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.


Averaged ROC with 95% CI band over 10-times repetition (†: RBMLP method; ‡: CRFs method).
© Copyright Policy
Related In: Results  -  Collection

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

ijerph-13-00912-f004: Averaged ROC with 95% CI band over 10-times repetition (†: RBMLP method; ‡: CRFs method).

Mentions: In Figure 4 and Figure 5, we present a more comprehensive comparison between the four learned models and the baseline models. As shown in Figure 4, for the averaged ROC over 10-time repetition, all our learned models outperform the baseline models by a considerable margin in MACE prediction and there is little difference between the four learned models’ performances and confident intervals. Moreover, the influences of changes of sample sizes on AUC values were illustrated in Figure 5. We randomly selected the same proportion of samples from positive and negative samples to construct datasets in different sizes. The AUC values of all four models gradually ascend in overall trend along with the increases of the sample sizes. And all models were able to achieve relatively stable performances with 20% of all patient samples, which illustrates that our models can obtain good performances under a small sample size.


Utilizing Chinese Admission Records for MACE Prediction of Acute Coronary Syndrome
Averaged ROC with 95% CI band over 10-times repetition (†: RBMLP method; ‡: CRFs method).
© Copyright Policy
Related In: Results  -  Collection

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

ijerph-13-00912-f004: Averaged ROC with 95% CI band over 10-times repetition (†: RBMLP method; ‡: CRFs method).
Mentions: In Figure 4 and Figure 5, we present a more comprehensive comparison between the four learned models and the baseline models. As shown in Figure 4, for the averaged ROC over 10-time repetition, all our learned models outperform the baseline models by a considerable margin in MACE prediction and there is little difference between the four learned models’ performances and confident intervals. Moreover, the influences of changes of sample sizes on AUC values were illustrated in Figure 5. We randomly selected the same proportion of samples from positive and negative samples to construct datasets in different sizes. The AUC values of all four models gradually ascend in overall trend along with the increases of the sample sizes. And all models were able to achieve relatively stable performances with 20% of all patient samples, which illustrates that our models can obtain good performances under a small sample size.

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.