(77 days)
The Indego® orthotically fits to the lower limbs and the trunk; the device is intended to enable individuals with spinal cord injury at levels T3 to L5 to perform ambulatory functions with supervision of a specially trained companion in accordance with the user assessment and training certification program. The device is also intended to enable individuals with spinal cord injury at levels C7 to L5 to perform ambulatory functions in rehabilitations in accordance with the user assessment and training certification program. Finally, the Indego® is also intended to enable individuals with hemiplegia (with motor function of 4/5 in at least one upper extremity) due to cerebrovascular accident (CVA) to perform ambulatory functions in rehabilitations in accordance with the user assessment and training certification program. The Indego is not intended for sports or stair climbing.
Parker Hannifin's Indego® device is a wearable powered exoskeleton that actively assists individuals to stand and walk; these are patients with walking impairments resulting from lower extremity weakness or paralysis. The Indego consists of snap-together components weighing 26 pounds total. The hip component houses a rechargeable battery pack, central processor, and Bluetooth radio, while each upper leg component houses two motors as well as embedded sensors and controllers.
In the original operational mode of the device, called Motion+, on-board microprocessors receive signals from integrated sensors which provide information on the user's posture and tilt. This allows the device to function in a manner similar to the Segway personal mobility device, which is controlled by the user's tilt. A user similarly controls the motions of the Indego by means of postural changes (e.g., to walk forward, the user just leans forward). Alternatively, the device can be placed in a second operating mode, referred to as Therapy+, in which the device responds to the motion of users who are able to initiate stepping on their own. When operating in Therapy+, the user walks normally while the system detects step initiation and assists the user. Therapy+ may be used only in a clinical setting under clinical supervision. The technology of the design links the low profile to advanced battery technology (smaller size), motors (smaller and more powerful), and micro controllers (state-of-the art). Visual cues from the LED lights on the hip and vibratory feedback inform both the patient and therapist or trained support person of the status and mode of operation.
The Indego controls are self-contained, with crutches or a walker used solely for stability. Users can perform sit-to-stand and stand-to-sit transitions and walk along even or uneven terrain up to about five degree (5°) grades. Tall hip wings and a tall torso pad are provided to support users who may need additional trunk support while walking. A physical therapist can configure, operate, and monitor the device during therapy and training to make adjustments as needed. This is achieved through the support of a wireless application that will run on mobile/wifi connected smart devices such as an iPod or iPhone. The patient and physical therapist will be able to work in concert to actions of transitioning from sitting to standing to walking, stop walking, and return from standing to sitting. The untethered, free-roaming design of the device allows it to be utilized in multiple indoor and outdoor locations within a rehabilitation or personal setting.
The provided text is a 510(k) Premarket Notification for the Indego® powered lower extremity exoskeleton. It details the device's indications for use, its description, and its comparison to predicate devices, along with non-clinical and clinical performance data.
However, the document does not contain typical "acceptance criteria" and "reported device performance" in the format of a table with specific metrics for an AI/ML powered device. Instead, the document focuses on demonstrating substantial equivalence to predicate devices through various tests and clinical studies for a physical medical device (an exoskeleton).
Therefore, I cannot directly provide a table of acceptance criteria and reported device performance as if it were an AI/ML algorithm being validated. The performance metrics discussed are for the physical functionality and safety of the exoskeleton, not for an algorithmic output.
Similarly, the information requested regarding "sample size for the test set," "data provenance (e.g. country of origin of the data, retrospective or prospective)," "number of experts used to establish the ground truth," "adjudication method," "MRMC study," "standalone performance," "type of ground truth," "sample size for the training set," and "how the ground truth for the training set was established" are all highly relevant to the clinical validation of AI/ML algorithms. This document does not describe an AI/ML algorithm for which these questions would apply in the traditional sense. The "software verification and validation testing per FDA Guidance and IEC 62304" mentioned in section 9 refers to software for controlling the physical device, not an AI for diagnostic or prognostic purposes.
Based on the provided text, here's what can be extracted and inferred regarding the closest relevant information, keeping in mind the context of a physical exoskeleton, not an AI/ML algorithm:
No direct "acceptance criteria" table for an AI/ML device can be constructed as this document is for a physical medical device (exoskeleton) and does not describe an AI/ML algorithm's performance.
The document does describe various non-clinical and clinical tests to demonstrate the safety and effectiveness of the Indego® exoskeleton. The "acceptance criteria" would be implied by the "PASS" status for non-clinical tests and the positive outcomes of the clinical studies.
Here's an attempt to adapt the requested information based on the provided text, while acknowledging its original context:
1. Table of Acceptance Criteria and Reported Device Performance (Adapted for Exoskeleton Functionality):
| Acceptance Criteria Category (Implied) | Specific Performance Metric (Where Available) | Reported Device Performance / Status |
|---|---|---|
| Non-Clinical Performance | Maximum Torque Testing (Knees & Hips) | PASS (met defined specifications) |
| Cleaning Chemical Compatibility Testing | PASS (integrity over 5 years) | |
| Component Life Cycle Testing | PASS (safe performance between servicing) | |
| Durability Testing | PASS (meets IEC 60601-1 factors of safety) | |
| Battery Life Cycle Testing | PASS (met specifications for charge, capacity, life) | |
| Storage and Transport Testing | PASS (protected during shipping, met ISTA standards) | |
| Software Performance | Software Verification and Validation Testing | Conformance to FDA Guidance & IEC 62304 |
| Electrical Safety | Electrical Safety Testing | Passed ANSI/AAMI ES60601-1:2005/(R)2012 |
| Electromagnetic Compatibility (EMC) | EMC Testing | Passed IEC 60601-1-2:2014 |
| Clinical Performance (Safety & Effectiveness) | Adverse Events (Trial-related) | 2 Reported (non-serious); Issue for one resolved with software update |
| Serious Adverse Events (Trial-related) | 0 Reported | |
| Gait Deviations (CVA study) | 21 of 30 subjects had fewer reported gait deviations at end of Session 6 vs. Session 1 | |
| Step Length (CVA study) | Equal step length reported in 26 of 108 sessions that began unequal | |
| STEPS taken in Indego (CVA study) | Increased 38% from Session 2 to Session 6 | |
| Time walking in Indego (CVA study) | Increased 18% (average) | |
| 10-Meter Walk Test (CVA study) | 23 of 30 subjects improved times in Session 6 | |
| Functional Ambulation Classification (FAC) | Average FAC score of 5 (walking independently on level surfaces), no change observed | |
| Subjects successfully learned to use Indego | All subjects in pilot studies learned within first session | |
| Improvements in gait parameters (Pilot Studies) | Demonstrated in pilot studies |
2. Sample Size and Data Provenance for Test Set:
- Test Set (Clinical Trials):
- Main Multisite Clinical Trial: 30 subjects
- Single-Site Pilot Study 1: 3 subjects
- Single-Site Pilot Study 2: 3 subjects
- Engineering Study: 6 subjects (ongoing)
- Total unique subjects across all clinical studies: 42 individuals with CVA.
- Data Provenance: The documents mention "eight clinical sites" for the main multisite trial but do not specify countries of origin other than "Shepherd Center (Atlanta, GA)" for the engineering study. The studies appear to be prospective clinical trials evaluating the device in use.
3. Number of Experts and Qualifications for Ground Truth:
- This section is not directly applicable in the AI/ML sense of establishing a "ground truth" for input data. The "ground truth" for the exoskeleton is the direct, observable performance of the device and the physiological responses of the users.
- Clinical data collection and assessments involved "physical therapists" and "specially trained companion(s)" who supervised and assessed the users. Their specific qualifications (e.g., years of experience, board certification) are not detailed but are implied by their roles in a clinical setting.
- The "IRB approved" and "Good Clinical Practice (GCP) compliant" nature of the studies indicates adherence to ethical and scientific standards in clinical research.
4. Adjudication Method for the Test Set:
- Not applicable in the context of AI/ML ground truth adjudication. Clinical trial data collection involves various assessments by clinicians. The document does not describe a formal multi-reader adjudication process for qualitative assessments but rather direct measurement and observation of physical outcomes by trained personnel.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:
- No, a MRMC study (typical for diagnostic or prognostic AI) was not done.
- The clinical studies focus on the device's ability to facilitate ambulatory functions and improve gait parameters in individuals with neurological impairments (SCI, CVA). There is no comparison of human readers with vs. without AI assistance. The "assistance" itself is the physical exoskeleton.
6. Standalone Performance (Algorithm Only):
- Not applicable. The "device" is a physical exoskeleton designed for human-in-the-loop operation. Its performance is measured in conjunction with a user, not as a standalone algorithm. The "software" component controls the physical device's functions.
7. Type of Ground Truth Used:
- The "ground truth" is derived from directly observable functional performance and physiological measurements during use of the physical device by human subjects. This includes:
- Functional Outcomes: Ability to sit, stand, walk, turn; walking speed (10MWT); Functional Ambulation Classification (FAC) scores.
- Physiological/Gait Parameters: Gait deviations, step length, stride length.
- Safety Data: Incidence of adverse events.
- Expert Observation/Assessment: Assessments by physical therapists and trained companions.
8. Sample Size for the Training Set:
- Not applicable as this is not an AI/ML algorithm in the context typically discussed for "training sets." The device undergoes extensive non-clinical testing and clinical evaluation.
- The document implies iterative design and testing for the physical device and its control software. For instance, the improvement in stand-to-sit transition after an adverse event suggests design modification based on observational data, akin to development cycles rather than a distinct "training set" for an AI model.
9. How the Ground Truth for the Training Set was Established:
- Not applicable for the same reasons as #8. The "training" here refers to device development and improvement, not algorithmic learning. System functionality and safety are established through engineering design principles, non-clinical validation (e.g., torque, durability, battery life tests), and iterative clinical testing.
§ 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).