UMIN-CTR Clinical Trial

Unique ID issued by UMIN	UMIN000052838
Receipt number	R000060299
Scientific Title	Understanding Interests (Interests and Desires) in Dialogue Analysis of Complaint Settlement Cases -Comparison of co-occurrence networks (econometric text analysis) and artificial intelligence (AI) generated in a local (data protection) environment-
Date of disclosure of the study information	2023/11/20
Last modified on	2023/11/18 15:29:52

* This page includes information on clinical trials registered in UMIN clinical trial registed system.
* We don't aim to advertise certain products or treatments

Basic information

Public title

Understanding Interests (Interests and Desires) in Dialogue Analysis of Complaint Settlement Cases
-Comparison of co-occurrence networks (econometric text analysis) and artificial intelligence (AI) generated in a local (data protection) environment-

Acronym

Scientific Title

Scientific Title:Acronym

Region

Japan

Condition

Cases of previous complaint settlements conducted by medical dialogue promoters and approved by patients/families

Classification by specialty

Not applicable

Classification by malignancy

Others

Genomic information

Objectives

Narrative objectives1

Medical mediation (collaborative dialogue in a tripolar structure) was founded in 2004 by Hitotaka Wada and Yoshimi Nakanishi to fit the Japanese medical culture. The concept has been adopted in Japan for over 15 years with the goal of promoting dialogue and collaborative decision-making. Medical mediation has improved the communication skills of healthcare providers and contributed to patient support systems, but there is a lack of evaluation and sharing tools.

Co-occurrence network analysis requires specialized skills, while generative AI is simpler to use. These tools are expected to contribute to a deeper understanding of patients' and families' needs and problems, building trust in the medical field, and improving education for medical professionals.

The purpose of this study is to compare and evaluate the performance of the new generative AI with that of linguistic analysis using co-occurrence networks conducted in previous studies. This will enable the selection of effective tools to support conflict recognition, causal evaluation, and clinical reasoning practices.

Basic objectives2

Efficacy

Basic objectives -Others

Trial characteristics_1

Trial characteristics_2

Developmental phase

Assessment

Primary outcomes

Correctness of Interests (Interests and Desires) of Parties by Generative AI in Local Environment in Grievance Settlement Dialogues

Key secondary outcomes

5-point rating for accuracy of estimation of generated AI by local environment, understanding of emotions, and understanding of factual relationships
Examination of key languages for prompt generation, investigation of languages and words of importance

Base

Study type

Others,meta-analysis etc

Study design

Basic design

Randomization

Randomization unit

Blinding

Control

Stratification

Dynamic allocation

Institution consideration

Blocking

Concealment

Intervention

No. of arms

Purpose of intervention

Type of intervention

Interventions/Control_1

Interventions/Control_2

Interventions/Control_3

Interventions/Control_4

Interventions/Control_5

Interventions/Control_6

Interventions/Control_7

Interventions/Control_8

Interventions/Control_9

Interventions/Control_10

Eligibility

Age-lower limit

20 years-old <=

Age-upper limit

80 years-old >

Gender

Male and Female

Key inclusion criteria

Complaint cases (including accident cases) that were settled and resolved. Cases in which consent/permission for research was obtained at the time of previous settlement resolution.

Key exclusion criteria

Cases where consent is not obtained, cases where there is no language (narrative) of complaint

Target sample size

Research contact person

Name of lead principal investigator

1st name Toshimi

Middle name

Last name Nakanishi

Organization

Yamagata University Medical School Hospital

Division name

Center for Comprehensive Medical Education

Zip code

990-2331

Address

2-2-2, Iida-Nishi, Yamagata City, Yamagata Prefecture

TEL

0236285400

Email

hayasakatatsuya1101@gmail.com

Public contact

Name of contact person

1st name Tatsuya

Middle name

Last name Hayasaka

Organization

Yamagata University Medical School Hospital

Division name

Department of Anesthesiology

Zip code

990-2331

Address

2-2-2, Iida-Nishi, Yamagata City, Yamagata Prefecture

TEL

0236285400

Homepage URL

Email

hayasakatatsuya1101@gmail.com

Sponsor or person

Institute

Yamagata Universal Faculty of Medcine

Institute

Department

Personal name

Funding Source

Organization

Department of Anesthesiology, Yamagata University Faculty of Medicine

Organization

Division

Category of Funding Organization

Self funding

Nationality of Funding Organization

Other related organizations

Co-sponsor

Name of secondary funder(s)

IRB Contact (For public release)

Organization

The Ethical Review Committee of Yamagata University Faculty of Medicine

Address

2-2-2, Iida-Nishi, Yamagata City, Yamagata Prefecture

Tel

0236285015

Email

ikekenkyu@jm.kj.yamagata-u.ac.jp

Secondary IDs

Study ID_1

Org. issuing International ID_1

Study ID_2

Org. issuing International ID_2

IND to MHLW

Institutions

Other administrative information

Date of disclosure of the study information

2023 Year 11 Month 20 Day

Related information

URL releasing protocol

Publication of results

Unpublished

Result

URL related to results and publications

Number of participants that the trial has enrolled

Results

Results date posted

Results Delayed

Results Delay Reason

Date of the first journal publication of results

Baseline Characteristics

Participant flow

Adverse events

Outcome measures

Plan to share IPD

IPD sharing Plan description

Progress

Recruitment status

Open public recruiting

Date of protocol fixation

2023 Year 10 Month 01 Day

Date of IRB

2023 Year 11 Month 09 Day

Anticipated trial start date

2023 Year 11 Month 13 Day

Last follow-up date

2030 Year 12 Month 31 Day

Date of closure to data entry

Date trial data considered complete

Date analysis concluded

Other

Other related information

The procedure for this study focuses on collecting 50 examples of patient narratives related to allegations that have been settled and entering them into the AI through prompts (ready for input) to generate responses. This process takes place in a local environment with no Internet access and generates multiple responses for each case. The creation of the prompts is based on the Fukatsu-style questioning technique and includes the role of the medical mediator, understanding of interest, classification of emotions (based on Pulchick's Circle of Emotions), and citation of the reasons for the presumed responses. In addition, the method used to create the co-occurrence network is based on Quantitative Text Analysis and KH Coder software. Finally, an expert evaluation is performed to assess multiple aspects of the interest's inferred answers, including accuracy, appropriateness, validity, understandability, feasibility, presence of misinformation, and readability. Emotional estimation is also a part of the evaluation.

Management information

Registered date

2023 Year 11 Month 18 Day

Last modified on

2023 Year 11 Month 18 Day

Link to view the page

Value
https://center6.umin.ac.jp/cgi-open-bin/ctr_e/ctr_view.cgi?recptno=R000060299