scholarly journals Health Care Analytics With Time-Invariant and Time-Variant Feature Importance to Predict Hospital-Acquired Acute Kidney Injury: Observational Longitudinal Study

10.2196/30805 ◽  
2021 ◽  
Vol 23 (12) ◽  
pp. e30805
Author(s):  
Horng-Ruey Chua ◽  
Kaiping Zheng ◽  
Anantharaman Vathsala ◽  
Kee-Yuan Ngiam ◽  
Hui-Kim Yap ◽  
...  
Keyword(s):  
Machine Learning ◽  
Acute Kidney Injury ◽  
Electronic Health Records ◽  
Lead Time ◽  
Kidney Injury ◽  
False Positives ◽  
Health Records ◽  
Electronic Health ◽  
Hospital Acquired ◽  
Time Invariant

Background Acute kidney injury (AKI) develops in 4% of hospitalized patients and is a marker of clinical deterioration and nephrotoxicity. AKI onset is highly variable in hospitals, which makes it difficult to time biomarker assessment in all patients for preemptive care. Objective The study sought to apply machine learning techniques to electronic health records and predict hospital-acquired AKI by a 48-hour lead time, with the aim to create an AKI surveillance algorithm that is deployable in real time. Methods The data were sourced from 20,732 case admissions in 16,288 patients over 1 year in our institution. We enhanced the bidirectional recurrent neural network model with a novel time-invariant and time-variant aggregated module to capture important clinical features temporal to AKI in every patient. Time-series features included laboratory parameters that preceded a 48-hour prediction window before AKI onset; the latter’s corresponding reference was the final in-hospital serum creatinine performed in case admissions without AKI episodes. Results The cohort was of mean age 53 (SD 25) years, of whom 29%, 12%, 12%, and 53% had diabetes, ischemic heart disease, cancers, and baseline eGFR <90 mL/min/1.73 m2, respectively. There were 911 AKI episodes in 869 patients. We derived and validated an algorithm in the testing dataset with an AUROC of 0.81 (0.78-0.85) for predicting AKI. At a 15% prediction threshold, our model generated 699 AKI alerts with 2 false positives for every true AKI and predicted 26% of AKIs. A lowered 5% prediction threshold improved the recall to 60% but generated 3746 AKI alerts with 6 false positives for every true AKI. Representative interpretation results produced by our model alluded to the top-ranked features that predicted AKI that could be categorized in association with sepsis, acute coronary syndrome, nephrotoxicity, or multiorgan injury, specific to every case at risk. Conclusions We generated an accurate algorithm from electronic health records through machine learning that predicted AKI by a lead time of at least 48 hours. The prediction threshold could be adjusted during deployment to optimize recall and minimize alert fatigue, while its precision could potentially be augmented by targeted AKI biomarker assessment in the high-risk cohort identified.

scholarly journals Health Care Analytics With Time-Invariant and Time-Variant Feature Importance to Predict Hospital-Acquired Acute Kidney Injury: Observational Longitudinal Study (Preprint)

2021 ◽  
Author(s):  
Horng-Ruey Chua ◽  
Kaiping Zheng ◽  
Anantharaman Vathsala ◽  
Kee-Yuan Ngiam ◽  
Hui-Kim Yap ◽  
...  
Keyword(s):  
Machine Learning ◽  
Acute Kidney Injury ◽  
Electronic Health Records ◽  
Lead Time ◽  
Kidney Injury ◽  
False Positives ◽  
Health Records ◽  
Electronic Health ◽  
Hospital Acquired ◽  
Time Invariant

BACKGROUND Acute kidney injury (AKI) develops in 4% of hospitalized patients and is a marker of clinical deterioration and nephrotoxicity. AKI onset is highly variable in hospitals, which makes it difficult to time biomarker assessment in all patients for preemptive care. OBJECTIVE The study sought to apply machine learning techniques to electronic health records and predict hospital-acquired AKI by a 48-hour lead time, with the aim to create an AKI surveillance algorithm that is deployable in real time. METHODS The data were sourced from 20,732 case admissions in 16,288 patients over 1 year in our institution. We enhanced the bidirectional recurrent neural network model with a novel time-invariant and time-variant aggregated module to capture important clinical features temporal to AKI in every patient. Time-series features included laboratory parameters that preceded a 48-hour prediction window before AKI onset; the latter’s corresponding reference was the final in-hospital serum creatinine performed in case admissions without AKI episodes. RESULTS The cohort was of mean age 53 (SD 25) years, of whom 29%, 12%, 12%, and 53% had diabetes, ischemic heart disease, cancers, and baseline eGFR &lt;90 mL/min/1.73 m<sup>2</sup>, respectively. There were 911 AKI episodes in 869 patients. We derived and validated an algorithm in the testing dataset with an AUROC of 0.81 (0.78-0.85) for predicting AKI. At a 15% prediction threshold, our model generated 699 AKI alerts with 2 false positives for every true AKI and predicted 26% of AKIs. A lowered 5% prediction threshold improved the recall to 60% but generated 3746 AKI alerts with 6 false positives for every true AKI. Representative interpretation results produced by our model alluded to the top-ranked features that predicted AKI that could be categorized in association with sepsis, acute coronary syndrome, nephrotoxicity, or multiorgan injury, specific to every case at risk. CONCLUSIONS We generated an accurate algorithm from electronic health records through machine learning that predicted AKI by a lead time of at least 48 hours. The prediction threshold could be adjusted during deployment to optimize recall and minimize alert fatigue, while its precision could potentially be augmented by targeted AKI biomarker assessment in the high-risk cohort identified.

scholarly journals Predicting Acute Kidney Injury: A Machine Learning Approach Using Electronic Health Records

Information ◽  
2020 ◽  
Vol 11 (8) ◽  
pp. 386
Author(s):  
Sheikh S. Abdullah ◽  
Neda Rostamzadeh ◽  
Kamran Sedig ◽  
Amit X. Garg ◽  
Eric McArthur
Keyword(s):  
Machine Learning ◽  
Emergency Department ◽  
Acute Kidney Injury ◽  
Electronic Health Records ◽  
Prediction Models ◽  
Kidney Injury ◽  
Machine Learning Techniques ◽  
Health Records ◽  
Mortality And Morbidity ◽  
Electronic Health

Acute kidney injury (AKI) is a common complication in hospitalized patients and can result in increased hospital stay, health-related costs, mortality and morbidity. A number of recent studies have shown that AKI is predictable and avoidable if early risk factors can be identified by analyzing Electronic Health Records (EHRs). In this study, we employ machine learning techniques to identify older patients who have a risk of readmission with AKI to the hospital or emergency department within 90 days after discharge. One million patients’ records are included in this study who visited the hospital or emergency department in Ontario between 2014 and 2016. The predictor variables include patient demographics, comorbid conditions, medications and diagnosis codes. We developed 31 prediction models based on different combinations of two sampling techniques, three ensemble methods, and eight classifiers. These models were evaluated through 10-fold cross-validation and compared based on the AUROC metric. The performances of these models were consistent, and the AUROC ranged between 0.61 and 0.88 for predicting AKI among 31 prediction models. In general, the performances of ensemble-based methods were higher than the cost-sensitive logistic regression. We also validated features that are most relevant in predicting AKI with a healthcare expert to improve the performance and reliability of the models. This study predicts the risk of AKI for a patient after being discharged, which provides healthcare providers enough time to intervene before the onset of AKI.

scholarly journals Leveraging Big Data and Electronic Health Records to Enhance Novel Approaches to Acute Kidney Injury Research and Care

2017 ◽  
Vol 44 (1) ◽  
pp. 68-76 ◽  
Author(s):  
Scott M. Sutherland ◽  
Stuart L. Goldstein ◽  
Sean M. Bagshaw
Keyword(s):  
Acute Kidney Injury ◽  
Electronic Health Records ◽  
Kidney Injury ◽  
Diagnostic Strategy ◽  
Consensus Definition ◽  
Health Records ◽  
Electronic Health ◽  
Predictive Approaches ◽  
Care Improvement ◽  
Injury Research

While acute kidney injury (AKI) has been poorly defined historically, a decade of effort has culminated in a standardized, consensus definition. In parallel, electronic health records (EHRs) have been adopted with greater regularity, clinical informatics approaches have been refined, and the field of EHR-enabled care improvement and research has burgeoned. Although both fields have matured in isolation, uniting the 2 has the capacity to redefine AKI-related care and research. This article describes how the application of a consistent AKI definition to the EHR dataset can accurately and rapidly diagnose and identify AKI events. Furthermore, this electronic, automated diagnostic strategy creates the opportunity to develop predictive approaches, optimize AKI alerts, and trace AKI events across institutions, care platforms, and administrative datasets.

scholarly journals Electronic health records accurately predict renal replacement therapy in acute kidney injury

2019 ◽  
Vol 20 (1) ◽  
Author(s):  
Sanmay Low ◽  
Anantharaman Vathsala ◽  
Tanusya Murali Murali ◽  
Long Pang ◽  
Graeme MacLaren ◽  
...  
Keyword(s):  
Acute Kidney Injury ◽  
Renal Replacement Therapy ◽  
Electronic Health Records ◽  
Replacement Therapy ◽  
Kidney Injury ◽  
Health Records ◽  
Electronic Health

scholarly journals Machine Learning Model for Risk Prediction of Community-Acquired Acute Kidney Injury Hospitalization From Electronic Health Records: Development and Validation Study

10.2196/16903 ◽  
2020 ◽  
Vol 22 (8) ◽  
pp. e16903
Author(s):  
Chien-Ning Hsu ◽  
Chien-Liang Liu ◽  
You-Lin Tain ◽  
Chin-Yu Kuo ◽  
Yun-Chun Lin
Keyword(s):  
Machine Learning ◽  
Acute Kidney Injury ◽  
General Population ◽  
Electronic Health Records ◽  
Hospital Admission ◽  
Risk Model ◽  
Validation Cohort ◽  
Kidney Injury ◽  
Health Records ◽  
Predictive Values

Background Community-acquired acute kidney injury (CA-AKI)-associated hospitalizations impose significant health care needs and contribute to in-hospital mortality. However, most risk prediction models developed to date have focused on AKI in a specific group of patients during hospitalization, and there is limited knowledge on the baseline risk in the general population for preventing CA-AKI-associated hospitalization. Objective To gain further insight into risk exploration, the aim of this study was to develop, validate, and establish a scoring system to facilitate health professionals in enabling early recognition and intervention of CA-AKI to prevent permanent kidney damage using different machine-learning techniques. Methods A nested case-control study design was employed using electronic health records derived from a group of Chang Gung Memorial Hospitals in Taiwan from 2010 to 2017 to identify 234,867 adults with at least two measures of serum creatinine at hospital admission. Patients were classified into a derivation cohort (2010-2016) and a temporal validation cohort (2017). Patients with the first episode of CA-AKI at hospital admission were classified into the case group and those without CA-AKI were classified in the control group. A total of 47 potential candidate variables, including age, gender, prior use of nephrotoxic medications, Charlson comorbid conditions, commonly measured laboratory results, and recent use of health services, were tested to develop a CA-AKI hospitalization risk model. Permutation-based selection with both the extreme gradient boost (XGBoost) and least absolute shrinkage and selection operator (LASSO) algorithms was performed to determine the top 10 important features for scoring function development. Results The discriminative ability of the risk model was assessed by the area under the receiver operating characteristic curve (AUC), and the predictive CA-AKI risk model derived by the logistic regression algorithm achieved an AUC of 0.767 (95% CI 0.764-0.770) on derivation and 0.761 on validation for any stage of AKI, with positive and negative predictive values of 19.2% and 96.1%, respectively. The risk model for prediction of CA-AKI stages 2 and 3 had an AUC value of 0.818 for the validation cohort with positive and negative predictive values of 13.3% and 98.4%, respectively. These metrics were evaluated at a cut-off value of 7.993, which was determined as the threshold to discriminate the risk of AKI. Conclusions A machine learning–generated risk score model can identify patients at risk of developing CA-AKI-related hospitalization through a routine care data-driven approach. The validated multivariate risk assessment tool could help clinicians to stratify patients in primary care, and to provide monitoring and early intervention for preventing AKI while improving the quality of AKI care in the general population.

scholarly journals Detection of Drug–Drug Interactions Inducing Acute Kidney Injury by Electronic Health Records Mining

Drug Safety ◽  
2015 ◽  
Vol 38 (9) ◽  
pp. 799-809 ◽  
Author(s):  
Yannick Girardeau ◽  
Claire Trivin ◽  
Pierre Durieux ◽  
Christine Le Beller ◽  
Lillo-Le Louet Agnes ◽  
...  
Keyword(s):  
Acute Kidney Injury ◽  
Electronic Health Records ◽  
Drug Interactions ◽  
Kidney Injury ◽  
Health Records ◽  
Electronic Health
Sign in / Sign up

Export Citation Format

Share Document