Format

Send to

Choose Destination
J Med Syst. 2018 May 30;42(7):123. doi: 10.1007/s10916-018-0977-7.

A System for Automated Determination of Perioperative Patient Acuity.

Author information

1
Department of Biomedical Informatics, Vanderbilt University, 2525 West End Ave, Suite 14113, Nashville, TN, 37203, USA. linda.zhang92@vanderbilt.edu.
2
Department of Biomedical Informatics, Vanderbilt University, 2525 West End Ave, Suite 14113, Nashville, TN, 37203, USA.
3
Department of Anesthesiology, Vanderbilt University, 1301 Medical Center Dr, Suite 4648, Nashville, TN, 37232, USA.

Abstract

The widely used American Society of Anesthesiologists Physical Status (ASA PS) classification is subjective, requires manual clinician review to score, and has limited granularity. Our objective was to develop a system that automatically generates an ASA PS with finer granularity by creating a continuous ASA PS score. Supervised machine learning methods were used to create a model that predicts a patient's ASA PS on a continuous scale using the patient's home medications and comorbidities. Three different types of predictive models were trained: regression models, ordinal models, and classification models. The performance and agreement of each model to anesthesiologists were compared by calculating the mean squared error (MSE), rounded MSE and Cohen's Kappa on a holdout set. To assess model performance on continuous ASA PS, model rankings were compared to two anesthesiologists on a subset of ASA PS 3 case pairs. The random forest regression model achieved the best MSE and rounded MSE. A model consisting of three random forest classifiers (split model) achieved the best Cohen's Kappa. The model's agreement with our anesthesiologists on the ASA PS 3 case pairs yielded fair to moderate Kappa values. The results suggest that the random forest split classification model can predict ASA PS with agreement similar to that of anesthesiologists reported in literature and produce a continuous score in which agreement in accurately judging granularity is fair to moderate.

KEYWORDS:

ASA PS; ASA prediction; Anesthesiologists; Machine learning

PMID:
29846806
DOI:
10.1007/s10916-018-0977-7
[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Springer
Loading ...
Support Center