Apply Machine Learning to the Interpretation of Urinary Crystal Morphology.
1 other identifier
observational
200
0 countries
N/A
Brief Summary
The goal of this observational study is to developing an image-based artificial intelligence software that can automatically interpret the types and sizes of crystals in urine. The main question\[s\] it aims to answer are:
- Allowing healthcare professionals to input urine images and receive real-time reading results on crystal types and sizes.
- This aims to provide a faster, more objective, and accurate analysis of crystals. We anticipate delivering an image AI software suitable for practical applications, promoting the automation and accuracy of urine crystal analysis.
Trial Health
Trial Health Score
Automated assessment based on enrollment pace, timeline, and geographic reach
participants targeted
Target at P75+ for all trials
Started Jan 2024
Shorter than P25 for all trials
Health score is calculated from publicly available data and should be used for screening purposes only.
Trial Relationships
Click on a node to explore related trials.
Study Timeline
Key milestones and dates
First Submitted
Initial submission to the registry
December 12, 2023
CompletedFirst Posted
Study publicly available on registry
December 21, 2023
CompletedStudy Start
First participant enrolled
January 1, 2024
CompletedPrimary Completion
Last participant's last visit for primary outcome
December 31, 2024
CompletedStudy Completion
Last participant's last visit for all outcomes
December 31, 2024
CompletedDecember 21, 2023
December 1, 2023
1 year
December 12, 2023
December 12, 2023
Conditions
Keywords
Outcome Measures
Primary Outcomes (1)
Kappa statistics
Used for comparing between a new instrument and a standard instrument to determine whether the new instrument exhibits a certain level of performance or accuracy.
The machine requires approximately 0.5 hours to complete the interpretation of around 800 urine crystal images.
Study Arms (2)
Manual microscopic observation
Control Group: Manual analysis of urine crystal images, distinguishing crystal types, recording accuracy, and analyzing the time consumed.
Machine interpretation
The urine crystal images undergo analysis for crystal types, followed by image preprocessing and category labeling for machine software learning and inference. Subsequently, the interpreted results will be subjected to statistical analysis software to assess accuracy.
Eligibility Criteria
Calcium oxalate kidney stone patient
You may qualify if:
- Retrospectively analyze the urine crystal images preserved from the previous study 107123-E for crystal type analysis. Subsequently, conduct image preprocessing and label categorization for machine software learning and inference. The interpreted results will then be assessed for accuracy using statistical analysis software.
You may not qualify if:
- Not applicable
Contact the study team to confirm eligibility.
Sponsors & Collaborators
- Yi-Shiou Tsenglead
MeSH Terms
Conditions
Condition Hierarchy (Ancestors)
Central Study Contacts
Study Design
- Study Type
- observational
- Observational Model
- CASE CONTROL
- Time Perspective
- RETROSPECTIVE
- Sponsor Type
- OTHER
- Responsible Party
- SPONSOR INVESTIGATOR
- PI Title
- Attending physician
Study Record Dates
First Submitted
December 12, 2023
First Posted
December 21, 2023
Study Start
January 1, 2024
Primary Completion
December 31, 2024
Study Completion
December 31, 2024
Last Updated
December 21, 2023
Record last verified: 2023-12
Data Sharing
- IPD Sharing
- Will not share
This study involves retrospectively analyzing urine crystal images preserved from a previous study (Intramural Research Project Code 107123-E at Far Eastern Memorial Hospital). Subsequently, image preprocessing and category labeling will be applied to facilitate machine software learning and inference. The interpreted results will then undergo statistical analysis for accuracy using dedicated software. Participant information and experimental data are stored on a computer in a shared laboratory, with access secured through password protection to ensure data security. Participant identities are encoded for confidentiality. Once the required information is collected, the original participant identities will be linked with their respective codes. Researchers will not obtain the list of potential participants through privacy-invasive means.