(89 days)
The Momentum Spine app is an optical contour sensing mobile application intended to quantify asymmetries, assess body angles and curve progression related to postural asymmetries, including scoliosis. The device is available directly to lay users (Over-the-Counter) and may also be prescribed for use by physicians.
The device is intended for use in patients 8 years and older.
Momentum Spine is an optical contour sensing mobile application intended to quantify asymmetries, assess body angles and curve progression related to postural asymmetries, including scoliosis. The device is available directly to lay users (Over-the-Counter) and may also be prescribed for use by physicians.
From a simple video taken on a mobile device. Momentum Spine ('app') reconstructs a 3D model of the torso to quantify asymmetry using 3D imaging and artificial intelligence. The app is intended to be used by a combination of lay users (parents, guardians etc.) and health care professionals. The patients do not use the device on themselves.
The app is intended to be used on patients 8 years and older to scan and monitor postural asymmetries. The app can be used by patient populations suffering from postural deformities mainly scoliosis. Additionally, the device can also be used by an otherwise healthy population to scan for and monitor their overall spinal health.
Here's a breakdown of the acceptance criteria and study details for the Momentum Spine device, based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criterion (Cobb Angle Prediction) | Reported Device Performance |
|---|---|
| Predicted Cobb angle within 10 degrees of X-ray derived Cobb Angle. | The document states this is the appropriateness of performance, implying this is the acceptance criterion, but it does not directly state a reported performance metric against this criterion in terms of accuracy (e.g., how many predictions met this criterion). |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size for Test Set: 212 individuals (split as 60/20/20 for training/validation/test, so 20% of 212 = 42 individuals for the test set).
- Data Provenance:
- Timeframe of Data Collection: April 2021 to June 2023
- Country of Origin: Canada
- Retrospective or Prospective: Not explicitly stated, but the collection timeframe and demographic details suggest a retrospective dataset was compiled.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
- Number of Experts: Not specified.
- Qualifications of Experts: Not specified. The document only mentions that the ground truth is a "cobb angle derived from an X-ray (radiograph)." It does not detail who derived this Cobb angle or their qualifications.
4. Adjudication Method for the Test Set
- Adjudication Method: Not specified. As the number of experts is not stated, an adjudication method like 2+1 or 3+1 cannot be determined.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done
- MRMC Study Done: No. The document does not mention any MRMC study or comparative effectiveness study involving human readers with and without AI assistance. The testing focused on the AI algorithm's standalone performance against a ground truth.
6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done
- Standalone Performance Done: Yes. The AI testing summary explicitly states: "Predicted cobb angle is derived from our machine learning model." This indicates a standalone performance evaluation of the algorithm.
7. The Type of Ground Truth Used
- Type of Ground Truth: Expert consensus (implied) from X-ray data. Specifically, "Ground truth is a cobb angle derived from an X-ray (radiograph)." While the number and qualifications of experts are not given, the derivation of a Cobb angle from an X-ray typically involves a skilled radiologist or orthopedic specialist.
8. The Sample Size for the Training Set
- Sample Size for Training Set: 212 individuals total, with a 60/20/20 split for training/validation/test. Therefore, 60% of 212 = 127 individuals were used for the training set. (An additional 20% or 42 individuals would be for the validation set, which is also used during training).
9. How the Ground Truth for the Training Set Was Established
- How Ground Truth for Training Set Was Established: The same method as the test set: "Ground truth is a cobb angle derived from an X-ray (radiograph)." This implies that for all individuals in the dataset (training, validation, and test), their ground truth Cobb angles were obtained from X-ray radiographs.
N/A