Use of Machine Learning to Develop and Evaluate Models Using Preoperative and Intraoperative Data to Identify Risks of Postoperative Complications (2021-03-01T00:00:00.000000Z)

TL;DR

It is suggested that machine learning models using preoperative and intraoperative data can predict postoperative complications and generate reliable and clinically meaningful interpretations for supporting clinical decisions along the perioperative care continuum.

Abstract

Key Points Question Can machine learning models predict patient risks of postoperative complications related to pneumonia, acute kidney injury, deep vein thrombosis, delirium, and pulmonary embolism? Findings In a cohort study of 111 888 operations at a large academic medical center, machine learning algorithms exhibited high areas under the receiver operating characteristic curve for predicting the risk of postoperative complications related to pneumonia, acute kidney injury, deep vein thrombosis, pulmonary embolism, and delirium. Meaning These findings suggest that machine learning models using preoperative and intraoperative data can predict postoperative complications and generate reliable and clinically meaningful interpretations for supporting clinical decisions along the perioperative care continuum.

Authors

Bing Xue

1 papers

Dingwen Li

1 papers

Chenyang Lu

1 papers

References46 items

Ascertaining Design Requirements for Postoperative Care Transition Interventions

Assessment of the Accuracy of Using ICD-9 Diagnosis Codes to Identify Pneumonia Etiology in Patients Hospitalized With Pneumonia

Development and validation of a deep neural network model to predict postoperative mortality, acute kidney injury, and reintubation using a single feature set

TL;DR

Abstract

Authors

References46 items

Ascertaining Design Requirements for Postoperative Care Transition Interventions

Assessment of the Accuracy of Using ICD-9 Diagnosis Codes to Identify Pneumonia Etiology in Patients Hospitalized With Pneumonia

Development and validation of a deep neural network model to predict postoperative mortality, acute kidney injury, and reintubation using a single feature set

Deep-learning model for predicting 30-day postoperative mortality.

CXPlain: Causal Explanations for Model Interpretation under Uncertainty

Prospective and External Evaluation of a Machine Learning Model to Predict In-Hospital Mortality

Recent Advances in Preventing and Managing Postoperative Delirium

Explaining individual predictions when features are dependent: More accurate approximations to Shapley values

Physician derived versus administrative data in identifying surgical complications. Fact versus Fiction.

Prevention of Postoperative Pneumonia in Noncardiac Surgical Patients: A Prospective Study Using the National Surgical Quality Improvement Program Database

Machine learning for real-time prediction of complications in critical care: a retrospective study.

Leveraging electronic health records for predictive modeling of post-surgical complications

Explainable machine-learning predictions for the prevention of hypoxaemia during surgery

Using machine learning techniques to develop forecasting algorithms for postoperative complications: protocol for a retrospective study

A Unified Approach to Interpreting Model Predictions

Identifying patients at higher risk of pneumonia after lung resection.

Postoperative pulmonary complications

Prevention of cardiac surgery-associated AKI by implementing the KDIGO guidelines in high risk patients identified by biomarkers: the PrevAKI randomized controlled trial

Imbalanced-learn: A Python Toolbox to Tackle the Curse of Imbalanced Datasets in Machine Learning

Convergent Validity of Three Methods for Measuring Postoperative Complications

TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems

XGBoost: A Scalable Tree Boosting System

EVALUATING RISK-PREDICTION MODELS USING DATA FROM ELECTRONIC HEALTH RECORDS.

“Why Should I Trust You?”: Explaining the Predictions of Any Classifier

Classification of hospital acquired complications using temporal clinical information from a large electronic health record

Postoperative Delirium in Cardiac Surgery: An Unavoidable Menace?

The validity of ICD codes coupled with imaging procedure codes for identifying acute venous thromboembolism using administrative data

Exploring the Frontier of Electronic Health Record Surveillance: The Case of Postoperative Complications

Postoperative complications and implications on patient-centered outcomes.

Older women with dementia can perform fast alternating forearm movements and performance is correlated with tests of lower extremity function

Delirium in the ICU: an overview

MissForest - non-parametric missing value imputation for mixed-type data

Multiple imputation by chained equations: what is it and how does it work?

Surgical site infections.

Scikit-learn: Machine Learning in Python

Using administrative data to identify surgical adverse events: an introduction to the Patient Safety Indicators.

Preventing deep vein thrombosis in hospital inpatients

Surgical risk factors, morbidity, and mortality in elderly patients.

The relationship between Precision-Recall and ROC curves

Antimicrobial prophylaxis for surgery: an advisory statement from the National Surgical Infection Prevention Project.

Surgical Outcomes for Patients Aged 80 and Older: Morbidity and Mortality from Major Noncardiac Surgery

Adverse events in surgical patients in Australia.

Complications in surgical patients.

The incidence and nature of surgical adverse events in Colorado and Utah in 1992.

Antimicrobial Prophylaxis for Surgery: An Advisory Statement From the National Surgical Infection Prevention Project

JAMA Network Open | Anesthesiology Use of Machine Learning to Identify Risks of Postoperative Complications JAMA Network Open

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names