FCAView Tab: Tab: FCAView A Concept- -Oriented View Generation - - PowerPoint PPT Presentation

▶
fcaview tab tab fcaview
SMART_READER_LITE
LIVE PREVIEW

FCAView Tab: Tab: FCAView A Concept- -Oriented View Generation - - PowerPoint PPT Presentation

May 13, 2023 407 likes •731 views

FCAView Tab: Tab: FCAView A Concept- -Oriented View Generation Tool for Oriented View Generation Tool for A Concept Clinical Data Using Formal Concept Analysis Clinical Data Using Formal Concept Analysis Guoqian Jiang Jiang, Katsuhiko

slide-1
SLIDE 1

FCAView FCAView Tab: Tab:

A Concept A Concept-

  • Oriented View Generation Tool for

Oriented View Generation Tool for Clinical Data Using Formal Concept Analysis Clinical Data Using Formal Concept Analysis

Guoqian Guoqian Jiang Jiang, Katsuhiko Ogasawara, Naoki , Katsuhiko Ogasawara, Naoki Nishimoto Nishimoto, , Akira Akira Endoh Endoh, , Tsunetaro Tsunetaro Sakurai Sakurai

Department of Medical Informatics, Hokkaido University Department of Medical Informatics, Hokkaido University Graduate School of Medicine, Sapporo, Japan Graduate School of Medicine, Sapporo, Japan

The 8 The 8th

th International Prot

International Proté

ég

gé

é Conference

Conference Madrid, Spain, July 20, 2005 Madrid, Spain, July 20, 2005

slide-2
SLIDE 2

Classification of Views for Electronic Patient Records Classification of Views for Electronic Patient Records

From Q.Zeng, et al. Journal of Biomedical Informatics. 2001;34(2):112-128

slide-3
SLIDE 3

Concept Concept-

  • Oriented Views

Oriented Views

  • Several studies have demonstrated that

Several studies have demonstrated that computer computer-

  • generated, concept

generated, concept-

  • oriented views for
  • riented views for

clinical data can be used to reduce clinicians clinical data can be used to reduce clinicians’

’

information overload and improve the accuracy information overload and improve the accuracy

  • f clinical data retrieval.
  • f clinical data retrieval.
  • However, the tasks for automating the

However, the tasks for automating the generation of concept generation of concept-

  • oriented views are
  • riented views are

challenging. challenging.

slide-4
SLIDE 4

Formal Concept Analysis Formal Concept Analysis

  • Formal concept analysis (FCA), a mathematical

Formal concept analysis (FCA), a mathematical approach to data analysis based on lattice theory, approach to data analysis based on lattice theory, has been advocated to represent and process has been advocated to represent and process medical knowledge in different topics related to medical knowledge in different topics related to decision support systems. decision support systems.

slide-5
SLIDE 5

Example: A family Example: A family

slide-6
SLIDE 6

Study Purpose Study Purpose

  • In the study, the potential role of formal

In the study, the potential role of formal concept analysis on concept concept analysis on concept-

  • oriented view
  • riented view

generation for clinical data is explored. generation for clinical data is explored.

slide-7
SLIDE 7

Materials Materials

  • Clinical Data

Clinical Data

  • A collection of 386 Japanese discharge summaries

A collection of 386 Japanese discharge summaries

  • btained from cardiovascular domain.
  • btained from cardiovascular domain.
  • Knowledge sources

Knowledge sources

  • The Japanese version of

The Japanese version of MeSH MeSH (MSHJPN) in (MSHJPN) in UMLS2005AA (54,550 entries). UMLS2005AA (54,550 entries).

Developed by the NLM

Developed by the NLM

  • MEDIS version 2.3

MEDIS version 2.3 --

  • -The Japanese standard

The Japanese standard dictionaries of diagnosis terms (19,660 entries) and dictionaries of diagnosis terms (19,660 entries) and procedural terms (9,686 entries). procedural terms (9,686 entries).

Developed by the MEDIS

Developed by the MEDIS-

  • DC in Japan

DC in Japan

slide-8
SLIDE 8

System Construction System Construction

  • FCAView

FCAView Tab: Tab: A Prot

A Proté

ég

gé

é-

  • 2000 tab plug

2000 tab plug-

  • in

in

  • A virtual patient records system

A virtual patient records system

  • A ontology

A ontology-

  • based knowledge base

based knowledge base

  • Medical concepts

Medical concepts

  • Formal concept analysis

Formal concept analysis

  • A natural language processing (NLP) module

A natural language processing (NLP) module

  • A formal concept analysis (FCA) module

A formal concept analysis (FCA) module

slide-9
SLIDE 9

The structure of The structure of discharge summary discharge summary represented by a represented by a XML file XML file

<?xml version="1.0" encoding="Shift_JIS"?> <!DOCTYPE DischargeSummary SYSTEM "DischargeSummary.dtd"> <DischargeSummary> <PatientDischargeSummary> <FileInformation> <FileID>pcdata</FileID> <PatientID>pcdata</PatientID> </FileInformation> <PatientInformation> <PatientAge>pcdata</PatientAge> <PatientSex>pcdata</PatientSex> <PatientOccupation>pcdata</PatientOccupation> </PatientInformation> <DateInformation> <AdmissionDate>pcdata</AdmissionDate> <DischargeDate>pcdata</DischargeDate> </DateInformation> <DiagnosisList> <PrimaryDiagnosis>pcdata</PrimaryDiagnosis> <SecondaryDiagnosis>pcdata</SecondaryDiagnosis> </DiagnosisList> <PatientSummary> <Complaint>pcdata</Complaint> <CurrentHistory>pcdata</CurrentHistory> <PastHistory>pcdata</PastHistory> <OtherHistory>pcdata</OtherHistory> <ExaminationRecords>pcdata</ExaminationRecords> <InvestigationRecords>pcdata</InvestigationRecords> <ProgressRecords>pcdata</ProgressRecords> </PatientSummary> </PatientDischargeSummary> </DischargeSummary>

slide-10
SLIDE 10

An Example of the Virtual Patient Records An Example of the Virtual Patient Records

slide-11
SLIDE 11

Ontology Ontology-

  • based Knowledge Base

based Knowledge Base

Class Slot Instance Case id

slide-12
SLIDE 12

NLP Module NLP Module

  • ChaSen

ChaSen version 2.3 version 2.3

A Japanese morphological analysis system

A Japanese morphological analysis system

Open source

Open source

Developed by Nara Institute of Science and Technology

Developed by Nara Institute of Science and Technology

  • MACD

MACD

Morphological Analyzer Connectivity Driver

Morphological Analyzer Connectivity Driver-

  • model

model

As the Java interface of

As the Java interface of ChaSen ChaSen

Developed by Nara Institute of Science and Technology

Developed by Nara Institute of Science and Technology

  • User dictionaries:

User dictionaries:

MSHJPN

MSHJPN

MEDIS version 2.3

MEDIS version 2.3

slide-13
SLIDE 13

FCA Module FCA Module

  • The Java API of Concept Explorer version 1.2

The Java API of Concept Explorer version 1.2

  • Open source project

Open source project

  • To generate the concept oriented views for the

To generate the concept oriented views for the clinical data clinical data

slide-14
SLIDE 14
slide-15
SLIDE 15

Results (I) Results (I)

  • View generation for individual patient records

View generation for individual patient records

  • The items about the structure knowledge of the patient

The items about the structure knowledge of the patient records used as the formal objects records used as the formal objects

Primary diagnosis

Primary diagnosis

Secondary diagnoses

Secondary diagnoses

Chief Complaints

Chief Complaints

Current history

Current history

Past history

Past history

Other histories

Other histories

Examination records

Examination records

Investigation records

Investigation records

Progress records

Progress records

  • The medical concepts extracted from each part used as

The medical concepts extracted from each part used as the formal attributes the formal attributes

slide-16
SLIDE 16

Context of an Individual Case by Cross Context of an Individual Case by Cross-

  • table

table

Medical Concepts Structural Items

slide-17
SLIDE 17

Concept Concept-

  • Oriented View of an Individual Case by Lattice

Oriented View of an Individual Case by Lattice

Effort Angina

Shortness of breath, A feeling of general fatigue Impaired liver function

slide-18
SLIDE 18

Results (II) Results (II)

  • View generation for the similar cases

View generation for the similar cases

  • The similar cases indicated by the case ids

The similar cases indicated by the case ids were used as the formal objects were used as the formal objects

  • The medical concepts extracted from each

The medical concepts extracted from each case were used as the formal attributes case were used as the formal attributes

slide-19
SLIDE 19

Context of the Similar Cases by Cross Context of the Similar Cases by Cross-

  • table

table

Medical Concepts Case Ids

slide-20
SLIDE 20

Concept Concept-

  • Oriented View of the Similar Cases by Lattice

Oriented View of the Similar Cases by Lattice

Effort Angina

Chest Pain Chest Discomfort Hyperlipidemia Shortness of Breath Diabetes Mellitus Type II

slide-21
SLIDE 21

Results (III) Results (III)

  • Implementation of information model for

Implementation of information model for practical use practical use

  • Converting the lattice diagram into a concept

Converting the lattice diagram into a concept tree tree

  • Developing the filters to restrict the context size

Developing the filters to restrict the context size

slide-22
SLIDE 22

For Context Of The Similar Cases For Context Of The Individual Case Impaired Liver Function Effort Angina

slide-23
SLIDE 23
  • Context filter using

Context filter using Structure Knowledge Structure Knowledge

Primary diagnosis

Primary diagnosis

Secondary diagnosis

Secondary diagnosis

Chief complaints

Chief complaints

Current history

Current history

Past history

Past history

Other history

Other history

Examination records

Examination records

Investigation records

Investigation records

Progress records

Progress records

Effort Angina

slide-24
SLIDE 24
  • Context filter using

Context filter using Semantic Knowledge Semantic Knowledge of

  • f

medical concepts medical concepts

  • Noun

Noun-

  • Diagnostic Term

Diagnostic Term

  • Noun

Noun-

  • Procedural Term

Procedural Term

  • Noun

Noun-

  • Modifier

Modifier

  • Noun

Noun-

  • MeSH

MeSH Term Term

  • Noun

Noun-

  • Compound Term

Compound Term

  • Noun

Noun-

  • Others

Others

Effort Angina

slide-25
SLIDE 25
  • The filtered context:

The filtered context:

  • Formal objects:

Formal objects:

32

32 cases with primary cases with primary diagnosis of diagnosis of Effort Effort Angina Angina

  • Formal attributes:

Formal attributes:

All medical concepts

All medical concepts with semantic type of with semantic type of Diagnosis Term Diagnosis Term, , extracted from the extracted from the Chief Complaints Chief Complaints part part

  • f records
  • f records

Effort Angina Chest Pain

slide-26
SLIDE 26

Discussion Discussion

  • Automating view generation by integrating the

Automating view generation by integrating the NLP, Ontology NLP, Ontology-

  • based knowledge base, with the

based knowledge base, with the FCA technique. FCA technique.

  • The individual patient records

The individual patient records

  • The similar cases

The similar cases

  • Features of the system

Features of the system

  • Processing free

Processing free-

  • text clinical data

text clinical data

  • Providing flexible way

Providing flexible way

for browsing using concept tree

for browsing using concept tree

for adapting the information needs of clinicians using

for adapting the information needs of clinicians using context filters that are based on structural knowledge and context filters that are based on structural knowledge and semantic knowledge semantic knowledge

slide-27
SLIDE 27

Discussion Discussion Generalization Consideration (I) Generalization Consideration (I)

  • To support HL

To support HL-

  • 7 Clinical Data Architecture (CDA) as

7 Clinical Data Architecture (CDA) as input format. input format.

Local Clinical Documents Local Clinical Documents HL7 CDA

Transformation

Input

Concept-Oriented View System

slide-28
SLIDE 28

Discussion Discussion Generalization Consideration (II) Generalization Consideration (II)

  • To visualize the Prot

To visualize the Proté

ég

gé

é-

  • based

based ontologies

  • ntologies.

.

  • We assume that the instances (i.e. the formal

We assume that the instances (i.e. the formal

  • bjects) of a class in Prot
  • bjects) of a class in Proté

ég

gé

é-

  • 2000, together

2000, together with its own slots (i.e. the formal attributes), with its own slots (i.e. the formal attributes), could form a formal context that would interests could form a formal context that would interests the users. the users.

  • the instances of a class with its slots in Boolean type

the instances of a class with its slots in Boolean type

  • the instances of a class with it slots in Multiple

the instances of a class with it slots in Multiple Instance type. Instance type.

slide-29
SLIDE 29
slide-30
SLIDE 30

Acknowledgements Acknowledgements

  • The study was supported in part by the Grants

The study was supported in part by the Grants-

  • in

in-

  • Aid of the Japan Society for the Promotion of

Aid of the Japan Society for the Promotion of Science. Science.

  • Special thanks to Mr. Harold R.

Special thanks to Mr. Harold R. Solbrig Solbrig in in Division of Division of BioMedical BioMedical Informatics, Mayo Clinic, Informatics, Mayo Clinic, Rochester, MN, who contributed the idea about Rochester, MN, who contributed the idea about the generalization of our the generalization of our FCAView FCAView Tab. Tab.