Key result
A data-driven prediction model using preoperative data accurately predicted 30-day, 90-day, and 1-year mortality after colorectal cancer surgery with AUROCs of 0.88, 0.878, and 0.861, respectively.
Why the study?
Existing postoperative mortality risk scores after colorectal cancer resection rely on intra- or postoperative variables or fail to represent contemporary clinical practice.
Observational (n=57,558)
Yes
A data-driven machine learning approach using nationwide health databases successfully developed highly discriminative and well-calibrated prediction models for short-term mortality after colorectal cancer surgery.
Answers are grounded in this paper and cite their sources.
Models for post-CRC surgery mortality may aid risk stratification; leaves open external validation and clinical utility.
Purpose: To develop prediction models for short-term mortality risk assessment following colorectal cancer surgery. Background: Individual risk prediction for mortality following CRC surgery can assist surgeons in clinical decision-making and patient-centered care. Several risk scoring systems exist to assess the risk of postoperative mortality following a CRC resection, but they are based on intra- or postoperative variables or do not represent contemporary clinical practice. Methods: Data was harmonized from four Danish observational health databases into the Observational Medical Outcomes Partnership Common Data Model. With a data-driven approach using the Least Absolute Shrinkage and Selection Operator logistic regression on preoperative data, we developed 30-day, 90-day, and 1-year mortality prediction models. We assessed discriminative performance using the area under the receiver operating characteristic and precision-recall curve and calibration using calibration slope, intercept, and calibration-in-the-large. We additionally assessed model performance in subgroups of curative, palliative, elective, and emergency surgery. Results: A total of 57,558 patients were included in the study population. The model showed good discrimination with an area under the receiver-operating characteristic curve of 0.88, 0.878, and 0.861 for 30-day, 90-day, and 1-year mortality respectively, and a calibration-in-the-large of 1.01, 0.99, and 0.99. Conclusion : We were able to train prediction models for the risk of short-term mortality on a data set of four combined national health databases with good discrimination and calibration.
No takes yet. Share an insight, caveat, or question.
Bräuner et al. (2023) conducted an observational in Colorectal cancer (n=57,558). Preoperative data-driven prediction model (LASSO logistic regression) was evaluated on 30-day, 90-day, and 1-year all-cause mortality. A data-driven prediction model using preoperative data accurately predicted 30-day, 90-day, and 1-year mortality after colorectal cancer surgery with AUROCs of 0.88, 0.878, and 0.861, respectively.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: