UMIN-CTR Clinical Trial

Public title

A study of AI conversation in telemedicine for Parkinson's disease

Acronym

A study of AI conversation in telemedicine for Parkinson's disease

Scientific Title

A Randomized study of AI dialogue in telemedicine for Parkinson's disease

Scientific Title:Acronym

A Randomized study of AI dialogue in telemedicine for Parkinson's disease

Region

Japan

Condition

Parkinson's disease

Classification by specialty

Neurology

Classification by malignancy

Others

Genomic information

NO

Narrative objectives1

Conversation with AI improves the facial expressions and utterances in Parkinson's disease.

Basic objectives2

Efficacy

Basic objectives -Others

Trial characteristics_1

Trial characteristics_2

Developmental phase

Primary outcomes

Sound parameters and Facial expression features during the talking between the subject and the doctor.

Key secondary outcomes

Study type

Interventional

Basic design

Parallel

Randomization

Randomized

Randomization unit

Cluster

Blinding

Open -no one is blinded

Control

No treatment

Stratification

Dynamic allocation

Institution consideration

Blocking

Concealment

No. of arms

2

Purpose of intervention

Treatment

Type of intervention

Other

Interventions/Control_1

Daily,for five months,talking with AI chatbot

Interventions/Control_2

Once or twice a week,for five months,talking with a doctor

Interventions/Control_3

Interventions/Control_4

Interventions/Control_5

Interventions/Control_6

Interventions/Control_7

Interventions/Control_8

Interventions/Control_9

Interventions/Control_10

Age-lower limit

20

years-old

<=

Age-upper limit

80

years-old

>=

Gender

Male and Female

Key inclusion criteria

1, Patients who satisfy the diagnostic criteria for Parkinson's disease.(MDS diagnostic criteria)
2, Ages between 20 and 80
3, Japanese and native language is Japanese
4, Participants who have been given sufficient explanations to participate in this study,and with sufficient understanding and who have given their informed consent

Key exclusion criteria

1, Patients who have been diagnosed with dementia (MMSE less than 20 points)
2, Patients who have a trouble to hear the sound of the iPad
3, In addition,patients who are judges by the investigation to be inappropriate as subjects

Target sample size

20

Name of lead principal investigator

1st name	Genko
Middle name
Last name	Oyama

Organization

Juntendo University Graduate School of Medicine

Division name

Department of Nerology

Zip code

1138421

Address

Hongo 2-1-1,Bunkyo-ku,Tokyo,Japan

TEL

0358023111

Email

g_oyama@juntendo.ac.jp

Name of contact person

1st name	Mayuko
Middle name
Last name	Ogawa

Organization

Juntendo University Graduate School of Medicine

Division name

Department of Nerodegenerative and Dementied Disorders

Zip code

1138421

Address

Hongo 2-1-1,Bunkyo-ku,Tokyo,Japan

TEL

0358023111

Homepage URL

Email

maogawa@juntendo.ac.jp

Institute

Juntendo University

Institute

Department

Personal name

Organization

Kirin Holdings Company, Limited
Mitsubishi UFJ Lease & Finance Company Limited
GLORY LTD.

Organization

Division

Category of Funding Organization

Profit organization

Nationality of Funding Organization

Co-sponsor

Name of secondary funder(s)

Organization

Juntendo Clinical Research and Trial Center

Address

Hongo3-1-3,Bunkyo-ku,Tokyo,Japan 113-8431

Tel

03-5802-1584

Email

kenkyu5858@juntendo.ac.jp

Secondary IDs

NO

Study ID_1

Org. issuing International ID_1

Study ID_2

Org. issuing International ID_2

IND to MHLW

Institutions

Date of disclosure of the study information

2020

Year

03

Month

04

Day

URL releasing protocol

https://pubmed.ncbi.nlm.nih.gov/35596975/

Publication of results

Published

URL related to results and publications

https://pubmed.ncbi.nlm.nih.gov/35596975/

Number of participants that the trial has enrolled

20

Results

A repeated-measures analysis of variance revealed that the chatbot conversations had a significant interaction effect on the mean and standard deviation of the smile index during smile sections(both P=0.02), maximum duration of the initial rise of the smile index(P=0.04), and frequency of filler words(P=0.04).Explorative analysis using statistical and machine-learning models revealed that the smile indices and several speech features were associated with motor symptoms, cognition, and mood in PD.

Results date posted

2023

Year

07

Month

19

Day

Results Delayed

Results Delay Reason

Date of the first journal publication of results

Baseline Characteristics

There were 20 participants (intervention group n=10, control group n=10). The mean age was 67.6(10.5) years in the intervention group and 64.3(6.9) years in the control group. Duration of disease was 10.7(4.2) years in the intervention group and 11.8(5.2) years in the control group.

Participant flow

Participants underwent an in-person clinical assessment by a neurologist at the time of recruitment, before and after the intervention. The following scales were administered when the participants were on medications: the MDS-sponsored revision of the Unified Parkinson's Disease Rating Scale (MDS-UPDRS), Mini-Mental State Examination (MMSE) and Japanese version of Montreal Cognitive Assessment (MoCA-J), Beck Depression Inventory-II (BDI-II), and Parkinson's Disease Questionnaire-39 (PDQ-39). Facial expressions were videotaped using an iPad Air 2 and c922 pro stream webcam as reference data for subsequent analysis, which were placed in front of the patients. We recorded two sets of "straight face" and "smile face", which were obtained by instructing participants to imitate the sample picture of a smile. Participants could see their faces during the recording with the iPad monitor.

Adverse events

Nothing

Outcome measures

Primary endpoints
(1) Speech features during the dialogue between the subject and the doctor: acoustic features (Jitter (frequency fluctuation), Shimmer (amplitude fluctuation), MFCC (vocal tract characteristics)), speech features (silent intervals, stuttering), content features (topic repetition frequency, inter-topic similarity, sentence length)
(2) Facial expression features during the dialogue between the subject and the doctor: number of occurrences, timing of occurrences, facial expression score (degree of smiling)


Secondary evaluation items

The following items will be measured as secondary endpoints
(1) Basic subject information: age, gender, diagnosis, medical history and treatment history
(2) Observation of interaction between the subject and the physician: time required, number of times the physician encouraged the subject to interact with the AI
(3) Motor function test: Movement Disorder Society-Unified Parkinson's Disease Rating Scale (MDS-UPDRS) evaluation under video recording
(4)Cognitive function tests: Mini Mental State Examination (MMSE), Montreal Cognitive Assessment (MoCA-J),
Digit Span, Stroop Test, Trail Making Test (TMT), Verbal Fluency Test (VFT), Logical Memory (LM) Ia/IIa, Digit Symbol Substitution Test (DSST), Rey Complex Figure Test (RCFT) Copy, Free and Cued Selective Reminding Test (FCSRT)
(5) Quality of Life (QoL) test: Parkinson's Disease Questionnaire-39 (PDQ-39)
(6) Depression scale: Beck Depression Index (BDI)

Plan to share IPD

IPD sharing Plan description

Recruitment status

Completed

Date of protocol fixation

2019

Year

04

Month

19

Day

Date of IRB

2019

Year

04

Month

19

Day

Anticipated trial start date

2019

Year

05

Month

01

Day

Last follow-up date

2021

Year

03

Month

31

Day

Date of closure to data entry

Date trial data considered complete

2020

Year

08

Month

31

Day

Date analysis concluded

Other related information

Registered date

2020

Year

03

Month

04

Day

Last modified on

2023

Year

07

Month

19

Day

Link to view the page

Value
https://center6.umin.ac.jp/cgi-open-bin/ctr_e/ctr_view.cgi?recptno=R000045276