Parsimonious Machine Learning Models to Predict Resource Use in Cardiac Surgery Across a Statewide Collaborative

Overview

Journal JTCVS Open

Specialty Cardiology & Vascular Diseases

Date 2022 Sep 29

PMID 36172420

Authors

Arjun Verma

Yas Sanaiha

Joseph Hadaya

Anthony Jason Maltagliati

Zachary Tran

Ramin Ramezani

Richard J Shemin

Peyman Benharash

Affiliations

Soon will be listed here.

Abstract

Objective: We sought to several develop parsimonious machine learning models to predict resource utilization and clinical outcomes following cardiac operations using only preoperative factors.

Methods: All patients undergoing coronary artery bypass grafting and/or valve operations were identified in the 2015-2021 University of California Cardiac Surgery Consortium repository. The primary end point of the study was length of stay (LOS). Secondary endpoints included 30-day mortality, acute kidney injury, reoperation, postoperative blood transfusion and duration of intensive care unit admission (ICU LOS). Linear regression, gradient boosted machines, random forest, extreme gradient boosting predictive models were developed. The coefficient of determination and area under the receiver operating characteristic (AUC) were used to compare models. Important predictors of increased resource use were identified using SHapley summary plots.

Results: Compared with all other modeling strategies, gradient boosted machines demonstrated the greatest performance in the prediction of LOS (coefficient of determination, 0.42), ICU LOS (coefficient of determination, 0.23) and 30-day mortality (AUC, 0.69). Advancing age, reduced hematocrit, and multiple-valve procedures were associated with increased LOS and ICU LOS. Furthermore, the gradient boosted machine model best predicted acute kidney injury (AUC, 0.76), whereas random forest exhibited greatest discrimination in the prediction of postoperative transfusion (AUC, 0.73). We observed no difference in performance between modeling strategies for reoperation (AUC, 0.80).

Conclusions: Our findings affirm the utility of machine learning in the estimation of resource use and clinical outcomes following cardiac operations. We identified several risk factors associated with increased resource use, which may be used to guide case scheduling in times of limited hospital capacity.

Citing Articles

ICD-10 based machine learning models outperform the Trauma and Injury Severity Score (TRISS) in survival prediction.

Tran Z, Verma A, Wurdeman T, Burruss S, Mukherjee K, Benharash P PLoS One. 2022; 17(10):e0276624.

PMID: 36301826 PMC: 9612528. DOI: 10.1371/journal.pone.0276624.

References

Bose S, Dasani S, Roberts S, Wirtalla C, DeMatteo R, Doherty G . The Cost of Quarantine: Projecting the Financial Impact of Canceled Elective Surgery on the Nation's Hospitals. Ann Surg. 2021; 273(5):844-849. DOI: 10.1097/SLA.0000000000004766. View

Engelman D, Lother S, George I, Ailawadi G, Atluri P, Grant M . Ramping Up Delivery of Cardiac Surgery During the COVID-19 Pandemic: A Guidance Statement From The Society of Thoracic Surgeons COVID-19 Task Force. Ann Thorac Surg. 2020; 110(2):712-717. PMC: 7215160. DOI: 10.1016/j.athoracsur.2020.05.002. View

Kilic A, Goyal A, Miller J, Gjekmarkaj E, Tam W, Gleason T . Predictive Utility of a Machine Learning Algorithm in Estimating Mortality Risk in Cardiac Surgery. Ann Thorac Surg. 2019; 109(6):1811-1819. DOI: 10.1016/j.athoracsur.2019.09.049. View

Shahian D, Jacobs J, Badhwar V, Kurlansky P, Furnary A, Cleveland Jr J . The Society of Thoracic Surgeons 2018 Adult Cardiac Surgery Risk Models: Part 1-Background, Design Considerations, and Model Development. Ann Thorac Surg. 2018; 105(5):1411-1418. DOI: 10.1016/j.athoracsur.2018.03.002. View

Almashrafi A, Elmontsri M, Aylin P . Systematic review of factors influencing length of stay in ICU after adult cardiac surgery. BMC Health Serv Res. 2016; 16:318. PMC: 4966741. DOI: 10.1186/s12913-016-1591-3. View

Kirmani B, Mazhar K, Saleh H, Ward A, Shaw M, Fabri B . External validity of the Society of Thoracic Surgeons risk stratification tool for deep sternal wound infection after cardiac surgery in a UK population. Interact Cardiovasc Thorac Surg. 2013; 17(3):479-84. PMC: 3745138. DOI: 10.1093/icvts/ivt222. View

Tran Z, Chervu N, Williamson C, Verma A, Hadaya J, Gandjian M . The Impact of Expedited Discharge on 30-Day Readmission After Lung Resection: A National Study. Ann Thorac Surg. 2021; 113(4):1274-1281. DOI: 10.1016/j.athoracsur.2021.04.009. View

Tseng P, Chen Y, Wang C, Chiu K, Peng Y, Hsu S . Prediction of the development of acute kidney injury following cardiac surgery by machine learning. Crit Care. 2020; 24(1):478. PMC: 7395374. DOI: 10.1186/s13054-020-03179-9. View

Tzeng C, Teshome M, Katz M, Weinberg J, Lai S, Antonoff M . Cancer Surgery Scheduling During and After the COVID-19 First Wave: The MD Anderson Cancer Center Experience. Ann Surg. 2020; 272(2):e106-e111. PMC: 7373457. DOI: 10.1097/SLA.0000000000004092. View

10.

Shimabukuro D, Barton C, Feldman M, Mataraso S, Das R . Effect of a machine learning-based severe sepsis prediction algorithm on patient survival and hospital length of stay: a randomised clinical trial. BMJ Open Respir Res. 2018; 4(1):e000234. PMC: 5687546. DOI: 10.1136/bmjresp-2017-000234. View

11.

Chan V, Ahrari A, Ruel M, Elmistekawy E, Hynes M, Mesana T . Perioperative deaths after mitral valve operations may be overestimated by contemporary risk models. Ann Thorac Surg. 2014; 98(2):605-10. DOI: 10.1016/j.athoracsur.2014.05.011. View

12.

Ad N, Luc J, Nguyen T . Cardiac surgery in North America and coronavirus disease 2019 (COVID-19): Regional variability in burden and impact. J Thorac Cardiovasc Surg. 2020; 162(3):893-903.e4. PMC: 7330597. DOI: 10.1016/j.jtcvs.2020.06.077. View

13.

Lafaro R, Pothula S, Kubal K, Inchiosa M, Pothula V, Yuan S . Neural Network Prediction of ICU Length of Stay Following Cardiac Surgery Based on Pre-Incision Variables. PLoS One. 2015; 10(12):e0145395. PMC: 4692524. DOI: 10.1371/journal.pone.0145395. View

14.

Salenger R, Etchill E, Ad N, Matthew T, Alejo D, Whitman G . The Surge After the Surge: Cardiac Surgery Post-COVID-19. Ann Thorac Surg. 2020; 110(6):2020-2025. PMC: 7196543. DOI: 10.1016/j.athoracsur.2020.04.018. View

15.

OBrien S, Feng L, He X, Xian Y, Jacobs J, Badhwar V . The Society of Thoracic Surgeons 2018 Adult Cardiac Surgery Risk Models: Part 2-Statistical Methods and Results. Ann Thorac Surg. 2018; 105(5):1419-1428. DOI: 10.1016/j.athoracsur.2018.03.003. View

16.

Prachand V, Milner R, Angelos P, Posner M, Fung J, Agrawal N . Medically Necessary, Time-Sensitive Procedures: Scoring System to Ethically and Efficiently Manage Resource Scarcity and Provider Risk During the COVID-19 Pandemic. J Am Coll Surg. 2020; 231(2):281-288. PMC: 7195575. DOI: 10.1016/j.jamcollsurg.2020.04.011. View

17.

Farrington W, Robinson N, Rahouma M, Lau C, Hameed I, Iannacone E . Cardiac Surgery Outcomes in an Epicenter of the COVID-19 Pandemic. Semin Thorac Cardiovasc Surg. 2021; 34(1):182-188. PMC: 7801821. DOI: 10.1053/j.semtcvs.2021.01.005. View

18.

Daghistani T, Elshawi R, Sakr S, Ahmed A, Al-Thwayee A, Al-Mallah M . Predictors of in-hospital length of stay among cardiac patients: A machine learning approach. Int J Cardiol. 2019; 288:140-147. DOI: 10.1016/j.ijcard.2019.01.046. View

19.

Messaoudi N, De Cocker J, Stockman B, Bossaert L, Rodrigus I . Prediction of prolonged length of stay in the intensive care unit after cardiac surgery: the need for a multi-institutional risk scoring system. J Card Surg. 2008; 24(2):127-33. DOI: 10.1111/j.1540-8191.2008.00716.x. View

20.

Afflu D, Seese L, Sultan I, Gleason T, Wang Y, Navid F . Very Early Discharge After Coronary Artery Bypass Grafting Does Not Affect Readmission or Survival. Ann Thorac Surg. 2020; 111(3):906-913. DOI: 10.1016/j.athoracsur.2020.05.159. View