Related Experiment Videos
Clinical applications of risk-assessment protocols in the management of individual patients
1Dartmouth-Hitchcock Medical Center, Lebanon, New Hampshire 03756, USA.
Insights
Cardiac surgical databases can predict patient outcomes like mortality after coronary artery bypass grafting using analytic techniques. These validated prediction rules aid clinical decision-making and can be expanded for broader applications.
Area of Science:
- Cardiovascular Surgery
- Health Informatics
- Predictive Analytics
Background:
- Cardiac surgical databases traditionally focus on performance comparison.
- Analytic techniques applied to clinical data can create reliable prediction models for surgical outcomes.
- Mortality prediction after coronary artery bypass grafting (CABG) is a key application.
Purpose of the Study:
- To develop and validate a predictive model for in-hospital mortality after CABG.
- To integrate prediction rules with clinical decision-support tools.
- To enhance clinician decision-making by providing data-driven insights.
Main Methods:
- Utilizing data from the Northern New England Cardiovascular Disease Study Group, collected from six regional cardiac institutions.
- Developing a mathematical model based on demographic information, comorbidity data, severity of illness, and outcomes.
- Validating the prediction rule's accuracy and discriminative ability.
Main Results:
- The Northern New England Cardiovascular Disease Study Group mortality prediction rule demonstrated strong predictive and discriminative performance.
- The rule is updated annually with current data.
- Integration with decision-support tools and patient-reported expectations at Dartmouth-Hitchcock Medical Center enhances clinical utility.
Conclusions:
- Prediction rules are valuable decision-support tools but have limitations.
- Accuracy is dependent on consistent data tracking; transferability to new populations requires caution.
- Future efforts should focus on developing and validating similar techniques for complex clinical scenarios.
Background:
Cardiac surgical databases are typically used to compare performance rather than to predict performance. Application of analytic techniques to representative clinical data allows for the creation of highly reliable prediction models for outcomes such as mortality after coronary artery bypass grafting.
Methods:
The Northern New England Cardiovascular Disease Study Group collects clinical data from the six regional cardiac institutions. The four basic components of the one-page clinical data form are demographic information, comorbidity data, severity of illness data, and outcomes. From these, a mathematical model predicts the likelihood of inhospital mortality after coronary artery bypass grafting.
Results:
The Northern New England Cardiovascular Disease Study Group mortality prediction rule was validated and found to predict and discriminate well. It is updated yearly based on the most current data. At Dartmouth-Hitchcock Medical Center, the rule has been combined with other decision-support tools based on American College of Cardiology/American Heart Association indications for coronary artery bypass grafting. These data are compared with data supplied by patients on their expectations for operation and their assessments of acceptable mortality risk. By expanding the database to include variables such as 5-year survival and additional outcomes, and additional interventions, an "electronic second opinion" is made available to clinicians.
Conclusions:
Although experience with decision-support tools has been positive, prediction rules have certain limitations. Their accuracy depends on data that are consistently tracked; thus, transfer to other patient populations must be approached with caution. The challenge for the future is to develop and validate similar techniques that apply to more difficult clinical situations.