Risk Prediction in AMI Shock

Improving Performance of Outcome Prediction for In-patients with Acute Myocardial Infarction Based on Embedding Representation Learned from Electronic Medical Records: Development and Validation Study (Preprint)

Background

The widespread secondary use of electronic medical records (EMRs) promotes health care quality improvement. Representation learning that can automatically extract hidden information from EMR data has gained increasing attention.

Objective

We aimed to propose a patient representation with more feature associations and task-specific feature importance to improve the outcome prediction performance for inpatients with acute myocardial infarction (AMI).

Methods

Medical concepts, including patients’ age, gender, disease diagnoses, laboratory tests, structured radiological features, procedures, and medications, were first embedded into real-value vectors using the improved skip-gram algorithm, where concepts in the context windows were selected by feature association strengths measured by association rule confidence. Then, each patient was represented as the sum of the feature embeddings weighted by the task-specific feature importance, which was applied to facilitate predictive model prediction from global and local perspectives. We finally applied the proposed patient representation into mortality risk prediction for 3010 and 1671 AMI inpatients from a public data set and a private data set, respectively, and compared it with several reference representation methods in terms of the area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC), and F1-score.

Results

Compared with the reference methods, the proposed embedding-based representation showed consistently superior predictive performance on the 2 data sets, achieving mean AUROCs of 0.878 and 0.973, AUPRCs of 0.220 and 0.505, and F1-scores of 0.376 and 0.674 for the public and private data sets, respectively, while the greatest AUROCs, AUPRCs, and F1-scores among the reference methods were 0.847 and 0.939, 0.196 and 0.283, and 0.344 and 0.361 for the public and private data sets, respectively. Feature importance integrated in patient representation reflected features that were also critical in prediction tasks and clinical practice.

Conclusions

The introduction of feature associations and feature importance facilitated an effective patient representation and contributed to prediction performance improvement and model interpretation.

An approach to explore for a sweet spot in randomized trials

OBJECTIVE

The objective of the study was to demonstrate how a conventional randomized trial can be analyzed through a stratified or a matched approach to identify a potential sweet spot where observed differences might be accentuated in the mid range of disease severity.

DESIGN AND SETTING

We review a landmark randomized trial of heart failure patients that tested whether implantable defibrillators reduce mortality (n = 2,521).

RESULTS

Overall, 22% (182/829) of the patients in the defibrillator group died compared with 29% (484/1,692) of patients in the control group. Proportional hazards analysis yielded a modest 25% survival benefit (hazard ratio = 0.75, 95% confidence interval: 0.63 to 0.89). Stratified analysis of the trial yielded a larger 52% survival benefit for those in the middle quintile of disease severity (hazard ratio = 0.48, 95% confidence interval: 0.29 to 0.79). In contrast, little of the survival benefit was explained by patients with the greatest disease severity (hazard ratio = 0.89, 95% confidence interval: 0.69 to 1.15). The discrepancy between crude and stratified analyses could be visualized by graphical displays and replicated with matched comparisons.

CONCLUSION

Our approach for analyzing a randomized trial could help identify a potential sweet spot of an accentuated treatment effect.