A novel delta check method for detecting laboratory errors

J. Sourati, D. Erdogmus, M. Akcakaya, Steven (Steve) Kazmierczak, T. K. Leen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Investigating the variation of clinical measurements of patients over time is a common technique, known as delta check, for detecting laboratory errors. They are based on the expected biological variations and machine imprecision, where the latter varies for different concentrations of the analytes. Here, we present a novel delta check method in the form of composite thresholding, and provide its sufficient statistics by constructing the corresponding discriminant function, which enables us to use statistical and learning analysis tools. Using the scores obtained from such a discriminant function, we statistically study the performance of our algorithm on a labeled data set for the purpose of detecting lab errors.

Original languageEnglish (US)
Title of host publicationIEEE International Workshop on Machine Learning for Signal Processing, MLSP
PublisherIEEE Computer Society
Volume2015-November
ISBN (Print)9781467374545
DOIs
StatePublished - Nov 10 2015
Event25th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2015 - Boston, United States
Duration: Sep 17 2015Sep 20 2015

Other

Other25th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2015
CountryUnited States
CityBoston
Period9/17/159/20/15

Fingerprint

Statistics
Composite materials

Keywords

  • Delta check
  • lab error detection
  • Sufficient statistics

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Signal Processing

Cite this

Sourati, J., Erdogmus, D., Akcakaya, M., Kazmierczak, S. S., & Leen, T. K. (2015). A novel delta check method for detecting laboratory errors. In IEEE International Workshop on Machine Learning for Signal Processing, MLSP (Vol. 2015-November). [7324343] IEEE Computer Society. https://doi.org/10.1109/MLSP.2015.7324343

A novel delta check method for detecting laboratory errors. / Sourati, J.; Erdogmus, D.; Akcakaya, M.; Kazmierczak, Steven (Steve); Leen, T. K.

IEEE International Workshop on Machine Learning for Signal Processing, MLSP. Vol. 2015-November IEEE Computer Society, 2015. 7324343.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sourati, J, Erdogmus, D, Akcakaya, M, Kazmierczak, SS & Leen, TK 2015, A novel delta check method for detecting laboratory errors. in IEEE International Workshop on Machine Learning for Signal Processing, MLSP. vol. 2015-November, 7324343, IEEE Computer Society, 25th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2015, Boston, United States, 9/17/15. https://doi.org/10.1109/MLSP.2015.7324343
Sourati J, Erdogmus D, Akcakaya M, Kazmierczak SS, Leen TK. A novel delta check method for detecting laboratory errors. In IEEE International Workshop on Machine Learning for Signal Processing, MLSP. Vol. 2015-November. IEEE Computer Society. 2015. 7324343 https://doi.org/10.1109/MLSP.2015.7324343
Sourati, J. ; Erdogmus, D. ; Akcakaya, M. ; Kazmierczak, Steven (Steve) ; Leen, T. K. / A novel delta check method for detecting laboratory errors. IEEE International Workshop on Machine Learning for Signal Processing, MLSP. Vol. 2015-November IEEE Computer Society, 2015.
@inproceedings{7c56645951de43e5bef99e2333ee7dea,
title = "A novel delta check method for detecting laboratory errors",
abstract = "Investigating the variation of clinical measurements of patients over time is a common technique, known as delta check, for detecting laboratory errors. They are based on the expected biological variations and machine imprecision, where the latter varies for different concentrations of the analytes. Here, we present a novel delta check method in the form of composite thresholding, and provide its sufficient statistics by constructing the corresponding discriminant function, which enables us to use statistical and learning analysis tools. Using the scores obtained from such a discriminant function, we statistically study the performance of our algorithm on a labeled data set for the purpose of detecting lab errors.",
keywords = "Delta check, lab error detection, Sufficient statistics",
author = "J. Sourati and D. Erdogmus and M. Akcakaya and Kazmierczak, {Steven (Steve)} and Leen, {T. K.}",
year = "2015",
month = "11",
day = "10",
doi = "10.1109/MLSP.2015.7324343",
language = "English (US)",
isbn = "9781467374545",
volume = "2015-November",
booktitle = "IEEE International Workshop on Machine Learning for Signal Processing, MLSP",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - A novel delta check method for detecting laboratory errors

AU - Sourati, J.

AU - Erdogmus, D.

AU - Akcakaya, M.

AU - Kazmierczak, Steven (Steve)

AU - Leen, T. K.

PY - 2015/11/10

Y1 - 2015/11/10

N2 - Investigating the variation of clinical measurements of patients over time is a common technique, known as delta check, for detecting laboratory errors. They are based on the expected biological variations and machine imprecision, where the latter varies for different concentrations of the analytes. Here, we present a novel delta check method in the form of composite thresholding, and provide its sufficient statistics by constructing the corresponding discriminant function, which enables us to use statistical and learning analysis tools. Using the scores obtained from such a discriminant function, we statistically study the performance of our algorithm on a labeled data set for the purpose of detecting lab errors.

AB - Investigating the variation of clinical measurements of patients over time is a common technique, known as delta check, for detecting laboratory errors. They are based on the expected biological variations and machine imprecision, where the latter varies for different concentrations of the analytes. Here, we present a novel delta check method in the form of composite thresholding, and provide its sufficient statistics by constructing the corresponding discriminant function, which enables us to use statistical and learning analysis tools. Using the scores obtained from such a discriminant function, we statistically study the performance of our algorithm on a labeled data set for the purpose of detecting lab errors.

KW - Delta check

KW - lab error detection

KW - Sufficient statistics

UR - http://www.scopus.com/inward/record.url?scp=84960889305&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84960889305&partnerID=8YFLogxK

U2 - 10.1109/MLSP.2015.7324343

DO - 10.1109/MLSP.2015.7324343

M3 - Conference contribution

AN - SCOPUS:84960889305

SN - 9781467374545

VL - 2015-November

BT - IEEE International Workshop on Machine Learning for Signal Processing, MLSP

PB - IEEE Computer Society

ER -