Do we know how to set decision thresholds for diabetes?

Y. Ben-Haim, M. Zacksenhouse, C. Keren, C. C. Dacso

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

The diagnosis of diabetes, based on measured fasting plasma glucose level, depends on choosing a threshold level for which the probability of failing to detect disease (missed diagnosis), as well as the probability of falsely diagnosing disease (false alarm), are both small. The Bayesian risk provides a tool for aggregating and evaluating the risks of missed diagnosis and false alarm. However, the underlying probability distributions are uncertain, which makes the choice of the decision threshold difficult. We discuss an hypothesis for choosing the threshold that can robustly achieve acceptable risk. Our analysis is based on info-gap decision theory, which is a non-probabilistic methodology for modelling and managing uncertainty. Our hypothesis is that the non-probabilistic method of info-gap robust decision making is able to select decision thresholds according to their probability of success. This hypothesis is motivated by the relationship between info-gap robustness and the probability of success, which has been observed in other disciplines (biology and economics). If true, it provides a valuable clinical tool, enabling the clinician to make reliable diagnostic decisions in the absence of extensive probabilistic information. Specifically, the hypothesis asserts that the physician is able to choose a diagnostic threshold that maximizes the probability of acceptably small Bayesian risk, without requiring accurate knowledge of the underlying probability distributions. The actual value of the Bayesian risk remains uncertain.

Original languageEnglish (US)
Pages (from-to)189-193
Number of pages5
JournalMedical Hypotheses
Volume73
Issue number2
DOIs
StatePublished - Aug 2009
Externally publishedYes

Fingerprint

Decision Theory
Uncertainty
Fasting
Decision Making
Economics
Physicians
Glucose

ASJC Scopus subject areas

  • Medicine(all)

Cite this

Ben-Haim, Y., Zacksenhouse, M., Keren, C., & Dacso, C. C. (2009). Do we know how to set decision thresholds for diabetes? Medical Hypotheses, 73(2), 189-193. https://doi.org/10.1016/j.mehy.2008.12.053

Do we know how to set decision thresholds for diabetes? / Ben-Haim, Y.; Zacksenhouse, M.; Keren, C.; Dacso, C. C.

In: Medical Hypotheses, Vol. 73, No. 2, 08.2009, p. 189-193.

Research output: Contribution to journalArticle

Ben-Haim, Y, Zacksenhouse, M, Keren, C & Dacso, CC 2009, 'Do we know how to set decision thresholds for diabetes?', Medical Hypotheses, vol. 73, no. 2, pp. 189-193. https://doi.org/10.1016/j.mehy.2008.12.053
Ben-Haim, Y. ; Zacksenhouse, M. ; Keren, C. ; Dacso, C. C. / Do we know how to set decision thresholds for diabetes?. In: Medical Hypotheses. 2009 ; Vol. 73, No. 2. pp. 189-193.
@article{563eaab89af94df2a5ab6655efc44935,
title = "Do we know how to set decision thresholds for diabetes?",
abstract = "The diagnosis of diabetes, based on measured fasting plasma glucose level, depends on choosing a threshold level for which the probability of failing to detect disease (missed diagnosis), as well as the probability of falsely diagnosing disease (false alarm), are both small. The Bayesian risk provides a tool for aggregating and evaluating the risks of missed diagnosis and false alarm. However, the underlying probability distributions are uncertain, which makes the choice of the decision threshold difficult. We discuss an hypothesis for choosing the threshold that can robustly achieve acceptable risk. Our analysis is based on info-gap decision theory, which is a non-probabilistic methodology for modelling and managing uncertainty. Our hypothesis is that the non-probabilistic method of info-gap robust decision making is able to select decision thresholds according to their probability of success. This hypothesis is motivated by the relationship between info-gap robustness and the probability of success, which has been observed in other disciplines (biology and economics). If true, it provides a valuable clinical tool, enabling the clinician to make reliable diagnostic decisions in the absence of extensive probabilistic information. Specifically, the hypothesis asserts that the physician is able to choose a diagnostic threshold that maximizes the probability of acceptably small Bayesian risk, without requiring accurate knowledge of the underlying probability distributions. The actual value of the Bayesian risk remains uncertain.",
author = "Y. Ben-Haim and M. Zacksenhouse and C. Keren and Dacso, {C. C.}",
year = "2009",
month = "8",
doi = "10.1016/j.mehy.2008.12.053",
language = "English (US)",
volume = "73",
pages = "189--193",
journal = "Medical Hypotheses",
issn = "0306-9877",
publisher = "Churchill Livingstone",
number = "2",

}

TY - JOUR

T1 - Do we know how to set decision thresholds for diabetes?

AU - Ben-Haim, Y.

AU - Zacksenhouse, M.

AU - Keren, C.

AU - Dacso, C. C.

PY - 2009/8

Y1 - 2009/8

N2 - The diagnosis of diabetes, based on measured fasting plasma glucose level, depends on choosing a threshold level for which the probability of failing to detect disease (missed diagnosis), as well as the probability of falsely diagnosing disease (false alarm), are both small. The Bayesian risk provides a tool for aggregating and evaluating the risks of missed diagnosis and false alarm. However, the underlying probability distributions are uncertain, which makes the choice of the decision threshold difficult. We discuss an hypothesis for choosing the threshold that can robustly achieve acceptable risk. Our analysis is based on info-gap decision theory, which is a non-probabilistic methodology for modelling and managing uncertainty. Our hypothesis is that the non-probabilistic method of info-gap robust decision making is able to select decision thresholds according to their probability of success. This hypothesis is motivated by the relationship between info-gap robustness and the probability of success, which has been observed in other disciplines (biology and economics). If true, it provides a valuable clinical tool, enabling the clinician to make reliable diagnostic decisions in the absence of extensive probabilistic information. Specifically, the hypothesis asserts that the physician is able to choose a diagnostic threshold that maximizes the probability of acceptably small Bayesian risk, without requiring accurate knowledge of the underlying probability distributions. The actual value of the Bayesian risk remains uncertain.

AB - The diagnosis of diabetes, based on measured fasting plasma glucose level, depends on choosing a threshold level for which the probability of failing to detect disease (missed diagnosis), as well as the probability of falsely diagnosing disease (false alarm), are both small. The Bayesian risk provides a tool for aggregating and evaluating the risks of missed diagnosis and false alarm. However, the underlying probability distributions are uncertain, which makes the choice of the decision threshold difficult. We discuss an hypothesis for choosing the threshold that can robustly achieve acceptable risk. Our analysis is based on info-gap decision theory, which is a non-probabilistic methodology for modelling and managing uncertainty. Our hypothesis is that the non-probabilistic method of info-gap robust decision making is able to select decision thresholds according to their probability of success. This hypothesis is motivated by the relationship between info-gap robustness and the probability of success, which has been observed in other disciplines (biology and economics). If true, it provides a valuable clinical tool, enabling the clinician to make reliable diagnostic decisions in the absence of extensive probabilistic information. Specifically, the hypothesis asserts that the physician is able to choose a diagnostic threshold that maximizes the probability of acceptably small Bayesian risk, without requiring accurate knowledge of the underlying probability distributions. The actual value of the Bayesian risk remains uncertain.

UR - http://www.scopus.com/inward/record.url?scp=67349218863&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67349218863&partnerID=8YFLogxK

U2 - 10.1016/j.mehy.2008.12.053

DO - 10.1016/j.mehy.2008.12.053

M3 - Article

C2 - 19349125

AN - SCOPUS:67349218863

VL - 73

SP - 189

EP - 193

JO - Medical Hypotheses

JF - Medical Hypotheses

SN - 0306-9877

IS - 2

ER -