Limits...
Utilizing Chinese Admission Records for MACE Prediction of Acute Coronary Syndrome

View Article: PubMed Central - PubMed

ABSTRACT

Background: Clinical major adverse cardiovascular event (MACE) prediction of acute coronary syndrome (ACS) is important for a number of applications including physician decision support, quality of care assessment, and efficient healthcare service delivery on ACS patients. Admission records, as typical media to contain clinical information of patients at the early stage of their hospitalizations, provide significant potential to be explored for MACE prediction in a proactive manner. Methods: We propose a hybrid approach for MACE prediction by utilizing a large volume of admission records. Firstly, both a rule-based medical language processing method and a machine learning method (i.e., Conditional Random Fields (CRFs)) are developed to extract essential patient features from unstructured admission records. After that, state-of-the-art supervised machine learning algorithms are applied to construct MACE prediction models from data. Results: We comparatively evaluate the performance of the proposed approach on a real clinical dataset consisting of 2930 ACS patient samples collected from a Chinese hospital. Our best model achieved 72% AUC in MACE prediction. In comparison of the performance between our models and two well-known ACS risk score tools, i.e., GRACE and TIMI, our learned models obtain better performances with a significant margin. Conclusions: Experimental results reveal that our approach can obtain competitive performance in MACE prediction. The comparison of classifiers indicates the proposed approach has a competitive generality with datasets extracted by different feature extraction methods. Furthermore, our MACE prediction model obtained a significant improvement by comparison with both GRACE and TIMI. It indicates that using admission records can effectively provide MACE prediction service for ACS patients at the early stage of their hospitalizations.

No MeSH data available.


The temporal relationship of data for MACE prediction.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC5036745&req=5

ijerph-13-00912-f003: The temporal relationship of data for MACE prediction.

Mentions: In this study, we extracted patient’s features from admission records mainly based on the two NLP techniques, i.e., RBMLP and CRFs, to construct MACE prediction models. An admission record sample has been shown in Figure 1. Furthermore, to determine whether the patients got MACE in their hospitalization, we recruited 4 clinical engineers to manually annotate the ischemic MACE, including all-cause death, Myocardial infarction, Angina attack, Heart failure, Arrhythmias, Re-revascularization, Transfer to undergo the CABG, Long length of stay, found in patient progress notes. Each progress note was annotated by at least three clinicians and the final results were determined over majority voting criterion by the three clinicians’ annotation results. The temporal relationship of data is illustrated in Figure 3, which indicates we employed the admission records to predict the MACE occurred in patients’ hospitalization.


Utilizing Chinese Admission Records for MACE Prediction of Acute Coronary Syndrome
The temporal relationship of data for MACE prediction.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC5036745&req=5

ijerph-13-00912-f003: The temporal relationship of data for MACE prediction.
Mentions: In this study, we extracted patient’s features from admission records mainly based on the two NLP techniques, i.e., RBMLP and CRFs, to construct MACE prediction models. An admission record sample has been shown in Figure 1. Furthermore, to determine whether the patients got MACE in their hospitalization, we recruited 4 clinical engineers to manually annotate the ischemic MACE, including all-cause death, Myocardial infarction, Angina attack, Heart failure, Arrhythmias, Re-revascularization, Transfer to undergo the CABG, Long length of stay, found in patient progress notes. Each progress note was annotated by at least three clinicians and the final results were determined over majority voting criterion by the three clinicians’ annotation results. The temporal relationship of data is illustrated in Figure 3, which indicates we employed the admission records to predict the MACE occurred in patients’ hospitalization.

View Article: PubMed Central - PubMed

ABSTRACT

Background: Clinical major adverse cardiovascular event (MACE) prediction of acute coronary syndrome (ACS) is important for a number of applications including physician decision support, quality of care assessment, and efficient healthcare service delivery on ACS patients. Admission records, as typical media to contain clinical information of patients at the early stage of their hospitalizations, provide significant potential to be explored for MACE prediction in a proactive manner. Methods: We propose a hybrid approach for MACE prediction by utilizing a large volume of admission records. Firstly, both a rule-based medical language processing method and a machine learning method (i.e., Conditional Random Fields (CRFs)) are developed to extract essential patient features from unstructured admission records. After that, state-of-the-art supervised machine learning algorithms are applied to construct MACE prediction models from data. Results: We comparatively evaluate the performance of the proposed approach on a real clinical dataset consisting of 2930 ACS patient samples collected from a Chinese hospital. Our best model achieved 72% AUC in MACE prediction. In comparison of the performance between our models and two well-known ACS risk score tools, i.e., GRACE and TIMI, our learned models obtain better performances with a significant margin. Conclusions: Experimental results reveal that our approach can obtain competitive performance in MACE prediction. The comparison of classifiers indicates the proposed approach has a competitive generality with datasets extracted by different feature extraction methods. Furthermore, our MACE prediction model obtained a significant improvement by comparison with both GRACE and TIMI. It indicates that using admission records can effectively provide MACE prediction service for ACS patients at the early stage of their hospitalizations.

No MeSH data available.