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.


Potential risk factors based on random forest models. (A) Risk factors based on RBMLP; (B) Risk factors based on CRFs (†: risk factor employed in GRACE; ‡: risk factor employed in TIMI; §: risk factor employed in top 20 of both random forest and ℓ1-LR model).
© Copyright Policy
Related In: Results  -  Collection

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

ijerph-13-00912-f006: Potential risk factors based on random forest models. (A) Risk factors based on RBMLP; (B) Risk factors based on CRFs (†: risk factor employed in GRACE; ‡: risk factor employed in TIMI; §: risk factor employed in top 20 of both random forest and ℓ1-LR model).

Mentions: As illustrated in above section, all four learned models achieved competitive performances in MACE prediction. Among all these models, random forest achieved the best performance, which can offer the most powerful risk factors in predicting MACE. Therefore, we extract some important features from random forest models in terms of the mean decrease accuracy. Figure 6 shows the top-rank 20 risk factors in the random forest model. In addition, ℓ1-LR can extract some important features that influence the prediction results when the other models lack the interpretability [39]. Note that the positive value of the coefficient in ℓ1-LR model indicates an increasing possibility for occurrence of MACE, while the negative value means the opposite, in which the possibility is decreasing. Figure 7 shows the top 20 risk factors with their coefficients.


Utilizing Chinese Admission Records for MACE Prediction of Acute Coronary Syndrome
Potential risk factors based on random forest models. (A) Risk factors based on RBMLP; (B) Risk factors based on CRFs (†: risk factor employed in GRACE; ‡: risk factor employed in TIMI; §: risk factor employed in top 20 of both random forest and ℓ1-LR model).
© Copyright Policy
Related In: Results  -  Collection

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

ijerph-13-00912-f006: Potential risk factors based on random forest models. (A) Risk factors based on RBMLP; (B) Risk factors based on CRFs (†: risk factor employed in GRACE; ‡: risk factor employed in TIMI; §: risk factor employed in top 20 of both random forest and ℓ1-LR model).
Mentions: As illustrated in above section, all four learned models achieved competitive performances in MACE prediction. Among all these models, random forest achieved the best performance, which can offer the most powerful risk factors in predicting MACE. Therefore, we extract some important features from random forest models in terms of the mean decrease accuracy. Figure 6 shows the top-rank 20 risk factors in the random forest model. In addition, ℓ1-LR can extract some important features that influence the prediction results when the other models lack the interpretability [39]. Note that the positive value of the coefficient in ℓ1-LR model indicates an increasing possibility for occurrence of MACE, while the negative value means the opposite, in which the possibility is decreasing. Figure 7 shows the top 20 risk factors with their coefficients.

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.