UMIN-ICDS Clinical Trial

Public title

Prediction of Postoperative Outcomes and Ultra-Long-Term Degeneration after Matrix-Associated Autologous Chondrocyte Implantation (MACI) using Artificial Intelligence

Acronym

Predicting outcomes after cultured cartilage transplant surgery (MACI) using AI

Scientific Title

Prediction of Postoperative Outcomes and Ultra-Long-Term Degeneration after Matrix-Associated Autologous Chondrocyte Implantation (MACI) using Artificial Intelligence: A Retrospective Observational Study

Scientific Title:Acronym

Postoperative outcome prediction model for cultured cartilage transplantation (MACI) using AI

Region

Japan

Condition

Traumatic cartilage defect, Osteochondritis dissecanse of the knee, knee osteoarthritis

Classification by specialty

Orthopedics

Classification by malignancy

Others

Genomic information

NO

Narrative objectives1

The goal of this study is to build predictive models for postoperative outcomes and ultra-long-term degradation patterns using machine learning and time-series deep learning algorithms for patients who underwent autologous cultured cartilage implantation (MACI) for knee joint cartilage defects. To overcome the ceiling effects in traditional evaluation criteria, we first calculate the clinical threshold (cutoff value) of MOI (Maximal Outcome Improvement) using the anchor method from our own institution's data. Next, we apply this threshold to a large-scale post-marketing registry in Japan (RWD) to determine whether each case achieved MOI or not. Finally, by constructing a machine learning model (such as LightGBM) with 'MOI achievement or failure' as the target variable, we analyze the factors influencing MOI achievement in domestic real-world data from multiple angles. This lays the foundation for a personalized shared decision-making (SDM) support system that can suggest the optimal surgical procedure or the necessity of combined surgeries (such as high tibial osteotomy [HTO]) based on preoperative patient background.

Basic objectives2

Safety,Efficacy

Basic objectives -Others

Trial characteristics_1

Trial characteristics_2

Developmental phase

Primary outcomes

MOI: Maximal Outcome Improvement

Key secondary outcomes

Study type

Others,meta-analysis etc

Basic design

Randomization

Randomization unit

Blinding

Control

Stratification

Dynamic allocation

Institution consideration

Blocking

Concealment

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

Age-lower limit

10

years-old

<=

Age-upper limit

70

years-old

>

Gender

Male and Female

Key inclusion criteria

Patients who underwent autologous cultured cartilage implantation: MACI for knee cartilage defects at the Orthopedic Surgery Department of Shimane University Hospital between January 1, 1996, and December 31, 2025.
Those from whom appropriate verbal consent by phone was obtained to use their medical information and interview data for this study.
Those who have clinical scores; Lysholm score, KOOS score, Forgotten Joint Score12 recorded preoperatively and postoperatively (at any time from 1 month after surgery to the final follow-up).
Those who provided answers to the anchor question in the phone survey, either "If a similar cartilage injury were found in your current knee and the doctor recommended the same 'cultured cartilage implantation,' would you want to undergo this surgery again?: Willingness for repeat surgery, primary analysis" or "Considering all daily activities, pain level, and physical function limitations, are you satisfied with your current condition? : Satisfaction, secondary analysis", or both. Patients who were aged 10 years or older and 70 years or younger at the time of surgery.

Key exclusion criteria

1) Those with an active joint infection in the same knee.
2) Those with severe inflammatory joint diseases, such as advanced rheumatoid arthritis.
3) Those whose follow-up data is completely missing, making it impossible to validate the AI model.

Target sample size

788

Name of lead principal investigator

1st name	YUJI
Middle name
Last name	UCHIO

Organization

Shimane University, Faculty of Medicine

Division name

Department of Orthopaedic Surgery

Zip code

693-8501

Address

89-1, Enya Town, Izumo City, Shimane Prefecture

TEL

0853202240

Email

uchio@med.shimane-u.ac.jp

Name of contact person

1st name	YUJI
Middle name
Last name	UCHIO

Organization

Shimane University, Faculty of Medicine

Division name

Department of Orthopaedic Surgery

Zip code

693-8501

Address

89-1, Enya Town, Izumo City, Shimane Prefecture

TEL

0853202240

Homepage URL

Email

uchio@med.shimane-u.ac.jp

Institute

Shimane University

Institute

Department

Personal name

Organization

Self funding

Organization

Division

Category of Funding Organization

Other

Nationality of Funding Organization

Co-sponsor

Name of secondary funder(s)

Organization

Shimane University Hospital, Clinical Trial Review Board

Address

89-1, Enya Town, Izumo City, Shimane Prefecture

Tel

0853-20-2515

Email

kenkyu@med.shimane-u.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

2026

Year

10

Month

16

Day

URL releasing protocol

Publication of results

Unpublished

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

Recruitment status

Preinitiation

Date of protocol fixation

2026

Year

10

Month

14

Day

Date of IRB

2026

Year

10

Month

14

Day

Anticipated trial start date

2026

Year

10

Month

19

Day

Last follow-up date

2031

Year

03

Month

31

Day

Date of closure to data entry

Date trial data considered complete

Date analysis concluded

Other related information

After getting approval from the ethics committee and permission from the head of the research institute, researchers will enter the following medical record information into a dedicated computer isolated from external access within the Department of Orthopedic Surgery at Shimane University Faculty of Medicine, and create a database (electronic survey form). We will clearly separate and manage the "existing information (preoperative data, etc.)" extracted from medical records and the "newly acquired information (postoperative scores and anchor questions)" obtained through telephone surveys.
Also, when receiving RWD data from the institution providing existing information: J-TEC Co., Ltd., the company will remove medical record IDs and names, and send data processed in a way that does not allow easy identification on our side (with study-specific ID assigned via encrypted communication or secure physical media. The collected items include all of the following: background factors: age, sex, BMI, cause, surgical factors, defect size, transplant site, cover material [periosteal flap/collagen membrane, presence of concurrent surgery [HTO, ligament reconstruction, etc., pre-op scores: Lysholm score, KOOS score, post-op scores: Lysholm score, KOOS score, FJS12 score, and complications/additional surgeries: tissue hypertrophy, joint contracture, graft detachment, additional surgery.

Registered date

2026

Year

10

Month

16

Day

Last modified on

2026

Year

10

Month

16

Day

Link to view the page

Value
https://center6.umin.ac.jp/cgi-open-bin/ctr_e/ctr_view.cgi?recptno=R000072467