Prediction of Acute Kidney Injury With a Machine Learning Algorithm Using Electronic Health Record Data
Hamid Mohamadlou, Anna Lynn-Palevsky, Christopher Barton, Uli Chettipally, Lisa Shieh, Jacob Calvert, Nicholas R Saber, Ritankar Das, Hamid Mohamadlou, Anna Lynn-Palevsky, Christopher Barton, Uli Chettipally, Lisa Shieh, Jacob Calvert, Nicholas R Saber, Ritankar Das
Abstract
Background: A major problem in treating acute kidney injury (AKI) is that clinical criteria for recognition are markers of established kidney damage or impaired function; treatment before such damage manifests is desirable. Clinicians could intervene during what may be a crucial stage for preventing permanent kidney injury if patients with incipient AKI and those at high risk of developing AKI could be identified.
Objective: In this study, we evaluate a machine learning algorithm for early detection and prediction of AKI.
Design: We used a machine learning technique, boosted ensembles of decision trees, to train an AKI prediction tool on retrospective data taken from more than 300 000 inpatient encounters.
Setting: Data were collected from inpatient wards at Stanford Medical Center and intensive care unit patients at Beth Israel Deaconess Medical Center.
Patients: Patients older than the age of 18 whose hospital stays lasted between 5 and 1000 hours and who had at least one documented measurement of heart rate, respiratory rate, temperature, serum creatinine (SCr), and Glasgow Coma Scale (GCS).
Measurements: We tested the algorithm's ability to detect AKI at onset and to predict AKI 12, 24, 48, and 72 hours before onset.
Methods: We tested AKI detection and prediction using the National Health Service (NHS) England AKI Algorithm as a gold standard. We additionally tested the algorithm's ability to detect AKI as defined by the Kidney Disease: Improving Global Outcomes (KDIGO) guidelines. We compared the algorithm's 3-fold cross-validation performance to the Sequential Organ Failure Assessment (SOFA) score for AKI identification in terms of area under the receiver operating characteristic (AUROC).
Results: The algorithm demonstrated high AUROC for detecting and predicting NHS-defined AKI at all tested time points. The algorithm achieves AUROC of 0.872 (95% confidence interval [CI], 0.867-0.878) for AKI detection at time of onset. For prediction 12 hours before onset, the algorithm achieves an AUROC of 0.800 (95% CI, 0.792-0.809). For 24-hour predictions, the algorithm achieves AUROC of 0.795 (95% CI, 0.785-0.804). For 48-hour and 72-hour predictions, the algorithm achieves AUROC values of 0.761 (95% CI, 0.753-0.768) and 0.728 (95% CI, 0.719-0.737), respectively.
Limitations: Because of the retrospective nature of this study, we cannot draw any conclusions about the impact the algorithm's predictions will have on patient outcomes in a clinical setting.
Conclusions: The results of these experiments suggest that a machine learning-based AKI prediction tool may offer important prognostic capabilities for determining which patients are likely to suffer AKI, potentially allowing clinicians to intervene before kidney damage manifests.
Keywords: acute kidney injury; machine learning.
Conflict of interest statement
Declaration of Conflicting Interests: The author(s) declared the following potential conflicts of interest with respect to the research, authorship, and/or publication of this article: Mohamadlou, Barton, Calvert, Lynn-Palevsky, Saber, and Das are employees of Dascena, developers of the predictive algorithm. Shieh reports receiving grant funding from Dascena.
Figures
References
- Waikar SS, Liu KD, Chertow GM. Diagnosis, epidemiology, and outcomes of acute kidney injury. Clin J Am Soc Nephrol. 2008;3(3):844-861. doi:10.2215/CJN.05191107.
- Chertow GM, Burdick E, Honour M, Bonventre JV, Bates DW. Acute kidney injury, mortality, length of stay, and costs in hospitalized patients. J Am Soc Nephrol. 2005;16(11):3365-3370. doi:10.1681/ASN.2004090740.
- Silver SA, Long J, Zheng Y, Chertow GM. Cost of acute kidney injury in hospitalized patients. J Hosp Med. 2017;12(2):70-76.
- Mehta RL, Kellum JA, Shah SV, et al. Acute Kidney Injury Network: report of an initiative to improve outcomes in acute kidney injury. Crit Care. 2007;11:R31. doi:10.1186/cc5713.
- Metnitz PG, Krenn CG, Steltzer H, et al. Effect of acute renal failure requiring renal replacement therapy on outcome in critically ill patients. Crit Care Med. 2002;30:2051-2058.
- De Corte W, Dhondt A, Vanholder R, et al. Long-term outcome in ICU patients with acute kidney injury treated with renal replacement therapy: a prospective cohort study. Crit Care. 2016;20:256. doi:10.1186/s13054-016-1409-z.
- Kolhe NV, Staples D, Reilly T, et al. Impact of compliance with a care bundle on acute kidney injury outcomes: a prospective observational study. PLoS One. 2015;10(7):e0132279. doi:10.1371/journal.pone.0132279.
- Kellum JA, Lameire N, Aspelin P, et al. Kidney Disease: Improving Global Outcomes (KDIGO) acute kidney injury work group KDIGO clinical practice guideline for acute kidney injury. Kidney Int Suppl. 2012;2:1-138.
- Star RA. Treatment of acute renal failure. Kidney Int. 1998;54(6):1817-1831.
- Praught ML, Shlipak MG. Are small changes in serum creatinine an important risk factor? Curr Opin Nephrol Hypertens. 2005;14:265-270.
- Mehta RL, Pascual MT, Soroko S, et al. Spectrum of acute renal failure in the intensive care unit: the PICARD experience. Kidney Int. 2004;66(4):1613-1621. doi:10.1111/j.1523-1755.2004.00927.x.
- Hoste EAJ, Clermont G, Kersten A, et al. RIFLE criteria for acute kidney injury are associated with hospital mortality in critically ill patients: a cohort analysis. Crit Care. 2006;10(3):R73. doi:10.1186/cc4915.
- Koyner JL, Adhikari R, Edelson DP, Churpek MM. Development of a multicenter ward-based AKI prediction model. Clin J Am Soc Nephrol. 2016;11:1935-1943.
- Fletchet M, Guiza F, Chetz M, et al. AKIpredictor, an online prognostic calculator for acute kidney injury in adult critically ill patients: development, validation and comparison to serum neutrophil gelatinase-associated lipocalin. Intensive Care Med. 2017;43(6):764-773. doi:10.1007/s00134-017-4678-3.
- Kate RJ, Perez RM, Mazumdar D, Pasupathy KS, Nilakantan V. Prediction and detection models for acute kidney injury in hospitalized older adults. BMC Med Informat Decis Making. 2016;16:39. doi:10.1186/s12911-016-0277-4.
- Porter CJ, Juurlink I, Bisset LH, Bavakunji R, Mehta RL, Devonald MA. A real-time electronic alert to improve detection of acute kidney injury in a large teaching hospital. Nephrol Dial Transplant. 2014;29(10):1888-1893. doi:10.1093/ndt/gfu082.
- Vincent JL, Moreno R, Takala J, et al. The SOFA (Sepsis-related Organ Failure Assessment) score to describe organ dysfunction/failure. On behalf of the working group on sepsis-related problems of the European Society of Intensive Care Medicine. Intensive Care Med. 1996;22(7):707-710. doi:10.1007/BF01709751.
- De Mendonca A, Vincent JL, Suter PM, et al. Acute renal failure in the ICU: risk factors and outcome evaluated by the SOFA score. Intensive Care Med. 2000;26:915-921.
- Johnson AEW, Pollard TJ, Shen L, et al. MIMIC-III, a freely accessible critical care database. Sci Data. 2016;3: 160035. doi:10.1038/sdata.2016.35.
- Mao Q, Jay M, Hoffman JL, et al. Multicentre validation of a sepsis prediction algorithm using only vital sign data in the emergency department, general ward and ICU. 2017. BMJ Open. 2018;8(1):e017833.
- Selby NM, Hill R, Fluck RJ. Standardizing the early identification of acute kidney injury: the NHS England national patient safety alert. Nephron. 2015; 131:113-117. doi:10.1159/000439146.
- Kellum JA, Lameire N. Diagnosis, evaluation, and management of acute kidney injury: a KDIGO summary (Part 1). On behalf of the KDIGO guideline AKI group. Crit Care. 2013;17(1):204. doi:10.1186/cc11454.
- Ricci Z, Cruz D, Ronco C. The RIFLE criteria and mortality in acute kidney injury: a systematic review. Kidney Int. 2008;73(5):538-546.
- Schuur JD, Chambers JG, Hou PC. Urinary catheter use and appropriateness in U.S. emergency departments, 1995-2010. Acad Emerg Med. 2014;21:292-300.
- Závada J, Hoste E, Cartin-Ceba R, et al. A comparison of three methods to estimate baseline creatinine for RIFLE classification. Nephrol Dial Transplant. 2010;25(12):3911-3918.
- Chen T, Guestrin C. XGBoost: a scalable tree boosting system. Paper presented at the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; August 2016; San Francisco, CA, USA.
- Pandharipande PP, Shintani AK, Hagerman HE, et al. Derivation and validation of SpO2/FiO2 ratio to impute for PaO2/FiO2 ratio in the respiratory component of the Sequential Organ Failure Assessment (SOFA) Score. Crit Care Med. 2009;37(4):1317-1321. doi:10.1097/CCM.0b013e31819cefa9.
- Palevsky PM, Liu KD, Brophy PD, et al. KDOQI US commentary on the 2012 KDIGO clinical practice guideline for acute kidney injury. Am J Kidney Dis. 2013;61(5):649-672.
- Calvert JS, Price DA, Chettipally UK, et al. A computational approach to early sepsis detection. Comp Biol Med. 2016;74:69-73.
- Desautels T, Calvert J, Hoffman J, et al. Prediction of sepsis in the intensive care unit with minimal electronic health record data: a machine learning approach. JMIR Med Inform. 2016;4(3):e28.
- Calvert J, Desautels T, Chettipally U, et al. High-performance detection and early prediction of septic shock for alcohol-use disorder patients. Ann Med Surg. 2016;8:50-55.
- Shimabukuro D, Barton CW, Feldman MD, Mataraso SJ, Das R. Effect of a machine learning-based severe sepsis prediction algorithm on patient survival and hospital length of stay: a randomized clinical trial. BMJ Open Respir Res. 2017;4:e000234.
- McCoy A, Das R. Reducing patient mortality, length of stay and readmissions through machine learning-based sepsis prediction in the emergency department, intensive care unit and hospital floor units. BMJ Open Qual. 2017;6:e000158. doi:10.1136/bmjoq-2017-000158.
Source: PubMed