Evaluation of data processing pipelines on real-world electronic health records data for the purpose of measuring patient similarity

Maria Pikoula; Constantinos Kallis; Sephora Madjiheurem; Jennifer K. Quint; Mona Bafadhel; Spiros Denaxas

doi:10.1371/journal.pone.0287264

Evaluation of data processing pipelines on real-world electronic health records data for the purpose of measuring patient similarity

Maria Pikoula^*, Constantinos Kallis, Sephora Madjiheurem, Jennifer K. Quint, Mona Bafadhel, Spiros Denaxas

^*Corresponding author for this work

Peter Gorer Department of Immunobiology

Research output: Contribution to journal › Article › peer-review

3 Citations (Scopus)

Abstract

Background The ever-growing size, breadth, and availability of patient data allows for a wide variety of clinical features to serve as inputs for phenotype discovery using cluster analysis. Data of mixed types in particular are not straightforward to combine into a single feature vector, and techniques used to address this can be biased towards certain data types in ways that are not immediately obvious or intended. In this context, the process of constructing clinically meaningful patient representations from complex datasets has not been systematically evaluated. Aims Our aim was to a) outline and b) implement an analytical framework to evaluate distinct methods of constructing patient representations from routine electronic health record data for the purpose of measuring patient similarity. We applied the analysis on a patient cohort diagnosed with chronic obstructive pulmonary disease. Methods Using data from the CALIBER data resource, we extracted clinically relevant features for a cohort of patients diagnosed with chronic obstructive pulmonary disease. We used four different data processing pipelines to construct lower dimensional patient representations from which we calculated patient similarity scores. We described the resulting representations, ranked the influence of each individual feature on patient similarity and evaluated the effect of different pipelines on clustering outcomes. Experts evaluated the resulting representations by rating the clinical relevance of similar patient suggestions with regard to a reference patient. Results Each of the four pipelines resulted in similarity scores primarily driven by a unique set of features. It was demonstrated that data transformations according to each pipeline prior to clustering can result in a variation of clustering results of over 40%. The most appropriate pipeline was selected on the basis of feature ranking and clinical expertise. There was moderate agreement between clinicians as measured by Cohen's kappa coefficient. Conclusions Data transformation has downstream and unforeseen consequences in cluster analysis. Rather than viewing this process as a black box, we have shown ways to quantitatively and qualitatively evaluate and select the appropriate preprocessing pipeline.

Original language	English
Article number	e0287264
Journal	PLoS ONE
Volume	18
Issue number	6 June
DOIs	https://doi.org/10.1371/journal.pone.0287264
Publication status	Published - Jun 2023

Access to Document

10.1371/journal.pone.0287264

Cite this

@article{cda2dac357b14b2394ec553b544c34b6,

title = "Evaluation of data processing pipelines on real-world electronic health records data for the purpose of measuring patient similarity",

abstract = "Background The ever-growing size, breadth, and availability of patient data allows for a wide variety of clinical features to serve as inputs for phenotype discovery using cluster analysis. Data of mixed types in particular are not straightforward to combine into a single feature vector, and techniques used to address this can be biased towards certain data types in ways that are not immediately obvious or intended. In this context, the process of constructing clinically meaningful patient representations from complex datasets has not been systematically evaluated. Aims Our aim was to a) outline and b) implement an analytical framework to evaluate distinct methods of constructing patient representations from routine electronic health record data for the purpose of measuring patient similarity. We applied the analysis on a patient cohort diagnosed with chronic obstructive pulmonary disease. Methods Using data from the CALIBER data resource, we extracted clinically relevant features for a cohort of patients diagnosed with chronic obstructive pulmonary disease. We used four different data processing pipelines to construct lower dimensional patient representations from which we calculated patient similarity scores. We described the resulting representations, ranked the influence of each individual feature on patient similarity and evaluated the effect of different pipelines on clustering outcomes. Experts evaluated the resulting representations by rating the clinical relevance of similar patient suggestions with regard to a reference patient. Results Each of the four pipelines resulted in similarity scores primarily driven by a unique set of features. It was demonstrated that data transformations according to each pipeline prior to clustering can result in a variation of clustering results of over 40%. The most appropriate pipeline was selected on the basis of feature ranking and clinical expertise. There was moderate agreement between clinicians as measured by Cohen's kappa coefficient. Conclusions Data transformation has downstream and unforeseen consequences in cluster analysis. Rather than viewing this process as a black box, we have shown ways to quantitatively and qualitatively evaluate and select the appropriate preprocessing pipeline.",

author = "Maria Pikoula and Constantinos Kallis and Sephora Madjiheurem and Quint, {Jennifer K.} and Mona Bafadhel and Spiros Denaxas",

note = "Publisher Copyright: {\textcopyright} 2023 Pikoula et al.",

year = "2023",

month = jun,

doi = "10.1371/journal.pone.0287264",

language = "English",

volume = "18",

journal = "PLoS ONE",

issn = "1932-6203",

publisher = "Public Library of Science",

number = "6 June",

}

TY - JOUR

T1 - Evaluation of data processing pipelines on real-world electronic health records data for the purpose of measuring patient similarity

AU - Pikoula, Maria

AU - Kallis, Constantinos

AU - Madjiheurem, Sephora

AU - Quint, Jennifer K.

AU - Bafadhel, Mona

AU - Denaxas, Spiros

PY - 2023/6

Y1 - 2023/6

N2 - Background The ever-growing size, breadth, and availability of patient data allows for a wide variety of clinical features to serve as inputs for phenotype discovery using cluster analysis. Data of mixed types in particular are not straightforward to combine into a single feature vector, and techniques used to address this can be biased towards certain data types in ways that are not immediately obvious or intended. In this context, the process of constructing clinically meaningful patient representations from complex datasets has not been systematically evaluated. Aims Our aim was to a) outline and b) implement an analytical framework to evaluate distinct methods of constructing patient representations from routine electronic health record data for the purpose of measuring patient similarity. We applied the analysis on a patient cohort diagnosed with chronic obstructive pulmonary disease. Methods Using data from the CALIBER data resource, we extracted clinically relevant features for a cohort of patients diagnosed with chronic obstructive pulmonary disease. We used four different data processing pipelines to construct lower dimensional patient representations from which we calculated patient similarity scores. We described the resulting representations, ranked the influence of each individual feature on patient similarity and evaluated the effect of different pipelines on clustering outcomes. Experts evaluated the resulting representations by rating the clinical relevance of similar patient suggestions with regard to a reference patient. Results Each of the four pipelines resulted in similarity scores primarily driven by a unique set of features. It was demonstrated that data transformations according to each pipeline prior to clustering can result in a variation of clustering results of over 40%. The most appropriate pipeline was selected on the basis of feature ranking and clinical expertise. There was moderate agreement between clinicians as measured by Cohen's kappa coefficient. Conclusions Data transformation has downstream and unforeseen consequences in cluster analysis. Rather than viewing this process as a black box, we have shown ways to quantitatively and qualitatively evaluate and select the appropriate preprocessing pipeline.

AB - Background The ever-growing size, breadth, and availability of patient data allows for a wide variety of clinical features to serve as inputs for phenotype discovery using cluster analysis. Data of mixed types in particular are not straightforward to combine into a single feature vector, and techniques used to address this can be biased towards certain data types in ways that are not immediately obvious or intended. In this context, the process of constructing clinically meaningful patient representations from complex datasets has not been systematically evaluated. Aims Our aim was to a) outline and b) implement an analytical framework to evaluate distinct methods of constructing patient representations from routine electronic health record data for the purpose of measuring patient similarity. We applied the analysis on a patient cohort diagnosed with chronic obstructive pulmonary disease. Methods Using data from the CALIBER data resource, we extracted clinically relevant features for a cohort of patients diagnosed with chronic obstructive pulmonary disease. We used four different data processing pipelines to construct lower dimensional patient representations from which we calculated patient similarity scores. We described the resulting representations, ranked the influence of each individual feature on patient similarity and evaluated the effect of different pipelines on clustering outcomes. Experts evaluated the resulting representations by rating the clinical relevance of similar patient suggestions with regard to a reference patient. Results Each of the four pipelines resulted in similarity scores primarily driven by a unique set of features. It was demonstrated that data transformations according to each pipeline prior to clustering can result in a variation of clustering results of over 40%. The most appropriate pipeline was selected on the basis of feature ranking and clinical expertise. There was moderate agreement between clinicians as measured by Cohen's kappa coefficient. Conclusions Data transformation has downstream and unforeseen consequences in cluster analysis. Rather than viewing this process as a black box, we have shown ways to quantitatively and qualitatively evaluate and select the appropriate preprocessing pipeline.

UR - http://www.scopus.com/inward/record.url?scp=85163379490&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0287264

DO - 10.1371/journal.pone.0287264

M3 - Article

C2 - 37319288

AN - SCOPUS:85163379490

SN - 1932-6203

VL - 18

JO - PLoS ONE

JF - PLoS ONE

IS - 6 June

M1 - e0287264

ER -

Evaluation of data processing pipelines on real-world electronic health records data for the purpose of measuring patient similarity

Abstract

Access to Document

Other files and links

Fingerprint

Cite this