Desiderata for sharable computable biomedical knowledge for learning health systems

Harold P Lehmann, Stephen M. Downs

Research output: Contribution to journalComment/debate

Abstract

In this commentary, we work out the specific desired functions required for sharing knowledge objects (based on statistical models) presumably to be used for clinical decision support derived from a learning health system, and, in so doing, discuss the implications for novel knowledge architectures. We will demonstrate how decision models, implemented as influence diagrams, satisfy the desiderata. The desiderata include locally validate discrimination, locally validate calibration, locally recalculate thresholds by incorporating local preferences, provide explanation, enable monitoring, enable debiasing, account for generalizability, account for semantic uncertainty, shall be findable, and others as necessary and proper. We demonstrate how formal decision models, especially when implemented as influence diagrams based on Bayesian networks, support both the knowledge artifact itself (the “primary decision”) and the “meta-decision” of whether to deploy the knowledge artifact. We close with a research and development agenda to put this framework into place.

Original languageEnglish (US)
Article numbere10065
JournalLearning Health Systems
Volume2
Issue number4
DOIs
StatePublished - Jan 1 2018

Fingerprint

Artifacts
Clinical Decision Support Systems
Learning
Health
Statistical Models
Semantics
Calibration
Uncertainty
Research
Discrimination (Psychology)

Keywords

  • Bayesian analysis
  • decision analysis
  • decision support
  • knowledge engineering
  • predictive modeling

ASJC Scopus subject areas

  • Public Health, Environmental and Occupational Health
  • Health Informatics
  • Health Information Management

Cite this

Desiderata for sharable computable biomedical knowledge for learning health systems. / Lehmann, Harold P; Downs, Stephen M.

In: Learning Health Systems, Vol. 2, No. 4, e10065, 01.01.2018.

Research output: Contribution to journalComment/debate

@article{8b024fcba77b49a9bb8784725d894bfc,
title = "Desiderata for sharable computable biomedical knowledge for learning health systems",
abstract = "In this commentary, we work out the specific desired functions required for sharing knowledge objects (based on statistical models) presumably to be used for clinical decision support derived from a learning health system, and, in so doing, discuss the implications for novel knowledge architectures. We will demonstrate how decision models, implemented as influence diagrams, satisfy the desiderata. The desiderata include locally validate discrimination, locally validate calibration, locally recalculate thresholds by incorporating local preferences, provide explanation, enable monitoring, enable debiasing, account for generalizability, account for semantic uncertainty, shall be findable, and others as necessary and proper. We demonstrate how formal decision models, especially when implemented as influence diagrams based on Bayesian networks, support both the knowledge artifact itself (the “primary decision”) and the “meta-decision” of whether to deploy the knowledge artifact. We close with a research and development agenda to put this framework into place.",
keywords = "Bayesian analysis, decision analysis, decision support, knowledge engineering, predictive modeling",
author = "Lehmann, {Harold P} and Downs, {Stephen M.}",
year = "2018",
month = "1",
day = "1",
doi = "10.1002/lrh2.10065",
language = "English (US)",
volume = "2",
journal = "Learning Health Systems",
issn = "2379-6146",
publisher = "John Wiley and Sons Inc.",
number = "4",

}

TY - JOUR

T1 - Desiderata for sharable computable biomedical knowledge for learning health systems

AU - Lehmann, Harold P

AU - Downs, Stephen M.

PY - 2018/1/1

Y1 - 2018/1/1

N2 - In this commentary, we work out the specific desired functions required for sharing knowledge objects (based on statistical models) presumably to be used for clinical decision support derived from a learning health system, and, in so doing, discuss the implications for novel knowledge architectures. We will demonstrate how decision models, implemented as influence diagrams, satisfy the desiderata. The desiderata include locally validate discrimination, locally validate calibration, locally recalculate thresholds by incorporating local preferences, provide explanation, enable monitoring, enable debiasing, account for generalizability, account for semantic uncertainty, shall be findable, and others as necessary and proper. We demonstrate how formal decision models, especially when implemented as influence diagrams based on Bayesian networks, support both the knowledge artifact itself (the “primary decision”) and the “meta-decision” of whether to deploy the knowledge artifact. We close with a research and development agenda to put this framework into place.

AB - In this commentary, we work out the specific desired functions required for sharing knowledge objects (based on statistical models) presumably to be used for clinical decision support derived from a learning health system, and, in so doing, discuss the implications for novel knowledge architectures. We will demonstrate how decision models, implemented as influence diagrams, satisfy the desiderata. The desiderata include locally validate discrimination, locally validate calibration, locally recalculate thresholds by incorporating local preferences, provide explanation, enable monitoring, enable debiasing, account for generalizability, account for semantic uncertainty, shall be findable, and others as necessary and proper. We demonstrate how formal decision models, especially when implemented as influence diagrams based on Bayesian networks, support both the knowledge artifact itself (the “primary decision”) and the “meta-decision” of whether to deploy the knowledge artifact. We close with a research and development agenda to put this framework into place.

KW - Bayesian analysis

KW - decision analysis

KW - decision support

KW - knowledge engineering

KW - predictive modeling

UR - http://www.scopus.com/inward/record.url?scp=85065054247&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85065054247&partnerID=8YFLogxK

U2 - 10.1002/lrh2.10065

DO - 10.1002/lrh2.10065

M3 - Comment/debate

VL - 2

JO - Learning Health Systems

JF - Learning Health Systems

SN - 2379-6146

IS - 4

M1 - e10065

ER -