LASSO-Based Machine Learning Algorithm for Prediction of PICS Associated with Sepsis

Overview

Journal Infect Drug Resist

Publisher Dove Medical Press

Date 2024 Jul 8

PMID 38974318

Authors

Kangping Hui

Chengying Hong

Yihan Xiong

Jinquan Xia

Wei Huang

Andi Xia

Shunyao Xu

Yuting Chen

Zhongwei Zhang

Huaisheng Chen

Affiliations

Soon will be listed here.

Abstract

Introduction: This study aims to establish a comprehensive, multi-level approach for tackling tropical diseases by proactively anticipating and managing Persistent Inflammation, Immunosuppression, and Catabolism Syndrome (PICS) within the initial 14 days of Intensive Care Unit (ICU) admission. The primary objective is to amalgamate a diverse array of indicators and pathogenic microbial data to pinpoint pivotal predictive variables, enabling effective intervention specifically tailored to the context of tropical diseases.

Methods: A focused analysis was conducted on 1733 patients admitted to the ICU between December 2016 and July 2019. Utilizing the Least Absolute Shrinkage and Selection Operator (LASSO) regression, disease severity and laboratory indices were scrutinized. The identified variables served as the foundation for constructing a predictive model designed to forecast the occurrence of PICS.

Results: Among the subjects, 13.79% met the diagnostic criteria for PICS, correlating with a mortality rate of 38.08%. Key variables, including red-cell distribution width coefficient of variation (RDW-CV), hemofiltration (HF), mechanical ventilation (MV), Norepinephrine (NE), lactic acidosis, and multiple-drug resistant bacteria (MDR) infection, were identified through LASSO regression. The resulting predictive model exhibited a robust performance with an Area Under the Curve (AUC) of 0.828, an accuracy of 0.862, and a specificity of 0.977. Subsequent validation in an independent cohort yielded an AUC of 0.848.

Discussion: The acquisition of RDW-CV, HF requirement, MV requirement, NE requirement, lactic acidosis, and MDR upon ICU admission emerges as a pivotal factor for prognosticating PICS onset in the context of tropical diseases. This study highlights the potential for significant improvements in clinical outcomes through the implementation of timely and targeted interventions tailored specifically to the challenges posed by tropical diseases.

References

Mankowski R, Anton S, Ghita G, Brumback B, Darden D, Bihorac A . Older Adults Demonstrate Biomarker Evidence of the Persistent Inflammation, Immunosuppression, and Catabolism Syndrome (PICS) After Sepsis. J Gerontol A Biol Sci Med Sci. 2021; 77(1):188-196. PMC: 8751807. DOI: 10.1093/gerona/glab080. View

Coggins S, Glaser K . Updates in Late-Onset Sepsis: Risk Assessment, Therapy, and Outcomes. Neoreviews. 2022; 23(11):738-755. PMC: 9675597. DOI: 10.1542/neo.23-10-e738. View

Jeffcote T, Foong M, Gold G, Glassford N, Robbins R, Iwashyna T . Patient characteristics, ICU-specific supports, complications, and outcomes of persistent critical illness. J Crit Care. 2019; 54:250-255. DOI: 10.1016/j.jcrc.2019.08.023. View

Wintermann G, Weidner K, Strauss B, Rosendahl J, Petrowski K . Predictors of posttraumatic stress and quality of life in family members of chronically critically ill patients after intensive care. Ann Intensive Care. 2016; 6(1):69. PMC: 4954797. DOI: 10.1186/s13613-016-0174-0. View

Gupta S, Lubree H, Sanghavi S . Compromised Nutritional Status as a Risk Factor for the Incidence of Nosocomial Infections. Cureus. 2023; 15(10):e46502. PMC: 10624772. DOI: 10.7759/cureus.46502. View

Farrelly K, Wardell J, Marsden E, Scarfe M, Najdzionek P, Turna J . The Impact of Recreational Cannabis Legalization on Cannabis Use and Associated Outcomes: A Systematic Review. Subst Abuse. 2023; 17:11782218231172054. PMC: 10176789. DOI: 10.1177/11782218231172054. View

Ding R, Qiu J, Liu B, Li X, Sun Y, Liang Y . [A retrospective clinical study of sixty-three cases with persistent inflammation immunosuppression and catabolism syndrome]. Zhonghua Nei Ke Za Zhi. 2016; 55(12):941-944. DOI: 10.3760/cma.j.issn.0578-1426.2016.12.007. View

Bassetti M, De Waele J, Eggimann P, Garnacho-Montero J, Kahlmeter G, Menichetti F . Preventive and therapeutic strategies in critically ill patients with highly resistant bacteria. Intensive Care Med. 2015; 41(5):776-95. PMC: 7080151. DOI: 10.1007/s00134-015-3719-z. View

Barker G, Winer J, Guirgis F, Reddy S . HDL and persistent inflammation immunosuppression and catabolism syndrome. Curr Opin Lipidol. 2021; 32(5):315-322. PMC: 8416792. DOI: 10.1097/MOL.0000000000000782. View

10.

Efron P, Mohr A, Bihorac A, Horiguchi H, Hollen M, Segal M . Persistent inflammation, immunosuppression, and catabolism and the development of chronic critical illness after surgery. Surgery. 2018; 164(2):178-184. PMC: 6056337. DOI: 10.1016/j.surg.2018.04.011. View

11.

Nakamura K, Ogura K, Ohbe H, Goto T . Clinical Criteria for Persistent Inflammation, Immunosuppression, and Catabolism Syndrome: An Exploratory Analysis of Optimal Cut-Off Values for Biomarkers. J Clin Med. 2022; 11(19). PMC: 9571101. DOI: 10.3390/jcm11195790. View

12.

Okada K, Ohde S, Yagi T, Hara Y, Yokobori S . Development and validation of prediction scores for the outcome associated with persistent inflammation, immunosuppression, and catabolism syndrome among patients with trauma. Trauma Surg Acute Care Open. 2023; 8(1):e001134. PMC: 10357651. DOI: 10.1136/tsaco-2023-001134. View

13.

Kataria S, Singh O, Juneja D, Goel A, Bhide M, Yadav D . Hypoperfusion context as a predictor of 28-d all-cause mortality in septic shock patients: A comparative observational study. World J Clin Cases. 2023; 11(16):3765-3779. PMC: 10294150. DOI: 10.12998/wjcc.v11.i16.3765. View

14.

Singer M, Deutschman C, Seymour C, Shankar-Hari M, Annane D, Bauer M . The Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3). JAMA. 2016; 315(8):801-10. PMC: 4968574. DOI: 10.1001/jama.2016.0287. View

15.

Okazaki T, Kawakami D, Fujitani S, Shinohara N, Kawakita K, Kuroda Y . Potential Interaction Between Sepsis and Acute Respiratory Distress Syndrome and Effect on the 6-Month Clinical Outcomes: A Preliminary Secondary Analysis of a Prospective Observational Study. J Intensive Care Med. 2022; 38(1):60-69. DOI: 10.1177/08850666221107559. View

16.

Wang C, Wang X, Zhang H, Liu D, Zhang C . Effect of Norepinephrine on Peripheral Perfusion Index and Its Association With the Prognosis of Patients With Sepsis. J Intensive Care Med. 2023; 39(1):21-27. DOI: 10.1177/08850666231187333. View

17.

Singh P, Holmen J . Multidrug-Resistant Infections in the Developing World. Pediatr Clin North Am. 2021; 69(1):141-152. DOI: 10.1016/j.pcl.2021.09.003. View

18.

Suganuma S, Idei M, Nakano H, Koyama Y, Hashimoto H, Yokoyama N . Impact of Persistent Inflammation, Immunosuppression, and Catabolism Syndrome during Intensive Care Admission on Each Post-Intensive Care Syndrome Component in a PICS Clinic. J Clin Med. 2023; 12(16). PMC: 10455637. DOI: 10.3390/jcm12165427. View

19.

Kobayashi H, Uchino S, Takinami M, Uezono S . The Impact of Ventilator-Associated Events in Critically Ill Subjects With Prolonged Mechanical Ventilation. Respir Care. 2017; 62(11):1379-1386. DOI: 10.4187/respcare.05073. View

20.

Eldem I, Almekdash M, Almadani O, Levent F, Al-Rahawan M . Red blood cell distribution width as a potential inflammatory marker in pediatric osteomyelitis. Proc (Bayl Univ Med Cent). 2023; 36(4):443-447. PMC: 10269384. DOI: 10.1080/08998280.2023.2209921. View