Limits...
Predictive modeling of structured electronic health records for adverse drug event detection.

Zhao J, Henriksson A, Asker L, Boström H - BMC Med Inform Decis Mak (2015)

Bottom Line: Feature selection is conducted on the various types of data to reduce dimensionality and sparsity, while allowing for an in-depth feature analysis of the usefulness of each data type and representation.Within each data type, combining multiple representations yields better predictive performance compared to using any single representation.Overall, clinical codes are more useful than measurements and, in specific cases, it is beneficial to combine the two.

View Article: PubMed Central - HTML - PubMed

ABSTRACT

Background: The digitization of healthcare data, resulting from the increasingly widespread adoption of electronic health records, has greatly facilitated its analysis by computational methods and thereby enabled large-scale secondary use thereof. This can be exploited to support public health activities such as pharmacovigilance, wherein the safety of drugs is monitored to inform regulatory decisions about sustained use. To that end, electronic health records have emerged as a potentially valuable data source, providing access to longitudinal observations of patient treatment and drug use. A nascent line of research concerns predictive modeling of healthcare data for the automatic detection of adverse drug events, which presents its own set of challenges: it is not yet clear how to represent the heterogeneous data types in a manner conducive to learning high-performing machine learning models.

Methods: Datasets from an electronic health record database are used for learning predictive models with the purpose of detecting adverse drug events. The use and representation of two data types, as well as their combination, are studied: clinical codes, describing prescribed drugs and assigned diagnoses, and measurements. Feature selection is conducted on the various types of data to reduce dimensionality and sparsity, while allowing for an in-depth feature analysis of the usefulness of each data type and representation.

Results: Within each data type, combining multiple representations yields better predictive performance compared to using any single representation. The use of clinical codes for adverse drug event detection significantly outperforms the use of measurements; however, there is no significant difference over datasets between using only clinical codes and their combination with measurements. For certain adverse drug events, the combination does, however, outperform using only clinical codes. Feature selection leads to increased predictive performance for both data types, in isolation and combined.

Conclusions: We have demonstrated how machine learning can be applied to electronic health records for the purpose of detecting adverse drug events and proposed solutions to some of the challenges this presents, including how to represent the various data types. Overall, clinical codes are more useful than measurements and, in specific cases, it is beneficial to combine the two.

No MeSH data available.


Related in: MedlinePlus

Accuracy of multiple classifiers using clinical measurements (M), clinical codes (C) and their combination (M+C) at each feature selection threshold.
© Copyright Policy - open-access
Related In: Results  -  Collection

License 1 - License 2
getmorefigures.php?uid=PMC4660129&req=5

Figure 9: Accuracy of multiple classifiers using clinical measurements (M), clinical codes (C) and their combination (M+C) at each feature selection threshold.

Mentions: Figure 9 and Figure 10 demonstrate the averaged accuracy and AUC, respectively, of eight additional commonly used learning algorithms using clinical measurements, clinical codes and their combination over the 27 datasets. It is clear that the random forest algorithm outperforms the others; for most learning algorithms, using clinical codes yields the best predictive performance; however, for learning algorithms that are very sensitive to high dimensionality, such as k nearest neighbors (kNN), using measurements alone and/or applying feature selection improve(s) the predictive performance, as the number of clinical measurements is far smaller than the number of clinical codes.


Predictive modeling of structured electronic health records for adverse drug event detection.

Zhao J, Henriksson A, Asker L, Boström H - BMC Med Inform Decis Mak (2015)

Accuracy of multiple classifiers using clinical measurements (M), clinical codes (C) and their combination (M+C) at each feature selection threshold.
© Copyright Policy - open-access
Related In: Results  -  Collection

License 1 - License 2
Show All Figures
getmorefigures.php?uid=PMC4660129&req=5

Figure 9: Accuracy of multiple classifiers using clinical measurements (M), clinical codes (C) and their combination (M+C) at each feature selection threshold.
Mentions: Figure 9 and Figure 10 demonstrate the averaged accuracy and AUC, respectively, of eight additional commonly used learning algorithms using clinical measurements, clinical codes and their combination over the 27 datasets. It is clear that the random forest algorithm outperforms the others; for most learning algorithms, using clinical codes yields the best predictive performance; however, for learning algorithms that are very sensitive to high dimensionality, such as k nearest neighbors (kNN), using measurements alone and/or applying feature selection improve(s) the predictive performance, as the number of clinical measurements is far smaller than the number of clinical codes.

Bottom Line: Feature selection is conducted on the various types of data to reduce dimensionality and sparsity, while allowing for an in-depth feature analysis of the usefulness of each data type and representation.Within each data type, combining multiple representations yields better predictive performance compared to using any single representation.Overall, clinical codes are more useful than measurements and, in specific cases, it is beneficial to combine the two.

View Article: PubMed Central - HTML - PubMed

ABSTRACT

Background: The digitization of healthcare data, resulting from the increasingly widespread adoption of electronic health records, has greatly facilitated its analysis by computational methods and thereby enabled large-scale secondary use thereof. This can be exploited to support public health activities such as pharmacovigilance, wherein the safety of drugs is monitored to inform regulatory decisions about sustained use. To that end, electronic health records have emerged as a potentially valuable data source, providing access to longitudinal observations of patient treatment and drug use. A nascent line of research concerns predictive modeling of healthcare data for the automatic detection of adverse drug events, which presents its own set of challenges: it is not yet clear how to represent the heterogeneous data types in a manner conducive to learning high-performing machine learning models.

Methods: Datasets from an electronic health record database are used for learning predictive models with the purpose of detecting adverse drug events. The use and representation of two data types, as well as their combination, are studied: clinical codes, describing prescribed drugs and assigned diagnoses, and measurements. Feature selection is conducted on the various types of data to reduce dimensionality and sparsity, while allowing for an in-depth feature analysis of the usefulness of each data type and representation.

Results: Within each data type, combining multiple representations yields better predictive performance compared to using any single representation. The use of clinical codes for adverse drug event detection significantly outperforms the use of measurements; however, there is no significant difference over datasets between using only clinical codes and their combination with measurements. For certain adverse drug events, the combination does, however, outperform using only clinical codes. Feature selection leads to increased predictive performance for both data types, in isolation and combined.

Conclusions: We have demonstrated how machine learning can be applied to electronic health records for the purpose of detecting adverse drug events and proposed solutions to some of the challenges this presents, including how to represent the various data types. Overall, clinical codes are more useful than measurements and, in specific cases, it is beneficial to combine the two.

No MeSH data available.


Related in: MedlinePlus