Development and multicentre validation of the FLEX score: personalised preoperative surgical risk prediction using attention-based ICD-10 and Current Procedural Terminology set embeddings.

adverse surgical outcomes billing codes machine learning multicentre study postoperative outcome risk prediction surgical comorbidities

Journal

British journal of anaesthesia
ISSN: 1471-6771
Titre abrégé: Br J Anaesth
Pays: England
ID NLM: 0372541

Informations de publication

Date de publication:
05 Jan 2024
Historique:
received: 29 06 2023
revised: 17 11 2023
accepted: 26 11 2023
medline: 7 1 2024
pubmed: 7 1 2024
entrez: 6 1 2024
Statut: aheadofprint

Résumé

Preoperative knowledge of surgical risks can improve perioperative care and patient outcomes. However, assessments requiring clinician examination of patients or manual chart review can be too burdensome for routine use. We conducted a multicentre retrospective study of 243 479 adult noncardiac surgical patients at four hospitals within the Mass General Brigham (MGB) system in the USA. We developed a machine learning method using routinely collected coding and patient characteristics data from the electronic health record which predicts 30-day mortality, 30-day readmission, discharge to long-term care, and hospital length of stay. Our method, the Flexible Surgical Set Embedding (FLEX) score, achieved state-of-the-art performance to identify comorbidities that significantly contribute to the risk of each adverse outcome. The contributions of comorbidities are weighted based on patient-specific context, yielding personalised risk predictions. Understanding the significant drivers of risk of adverse outcomes for each patient can inform clinicians of potential targets for intervention. FLEX utilises information from a wider range of medical diagnostic and procedural codes than previously possible and can adapt to different coding practices to accurately predict adverse postoperative outcomes.

Sections du résumé

BACKGROUND BACKGROUND
Preoperative knowledge of surgical risks can improve perioperative care and patient outcomes. However, assessments requiring clinician examination of patients or manual chart review can be too burdensome for routine use.
METHODS METHODS
We conducted a multicentre retrospective study of 243 479 adult noncardiac surgical patients at four hospitals within the Mass General Brigham (MGB) system in the USA. We developed a machine learning method using routinely collected coding and patient characteristics data from the electronic health record which predicts 30-day mortality, 30-day readmission, discharge to long-term care, and hospital length of stay.
RESULTS RESULTS
Our method, the Flexible Surgical Set Embedding (FLEX) score, achieved state-of-the-art performance to identify comorbidities that significantly contribute to the risk of each adverse outcome. The contributions of comorbidities are weighted based on patient-specific context, yielding personalised risk predictions. Understanding the significant drivers of risk of adverse outcomes for each patient can inform clinicians of potential targets for intervention.
CONCLUSIONS CONCLUSIONS
FLEX utilises information from a wider range of medical diagnostic and procedural codes than previously possible and can adapt to different coding practices to accurately predict adverse postoperative outcomes.

Identifiants

DOI: 10.1016/j.bja.2023.11.039 PMID: 38184474
pubmed: 38184474
pii: S0007-0912(23)00665-7
doi: 10.1016/j.bja.2023.11.039
pii:
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Informations de copyright

Copyright © 2023 The Authors. Published by Elsevier Ltd.. All rights reserved.

Auteurs

Ran Liu (R)

Department of Anesthesia, Critical Care and Pain Medicine, Massachusetts General Hospital, Boston, MA, USA; Harvard Medical School, Boston, MA, USA.

Tom A D Stone (TAD)

Department of Anesthesia, Critical Care and Pain Medicine, Massachusetts General Hospital, Boston, MA, USA; Harvard Medical School, Boston, MA, USA.

Praachi Raje (P)

Harvard Medical School, Boston, MA, USA; Department of Surgery, Massachusetts General Hospital, Boston, MA, USA.

Rory V Mather (RV)

Department of Anesthesia, Critical Care and Pain Medicine, Massachusetts General Hospital, Boston, MA, USA; Harvard Medical School, Boston, MA, USA; Harvard-MIT Program in Health Sciences and Technology, Cambridge, MA, USA.

Laura A Santa Cruz Mercado (LA)

Department of Anesthesia, Critical Care and Pain Medicine, Massachusetts General Hospital, Boston, MA, USA; Harvard Medical School, Boston, MA, USA; Department of Anesthesia, Critical Care and Pain Medicine, Beth Israel Deaconess Hospital, Boston, MA, USA.

Kishore Bharadwaj (K)

Department of Anesthesia, Critical Care and Pain Medicine, Massachusetts General Hospital, Boston, MA, USA; Harvard Medical School, Boston, MA, USA.

Jasmine Johnson (J)

Department of Anesthesia, Critical Care and Pain Medicine, Massachusetts General Hospital, Boston, MA, USA; Harvard Medical School, Boston, MA, USA.

Masaya Higuchi (M)

Harvard Medical School, Boston, MA, USA; Department of Medicine, Division of Palliative Care and Geriatric Medicine, Massachusetts General Hospital, Boston, MA, USA.

Ryan D Nipp (RD)

Section of Hematology/Oncology, Department of Internal Medicine, University of Oklahoma Health Sciences Center, Stephenson Cancer Center, Oklahoma City, OK, USA.

Hiroko Kunitake (H)

Harvard Medical School, Boston, MA, USA; Department of Surgery, Massachusetts General Hospital, Boston, MA, USA.

Patrick L Purdon (PL)

Department of Anesthesia, Critical Care and Pain Medicine, Massachusetts General Hospital, Boston, MA, USA; Harvard Medical School, Boston, MA, USA. Electronic address: ppurdon@stanford.edu.

Classifications MeSH