Big data cohort extraction for personalized statin treatment and machine learning

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

The creation of big clinical data cohorts for machine learning and data analysis require a number of steps from the beginning to successful completion. Similar to data set preprocessing in other fields, there is an initial need to complete data quality evaluation; however, with large heterogeneous clinical data sets, it is important to standardize the data in order to facilitate dimensionality reduction. This is particularly important for clinical data sets including medications as a core data component due to the complexity of coded medication data. Data integration at the individual subject level is essential with medication-related machine learning applications since it can be difficult to accurately identify drug exposures, therapeutic effects, and adverse drug events without having high-quality data integration of insurance, medication, and medical data. Successful data integration and standardization efforts can substantially improve the ability to identify and replicate personalized treatment pathways to optimize drug therapy.

Original languageEnglish (US)
Title of host publicationMethods in Molecular Biology
PublisherHumana Press Inc.
Pages255-272
Number of pages18
DOIs
StatePublished - Jan 1 2019

Publication series

NameMethods in Molecular Biology
Volume1939
ISSN (Print)1064-3745

Fingerprint

Hydroxymethylglutaryl-CoA Reductase Inhibitors
Therapeutic Uses
Insurance
Drug-Related Side Effects and Adverse Reactions
Therapeutics
Drug Therapy
Pharmaceutical Preparations
Datasets
Machine Learning
Data Accuracy

Keywords

  • Clinical comorbidity evaluation
  • Clinical data integration
  • Medication safety
  • Personalized medication therapy

PubMed: MeSH publication types

  • Journal Article

Cite this

Adam, T. J., & Chi, C-L. (2019). Big data cohort extraction for personalized statin treatment and machine learning. In Methods in Molecular Biology (pp. 255-272). (Methods in Molecular Biology; Vol. 1939). Humana Press Inc.. https://doi.org/10.1007/978-1-4939-9089-4_14

Big data cohort extraction for personalized statin treatment and machine learning. / Adam, Terrence J; Chi, Chih-Lin.

Methods in Molecular Biology. Humana Press Inc., 2019. p. 255-272 (Methods in Molecular Biology; Vol. 1939).

Research output: Chapter in Book/Report/Conference proceedingChapter

Adam, TJ & Chi, C-L 2019, Big data cohort extraction for personalized statin treatment and machine learning. in Methods in Molecular Biology. Methods in Molecular Biology, vol. 1939, Humana Press Inc., pp. 255-272. https://doi.org/10.1007/978-1-4939-9089-4_14
Adam TJ, Chi C-L. Big data cohort extraction for personalized statin treatment and machine learning. In Methods in Molecular Biology. Humana Press Inc. 2019. p. 255-272. (Methods in Molecular Biology). https://doi.org/10.1007/978-1-4939-9089-4_14
Adam, Terrence J ; Chi, Chih-Lin. / Big data cohort extraction for personalized statin treatment and machine learning. Methods in Molecular Biology. Humana Press Inc., 2019. pp. 255-272 (Methods in Molecular Biology).
@inbook{37307fcbd94a45ba9d3103b56279e837,
title = "Big data cohort extraction for personalized statin treatment and machine learning",
abstract = "The creation of big clinical data cohorts for machine learning and data analysis require a number of steps from the beginning to successful completion. Similar to data set preprocessing in other fields, there is an initial need to complete data quality evaluation; however, with large heterogeneous clinical data sets, it is important to standardize the data in order to facilitate dimensionality reduction. This is particularly important for clinical data sets including medications as a core data component due to the complexity of coded medication data. Data integration at the individual subject level is essential with medication-related machine learning applications since it can be difficult to accurately identify drug exposures, therapeutic effects, and adverse drug events without having high-quality data integration of insurance, medication, and medical data. Successful data integration and standardization efforts can substantially improve the ability to identify and replicate personalized treatment pathways to optimize drug therapy.",
keywords = "Clinical comorbidity evaluation, Clinical data integration, Medication safety, Personalized medication therapy",
author = "Adam, {Terrence J} and Chih-Lin Chi",
year = "2019",
month = "1",
day = "1",
doi = "10.1007/978-1-4939-9089-4_14",
language = "English (US)",
series = "Methods in Molecular Biology",
publisher = "Humana Press Inc.",
pages = "255--272",
booktitle = "Methods in Molecular Biology",

}

TY - CHAP

T1 - Big data cohort extraction for personalized statin treatment and machine learning

AU - Adam, Terrence J

AU - Chi, Chih-Lin

PY - 2019/1/1

Y1 - 2019/1/1

N2 - The creation of big clinical data cohorts for machine learning and data analysis require a number of steps from the beginning to successful completion. Similar to data set preprocessing in other fields, there is an initial need to complete data quality evaluation; however, with large heterogeneous clinical data sets, it is important to standardize the data in order to facilitate dimensionality reduction. This is particularly important for clinical data sets including medications as a core data component due to the complexity of coded medication data. Data integration at the individual subject level is essential with medication-related machine learning applications since it can be difficult to accurately identify drug exposures, therapeutic effects, and adverse drug events without having high-quality data integration of insurance, medication, and medical data. Successful data integration and standardization efforts can substantially improve the ability to identify and replicate personalized treatment pathways to optimize drug therapy.

AB - The creation of big clinical data cohorts for machine learning and data analysis require a number of steps from the beginning to successful completion. Similar to data set preprocessing in other fields, there is an initial need to complete data quality evaluation; however, with large heterogeneous clinical data sets, it is important to standardize the data in order to facilitate dimensionality reduction. This is particularly important for clinical data sets including medications as a core data component due to the complexity of coded medication data. Data integration at the individual subject level is essential with medication-related machine learning applications since it can be difficult to accurately identify drug exposures, therapeutic effects, and adverse drug events without having high-quality data integration of insurance, medication, and medical data. Successful data integration and standardization efforts can substantially improve the ability to identify and replicate personalized treatment pathways to optimize drug therapy.

KW - Clinical comorbidity evaluation

KW - Clinical data integration

KW - Medication safety

KW - Personalized medication therapy

UR - http://www.scopus.com/inward/record.url?scp=85062603086&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062603086&partnerID=8YFLogxK

U2 - 10.1007/978-1-4939-9089-4_14

DO - 10.1007/978-1-4939-9089-4_14

M3 - Chapter

T3 - Methods in Molecular Biology

SP - 255

EP - 272

BT - Methods in Molecular Biology

PB - Humana Press Inc.

ER -