(185 days)
The Atalante exoskeleton is intended to enable individuals with hemiplegia due to cerebrovascular accident (CVA) to perform ambulatory functions and mobility exercises, hands-free, in rehabilitation under the supervision of a trained operator. The operator must complete a training program prior to use of the device.
The Atalante system is intended to be used on adolescents of 18 years and older and adults, able to tolerate a stand-up position.
The device is not intended for sports or stair climbing.
The Atalante is a completely self-balancing walking system for people with mobility disabilities. It is a fully powered hip-knee-ankle lower body exoskeleton with 12 actuated degrees of freedom. Atalante is self-balancing and includes dynamic-walking control. Dynamic-walking allows the Atalante to consume significantly less power and have a more natural gait.
The provided text describes the Atalante exoskeleton and its substantial equivalence submission to the FDA. However, the document does not contain acceptance criteria for device performance in the format of a table, nor does it detail a study specifically designed to prove the device meets such criteria with precise metrics like accuracy, sensitivity, or specificity.
Instead, the document focuses on:
- Non-Clinical Performance Data: Demonstrating that the device meets internal, national, and international standards for electrical safety, EMC, software validation, mechanical verification, thermal testing, and useful life. This is reported as "Passed" for each test.
- Clinical Performance Data: Highlighting two clinical studies and real-world evidence to show safety and effectiveness in improving functional ambulation and overall balance in CVA patients. It states that all subjects completed performance outcome measures successfully and there were no serious adverse events.
Since the request asks for specific information that is not present in the provided text (such as a table of acceptance criteria with reported performance, sample sizes for test sets, expert qualifications, adjudication methods, MRMC studies, standalone performance, and detailed ground truth information for training sets), I will have to state where the information is absent.
Here's the breakdown of the information requested, based only on the provided text:
1. A table of acceptance criteria and the reported device performance
The document does not provide a table of acceptance criteria with specific quantitative performance metrics (e.g., accuracy, sensitivity, specificity, or numerical thresholds for functional improvement) and corresponding reported device performance. It generally states that the device "Passed" various tests or that clinical studies "demonstrated" safety and effectiveness.
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
- Sample Size for Clinical Studies (Test Set): "Two clinical studies with a total of 43 patients with cerebrovascular accident (CVA) were undertaken."
- Data Provenance: Not specified in terms of country of origin or whether the studies were retrospective or prospective. Given they are referred to as "clinical studies," they are typically prospective, but this is not explicitly stated. The mention of "real world evidence of use by over 250 patients" suggests a broader patient base but does not specify its provenance or use as a formal "test set" for performance evaluation in the same way as the 43 patients.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)
This information is not provided in the document. The clinical studies evaluated patient outcomes, but there's no mention of specific experts establishing a "ground truth" in the context of diagnostic or interpretive performance.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
This information is not provided in the document.
5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance
This type of study is not mentioned in the document. The device is a powered exoskeleton, not an AI-assisted diagnostic or interpretive tool where "human readers" would be involved in interpretation. The clinical studies assessed patient functional improvements.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
The device is a "Powered Lower Extremity Exoskeleton" intended to be used "under the supervision of a trained operator." Therefore, a "standalone" algorithm-only performance assessment in the context of diagnostic AI is not applicable. The device's performance is intrinsically tied to its use by a patient under operator supervision.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
For the clinical studies, the "ground truth" or primary outcome measured would be outcomes data related to functional ambulation abilities and overall balance improvement in CVA patients. These improvements are assessed through standard rehabilitation performance outcome measures.
8. The sample size for the training set
The document explicitly mentions clinical studies (test set) and real-world evidence, but does not provide a specific sample size for a "training set" in the context of machine learning model development. This device, as an exoskeleton, may undergo continuous calibration or adaptation, but the concept of a distinct "training set" for an AI model's ground truth, as typically understood in diagnostic AI, is not detailed.
9. How the ground truth for the training set was established
As no specific "training set" for an AI model is detailed, the method for establishing its "ground truth" is not provided. The documentation focuses on engineering validation and clinical outcomes for device performance.
§ 890.3480 Powered lower extremity exoskeleton.
(a)
Identification. A powered lower extremity exoskeleton is a prescription device that is composed of an external, powered, motorized orthosis that is placed over a person's paralyzed or weakened limbs for medical purposes.(b)
Classification. Class II (special controls). The special controls for this device are:(1) Elements of the device materials that may contact the patient must be demonstrated to be biocompatible.
(2) Appropriate analysis/testing must validate electromagnetic compatibility/interference (EMC/EMI), electrical safety, thermal safety, mechanical safety, battery performance and safety, and wireless performance, if applicable.
(3) Appropriate software verification, validation, and hazard analysis must be performed.
(4) Design characteristics must ensure geometry and materials composition are consistent with intended use.
(5) Non-clinical performance testing must demonstrate that the device performs as intended under anticipated conditions of use. Performance testing must include:
(i) Mechanical bench testing (including durability testing) to demonstrate that the device will withstand forces, conditions, and environments encountered during use;
(ii) Simulated use testing (
i.e., cyclic loading testing) to demonstrate performance of device commands and safeguard under worst case conditions and after durability testing;(iii) Verification and validation of manual override controls are necessary, if present;
(iv) The accuracy of device features and safeguards; and
(v) Device functionality in terms of flame retardant materials, liquid/particle ingress prevention, sensor and actuator performance, and motor performance.
(6) Clinical testing must demonstrate a reasonable assurance of safe and effective use and capture any adverse events observed during clinical use when used under the proposed conditions of use, which must include considerations for:
(i) Level of supervision necessary, and
(ii) Environment of use (
e.g., indoors and/or outdoors) including obstacles and terrain representative of the intended use environment.(7) A training program must be included with sufficient educational elements so that upon completion of training program, the clinician, user, and companion can:
(i) Identify the safe environments for device use,
(ii) Use all safety features of device, and
(iii) Operate the device in simulated or actual use environments representative of indicated environments and use.
(8) Labeling for the Physician and User must include the following:
(i) Appropriate instructions, warning, cautions, limitations, and information related to the necessary safeguards of the device, including warning against activities and environments that may put the user at greater risk.
(ii) Specific instructions and the clinical training needed for the safe use of the device, which includes:
(A) Instructions on assembling the device in all available configurations;
(B) Instructions on fitting the patient;
(C) Instructions and explanations of all available programs and how to program the device;
(D) Instructions and explanation of all controls, input, and outputs;
(E) Instructions on all available modes or states of the device;
(F) Instructions on all safety features of the device; and
(G) Instructions for properly maintaining the device.
(iii) Information on the patient population for which the device has been demonstrated to have a reasonable assurance of safety and effectiveness.
(iv) Pertinent non-clinical testing information (
e.g., EMC, battery longevity).(v) A detailed summary of the clinical testing including:
(A) Adverse events encountered under use conditions,
(B) Summary of study outcomes and endpoints, and
(C) Information pertinent to use of the device including the conditions under which the device was studied (
e.g., level of supervision or assistance, and environment of use (e.g., indoors and/or outdoors) including obstacles and terrain).