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

Takkavatakarn, Kullaya; Oh, Wonsuk; Chan, Lili; Hofer, Ira; Shawwa, Khaled; Kraft, Monica; Shah, Neomi; Kohli-Seth, Roopa; Nadkarni, Girish N.; Sakhuja, Ankit

doi:10.1186/s13054-024-04935-x

Cited by 3 publications

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Development and validation of a deep learning algorithm for the prediction of serum creatinine in critically ill patients

Ghanbari,

Lam,

Shashikumar

et al. 2024

JAMIA Open

View full text Add to dashboard Cite

Objectives Serum creatinine (SCr) is the primary biomarker for assessing kidney function; however, it may lag behind true kidney function, especially in instances of acute kidney injury (AKI). The objective of the work is to develop Nephrocast, a deep-learning model to predict next-day SCr in adult patients treated in the intensive care unit (ICU). Materials and Methods Nephrocast was trained and validated, temporally and prospectively, using electronic health record data of adult patients admitted to the ICU in the University of California San Diego Health (UCSDH) between January 1, 2016 and June 22, 2024. The model features consisted of demographics, comorbidities, vital signs and laboratory measurements, and medications. Model performance was evaluated by mean absolute error (MAE) and root-mean-square error (RMSE) and compared against the prediction day’s SCr as a reference. Results A total of 28 191 encounters met the eligibility criteria, corresponding to 105 718 patient-days. The median (interquartile range [IQR]) MAE and RMSE in the internal test set were 0.09 (0.085-0.09) mg/dL and 0.15 (0.146-0.152) mg/dL, respectively. In the prospective validation, the MAE and RMSE were 0.09 mg/dL and 0.14 mg/dL, respectively. The model’s performance was superior to the reference SCr. Discussion and Conclusion Our model demonstrated good performance in predicting next-day SCr by leveraging clinical data routinely collected in the ICU. The model could aid clinicians in in identifying high-risk patients for AKI, predicting AKI trajectory, and informing the dosing of renally eliminated drugs.

show abstract

Development and validation of a deep learning algorithm for the prediction of serum creatinine in critically ill patients

Ghanbari,

Lam,

Shashikumar

et al. 2024

JAMIA Open

View full text Add to dashboard Cite

show abstract

Development and Validation of a Policy Tree Approach for Optimizing Intravenous Fluids in Critically Ill Patients with Sepsis and Acute Kidney Injury

Oh,

Takkavatakarn,

Kittrell

et al. 2024

Preprint

View full text Add to dashboard Cite

PurposeIntravenous fluids are mainstay of management of acute kidney injury (AKI) after sepsis but can cause fluid overload. Recent literature shows that restrictive fluid strategy may be beneficial in some patients with AKI, however, identifying these patients is challenging. We aimed to develop and validate a machine learning algorithm to identify patients who would benefit from a restrictive fluid strategy.MethodsWe included patients with sepsis who developed AKI within 48 hours of ICU admission and defined restrictive fluid strategy as receiving <500mL fluids within 24 hours after AKI. Our primary outcome was early AKI reversal within 48 hours of AKI onset, and secondary outcomes included sustained AKI reversal and major adverse kidney events (MAKE) at discharge. We used a causal forest, a machine learning algorithm to estimate individual treatment effects and policy tree algorithm to identify patients who would benefit by restrictive fluid strategy. We developed the algorithm in MIMIC-IV and validated it in eICU database.ResultsAmong 2,091 patients in the external validation cohort, policy tree recommended restrictive fluids for 88.2%. Among these, patients who received restrictive fluids demonstrated significantly higher rate of early AKI reversal (48.2% vs 39.6%, p<0.001), sustained AKI reversal (36.7% vs 27.4%, p<0.001) and lower rates of MAKE by discharge (29.3% vs 35.1%, p=0.019). These results were consistent in adjusted analysis.ConclusionPolicy tree based on causal machine learning can identify septic patients with AKI who benefit from a restrictive fluid strategy. This approach needs to be validated in prospective trials.Take-home messageIntravenous fluids are the mainstay of management of acute kidney injury (AKI) after sepsis but can cause fluid overload. In this study using two large, distinct critical care databases, we developed and validated a causal machine learning based Policy Tree approach to identify septic patients with AKI who benefit from a restrictive fluid strategy, enhancing early and sustained AKI reversal, and reducing major adverse kidney events at discharge.

show abstract

Machine learning method to derive serum chlorine in acute kidney injury with traumatic brain injury

Li,

Zhang,

Zhao

et al. 2024

Preprint

View full text Add to dashboard Cite

Background and purpose: Acute kidney injury (（AKI)） is a serious complication of traumatic brain injury (TBI), thatwhich affects the survival rate of patients with TBI patients. Hyperchloremia is an important factor leading to TBI-associated AKI and affects the prognosis of TBI patients with TBI; however,. but the The highest blood chlorine value is usually uselected to define it. However, the effectimpact of changes in the trajectory of early blood chlorine levels on the prognosis of patients with TBI-associated AKI remains unclear. Methods: We used the Critical Medicine Database (MIME-IV) and eICU to include TBI patients with TBI and AKI admitted to the ICU. We used the potential class model to determine the AKI class inof athe blood chlorine trial of patients with TBI. The primary endpoint was 28 day all-cause mortality, and the secondary endpoints were the development of acute kidney disease (CAD) and 7 day all-cause mortality. Multivariate regression was used performed to assess the effect of classification based on blood chlorine levels, and external validation was performed using the eICU database. Results: In 640 patients with TBI-associated AKI, we identified five categories based on blood chlorine trials with different characteristics. Compared with patients with slightly elevated blood chlorine levels late in life, those with rapidly elevated blood chlorine levels early in life had the highest risk of all-cause mortality at 28 days (HR: 2.47 (1.16, 5.65), P = 0.019), a higher risk of death at 7 days (HR: 3.18 (1.21-8.36), P = 0.019), and the highest adjusted risk of developing acute kidney disease (HR: 5.40 (1.44-20.22), P = 0.012). These associations were similar in external validation. Conclusion: The stratification of early blood chlorine trajectories can be used as a prognostic indicator for TBI-associated AKI patients.

show abstract

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

Cited by 3 publications

References 36 publications

Development and validation of a deep learning algorithm for the prediction of serum creatinine in critically ill patients

Development and validation of a deep learning algorithm for the prediction of serum creatinine in critically ill patients

Development and Validation of a Policy Tree Approach for Optimizing Intravenous Fluids in Critically Ill Patients with Sepsis and Acute Kidney Injury

Machine learning method to derive serum chlorine in acute kidney injury with traumatic brain injury

Contact Info

Product

Resources

About