Development and validation of machine learning models to identify high-risk surgical patients using automatically curated electronic health record data (Pythia): A retrospective, single-site study

PLoS Med. 2018 Nov 27;15(11):e1002701. doi: 10.1371/journal.pmed.1002701. eCollection 2018 Nov.

Abstract

Background: Pythia is an automated, clinically curated surgical data pipeline and repository housing all surgical patient electronic health record (EHR) data from a large, quaternary, multisite health institute for data science initiatives. In an effort to better identify high-risk surgical patients from complex data, a machine learning project trained on Pythia was built to predict postoperative complication risk.

Methods and findings: A curated data repository of surgical outcomes was created using automated SQL and R code that extracted and processed patient clinical and surgical data across 37 million clinical encounters from the EHRs. A total of 194 clinical features including patient demographics (e.g., age, sex, race), smoking status, medications, comorbidities, procedure information, and proxies for surgical complexity were constructed and aggregated. A cohort of 66,370 patients that had undergone 99,755 invasive procedural encounters between January 1, 2014, and January 31, 2017, was studied further for the purpose of predicting postoperative complications. The average complication and 30-day postoperative mortality rates of this cohort were 16.0% and 0.51%, respectively. Least absolute shrinkage and selection operator (lasso) penalized logistic regression, random forest models, and extreme gradient boosted decision trees were trained on this surgical cohort with cross-validation on 14 specific postoperative outcome groupings. Resulting models had area under the receiver operator characteristic curve (AUC) values ranging between 0.747 and 0.924, calculated on an out-of-sample test set from the last 5 months of data. Lasso penalized regression was identified as a high-performing model, providing clinically interpretable actionable insights. Highest and lowest performing lasso models predicted postoperative shock and genitourinary outcomes with AUCs of 0.924 (95% CI: 0.901, 0.946) and 0.780 (95% CI: 0.752, 0.810), respectively. A calculator requiring input of 9 data fields was created to produce a risk assessment for the 14 groupings of postoperative outcomes. A high-risk threshold (15% risk of any complication) was determined to identify high-risk surgical patients. The model sensitivity was 76%, with a specificity of 76%. Compared to heuristics that identify high-risk patients developed by clinical experts and the ACS NSQIP calculator, this tool performed superiorly, providing an improved approach for clinicians to estimate postoperative risk for patients. Limitations of this study include the missingness of data that were removed for analysis.

Conclusions: Extracting and curating a large, local institution's EHR data for machine learning purposes resulted in models with strong predictive performance. These models can be used in clinical settings as decision support tools for identification of high-risk patients as well as patient evaluation and care management. Further work is necessary to evaluate the impact of the Pythia risk calculator within the clinical workflow on postoperative outcomes and to optimize this data flow for future machine learning efforts.

Publication types

  • Research Support, Non-U.S. Gov't
  • Validation Study

MeSH terms

  • Adolescent
  • Adult
  • Aged
  • Automation
  • Comorbidity
  • Data Mining / methods*
  • Electronic Health Records*
  • Female
  • Health Status
  • Humans
  • Machine Learning*
  • Male
  • Middle Aged
  • Postoperative Complications / etiology*
  • Reproducibility of Results
  • Retrospective Studies
  • Risk Assessment
  • Risk Factors
  • Surgical Procedures, Operative / adverse effects*
  • Young Adult

Grant support

KC and SK were partially supported by the Duke Institute for Health Innovation Clinical Research and Innovation Scholarship. EL was supported the Duke Forge graduate fellowship. MTH was supported by the U.S. Health Resources and Services Administration Geriatric Workforce Enhancement Program Grant: U1QHP28708. This study was funded in part by a Duke Institute for Health Innovation (DIHI, https://dihi.org/) pilot grant. DIHI employees participated in this study and were involved in the study design, data collection and analysis, and preparation of the manuscript. The Duke University Department of Surgery is supporting the continued development of this project. No funders had a role in the decision to publish. No additional external funding was received for this study.