Artificial Intelligence-based Prediction of Transfusion in the Intensive Care Unit in Patients with Gastrointestinal Bleeding

Overview

Journal BMJ Health Care Inform

Specialties Medical Informatics
Public Health

Date 2021 Jan 18

PMID 33455913

Citations 14

Authors

Riccardo Levi

Francesco Carli

Aldo Robles Arevalo

Yuksel Altinel

Daniel J Stein

Matteo Maria Naldini

Federica Grassi

Andrea Zanoni

Stan Finkelstein

Susana M Vieira

Joao Sousa

Riccardo Barbieri

Leo Anthony Celi

Affiliations

Soon will be listed here.

Abstract

Objective: Gastrointestinal (GI) bleeding commonly requires intensive care unit (ICU) in cases of potentialhaemodynamiccompromise or likely urgent intervention. However, manypatientsadmitted to the ICU stop bleeding and do not require further intervention, including blood transfusion. The present work proposes an artificial intelligence (AI) solution for the prediction of rebleeding in patients with GI bleeding admitted to ICU.

Methods: A machine learning algorithm was trained and tested using two publicly available ICU databases, the Medical Information Mart for Intensive Care V.1.4 database and eICU Collaborative Research Database using freedom from transfusion as a proxy for patients who potentially did not require ICU-level care. Multiple initial observation time frames were explored using readily available data including labs, demographics and clinical parameters for a total of 20 covariates.

Results: The optimal model used a 5-hour observation period to achieve an area under the curve of the receiving operating curve (ROC-AUC) of greater than 0.80. The model was robust when tested against both ICU databases with a similar ROC-AUC for all.

Conclusions: The potential disruptive impact of AI in healthcare innovation is acknowledge, but awareness of AI-related risk on healthcare applications and current limitations should be considered before implementation and deployment. The proposed algorithm is not meant to replace but to inform clinical decision making. Prospective clinical trial validation as a triage tool is warranted.

Citing Articles

Management of gastrointestinal bleed in the intensive care setting, an updated literature review.

Nagesh V, Pulipaka S, Bhuju R, Martinez E, Badam S, Nageswaran G World J Crit Care Med. 2025; 14(1):101639.

PMID: 40060732 PMC: 11671843. DOI: 10.5492/wjccm.v14.i1.101639.

Predicting blood transfusion demand in intensive care patients after surgery by comparative analysis of temporally extended data selection.

Sheikhalishahi S, Goss S, Seidlmayer L, Zaghdoudi S, Hinske L, Kaspar M BMC Med Inform Decis Mak. 2024; 24(1):397.

PMID: 39695617 PMC: 11657635. DOI: 10.1186/s12911-024-02800-z.

Blood Bonds: Transforming Blood Donation Through Innovation, Inclusion, and Engagement.

Sagar A JMIR Perioper Med. 2024; 7:e63817.

PMID: 39331421 PMC: 11470213. DOI: 10.2196/63817.

Proenkephalin improves cardio-renal risk prediction in acute coronary syndromes: the KID-ACS score.

Wenzl F, Wang P, Arrigo M, Parenica J, Jones D, Bruno F Eur Heart J. 2024; 46(1):38-54.

PMID: 39215600 PMC: 11695896. DOI: 10.1093/eurheartj/ehae602.

Validation of an Electronic Health Record-Based Machine Learning Model Compared With Clinical Risk Scores for Gastrointestinal Bleeding.

Shung D, Chan C, You K, Nakamura S, Saarinen T, Zheng N Gastroenterology. 2024; 167(6):1198-1212.

PMID: 38971198 PMC: 11493512. DOI: 10.1053/j.gastro.2024.06.030.

References

Robertson M, Majumdar A, Boyapati R, Chung W, Worland T, Terbah R . Risk stratification in acute upper GI bleeding: comparison of the AIMS65 score with the Glasgow-Blatchford and Rockall scoring systems. Gastrointest Endosc. 2015; 83(6):1151-60. DOI: 10.1016/j.gie.2015.10.021. View

Beam A, Kohane I . Big Data and Machine Learning in Health Care. JAMA. 2018; 319(13):1317-1318. DOI: 10.1001/jama.2017.18391. View

Esrailian E, Gralnek I . Nonvariceal upper gastrointestinal bleeding: epidemiology and diagnosis. Gastroenterol Clin North Am. 2005; 34(4):589-605. DOI: 10.1016/j.gtc.2005.08.006. View

Pollard T, Johnson A, Raffa J, Celi L, Mark R, Badawi O . The eICU Collaborative Research Database, a freely available multi-center database for critical care research. Sci Data. 2018; 5:180178. PMC: 6132188. DOI: 10.1038/sdata.2018.178. View

Kindle R, Badawi O, Celi L, Sturland S . Intensive Care Unit Telemedicine in the Era of Big Data, Artificial Intelligence, and Computer Clinical Decision Support Systems. Crit Care Clin. 2019; 35(3):483-495. DOI: 10.1016/j.ccc.2019.02.005. View

Virtanen P, Gommers R, Oliphant T, Haberland M, Reddy T, Cournapeau D . SciPy 1.0: fundamental algorithms for scientific computing in Python. Nat Methods. 2020; 17(3):261-272. PMC: 7056644. DOI: 10.1038/s41592-019-0686-2. View

Blatchford O, Murray W, Blatchford M . A risk score to predict need for treatment for upper-gastrointestinal haemorrhage. Lancet. 2000; 356(9238):1318-21. DOI: 10.1016/S0140-6736(00)02816-6. View

Chu A, Ahn H, Halwan B, Kalmin B, Artifon E, Barkun A . A decision support system to facilitate management of patients with acute gastrointestinal bleeding. Artif Intell Med. 2007; 42(3):247-59. DOI: 10.1016/j.artmed.2007.10.003. View

Celi L, Hassan E, Marquardt C, Breslow M, Rosenfeld B . The eICU: it's not just telemedicine. Crit Care Med. 2001; 29(8 Suppl):N183-9. DOI: 10.1097/00003246-200108001-00007. View

10.

Cosgriff C, Celi L, Stone D . Critical Care, Critical Data. Biomed Eng Comput Biol. 2019; 10:1179597219856564. PMC: 6563388. DOI: 10.1177/1179597219856564. View

11.

The Lancet Digital Health . Walking the tightrope of artificial intelligence guidelines in clinical practice. Lancet Digit Health. 2020; 1(3):e100. DOI: 10.1016/S2589-7500(19)30063-9. View

12.

Topol E . High-performance medicine: the convergence of human and artificial intelligence. Nat Med. 2019; 25(1):44-56. DOI: 10.1038/s41591-018-0300-7. View

13.

Minne L, Abu-Hanna A, de Jonge E . Evaluation of SOFA-based models for predicting mortality in the ICU: A systematic review. Crit Care. 2008; 12(6):R161. PMC: 2646326. DOI: 10.1186/cc7160. View

14.

Ruffle J, Farmer A, Aziz Q . Artificial Intelligence-Assisted Gastroenterology- Promises and Pitfalls. Am J Gastroenterol. 2018; 114(3):422-428. DOI: 10.1038/s41395-018-0268-4. View

15.

Akaraborworn O, Chaiwat O, Chatmongkolchart S, Kitsiripant C, Chittawatanarat K, Morakul S . Prediction of massive transfusion in trauma patients in the surgical intensive care units (THAI-SICU study). Chin J Traumatol. 2019; 22(4):219-222. PMC: 6667990. DOI: 10.1016/j.cjtee.2019.04.004. View

16.

Das A, Ben-Menachem T, Farooq F, Cooper G, Chak A, Sivak Jr M . Artificial neural network as a predictive instrument in patients with acute nonvariceal upper gastrointestinal hemorrhage. Gastroenterology. 2007; 134(1):65-74. DOI: 10.1053/j.gastro.2007.10.037. View

17.

Johnson A, Pollard T, Shen L, Lehman L, Feng M, Ghassemi M . MIMIC-III, a freely accessible critical care database. Sci Data. 2016; 3:160035. PMC: 4878278. DOI: 10.1038/sdata.2016.35. View

18.

Cismondi F, Celi L, Fialho A, Vieira S, Reti S, Sousa J . Reducing unnecessary lab testing in the ICU with artificial intelligence. Int J Med Inform. 2013; 82(5):345-58. PMC: 5694620. DOI: 10.1016/j.ijmedinf.2012.11.017. View

19.

Rahman S, Saeian K . Nonvariceal Upper Gastrointestinal Bleeding. Crit Care Clin. 2016; 32(2):223-39. DOI: 10.1016/j.ccc.2015.12.002. View

20.

Futoma J, Simons M, Panch T, Doshi-Velez F, Celi L . The myth of generalisability in clinical research and machine learning in health care. Lancet Digit Health. 2020; 2(9):e489-e492. PMC: 7444947. DOI: 10.1016/S2589-7500(20)30186-2. View