Search Results

The Ekso™ (version 1.1) and Ekso GT™ (version 1.2) are intended to perform ambulatory functions in rehabilitation institutions under the supervision of a trained physical therapist for the following population:
• Individuals with hemiplegia due to stroke (upper extremity motor function of at least 4/5 in at least one arm)
• Individuals with spinal cord injuries at levels T4 to L5 (upper extremity motor function of at least 4/5 in both arms)
• Individuals with spinal cord injuries at levels of C7 to T3 (ASIA D with upper extremity motor function of at least 4/5 in both arms).
The therapist must complete a training program prior to use of the device. The devices are not intended for sports or stair climbing.

The Ekso is a powered motorized orthosis. It consists of a fitted metal brace that supports the legs, feet, and torso. It is worn via straps on the body, legs, and feet. Battery powered motors drive knee and hip joints. It has an integrated solid torso containing the computer and power supply. It has a hand-held user interface to specify settings and initiate steps. The Ekso is used with a cane, crutch, or walker.

Here's an analysis of the acceptance criteria and supporting study for the Ekso™ (version 1.1) and Ekso GT™ (version 1.2) based on the provided document.

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of numerical acceptance criteria with corresponding device performance metrics in the way one might see for diagnostic accuracy. Instead, the acceptance criteria are implicitly defined by the safety and effectiveness demonstrated in the clinical studies, particularly for the expanded Indications for Use. The core acceptance criterion appears to be: safe and effective ambulation for the specified patient populations, demonstrated by a lack of adverse events.

2. Sample Sizes and Data Provenance

• Test Set (Clinical Studies):

  • Study 1: 54 subjects total.
    • 34 subjects with affected upper extremity (UE) motor function of less than 4/5 in one arm.
    • 1 patient with affected UE motor function of 4/5.
    • 19 patients with UE motor function not recorded.
    • 216 walking sessions across both studies.
  • Study 2: 8 subjects total.
    • All 8 subjects were limited household ambulators at recruitment.
  • Data Provenance: Both studies are described as "Single center, prospective studies." The country of origin is not explicitly stated, but given the FDA submission, it is likely the United States.

• Training Set: Not applicable for this device as it is a physical exoskeleton, not an AI/software device that requires a "training set" in the machine learning sense. The "training" described in the document refers to human therapist training.

3. Number of Experts and Qualifications for Ground Truth

• Ground Truth for Test Set: The "ground truth" here is the clinical assessment of safety and ability to ambulate. This would have been established by the trained physical therapists supervising the sessions and likely by the principal investigator(s) of the studies. The document states the device is used "under the supervision of a trained physical therapist," and the therapists themselves undergo certification. While no specific number of "experts" are listed for establishing ground truth post-hoc, the safety and effectiveness were directly observed and recorded during the prospective studies by qualified clinical personnel. Their qualifications are implied by their role as physical therapists and study investigators.

• Training Set Ground Truth: Not applicable.

4. Adjudication Method for the Test Set

The document does not describe a formal adjudication method (like 2+1 or 3+1 consensus) for the outcome of the clinical studies. The results are presented as direct observations and reports from the prospective studies ("No falls or other adverse events reported"). This implies the safety and functional performance were observed and recorded directly by the study investigators/therapists.

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

• No, an MRMC comparative effectiveness study was not done. This type of study (comparing human readers with and without AI assistance) is relevant for diagnostic imaging AI. The Ekso device is a physical exoskeleton for rehabilitation, not a diagnostic AI.

6. Standalone (Algorithm Only) Performance

• Not applicable. The Ekso is an exoskeleton requiring human interaction (the patient wearing it, the therapist supervising it). It does not have a "standalone" algorithm performance in the way an AI diagnostic tool would. Its performance is intrinsically linked to the human operator and patient.

7. Type of Ground Truth Used

• Clinical Observation and Outcomes Data:
  • The primary ground truth for the clinical studies was the direct clinical observation of patient safety (absence of falls, adverse events) and their ability to perform ambulatory functions while using the device, as assessed by trained physical therapists and study investigators.
  • The "results" section directly references "safely performed ambulatory functions" and "no falls or other adverse events reported," which are observed clinical outcomes.

8. Sample Size for the Training Set

• Not applicable. As noted above, this is a physical medical device, not an AI/machine learning algorithm requiring a "training set" of data. The "training" refers to physical therapist training.

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

• Not applicable. See point 8. The training for therapists involves demonstrating competence in operating the device and supervising patients safely, as evaluated by the "Ekso Bionics Clinical Training Team."

Ask a specific question about this device