Search Results

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. 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. 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 of the Indego by means of postural changes (e.g., to walk forward, the user just leans forward). The technology of the design links the low weight and 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 forearm 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. Taller torso "wings" 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 achieve the actions of transitioning from sitting to standing, standing to walking, stop walking, and return from standing to sitting. The untethered, free roaming design of the device will allow it to be utilized in multiple indoor and outdoor locations in either a rehabilitation setting with a certified Indego Specialist or a personal setting with a trained support person.

The provided text describes the Indego® powered lower extremity exoskeleton, and its substantial equivalence submission (K171334) to the FDA. The submission emphasizes clinical and non-clinical data to support expanded indications for use.

Here's an analysis of the acceptance criteria and the study proving the device meets these criteria, based on the provided text:

Key Takeaway: The device's "acceptance criteria" are not explicitly defined as specific numerical thresholds for performance metrics to achieve FDA clearance in the same way clinical trials for pharmaceuticals might state primary endpoints. Instead, the "acceptance criteria" are implicitly demonstrated by showing the device's safety and effectiveness for its intended use, comparable performance to predicate devices, and successful completion of various non-clinical and clinical tests. The primary measure of clinical success appears to be enabling ambulatory functions with minimal assistance (FIM score of 4 or higher) and demonstrating walking speed.

1. Table of Acceptance Criteria and Reported Device Performance

Since explicit acceptance criteria with numerical targets are not stated, the table below will summarize the demonstrated performance and implicitly infer the "acceptance criteria" based on the successful clearance. The core "acceptance criterion" appears to be demonstrating safety and effectiveness for the stated Indications for Use, with performance comparable or better than predicate devices.

2. Sample Size Used for the Test Set and Data Provenance

The terms "test set" and "training set" are typically used in machine learning. However, for medical device clinical studies, we can interpret the clinical data used for evaluation (which serves a similar purpose to a "test set" in demonstrating performance) as follows:

• Pilot Study: 16 subjects
• Multi-Site Clinical Trial: 45 subjects
• Postmarket Clinical Data (Rehabilitation Use): 37 subjects
• Personal Use Training Program Study: 4 subjects (user and support person teams)
• Postmarket Personal Use Data: 5 subjects (user and support person teams)

Total unique subjects across all reported clinical studies: While there might be some overlap, the text states "TOTAL SCI SUBJECTS: 107" for Indego data (comparing to Ekso's 56). This suggests the aggregate number of unique individuals whose data contributed to the clinical evaluation is 107.

Data Provenance:

• The text doesn't explicitly state the country of origin for all clinical data. However, the contact information for the sponsor (Parker Hannifin) is in USA (Ohio), and the submission correspondent (Emergo) is in USA (Texas). The postmarket personal use data mentions "5 trained Indego personal users worldwide. One of these individuals is a European user... The other 4 are from the United States." This indicates a mix of US and implied international data for personal use.
• The studies were prospective in nature, as they describe "Pilot Study", "Multi-Site Clinical Trial", and "Personal Use Training Program Study" which were IRB-approved and conducted according to GCP. Postmarket data would be collected retrospectively from existing users.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications

This device is not an AI/ML diagnostic tool, so the concept of "ground truth" derived from expert consensus (e.g., radiologists interpreting images) isn't directly applicable in the same way.

Instead, for this exoskeleton device, "ground truth" or clinical outcomes are established through:

• Direct observation and measurement by trained clinical personnel (e.g., physical therapists, study coordinators) conducting the tests (10 MWT, 6 MWT, TUG, WISCI, FIM scores).
• Patient self-report/feedback for aspects like ease of use and satisfaction with training.
• Physician assessment for patient suitability and injury levels.

The qualifications of the personnel involved are implied by references to "specially trained companion", "physical therapist," "Indego Specialist," and "clinicians." The training and certification programs for both clinicians and personal users (with support persons) indicate a standardized approach to application and performance assessment. No specific number of "experts" for a consensus ground truth committee is mentioned, as the data collection methods are objective measurement and direct clinical observation.

4. Adjudication Method for the Test Set

Given that this is a physical therapy/mobility device study, and not an image-based diagnostic study where multiple readers might interpret findings, a formal "adjudication method" like "2+1" or "3+1" (common for reconciling discordant image interpretations) is not applicable here. Performance measures (e.g., walking speed, distance, FIM scores) are objective and directly measured or scored by the trained clinical staff involved in the studies. Adverse events are recorded and investigated as part of standard clinical trial procedures.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not done.

MRMC studies are typically used to evaluate the impact of a diagnostic tool (like an AI algorithm) on human reader performance, usually in radiology, by comparing diagnostic accuracy or efficiency with and without AI assistance across multiple cases and readers. This exoskeleton is a treatment/assistive device, not a diagnostic one.

The studies focused on the device's standalone performance and safety in enabling mobility for individuals with SCI, rather than assisting human readers in interpreting data. The "assistance" refers to the device assisting the patient, not AI assisting a human healthcare provider's diagnostic process.

6. Standalone Performance (i.e. algorithm only without human-in-the loop performance)

Again, this is not an AI/ML algorithm in the diagnostic sense, but a powered mechanical device. Therefore, a "standalone algorithm only" performance is not relevant.

However, the "performance" of the device itself (independent of human diagnostic input, but certainly dependent on human operation and supervision) is extensively reported through:

• Non-Clinical Performance Data: Maximum Torque Testing, Cleaning Chemical Compatibility Testing, Component Life Cycle Testing, Durability Testing, Battery Life Cycle Testing, Storage and Transport Testing, Software verification and validation testing, Electrical safety testing, Electromagnetic compatibility testing – all reported as "PASS."
• Clinical Performance Data: The various functional mobility tests (10 MWT, 6 MWT, TUG, WISCI, FIM). These tests assess the patient's ability to ambulate with the device, which is essentially the device's functional performance in combination with the user. The device acts in conjunction with the user's postural changes and the supervision of a trained human.

7. The Type of Ground Truth Used

As discussed in #3, for this type of medical device, "ground truth" is established through:

• Objective Clinical Measurements: Quantifiable outcomes from standardized mobility tests (e.g., 10 Meter Walk Test, 6 Minute Walk Test, Timed Up and Go Test).
• Functional Independence Measures (FIM) and Walking Index for Spinal Cord Injury (WISCI) Scores: These are standardized clinical rating scales, where scores are determined by trained clinicians (Indego Specialists) based on observation of the patient's performance and the level of assistance required.
• Adverse Event Reporting: Direct observation and documentation of any adverse events during use.
• Patient and Trainer Feedback: Qualitative feedback on training adequacy and real-world use.

Unlike diagnostic tools, there isn't a "true positive/negative" outcome like disease presence confirmed by biopsy. Instead, the "ground truth" is the demonstrated functional ability and safety of the patient using the device as measured by validated clinical instruments.

8. The Sample Size for the Training Set

The text refers to "training" in two contexts:

1. Device training for users: Subjects undergo extensive training to learn how to use the Indego. This is training for the human user, not training data for an AI algorithm.
2. Training data for the device itself: If the device contained adaptable AI/ML components that learn from data, this section would be relevant. However, the description of the Indego's "on-board microprocessors receive signals from integrated sensors which provide information on the user's posture and tilt" and "user similarly controls of the Indego by means of postural changes" suggests deterministic or rule-based control rather than a deep learning model that would require a large "training set" of performance data. There is no mention of a machine learning "training set" size for the device's internal algorithms.

9. How the Ground Truth for the Training Set Was Established

As there's no explicitly described "training set" for an AI/ML algorithm within the device. Thus, the method for establishing "ground truth for the training set" is not applicable in the context of an AI/ML model for this device. The device's control mechanisms appear to be based on pre-programmed logic derived from engineering principles and biomechanics, rather than learned from a large dataset.

Ask a specific question about this device