Hydronephrosis, Hydronephrosis Congenital
Conditions
Brief summary
Hydronephrosis is a common congenital kidney anomaly. While most cases resolve on their own, some require surgery. Clinicians rely on repeated ultrasounds and sometimes invasive tests to decide if surgery is needed, but predicting outcomes is difficult. Researchers at SickKids developed an AI model that analyzes ultrasound images to assist in diagnosing and managing hydronephrosis. This study tests how well the AI integrates into real-world care. Clinicians will first make care decisions without AI and then review the AI's prediction before deciding whether to change their plan. A separate expert, unaware of whether AI influenced the first clinician's plan, will make the final decision to ensure care remains unchanged. The study will assess whether AI improves decision-making, reduces unnecessary tests, and fits into clinical workflows. If successful, the AI model could serve as a complementary tool to make diagnoses more efficient and precise while minimizing invasive procedures.
Interventions
The AI intervention is a deep learning algorithm used to predict obstructive hydronephrosis. It was developed at SickKids and has recently completed the silent trial phase. This clinical trial aims to validate the model's clinical integration by assessing its impact on clinician decision-making and care plan recommendations. To uphold standard care, a blinded clinician will make final decisions.
Sponsors
The Hospital for Sick Children
Study design
Allocation
NA
Intervention model
SINGLE_GROUP
Primary purpose
OTHER
Masking
NONE
Masking description
This study will be a partially blinded trial as a third blinded clinician who makes the final clinical decision will be unaware if and what changes were made after clinician exposure to the AI model. Since, standard of care is maintained, patients will not be aware of the impact of the AI model
Intervention model description
The intervention is an AI algorithm for the prediction of obstructive HN. When children with HN are seen in clinic, their ultrasound imaging and history will be provided to an initial clinician who will first formulate a plan of care without access to the AI model as per the standard of care. After the initial plan is documented and before discussion with the primary provider, the initial clinician will then be granted access to the AI model, where they can input the ultrasound images and receive the model's prediction. The clinician can choose to modify or maintain their drafted plan based on the model's output. The clinician's final drafted plan will subsequently be discussed with the blinded final clinical expert (primary provider) who will make the final decision to maintain the standard of care for each patient. The final clinical expert will be blinded to whether the initial clinician changed their plan or not given the AI model.
Eligibility
Sex/Gender
ALL
Age
0 Months to 24 Months
Healthy volunteers
No
Inclusion criteria
* Seen for HN in-person in the Pediatric Urology clinic with ultrasound scans taken at SickKids * New and follow-up patients 0-24 months.
Exclusion criteria
* Older than 24m * Concurrent urinary tract anomalies (duplex configurations; PUV etc.) * History of renal surgical intervention (post-op patients)
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Change in Clinician Management Decisions Following Exposure to the AI Model | Immediately after AI model exposure during each case review session, through study completion (average of 6 months) | The proportion of clinician management decisions revised immediately after exposure to the AI model output. Management decisions include: (1) discharge, (2) monitor with ultrasound, (3) additional invasive testing, or (4) referral for surgery. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Agreement Between Clinician Decisions and Expert Reference Decisions Using Cohen's Kappa | Immediately after clinician review and AI model exposure during each case review session, through study completion (average of 6 months) | Agreement between clinician management decisions and the expert reference decision will be assessed before and after AI exposure using Cohen's kappa statistic. Higher kappa values indicate greater agreement. |
| Proportion of Management Decision Changes Stratified by Clinician Experience Level | Immediately after AI model exposure during each case review session, through study completion (average of 6 months) | The proportion of clinician management decisions revised after AI model exposure will be compared across clinician subgroups, including training level and years of experience. |
Outcome results
None listed