. Most agreed that, if health authorities could identify people at high risk of a treatable life-threatening illness if caught early enough, there is a social responsibility to notify people. While privacy laws allow for free flow of health information among health care providers who provide direct clinical care, the proposed case-finding and outreach falls outside that model. Enabling this kind of information flow will require greater clarity in existing laws or revisions to these laws. This also requires adequate notification and culture change for health care providers and the public around information uses and flows.

Development and validation of a deep interpretable network for continuous acute kidney injury prediction in critically ill patients

Early detection of acute kidney injury (AKI) may provide a crucial window of opportunity to prevent further injury, which helps improve clinical outcomes. This study aimed to develop a deep interpretable network for continuously predicting the 24-hour AKI risk in real-time and evaluate its performance internally and externally in critically ill patients. A total of 21,163 patients' electronic health records sourced from Beth Israel Deaconess Medical Center (BIDMC) were first included in building the model. Two external validation populations included 3025 patients from the Philips eICU Research Institute and 2625 patients from Zhongda Hospital Southeast University. A total of 152 intelligently engineered predictors were extracted on an hourly basis. The prediction model referred to as DeepAKI was designed with the basic framework of squeeze-and-excitation networks with dilated causal convolution embedded. The integrated gradients method was utilized to explain the prediction model. When performed on the internal validation set (3175 [15 %] patients from BIDMC) and the two external validation sets, DeepAKI obtained the area under the curve of 0.799 (95 % CI 0.791-0.806), 0.763 (95 % CI 0.755-0.771) and 0.676 (95 % CI 0.668-0.684) for continuousAKI prediction, respectively. For model interpretability, clinically relevant important variables contributing to the model prediction were informed, and individual explanations along the timeline were explored to show how AKI risk arose. The potential threats to generalisability in deep learning-based models when deployed across health systems in real-world settings were analyzed.

Algorithm Versus Expert: Machine Learning Versus Surgeon-Predicted Symptom Improvement After Carpal Tunnel Release

BACKGROUND AND OBJECTIVES

Surgeons rely on clinical experience when making predictions about treatment effects. Incorporating algorithm-based predictions of symptom improvement after carpal tunnel release (CTR) could support medical decision-making. However, these algorithm-based predictions need to outperform predictions made by surgeons to add value. We compared predictions of a validated prediction model for symptom improvement after CTR with predictions made by surgeons.

METHODS

This cohort study included 97 patients scheduled for CTR. Preoperatively, surgeons estimated each patient's probability of improvement 6 months after surgery, defined as reaching the minimally clinically important difference on the Boston Carpal Tunnel Syndrome Symptom Severity Score. We assessed model and surgeon performance using calibration (calibration belts), discrimination (area under the curve [AUC]), sensitivity, and specificity. In addition, we assessed the net benefit of decision-making based on the prediction model's estimates vs the surgeon's judgement.

RESULTS

The surgeon predictions had poor calibration and suboptimal discrimination (AUC 0.62, 95%-CI 0.49-0.74), while the prediction model showed good calibration and appropriate discrimination (AUC 0.77, 95%-CI 0.66-0.89, P = .05). The accuracy of surgeon predictions was 0.65 (95%-CI 0.37-0.78) vs 0.78 (95%-CI 0.67-0.89) for the prediction model ( P = .03). The sensitivity of surgeon predictions and the prediction model was 0.72 (95%-CI 0.15-0.96) and 0.85 (95%-CI 0.62-0.97), respectively ( P = .04). The specificity of the surgeon predictions was similar to the model's specificity ( P = .25). The net benefit analysis showed better decision-making based on the prediction model compared with the surgeons' decision-making (ie, more correctly predicted improvements and/or fewer incorrectly predicted improvements).

CONCLUSION

The prediction model outperformed surgeon predictions of improvement after CTR in terms of calibration, accuracy, and sensitivity. Furthermore, the net benefit analysis indicated that using the prediction model instead of relying solely on surgeon decision-making increases the number of patients who will improve after CTR, without increasing the number of unnecessary surgeries.

Machine-learning model for predicting oliguria in critically ill patients

This retrospective cohort study aimed to develop and evaluate a machine-learning algorithm for predicting oliguria, a sign of acute kidney injury (AKI). To this end, electronic health record data from consecutive patients admitted to the intensive care unit (ICU) between 2010 and 2019 were used and oliguria was defined as a urine output of less than 0.5 mL/kg/h. Furthermore, a light-gradient boosting machine was used for model development. Among the 9,241 patients who participated in the study, the proportions of patients with urine output < 0.5 mL/kg/h for 6 h and with AKI during the ICU stay were 27.4% and 30.2%, respectively. The area under the curve (AUC) values provided by the prediction algorithm for the onset of oliguria at 6 h and 72 h using 28 clinically relevant variables were 0.964 (a 95% confidence interval (CI) of 0.963-0.965) and 0.916 (a 95% CI of 0.914-0.918), respectively. The Shapley additive explanation analysis for predicting oliguria at 6 h identified urine values, severity scores, serum creatinine, oxygen partial pressure, fibrinogen/fibrin degradation products, interleukin-6, and peripheral temperature as important variables. Thus, this study demonstrates that a machine-learning algorithm can accurately predict oliguria onset in ICU patients, suggesting the importance of oliguria in the early diagnosis and optimal management of AKI.

Mortality prediction with adaptive feature importance recalibration for peritoneal dialysis patients

The study aims to develop AICare, an interpretable mortality prediction model, using electronic medical records (EMR) from follow-up visits for end-stage renal disease (ESRD) patients. AICare includes a multichannel feature extraction module and an adaptive feature importance recalibration module. It integrates dynamic records and static features to perform personalized health context representation learning. The dataset encompasses 13,091 visits and demographic data of 656 peritoneal dialysis (PD) patients spanning 12 years. An additional public dataset of 4,789 visits from 1,363 hemodialysis (HD) patients is also considered. AICare outperforms traditional deep learning models in mortality prediction while retaining interpretability. It uncovers mortality-feature relationships and variations in feature importance and provides reference values. An AI-doctor interaction system is developed for visualizing patients' health trajectories and risk indicators.

Digital health and acute kidney injury: consensus report of the 27th Acute Disease Quality Initiative workgroup

Acute kidney injury (AKI), which is a common complication of acute illnesses, affects the health of individuals in community, acute care and post-acute care settings. Although the recognition, prevention and management of AKI has advanced over the past decades, its incidence and related morbidity, mortality and health care burden remain overwhelming. The rapid growth of digital technologies has provided a new platform to improve patient care, and reports show demonstrable benefits in care processes and, in some instances, in patient outcomes. However, despite great progress, the potential benefits of using digital technology to manage AKI has not yet been fully explored or implemented in clinical practice. Digital health studies in AKI have shown variable evidence of benefits, and the digital divide means that access to digital technologies is not equitable. Upstream research and development costs, limited stakeholder participation and acceptance, and poor scalability of digital health solutions have hindered their widespread implementation and use. Here, we provide recommendations from the Acute Disease Quality Initiative consensus meeting, which involved experts in adult and paediatric nephrology, critical care, pharmacy and data science, at which the use of digital health for risk prediction, prevention, identification and management of AKI and its consequences was discussed.

Interpretable machine learning models for early prediction of acute kidney injury after cardiac surgery

OBJECTIVE

Postoperative acute kidney injury (PO-AKI) is a common complication after cardiac surgery. We aimed to evaluate whether machine learning algorithms could significantly improve the risk prediction of PO-AKI.

METHODS

The retrospective cohort study included 2310 adult patients undergoing cardiac surgery in a tertiary teaching hospital, China. Postoperative AKI and severe AKI were identified by the modified KDIGO definition. The sample was randomly divided into a derivation set and a validation set based on a ratio of 4:1. Exploiting conventional logistic regression (LR) and five ML algorithms including decision tree, random forest, gradient boosting classifier (GBC), Gaussian Naive Bayes and multilayer perceptron, we developed and validated the prediction models of PO-AKI. We implemented the interpretation of models using SHapley Additive exPlanation (SHAP) analysis.

RESULTS

Postoperative AKI and severe AKI occurred in 1020 (44.2%) and 286 (12.4%) patients, respectively. Compared with the five ML models, LR model for PO-AKI exhibited the largest AUC (0.812, 95%CI: 0.756, 0.860, all P < 0.05), sensitivity (0.774, 95%CI: 0.719, 0.813), accuracy (0.753, 95%CI: 0.719, 0.781) and Youden index (0.513, 95%CI: 0.451, 0.573). Regarding severe AKI, GBC algorithm showed a significantly higher AUC than the other four ML models (all P < 0.05). Although no significant difference (P = 0.173) was observed in AUCs between GBC (0.86, 95%CI: 0.808, 0.902) and conventional logistic regression (0.803, 95%CI: 0.746, 0.852), GBC achieved greater sensitivity, accuracy and Youden index than conventional LR. Notably, SHAP analyses showed that preoperative serum creatinine, hyperlipidemia, lipid-lowering agents and assisted ventilation time were consistently among the top five important predictors for both postoperative AKI and severe AKI.

CONCLUSION

Logistic regression and GBC algorithm demonstrated moderate to good discrimination and superior performance in predicting PO-AKI and severe AKI, respectively. Interpretation of the models identified the key contributors to the predictions, which could potentially inform clinical interventions.

Dialysis resource allocation in critical care: the impact of the COVID-19 pandemic and the promise of big data analytics

The COVID-19 pandemic resulted in an unprecedented burden on intensive care units (ICUs). With increased demands and limited supply, critical care resources, including dialysis machines, became scarce, leading to the undertaking of value-based cost-effectiveness analyses and the rationing of resources to deliver patient care of the highest quality. A high proportion of COVID-19 patients admitted to the ICU required dialysis, resulting in a major burden on resources such as dialysis machines, nursing staff, technicians, and consumables such as dialysis filters and solutions and anticoagulation medications. Artificial intelligence (AI)-based big data analytics are now being utilized in multiple data-driven healthcare services, including the optimization of healthcare system utilization. Numerous factors can impact dialysis resource allocation to critically ill patients, especially during public health emergencies, but currently, resource allocation is determined using a small number of traditional factors. Smart analytics that take into account all the relevant healthcare information in the hospital system and patient outcomes can lead to improved resource allocation, cost-effectiveness, and quality of care. In this review, we discuss dialysis resource utilization in critical care, the impact of the COVID-19 pandemic, and how AI can improve resource utilization in future public health emergencies. Research in this area should be an important priority.

Leveling Up: A Review of Machine Learning Models in the Cardiac ICU

Machine learning has emerged as a significant tool to augment the medical decision-making process. Studies have steadily accrued detailing algorithms and models designed using machine learning to predict and anticipate pathologic states. The cardiac intensive care unit is an area where anticipation is crucial in the division between life and death. In this paper, we aim to review important studies describing the utility of machine learning algorithms to describe the future of artificial intelligence in the cardiac intensive care unit, especially in regards to the prediction of successful ventilatory weaning, acute respiratory distress syndrome, arrhythmia, and acute kidney injury.

Early recognition and prevention of acute kidney injury in hospitalised children

Acute kidney injury is common in hospitalised children and is associated with poor patient outcomes. Once acute kidney injury occurs, effective therapies to improve patient outcomes or kidney recovery are scarce. Early identification of children at risk of acute kidney injury or at an early injury stage is essential to prevent progression and mitigate complications. Paediatric acute kidney injury is under-recognised by clinicians, which is a barrier to optimisation of inpatient care and follow-up. Acute kidney injury definitions rely on functional biomarkers (ie, serum creatinine and urine output) that are inadequate, since they do not account for biological variability, analytical issues, or physiological responses to volume depletion. Improved predictive tools and diagnostic biomarkers of kidney injury are needed for earlier detection. Novel strategies, including biomarker-guided care algorithms, machine-learning methods, and electronic alerts tied to clinical decision support tools, could improve paediatric acute kidney injury care. Clinical prediction models should be studied in different paediatric populations and acute kidney injury phenotypes. Research is needed to develop and test prevention strategies for acute kidney injury in hospitalised children, including care bundles and therapeutics.

A deep learning-based dynamic model for predicting acute kidney injury risk severity in postoperative patients

BACKGROUND

Acute kidney injury is a common postoperative complication affecting between 10% and 30% of surgical patients. Acute kidney injury is associated with increased resource usage and chronic kidney disease development, with more severe acute kidney injury suggesting more aggressive deterioration in clinical outcomes and mortality.

METHODS

We considered 42,906 surgical patients admitted to University of Florida Health (n = 51,806) between 2014 and 2021. Acute kidney injury stages were determined using the Kidney Disease Improving Global Outcomes serum creatinine criteria. We developed a recurrent neural network-based model to continuously predict acute kidney injury risk and state in the following 24 hours and compared it with logistic regression, random forest, and multi-layer perceptron models. We used medications, laboratory and vital measurements, and derived features from past one-year records as inputs. We analyzed the proposed model with integrated gradients for enhanced explainability.

RESULTS

Postoperative acute kidney injury at any stage developed in 20% (10,664) of the cohort. The recurrent neural network model was more accurate in predicting nearly all categories of next-day acute kidney injury stages (including the no acute kidney injury group). The area under the receiver operating curve and 95% confidence intervals for recurrent neural network and logistic regression models were for no acute kidney injury (0.98 [0.98-0.98] vs 0.93 [0.93-0.93]), stage 1 (0.95 [0.95-0.95] vs. 0.81 [0.80-0.82]), stage 2/3 (0.99 [0.99-0.99] vs 0.96 [0.96-0.97]), and stage 3 with renal replacement therapy (1.0 [1.0-1.0] vs 1.0 [1.0-1.0].

CONCLUSION

The proposed model demonstrates that temporal processing of patient information can lead to more granular and dynamic modeling of acute kidney injury status and result in more continuous and accurate acute kidney injury prediction. We showcase the integrated gradients framework's utility as a mechanism for enhancing model explainability, potentially facilitating clinical trust for future implementation.

Assessment of Prediction Tasks and Time Window Selection in Temporal Modeling of Electronic Health Record Data: a Systematic Review

Temporal electronic health record (EHR) data are often preferred for clinical prediction tasks because they offer more complete representations of a patient's pathophysiology than static data. A challenge when working with temporal EHR data is problem formulation, which includes defining the time windows of interest and the prediction task. Our objective was to conduct a systematic review that assessed the definition and reporting of concepts relevant to temporal clinical prediction tasks. We searched PubMed® and IEEE Xplore® databases for studies from January 1, 2010 applying machine learning models to EHR data for patient outcome prediction. Publications applying time-series methods were selected for further review. We identified 92 studies and summarized them by clinical context and definition and reporting of the prediction problem. For the time windows of interest, 12 studies did not discuss window lengths, 57 used a single set of window lengths, and 23 evaluated the relationship between window length and model performance. We also found that 72 studies had appropriate reporting of the prediction task. However, evaluation of prediction problem formulation for temporal EHR data was complicated by heterogeneity in assessing and reporting of these concepts. Even among studies modeling similar clinical outcomes, there were variations in terminology used to describe the prediction problem, rationale for window lengths, and determination of the outcome of interest. As temporal modeling using EHR data expands, minimal reporting standards should include time-series specific concerns to promote rigor and reproducibility in future studies and facilitate model implementation in clinical settings.

Supplementary Information

The online version contains supplementary material available at 10.1007/s41666-023-00143-4.

Association of the perfusion index with postoperative acute kidney injury: a retrospective study

BACKGROUND

Many studies have examined the risk factors for postoperative acute kidney injury (AKI), but few have focused on intraoperative peripheral perfusion index (PPI) that has recently been shown to be associated with postoperative morbidity and mortality. Therefore, this study aimed to evaluate the relationship between intraoperative PPI and postoperative AKI under the hypothesis that lower intraoperative PPI is associated with AKI occurrence.

METHODS

We retrospectively searched electronic medical records to identify patients who underwent surgery at the general surgery department from May 2021 to November 2021. Patient baseline characteristics, pre- and post-operative laboratory test results, comorbidities, intraoperative vital signs, and discharge profiles were obtained from the Institutional Clinical Data Warehouse and VitalDB. Intraoperative PPI was the primary exposure variable, and the primary outcome was postoperative AKI.

RESULTS

Overall, 2,554 patients were identified and 1,586 patients were included in our analysis. According to Kidney Disease Improving Global Outcomes (KDIGO) criteria, postoperative AKI occurred in 123 (7.8%) patients. We found that risks of postoperative AKI increased (odds ratio: 2.00, 95% CI [1.16, 3.44], P = 0.012) when PPI was less than 0.5 for more than 10% of surgery time. Other risk factors for AKI occurrence were male sex, older age, higher American Society of Anesthesiologists physical status, obesity, underlying renal disease, prolonged operation time, transfusion, and emergent operation.

CONCLUSIONS

Low intraoperative PPI was independently associated with postoperative AKI.

Development, External Validation, and Visualization of Machine Learning Models for Predicting Occurrence of Acute Kidney Injury after Cardiac Surgery

Background

Cardiac surgery-associated acute kidney injury (CSA-AKI) is a major complication that results in short- and long-term mortality among patients. Here, we adopted machine learning algorithms to build prediction models with the overarching goal of identifying patients who are at a high risk of such unfavorable kidney outcomes.

Methods

A total of 1686 patients (development cohort) and 422 patients (validation cohort), with 126 pre- and intra-operative variables, were recruited from the First Medical Centre and the Sixth Medical Centre of Chinese PLA General Hospital in Beijing, China, respectively. Analyses were performed using six machine learning techniques, namely K-nearest neighbor, logistic regression, decision tree, random forest (RF), support vector machine, and neural network, and the APPROACH score, a previously established risk score for CSA-AKI. For model tuning, optimal hyperparameter was achieved by using GridSearch with 5-fold cross-validation from the scikit-learn library. Model performance was externally assessed via the receiver operating characteristic (ROC) and decision curve analysis (DCA). Explainable machine learning was performed using the Python SHapley Additive exPlanation (SHAP) package and Seaborn library, which allow the calculation of marginal contributory SHAP value.

Results

637 patients (30.2%) developed CSA-AKI within seven days after surgery. In the external validation, the RF classifier exhibited the best performance among the six machine learning techniques, as shown by the ROC curve and DCA, while the traditional APPROACH risk score showed a relatively poor performance. Further analysis found no specific causative factor contributing to the development of CSA-AKI; rather, the development of CSA-AKI appeared to be a complex process resulting from a complex interplay of multiple risk factors. The SHAP summary plot illustrated the positive or negative contribution of RF-top 20 variables and extrapolated risk of developing CSA-AKI at individual levels. The Seaborn library showed the effect of each single feature on the model output of the RF prediction.

Conclusions

Efficient machine learning approaches were successfully established to predict patients with a high probability of developing acute kidney injury after cardiac surgery. These findings are expected to help clinicians to optimize treatment strategies and minimize postoperative complications.

Clinical Trial Registration

The study protocol was registered at the ClinicalTrials Registration System (https://www.clinicaltrials.gov/, #NCT04966598) on July 26, 2021.

Genitourinary Cancer: Updates on Treatments and Their Impact on the Kidney

Genitourinary cancers are diverse in their presentation, prevalence, and mortality risk. Although there have been significant advancements in medical (eg, immune checkpoint inhibitors and tyrosine kinase inhibitors) and surgical treatments of genitourinary cancers, patients are still at risk for chronic kidney disease, hypertension, and electrolyte derangements in the short and long term. In addition, pre-existing kidney disease may increase the risk of developing some genitourinary cancers. This review focuses on the kidney-related effects of treatments for renal cell carcinoma and bladder and prostate cancers.

Characterization of Risk Prediction Models for Acute Kidney Injury: A Systematic Review and Meta-analysis

Importance

Despite the expansion of published prediction models for acute kidney injury (AKI), there is little evidence of uptake of these models beyond their local derivation nor data on their association with patient outcomes.

Objective

To systematically review published AKI prediction models across all clinical subsettings.

Data Sources

MEDLINE via PubMed (January 1946 to April 2021) and Embase (January 1947 to April 2021) were searched using medical subject headings and text words related to AKI and prediction models.

Study Selection

All studies that developed a prediction model for AKI, defined as a statistical model with at least 2 predictive variables to estimate future occurrence of AKI, were eligible for inclusion. There was no limitation on study populations or methodological designs.

Data Extraction and Synthesis

Two authors independently searched the literature, screened the studies, and extracted and analyzed the data following the Preferred Reporting Items for Systematic Review and Meta-analyses guideline. The data were pooled using a random-effects model, with subgroups defined by 4 clinical settings. Between-study heterogeneity was explored using multiple methods, and funnel plot analysis was used to identify publication bias.

Main Outcomes and Measures

C statistic was used to measure the discrimination of prediction models.

Results

Of the 6955 studies initially identified through literature searching, 150 studies, with 14.4 million participants, met the inclusion criteria. The study characteristics differed widely in design, population, AKI definition, and model performance assessments. The overall pooled C statistic was 0.80 (95% CI, 0.79-0.81), with pooled C statistics in different clinical subsettings ranging from 0.78 (95% CI, 0.75-0.80) to 0.82 (95% CI, 0.78-0.86). Between-study heterogeneity was high overall and in the different clinical settings (eg, contrast medium-associated AKI: I2 = 99.9%; P < .001), and multiple methods did not identify any clear sources. A high proportion of models had a high risk of bias (126 [84.4%]) according to the Prediction Model Risk Of Bias Assessment Tool.

Conclusions and Relevance

In this study, the discrimination of the published AKI prediction models was good, reflected by high C statistics; however, the wide variation in the clinical settings, populations, and predictive variables likely drives the highly heterogenous findings that limit clinical utility. Standardized procedures for development and validation of prediction models are urgently needed.

Overcoming barriers in the design and implementation of clinical trials for acute kidney injury: a report from the 2020 Kidney Disease Clinical Trialists meeting

Acute kidney injury (AKI) is a growing epidemic and is independently associated with increased risk of death, chronic kidney disease (CKD) and cardiovascular events. Randomized-controlled trials (RCTs) in this domain are notoriously challenging and many clinical studies in AKI have yielded inconclusive findings. Underlying this conundrum is the inherent heterogeneity of AKI in its etiology, presentation and course. AKI is best understood as a syndrome and identification of AKI subphenotypes is needed to elucidate the disease's myriad etiologies and to tailor effective prevention and treatment strategies. Conventional RCTs are logistically cumbersome and often feature highly selected patient populations that limit external generalizability and thus alternative trial designs should be considered when appropriate. In this narrative review of recent developments in AKI trials based on the Kidney Disease Clinical Trialists (KDCT) 2020 meeting, we discuss barriers to and strategies for improved design and implementation of clinical trials for AKI patients, including predictive and prognostic enrichment techniques, the use of pragmatic trials and adaptive trials.

Algorithm-based detection of acute kidney injury according to full KDIGO criteria including urine output following cardiac surgery: a descriptive analysis

BACKGROUND

Automated data analysis and processing has the potential to assist, improve and guide decision making in medical practice. However, by now it has not yet been fully integrated in a clinical setting. Herein we present the first results of applying algorithm-based detection to the diagnosis of postoperative acute kidney injury (AKI) comprising patient data from a cardiac surgical intensive care unit (ICU).

METHODS

First, we generated a well-defined study population of cardiac surgical ICU patients by implementing an application programming interface (API) to extract, clean and select relevant data from the archived digital patient management system. Health records of N = 21,045 adult patients admitted to the ICU following cardiac surgery between 2012 and 2022 were analyzed. Secondly, we developed a software functionality to detect the incidence of AKI according to Kidney Disease: Improving Global Outcomes (KDIGO) criteria, including urine output. Incidence, severity, and temporal evolution of AKI were assessed.

RESULTS

With the use of our automated data analyzing model the overall incidence of postoperative AKI was 65.4% (N = 13,755). Divided by stages, AKI 2 was the most frequent maximum disease stage with 30.5% of patients (stage 1 in 17.6%, stage 3 in 17.2%). We observed considerable temporal divergence between first detections and maximum AKI stages: 51% of patients developed AKI stage 2 or 3 after a previously identified lower stage. Length of ICU stay was significantly prolonged in AKI patients (8.8 vs. 6.6 days, p <  0.001) and increased for higher AKI stages up to 10.1 days on average. In terms of AKI criteria, urine output proved to be most relevant, contributing to detection in 87.3% (N = 12,004) of cases.

CONCLUSION

The incidence of postoperative AKI following cardiac surgery is strikingly high with 65.4% when using full KDIGO-criteria including urine output. Automated data analysis demonstrated reliable early detection of AKI with progressive deterioration of renal function in the majority of patients, therefore allowing for potential earlier therapeutic intervention for preventing or lessening disease progression, reducing the length of ICU stay, and ultimately improving overall patient outcomes.

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.

Deep Learning Using Electrocardiograms in Patients on Maintenance Dialysis

Cardiovascular morbidity and mortality occur with an extraordinarily high incidence in the hemodialysis-dependent end-stage kidney disease population. There is a clear need to improve identification of those individuals at the highest risk of cardiovascular complications in order to better target them for preventative therapies. Twelve-lead electrocardiograms are ubiquitous and use inexpensive technology that can be administered with minimal inconvenience to patients and at a minimal burden to care providers. The embedded waveforms encode significant information on the cardiovascular structure and function that might be unlocked and used to identify at-risk individuals with the use of artificial intelligence techniques like deep learning. In this review, we discuss the experience with deep learning-based analysis of electrocardiograms to identify cardiovascular abnormalities or risk and the potential to extend this to the setting of dialysis-dependent end-stage kidney disease.

Artificial intelligence for the prediction of acute kidney injury during the perioperative period: systematic review and Meta-analysis of diagnostic test accuracy

BACKGROUND

Acute kidney injury (AKI) is independently associated with morbidity and mortality in a wide range of surgical settings. Nowadays, with the increasing use of electronic health records (EHR), advances in patient information retrieval, and cost reduction in clinical informatics, artificial intelligence is increasingly being used to improve early recognition and management for perioperative AKI. However, there is no quantitative synthesis of the performance of these methods. We conducted this systematic review and meta-analysis to estimate the sensitivity and specificity of artificial intelligence for the prediction of acute kidney injury during the perioperative period.

METHODS

Pubmed, Embase, and Cochrane Library were searched to 2nd October 2021. Studies presenting diagnostic performance of artificial intelligence in the early detection of perioperative acute kidney injury were included. True positives, false positives, true negatives and false negatives were pooled to collate specificity and sensitivity with 95% CIs and results were portrayed in forest plots. The risk of bias of eligible studies was assessed using the PROBAST tool.

RESULTS

Nineteen studies involving 304,076 patients were included. Quantitative random-effects meta-analysis using the Rutter and Gatsonis hierarchical summary receiver operating characteristics (HSROC) model revealed pooled sensitivity, specificity, and diagnostic odds ratio of 0.77 (95% CI: 0.73 to 0.81),0.75 (95% CI: 0.71 to 0.80), and 10.7 (95% CI 8.5 to 13.5), respectively. Threshold effect was found to be the only source of heterogeneity, and there was no evidence of publication bias.

CONCLUSIONS

Our review demonstrates the promising performance of artificial intelligence for early prediction of perioperative AKI. The limitations of lacking external validation performance and being conducted only at a single center should be overcome.

TRIAL REGISTRATION

This study was not registered with PROSPERO.

A time-aware attention model for prediction of acute kidney injury after pediatric cardiac surgery

OBJECTIVE

Acute kidney injury (AKI) is a common complication after pediatric cardiac surgery, and the early detection of AKI may allow for timely preventive or therapeutic measures. However, current AKI prediction researches pay less attention to time information among time-series clinical data and model building strategies that meet complex clinical application scenario. This study aims to develop and validate a model for predicting postoperative AKI that operates sequentially over individual time-series clinical data.

MATERIALS AND METHODS

A retrospective cohort of 3386 pediatric patients extracted from PIC database was used for training, calibrating, and testing purposes. A time-aware deep learning model was developed and evaluated from 3 clinical perspectives that use different data collection windows and prediction windows to answer different AKI prediction questions encountered in clinical practice. We compared our model with existing state-of-the-art models from 3 clinical perspectives using the area under the receiver operating characteristic curve (ROC AUC) and the area under the precision-recall curve (PR AUC).

RESULTS

Our proposed model significantly outperformed the existing state-of-the-art models with an improved average performance for any AKI prediction from the 3 evaluation perspectives. This model predicted 91% of all AKI episodes using data collected at 24 h after surgery, resulting in a ROC AUC of 0.908 and a PR AUC of 0.898. On average, our model predicted 83% of all AKI episodes that occurred within the different time windows in the 3 evaluation perspectives. The calibration performance of the proposed model was substantially higher than the existing state-of-the-art models.

CONCLUSIONS

This study showed that a deep learning model can accurately predict postoperative AKI using perioperative time-series data. It has the potential to be integrated into real-time clinical decision support systems to support postoperative care planning.

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.

Perioperative Management of the Patient at High-Risk for Cardiac Surgery-Associated Acute Kidney Injury

Acute kidney injury (AKI) is one of the most common major complications of cardiac surgery, and is associated with increased morbidity and mortality. Cardiac surgery-associated AKI has a complex, multifactorial etiology, including numerous factors such as primary cardiac dysfunction, hemodynamic derangements of cardiac surgery and cardiopulmonary bypass, and the possibility of a large volume of blood transfusion. There are no truly effective pharmacologic therapies for the management of AKI, and, therefore, anesthesiologists, intensivists, and cardiac surgeons must remain vigilant and attempt to minimize the risk of developing renal dysfunction. This narrative review describes the current state of the scientific literature concerning the specific aspects of cardiac surgery-associated AKI, and presents it in a chronological fashion to aid the perioperative clinician in their approach to this high-risk patient group. The evidence was considered for risk prediction models, preoperative optimization, and the intraoperative and postoperative management of cardiac surgery patients to improve renal outcomes.

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.

Evaluation of a clinical decision support system for detection of patients at risk after kidney transplantation

Patient care after kidney transplantation requires integration of complex information to make informed decisions on risk constellations. Many machine learning models have been developed for detecting patient outcomes in the past years. However, performance metrics alone do not determine practical utility. We present a newly developed clinical decision support system (CDSS) for detection of patients at risk for rejection and death-censored graft failure. The CDSS is based on clinical routine data including 1,516 kidney transplant recipients and more than 100,000 data points. In a reader study we compare the performance of physicians at a nephrology department with and without the CDSS. Internal validation shows AUC-ROC scores of 0.83 for rejection, and 0.95 for graft failure. The reader study shows that predictions by physicians converge toward the CDSS. However, performance does not improve (AUC-ROC; 0.6413 vs. 0.6314 for rejection; 0.8072 vs. 0.7778 for graft failure). Finally, the study shows that the CDSS detects partially different patients at risk compared to physicians. This indicates that the combination of both, medical professionals and a CDSS might help detect more patients at risk for graft failure. However, the question of how to integrate such a system efficiently into clinical practice remains open.