Machine Learning Can Accurately Predict Pre-admission Baseline Hemoglobin and Creatinine in Intensive Care Patients

Overview

Journal NPJ Digit Med

Specialty Medical Informatics

Date 2019 Dec 10

PMID 31815192

Citations 7

Authors

Antonin Dauvin

Carolina Donado

Patrik Bachtiger

Ke-Chun Huang

Christopher Martin Sauer

Daniele Ramazzotti

Matteo Bonvini

Leo Anthony Celi

Molly J Douglas

Affiliations

Soon will be listed here.

Abstract

Patients admitted to the intensive care unit frequently have anemia and impaired renal function, but often lack historical blood results to contextualize the acuteness of these findings. Using data available within two hours of ICU admission, we developed machine learning models that accurately (AUC 0.86-0.89) classify an individual patient's baseline hemoglobin and creatinine levels. Compared to assuming the baseline to be the same as the admission lab value, machine learning performed significantly better at classifying acute kidney injury regardless of initial creatinine value, and significantly better at predicting baseline hemoglobin value in patients with admission hemoglobin of <10 g/dl.

Citing Articles

Entering the new digital era of intensive care medicine: an overview of interdisciplinary approaches to use artificial intelligence for patients' benefit.

Old O, Friedrichson B, Zacharowski K, Kloka J Eur J Anaesthesiol Intensive Care. 2025; 2(1):e0014.

PMID: 39916758 PMC: 11783618. DOI: 10.1097/EA9.0000000000000014.

Interpretable machine learning models for predicting in-hospital and 30 days adverse events in acute coronary syndrome patients in Kuwait.

Alkhamis M, Al Jarallah M, Attur S, Zubaid M Sci Rep. 2024; 14(1):1243.

PMID: 38216605 PMC: 10786865. DOI: 10.1038/s41598-024-51604-8.

SpeCamX: mobile app that turns unmodified smartphones into multispectral imagers.

He Q, Li W, Shi Y, Yu Y, Geng W, Sun Z Biomed Opt Express. 2023; 14(9):4929-4946.

PMID: 37791269 PMC: 10545193. DOI: 10.1364/BOE.497602.

Machine learning-based risk factor analysis and prevalence prediction of intestinal parasitic infections using epidemiological survey data.

Zafar A, Attia Z, Tesfaye M, Walelign S, Wordofa M, Abera D PLoS Negl Trop Dis. 2022; 16(6):e0010517.

PMID: 35700192 PMC: 9236253. DOI: 10.1371/journal.pntd.0010517.

Use of Artificial Intelligence in Non-Oncologic Interventional Radiology: Current State and Future Directions.

Malpani R, Petty C, Bhatt N, Staib L, Chapiro J Dig Dis Interv. 2022; 5(4):331-337.

PMID: 35005333 PMC: 8740955. DOI: 10.1055/s-0041-1726300.

References

Carson J, Grossman B, Kleinman S, Tinmouth A, Marques M, Fung M . Red blood cell transfusion: a clinical practice guideline from the AABB*. Ann Intern Med. 2012; 157(1):49-58. DOI: 10.7326/0003-4819-157-1-201206190-00429. View

Gulshan V, Peng L, Coram M, Stumpe M, Wu D, Narayanaswamy A . Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs. JAMA. 2016; 316(22):2402-2410. DOI: 10.1001/jama.2016.17216. View

Levey A, Eckardt K, Tsukamoto Y, Levin A, Coresh J, Rossert J . Definition and classification of chronic kidney disease: a position statement from Kidney Disease: Improving Global Outcomes (KDIGO). Kidney Int. 2005; 67(6):2089-100. DOI: 10.1111/j.1523-1755.2005.00365.x. View

Moreno R, Metnitz B, Adler L, Hoechtl A, Bauer P, Metnitz P . Sepsis mortality prediction based on predisposition, infection and response. Intensive Care Med. 2007; 34(3):496-504. DOI: 10.1007/s00134-007-0943-1. View

Hannun A, Rajpurkar P, Haghpanahi M, Tison G, Bourn C, Turakhia M . Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network. Nat Med. 2019; 25(1):65-69. PMC: 6784839. DOI: 10.1038/s41591-018-0268-3. View

Jiang F, Jiang Y, Zhi H, Dong Y, Li H, Ma S . Artificial intelligence in healthcare: past, present and future. Stroke Vasc Neurol. 2018; 2(4):230-243. PMC: 5829945. DOI: 10.1136/svn-2017-000101. View

Tyler P, Du H, Feng M, Bai R, Xu Z, Horowitz G . Assessment of Intensive Care Unit Laboratory Values That Differ From Reference Ranges and Association With Patient Mortality and Length of Stay. JAMA Netw Open. 2019; 1(7):e184521. PMC: 6324400. DOI: 10.1001/jamanetworkopen.2018.4521. View

Lee J, Jun S, Cho Y, Lee H, Kim G, Seo J . Deep Learning in Medical Imaging: General Overview. Korean J Radiol. 2017; 18(4):570-584. PMC: 5447633. DOI: 10.3348/kjr.2017.18.4.570. View

Rudin R, Motala A, Goldzweig C, Shekelle P . Usage and effect of health information exchange: a systematic review. Ann Intern Med. 2014; 161(11):803-11. DOI: 10.7326/M14-0877. View

10.

Vandenbroucke J, von Elm E, Altman D, Gotzsche P, Mulrow C, Pocock S . Strengthening the Reporting of Observational Studies in Epidemiology (STROBE): explanation and elaboration. Ann Intern Med. 2007; 147(8):W163-94. DOI: 10.7326/0003-4819-147-8-200710160-00010-w1. View

11.

Waljee A, Mukherjee A, Singal A, Zhang Y, Warren J, Balis U . Comparison of imputation methods for missing laboratory data in medicine. BMJ Open. 2013; 3(8). PMC: 3733317. DOI: 10.1136/bmjopen-2013-002847. View

12.

Pivovarov R, Albers D, Sepulveda J, Elhadad N . Identifying and mitigating biases in EHR laboratory tests. J Biomed Inform. 2014; 51:24-34. PMC: 4194228. DOI: 10.1016/j.jbi.2014.03.016. View

13.

Khwaja A . KDIGO clinical practice guidelines for acute kidney injury. Nephron Clin Pract. 2012; 120(4):c179-84. DOI: 10.1159/000339789. View

14.

Kourou K, Exarchos T, Exarchos K, Karamouzis M, Fotiadis D . Machine learning applications in cancer prognosis and prediction. Comput Struct Biotechnol J. 2015; 13:8-17. PMC: 4348437. DOI: 10.1016/j.csbj.2014.11.005. View

15.

Knaus W, Draper E, Wagner D, Zimmerman J . APACHE II: a severity of disease classification system. Crit Care Med. 1985; 13(10):818-29. View

16.

Wang S, Summers R . Machine learning and radiology. Med Image Anal. 2012; 16(5):933-51. PMC: 3372692. DOI: 10.1016/j.media.2012.02.005. View

17.

Deyo D, Khaliq A, Mitchell D, Hughes D . Electronic sharing of diagnostic information and patient outcomes. Am J Manag Care. 2018; 24(1):32-37. View

18.

Hall W, Chapman M, Lee K, Merino Y, Thomas T, Payne B . Implicit Racial/Ethnic Bias Among Health Care Professionals and Its Influence on Health Care Outcomes: A Systematic Review. Am J Public Health. 2015; 105(12):e60-76. PMC: 4638275. DOI: 10.2105/AJPH.2015.302903. View

19.

Celi L, Tang R, Villarroel M, Davidzon G, Lester W, Chueh H . A Clinical Database-Driven Approach to Decision Support: Predicting Mortality Among Patients with Acute Kidney Injury. J Healthc Eng. 2012; 2(1):97-110. PMC: 3404157. DOI: 10.1260/2040-2295.2.1.97. View

20.

Shah N, Osea E, Martinez G . Accuracy of noninvasive hemoglobin and invasive point-of-care hemoglobin testing compared with a laboratory analyzer. Int J Lab Hematol. 2013; 36(1):56-61. PMC: 4232003. DOI: 10.1111/ijlh.12118. View