Key result
Postoperative machine learning models incorporating intraoperative EMR data achieved high predictive performance for surgical site infections and leaks, outperforming preoperative models.
Why the study?
Current machine learning-based risk prediction models are frequently black-box models whose patterns may not reflect medically relevant relationships, limiting actionable clinical insights.
Observational (n=3,440)
No
Explainable machine learning models utilizing EMR data can accurately predict postoperative complications, with postoperative models incorporating intraoperative data outperforming preoperative models.
Answers are grounded in this paper and cite their sources.
Postoperative models may improve complication prediction via EMR data; hypothesis-generating for prospective validation before clinical use.
Machine-learning based risk prediction models have the potential to improve patient outcomes by assessing risk more accurately than clinicians. Significant additional value lies in these models providing feedback about the factors that amplify an individual patient's risk. Identification of risk factors enables more informed decisions on interventions to mitigate or ameliorate modifiable factors. For these reasons, risk prediction models must be explainable and grounded on medical knowledge. Current machine learning-based risk prediction models are frequently 'black-box' models whose inner workings cannot be understood easily, making it difficult to define risk drivers. Since machine learning models follow patterns in the data rather than looking for medically relevant relationships, possible risk factors identified by these models do not necessarily translate into actionable insights for clinicians. Here, we use the example of risk assessment for postoperative complications to demonstrate how explainable and medically grounded risk prediction models can be developed. Pre- and postoperative risk prediction models are trained based on clinically relevant inputs extracted from electronic medical record data. We show that these models have similar predictive performance as models that incorporate a wider range of inputs and explain the models' decision-making process by visualizing how different model inputs and their values affect the models' predictions.
No takes yet. Share an insight, caveat, or question.
Twick et al. (2022) conducted an observational in Postoperative complications (surgical site infection and leaks) (n=3,440). Postoperative machine learning risk prediction model vs. Preoperative risk prediction model was evaluated on Area under the ROC curve (AUC) for prediction of surgical site infection (SSI). Postoperative machine learning models incorporating intraoperative EMR data achieved high predictive performance for surgical site infections and leaks, outperforming preoperative models.
Synapse has enriched 10 related papers. Consider them for comparative context: