Real time AKI risk Calculator using changes in serum creatinine
Notebook of this article is available at : https://github.com/mohcinemadkour/AKI-risk-Calculator-
Acute Kidney Injury (AKI) is a sudden reduction in kidney function that occurs without causing any symptoms or signs and its presence frequently goes unrecognized by patients and health care providers. It is associated with up to five-fold increases in risk for both other serious complications and hospital death, and an increase in hospital cost of up to $28,000 per hospitalization. It is estimated that 1 in 5 emergency admissions to the hospital are associated with AKI, resulting in prolonged inpatient care and contributing to 100,000 inpatient deaths annually. Research has demonstrated that AKI, characterized by a decrease in kidney function ranging from 10% to complete failure, affected up to 30% of surgical patients and even if the AKI resolved it still was associated with increased risks for chronic kidney disease (CKD), hemodialysis and death years after surgery. Recent National Confidential Enquiry into Patient Outcome and Death (NCEPOD) estimated that one quarter to one third of cases have the potential to be prevented.
Although a standardized definition for AKI that uses an increase in routinely measured serum creatinine level to quantify three severity stages has been in place for the last several years, adoption among physicians is low and awareness among patients for this devastating complication is even lower. Recent national patient safety data from the United Kingdom demonstrated that patient mortality and injury increases with any delay in detecting AKI, and the UK has launched a National AKI Prevention Program. The goal of this program is to develop and adopt e-alert systems, based on serum creatinine, which will pro-actively notify clinicians when a patient has AKI. We propose an algorithm to identify AKI risk in real time using changes in serum creatinine which would decrease harm due to any delay in detecting AKI.
Input Data
We have patient’s creatinine values collected in different lab dates. Each patient is identified by a unique Medical Record Number and has Demographic identifiers of age, gender, and race.
AKI Calculator
Formulas for calculating eGFR (estimated Glomerular Filtration Rate) from Demographic information: Age, Gender, and Race
141 × min(cr/κ, 1)**α × max(cr/κ, 1)**(-1.209) × 0.993**age × g × r
- Scr is serum creatinine in mg/dL,
- κ is 0.7 for females and 0.9 for males,
- α is -0.329 for females and -0.411 for males,
- g is 1.018 for females and 1 for males,
- r is 1.159 for blacks and 1 for other races
Baseline creatinine is calculated based on the 25 percentile of the overall creatinine values. Peak creatinine is set to True is a following creatinine slope is negative. AKI can be calculated via comparing the baseline creatinine, and the peak creatinine. If creatinine value is more than 1.5 times the baseline creatinine and Peak creatinine is True then APK is True. The CKD stage is computed from the GFR value according to the schema bellow.
Results
Conclusion
- In this article I implement an algorithm that helps identify episodes of acute kidney injury based on the trend of serum creatinine over time.
- This program analyses a series of creatinine laboratory values and calculates the number of AKI, and their dates. It also has the ability to plot the results.
- The program can be used to assess a patient’s baseline creatinine based on multiple labs , it can be used to highlight the patient’s peak creatinine during hospitalization.
References
https://www.ncbi.nlm.nih.gov/pubmed/23727171
https://kdigo.org/wp-content/uploads/2017/04/KDIGO-CKD-Guideline-Manila_Kasiske.pdf
