Cross-domain probabilistic inference in a clinical decision support system

Examples for dermatology and rheumatology

Ying Jui Chang, Min Li Yeh, Chyou Shen Lee, Chien Yeh Hsu, Yu Chuan Jack Li, Wen Ta Chiu

研究成果: 雜誌貢獻文章

7 引文 (Scopus)

摘要

Introduction: Maintaining a large diagnostic knowledge base (KB) is a demanding task for any person or organization. Future clinical decision support system (CDSS) may rely on multiple, smaller and more focused KBs developed and maintained at different locations that work together seamlessly. A cross-domain inference tool has great clinical import and utility. Methods: We developed a modified multi-membership Bayes formulation to facilitate the cross-domain probabilistic inferencing among KBs with overlapping diseases. Two KBs developed for evaluation were non-infectious generalized blistering diseases (GBD) and autoimmune diseases (AID). After the KBs were finalized, they were evaluated separately for validity. Result: Ten cases from medical journal case reports were used to evaluate this "cross-domain" inference across the two KBs. The resultant non-error rate (NER) was 90%, and the average of probabilities assigned to the correct diagnosis (AVP) was 64.8% for cross-domain consultations. Conclusion: A novel formulation is now available to deal with problems occurring in a clinical diagnostic decision support system with multi-domain KBs. The utilization of this formulation will help in the development of more integrated KBs with greater focused knowledge domains.

原文英語
頁(從 - 到)286-291
頁數6
期刊Computer Methods and Programs in Biomedicine
104
發行號2
DOIs
出版狀態已發佈 - 十一月 2011

指紋

Clinical Decision Support Systems
Dermatology
Rheumatology
Decision support systems
Knowledge Bases
Workplace
Autoimmune Diseases
Referral and Consultation
Organizations

ASJC Scopus subject areas

  • Computer Science Applications
  • Software
  • Health Informatics

引用此文

Cross-domain probabilistic inference in a clinical decision support system : Examples for dermatology and rheumatology. / Chang, Ying Jui; Yeh, Min Li; Lee, Chyou Shen; Hsu, Chien Yeh; Li, Yu Chuan Jack; Chiu, Wen Ta.

於: Computer Methods and Programs in Biomedicine, 卷 104, 編號 2, 11.2011, p. 286-291.

研究成果: 雜誌貢獻文章

Chang, Ying Jui ; Yeh, Min Li ; Lee, Chyou Shen ; Hsu, Chien Yeh ; Li, Yu Chuan Jack ; Chiu, Wen Ta. / Cross-domain probabilistic inference in a clinical decision support system : Examples for dermatology and rheumatology. 於: Computer Methods and Programs in Biomedicine. 2011 ; 卷 104, 編號 2. 頁 286-291.
@article{a8c0850afd9b4c4dbff03cdd67bdfda1,
title = "Cross-domain probabilistic inference in a clinical decision support system: Examples for dermatology and rheumatology",
abstract = "Introduction: Maintaining a large diagnostic knowledge base (KB) is a demanding task for any person or organization. Future clinical decision support system (CDSS) may rely on multiple, smaller and more focused KBs developed and maintained at different locations that work together seamlessly. A cross-domain inference tool has great clinical import and utility. Methods: We developed a modified multi-membership Bayes formulation to facilitate the cross-domain probabilistic inferencing among KBs with overlapping diseases. Two KBs developed for evaluation were non-infectious generalized blistering diseases (GBD) and autoimmune diseases (AID). After the KBs were finalized, they were evaluated separately for validity. Result: Ten cases from medical journal case reports were used to evaluate this {"}cross-domain{"} inference across the two KBs. The resultant non-error rate (NER) was 90{\%}, and the average of probabilities assigned to the correct diagnosis (AVP) was 64.8{\%} for cross-domain consultations. Conclusion: A novel formulation is now available to deal with problems occurring in a clinical diagnostic decision support system with multi-domain KBs. The utilization of this formulation will help in the development of more integrated KBs with greater focused knowledge domains.",
keywords = "Bayes formulation, Clinical decision support system, Knowledge base",
author = "Chang, {Ying Jui} and Yeh, {Min Li} and Lee, {Chyou Shen} and Hsu, {Chien Yeh} and Li, {Yu Chuan Jack} and Chiu, {Wen Ta}",
year = "2011",
month = "11",
doi = "10.1016/j.cmpb.2011.07.008",
language = "English",
volume = "104",
pages = "286--291",
journal = "Computer Methods and Programs in Biomedicine",
issn = "0169-2607",
publisher = "Elsevier Ireland Ltd",
number = "2",

}

TY - JOUR

T1 - Cross-domain probabilistic inference in a clinical decision support system

T2 - Examples for dermatology and rheumatology

AU - Chang, Ying Jui

AU - Yeh, Min Li

AU - Lee, Chyou Shen

AU - Hsu, Chien Yeh

AU - Li, Yu Chuan Jack

AU - Chiu, Wen Ta

PY - 2011/11

Y1 - 2011/11

N2 - Introduction: Maintaining a large diagnostic knowledge base (KB) is a demanding task for any person or organization. Future clinical decision support system (CDSS) may rely on multiple, smaller and more focused KBs developed and maintained at different locations that work together seamlessly. A cross-domain inference tool has great clinical import and utility. Methods: We developed a modified multi-membership Bayes formulation to facilitate the cross-domain probabilistic inferencing among KBs with overlapping diseases. Two KBs developed for evaluation were non-infectious generalized blistering diseases (GBD) and autoimmune diseases (AID). After the KBs were finalized, they were evaluated separately for validity. Result: Ten cases from medical journal case reports were used to evaluate this "cross-domain" inference across the two KBs. The resultant non-error rate (NER) was 90%, and the average of probabilities assigned to the correct diagnosis (AVP) was 64.8% for cross-domain consultations. Conclusion: A novel formulation is now available to deal with problems occurring in a clinical diagnostic decision support system with multi-domain KBs. The utilization of this formulation will help in the development of more integrated KBs with greater focused knowledge domains.

AB - Introduction: Maintaining a large diagnostic knowledge base (KB) is a demanding task for any person or organization. Future clinical decision support system (CDSS) may rely on multiple, smaller and more focused KBs developed and maintained at different locations that work together seamlessly. A cross-domain inference tool has great clinical import and utility. Methods: We developed a modified multi-membership Bayes formulation to facilitate the cross-domain probabilistic inferencing among KBs with overlapping diseases. Two KBs developed for evaluation were non-infectious generalized blistering diseases (GBD) and autoimmune diseases (AID). After the KBs were finalized, they were evaluated separately for validity. Result: Ten cases from medical journal case reports were used to evaluate this "cross-domain" inference across the two KBs. The resultant non-error rate (NER) was 90%, and the average of probabilities assigned to the correct diagnosis (AVP) was 64.8% for cross-domain consultations. Conclusion: A novel formulation is now available to deal with problems occurring in a clinical diagnostic decision support system with multi-domain KBs. The utilization of this formulation will help in the development of more integrated KBs with greater focused knowledge domains.

KW - Bayes formulation

KW - Clinical decision support system

KW - Knowledge base

UR - http://www.scopus.com/inward/record.url?scp=80054118214&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80054118214&partnerID=8YFLogxK

U2 - 10.1016/j.cmpb.2011.07.008

DO - 10.1016/j.cmpb.2011.07.008

M3 - Article

VL - 104

SP - 286

EP - 291

JO - Computer Methods and Programs in Biomedicine

JF - Computer Methods and Programs in Biomedicine

SN - 0169-2607

IS - 2

ER -