Search Results

The ReWalk® 7 Personal Exoskeleton fits to the lower limbs and part of the upper body and is intended to enable individuals with spinal cord injury at levels T7 to L5 to perform ambulatory functions in home and community settings with supervision of a specially certified 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 T4 to T6 to perform ambulatory functions in accordance with the User assessment and training certification program. The ReWalk 7 is intended for including standing and walking on level surfaces and mild slopes, and ascending and descending stairs and curbs.

The ReWalk® 7 Personal Exoskeleton is a wearable, battery-powered prescription device intended for use by certified individuals at least 18 years old with lower limb disability to perform routine ambulatory functions at home and in the community.

Control of the exoskeleton is achieved through a user-worn wireless, web connected wrist control unit (WCU), a wireless crutch-mounted control unit (CCU), and specific body movements as measured through a tilt sensor. The powered device movements are performed by a set of gears and motors at the knee and the hip joints.

The ReWalk 7 Personal Exoskeleton includes the exoskeleton (incl. rigid frames, waist pack, and straps), battery power supply, crutches with integrated powered crutch control add-on unit (CCU), and the Wrist Control Unit (WCU). The wireless, web connected therapist handheld device (THD) is used by certified therapists for device configuration and control.

All ReWalk 7 Personal Exoskeleton components are suitable for indoor and outdoor use.

The ReWalk use includes standing, walking on level surfaces, mild slopes, ascending and descending stairs and curbs.

Here's a breakdown of the acceptance criteria and study information based on the provided text, focusing on what is present and noting what is not:

1. Table of Acceptance Criteria and Reported Device Performance

The provided document does not explicitly list quantitative acceptance criteria for performance outcomes like gait speed, distance, or specific functional improvements. Instead, it focuses on demonstrating that the ReWalk® 7 Personal Exoskeleton:

• Performs safely and effectively according to its intended use.
• Is substantially equivalent to the predicate device (ReWalk® P6.0) regarding intended use, indications, contraindications, and basic principles of operation.
• Meets recognized consensus standards and regulatory requirements related to electrical safety, electromagnetic compatibility, usability, software lifecycle, biological compatibility, risk management, and shipping.

Therefore, a table of acceptance criteria and reported device performance in the typical sense of a clinical trial cannot be created from this document. The "performance" being demonstrated is primarily compliance with safety standards and functional equivalence to the previously cleared device.

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

• Sample Size for Test Set: Not mentioned. The document primarily refers to non-clinical tests based on standards and analyses, rather than a clinical user study with a specific test set of patients.
• Data Provenance: Not mentioned. The tests were likely conducted by the manufacturer or contracted labs in accordance with the specified standards.

3. Number of Experts Used to Establish Ground Truth and Qualifications

• Not applicable. This section does not describe a study where ground truth was established by experts in the context of clinical performance data. The "ground truth" here is compliance with technical standards and validated design changes.

4. Adjudication Method for the Test Set

• Not applicable. No clinical test set requiring adjudication is described.

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

• Not applicable. The device is an exoskeleton, not an imaging or diagnostic device that would typically involve a multi-reader multi-case study.

6. Standalone Performance Study (Algorithm Only)

• Not applicable. The ReWalk 7 is a physical powered exoskeleton, not a standalone algorithm. Its performance is intrinsically tied to human interaction and the physical device.

7. Type of Ground Truth Used

• Compliance with Recognized Consensus Standards and Technical Analyses: The "ground truth" for the device's safety and effectiveness in this submission is established through rigorous testing against a wide array of international standards (e.g., IEC 60601 series, ISO 10993 series, ISO 14971), internal technical analyses (e.g., assessing weight change impact), and demonstration of substantial equivalence to a legally marketed predicate device.

8. Sample Size for the Training Set

• Not applicable. The document does not describe a "training set" in the context of machine learning or AI. The design and validation process followed traditional engineering and regulatory pathways, focusing on design controls, testing, and compliance.

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

• Not applicable. As there is no training set mentioned, this question is not relevant to the provided text.

Summary of the Study (as described in the document):

The document details a non-clinical study approach to demonstrate the safety and effectiveness of the ReWalk® 7 Personal Exoskeleton. The core of this demonstration relies on:

• Technical Bench Testing and Analysis: Evaluation of the device's electrical safety, electromagnetic compatibility, usability, software functionality, biological compatibility (for materials in contact with skin), and risk management processes against a comprehensive list of recognized international consensus standards.
• Comparison to a Predicate Device: The ReWalk 7 is presented as an enhanced version of the previously cleared ReWalk® P6.0. The submission argues for substantial equivalence based on identical intended use, indications for use, contraindications, environment of use, intended users, and basic principles of operation. The enhancements (battery change, new control units, updated modes, cloud connectivity) were individually assessed through testing and analysis to ensure they did not introduce new safety or effectiveness concerns.
• Conclusion: The study concludes that the ReWalk 7 performs safely and effectively according to its intended use and is substantially equivalent to the predicate device, thus not raising different questions of safety and effectiveness. Clinical tests were not required because the device's indications and contraindications are identical to the predicate device, and the changes were primarily technical refinements verified through non-clinical means.

Ask a specific question about this device

Medical HAL Lower Limb Type orthotically fits to the lower limbs and trunk; HAL is a gait training device intended to temporarily help improve ambulation upon completion of the HAL gait training intervention. HAL must be used with a Body Weight Support system. HAL is not intended for sports or stair climbing. HAL gait training is intended to be used in conjunction with regular physiotherapy.

The device is intended for individuals with:

• spinal cord iniurv at levels C4 to L5 (ASIA C. ASIA D) and T11 to L5 (ASIA A with Zones of Partial Preservation, ASIA B);

• post stroke paresis

• paraplegia due to progressive neuromuscular diseases (spinal muscular atrophy, spinal and bulbar muscular atrophy, amyotrophic lateral sclerosis, Charcot-Marie-Tooth disease, distal muscular dystrophy, inclusion body myositis, congenital myopathy, muscular dystrophy)

-cerebral palsy and are 12 years or older

-spastic paraplegia caused by either HTLV-1 Associated Myelopathy (HAM) or hereditary spastic paraplegia (HSP)

who exhibit sufficient residual motor and movement-related functions of the hip and knee to trigger and control HAL.

In preparation for HAL gait training, the controller can be used while the exoskeleton is not donned to provide biofeedback training through the visualization of surface electromyography bioelectrical signals recorded.

HAL is intended to be used inside healthcare facilities while under trained medical supervision in accordance with the user assessment and training certification program.

Medical HAL Lower Limb Type is a battery powered bi-lateral ower extremity exoskeleton that provides assistive torque at the knee and hip joints for gait training. HAL is comprised of a controller, a main unit, and sensor shoes in 30 size variations (variation same as predicate: 3 different leg lengths, 2 different leg lengths, 2 different waist widths >> total 24. New size variation: 3 different leg configurations, 1 leg lengths, 2 different waist widths >> total 6) and weighs ~9.5 kg (21 lbs). The main difference between the Model ML05 and ML07 is the leglengths. ML05 has S.M, L, XL sizes, while ML07 has 2S sizes. The device uses legally marketed electrodes (up to 18 electrodes) to record surface electromyography bioelectrical signals that are processed using a propriety signal processing algorithm. The propriety processing algorithm allows the detect surface electromyography bioelectrical signals to control the HAL device in CVC mode and provide visualization of the surface electromyography bioelectrical signals during biofeedback training. The assistive torque can be adjusted using three parameters: sensitivity level, torque tuner, and balance tuner. The device can also provide two additional modes: Cybernic Autonomous Control (CAC) mode and Cybernic Impedance Control (ClC) mode. CAC mode provides assistive torque leg trajectories based on postural cues and sensor shoe measurements. CC mode provides torque to compensate for frictional resistance of the motor based on joint motion. CIC mode does not provide torque assistance for dictating joint trajectories. A trained medical professional (i.e., physical therapist, etc.) can configure, operate, and monitor the device during gait training to make adjustments as needed.

Patients must exhibit sufficient residual motor and movement-related functions of the hip and knee to trigger and control HAL. The patient must be supported by a Body Weight Support (BWS) system before and during device use. The BWS must not be detached from the patient before doffing this device. HAL is not intended to provide sit-stand or stand-sit movements. HAL is capable of gait speeds up to approximately 2 km/hour on level ground. HAL is not intended for sports or stairclimbing.

In preparation to using HAL, the controller can be used while the exoskeleton is not donned to provide biofeedback training through the visualization of surface electromyography bioelectrical signals recorded. HAL is intended to be used in conjunction with regular physiotherapy. HAL is intended to be used inside a medical facility under the supervision of trained medical professionals who have successfully completed the HAL training program.

The provided text, a 510(k) summary for the Medical HAL Lower Limb Type (HAL-ML), describes the device, its intended use, and its equivalence to a predicate device (HAL for Medical Use (Lower Limb Type), K201559). It primarily focuses on regulatory approval and equivalence, particularly regarding the expansion of indications for use to include Cerebral Palsy and Spastic Paraplegia.

While the document references "clinical data to support the safety and efficacy" and "clinical evaluation procedure," it does not provide a detailed breakdown of acceptance criteria or the specific study results proving the device meets those criteria in the format requested. It states that the "nonclinical and clinical tests submitted demonstrate that the device is as safe and as effective, and performs as well as the legally marketed device cleared as K201559." However, it does not offer the granular information needed to fulfill all aspects of your request (e.g., specific performance metrics, sample sizes for test sets, expert qualifications, or MRMC study details).

Therefore, based only on the provided text, I can infer some information regarding the clinical evaluation but cannot fully populate the table or answer all sub-questions as the detailed study design, acceptance criteria with numerical performance data, and other specifics are not disclosed in this regulatory summary.

Here's an attempt to answer your questions based on the available information, with clear indications where the information is not provided in the text:

1. A table of acceptance criteria and the reported device performance

The document does not specify quantitative acceptance criteria or report specific performance metrics for the efficacy of the device in a table format. It broadly states that the clinical evaluation "results are sufficient to support the claims identified in the Indications for Use for this submission" and that the device is "sufficiently safe".

2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

• Sample Size for Test Set: Not provided. The document mentions clinical evaluations for five indication groups but does not state the number of subjects in these evaluations.
• Data Provenance: Not provided. The country of origin of the data (e.g., Japan, where the manufacturer is located) and whether the studies were retrospective or prospective are not mentioned.

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. Ground truth for a device like HAL-ML would likely refer to clinical outcomes or functional improvements, which are assessed by medical professionals during the study, rather than "experts establishing ground truth" in the same way it might apply to an imaging AI algorithm. The document mentions "trained medical professionals (i.e., physical therapist, etc.)" configure, operate, and monitor the device, but not their specific role in establishing ground truth for a study.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

This information is not provided.

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

An MRMC study is typically performed for diagnostic imaging devices where human readers interpret medical images. This type of study is not applicable to the Medical HAL Lower Limb Type, which is a gait training device. Therefore, no information on MRMC studies or human reader improvement with AI assistance is present or relevant here.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

The device is a physical exoskeleton used for gait training, highly dependent on human interaction (patient and trained medical professional). It's not an algorithm-only device. The "propriety processing algorithm" processes sEMG signals to control the device, but its performance is intrinsically tied to the Human-in-the-loop interaction for gait training. Therefore, a "standalone algorithm only" performance study in the typical AI sense is not relevant or described.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)

The document states "The safety and effectiveness of the subject device is demonstrated through the following clinical evaluation procedure for each of the 5 indication groups... The evaluation results are sufficient to support the claims identified in the Indications for Use." This strongly implies that the ground truth would be based on clinical outcomes data related to ambulation improvement, safety, and effectiveness in the specified patient populations. However, the specific metrics or "ground truth" definitions (e.g., specific scores on mobility scales) are not detailed.

8. The sample size for the training set

The document describes clinical evaluation for the safety and effectiveness of the device as a whole. It does not mention a "training set" in the context of an AI/ML model for which a distinct training set would be used. The "propriety processing algorithm" is part of the device's functionality, but the document does not provide details about its development, including specific training set sizes if machine learning were used this way.

9. How the ground truth for the training set was established

As there is no mention of a "training set" in the context of an AI/ML model with externally established ground truth for training purposes, this information is not provided. The algorithm processes sEMG signals to control the device, which is an engineering function, not necessarily a machine learning model that requires a distinct "training set ground truth" in the way a diagnostic AI would.

In summary, the provided 510(k) summary serves as a regulatory document for substantial equivalence, not a detailed scientific publication of clinical trial results. It confirms that clinical evaluations were performed to support the expanded indications but does not provide the granular data, methodology, or specific acceptance criteria and performance statistics that you've requested beyond a general statement of safety and effectiveness.

Ask a specific question about this device

Atalante X is intended to perform ambulatory functions and mobility exercises, hands-free, in rehabilitation institutions under the supervision of a trained operator for the following populations:

• Individuals with hemiplegia due to cerebrovascular accident (CVA).

• Individuals with spinal cord injuries at levels T5 to L5 (SCI).

The operator must complete a training program prior to use of the device.

Atalante X 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.

Atalante X 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 X is selfbalancing and includes dynamic-walking control. Dynamic-walking allows the Atalante X to consume significantly less power and have a more natural gait.

The provided text describes the Wandercraft SAS Atalante X, a powered lower extremity exoskeleton. The document is an FDA 510(k) premarket notification. It does not contain information about the acceptance criteria or a specific study proving the device meets those criteria, as typically found in a clinical study report. Instead, it focuses on demonstrating substantial equivalence to predicate devices through a comparison of characteristics and non-clinical/clinical performance data.

Therefore, many of the requested details about acceptance criteria, specific study design for ground truth, sample sizes for test/training sets, adjudication methods, and MRMC studies are not available in the provided document.

However, based on the information available, a summary of the performance demonstration is provided below, focusing on what can be extracted.

Table of Acceptance Criteria (Inferred from Performance Data) and Reported Device Performance

Since explicit acceptance criteria are not stated, the "acceptance criteria" are inferred from the safety and effectiveness claims made and the reported outcomes.

Study Details

Detailed aspects of the clinical studies are limited in this summary.

1. Sample size used for the test set and data provenance:

   • Test Set (Clinical Studies): 21 patients with spinal cord injury (SCI) across two clinical studies.
   • Data Provenance: Not specified (e.g., country of origin). The document mentions "real world evidence of use." It is implied to be prospective for the two clinical studies.
   • Real-world evidence: Over 481 patients, including 40 SCI patients at levels C3-L3, who performed 3 or more sessions. This broader "real-world" data is mentioned to support findings, not as a primary "test set" with a pre-defined ground truth assessment for evaluation.

2. Number of experts used to establish the ground truth for the test set and qualifications of those experts:

   • Not specified. The clinical studies would likely have involved trained clinical staff to assess patient performance and adverse events, but the number and qualifications are not detailed. The device is intended to be used under the supervision of a "trained operator."

3. Adjudication method for the test set:

   • Not specified.

4. 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:

   • Not applicable. This device is an exoskeleton, not an imaging AI diagnostic tool. Therefore, MRMC studies involving human readers and AI assistance are not relevant.

5. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:

   • N/A (not directly applicable in the same sense as an AI diagnostic tool). The device itself is the "algorithm only" in terms of its automated function (dynamic-walking control). The performance claims relate to the device operating in its intended environment with human supervision. The "comparable speed to that of the predicates" is a standalone performance metric for the exoskeleton's function.

6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

   • For the clinical studies, the "ground truth" would be related to clinical measures of ambulatory function (e.g., ability to perform tasks, speed, mobility exercises) and safety events (e.g., skin lesions, other adverse events). These are clinical observations and patient outcomes, likely assessed by clinicians or trained operators.

7. The sample size for the training set:

   • Not specified. The document mentions "Wandercraft Customer Care" visits and a "training program" for operators, but this "training set" refers to personnel training, not machine learning model training data. The device's control algorithms (dynamic-walking control) are developed through engineering and likely extensive non-clinical testing and internal validation, but a "training set" in the machine learning sense is not explicitly discussed as part of this submission summary.

8. How the ground truth for the training set was established:

   • Not specified. As above, a traditional "training set" with ground truth in the context of machine learning is not detailed. The device's functionality is based on its mechanical and software design, which would be validated against engineering specifications and performance targets rather than a specific ground truth dataset for training a learning algorithm described in this document.

Ask a specific question about this device

The ReWalk® P6.0 fits to the lower limbs and part ofthe upper body and is intended to enable individuals with spinal cord injury at levels T7 to L5 to perform ambulatory functions in home and community settings with supervision of a specially certified 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 T4 to T6 to perform ambulatory functions in rehabilitation institutions in accordance with the user assessment and training certification program. The ReWalk P6.0 is intended for indoor and outdoor use: including standing and walking on level surfaces and mild slopes and ascending and descending stairs and curbs.

The ReWalk® P6.0 Exoskeleton is a prescription device which enables individuals with spinal cord injuries to perform ambulatory functions and composed of an external, powered, motorized frame that fits to the lower limbs and part of the upper body.

The ReWalk is intended to enable certified users with spinal cord injuries at levels T7 to L5 to perform ambulatory functions in in home and community setting accompanied by a certified companion. Additionally, the ReWalk Personal Exoskeleton 6.0 is intended to enable certified users with spinal cord injuries at levels T4 to T6 to perform ambulatory functions in rehabilitation centers accompanied by a certified therapist.

Control of the device is achieved through a wrist-worn User-operated wireless remote controller (RC), tilt sensor and specific body movements. The gait movements are performed by a set of gears and motors at the knee and the hip joints. The ReWalk system includes Remote control (RC) Communicator, Exoskeleton (Inc. Rigid Frames, Waistpack and Straps), Battery charger and Laptop (GUI), and off the shelf crutches. All of the ReWalk components are mandatory, suitable for indoor and outdoor usage. The device is intended for indoor use: including standing and walking on level surfaces and mild slopes, and ascending and descending stairs and curbs for users who are at least 18 years old.

The ReWalk® P6.0 device, an exoskeleton for individuals with spinal cord injury, had its stairs ascend and descend functionality reviewed. The acceptance criteria and the study proving its performance are detailed below:

1. Table of Acceptance Criteria and Reported Device Performance:

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

• Clinical Performance Test Set (ReWalk P6.0 Active Users Field Survey Study-Stairs Usage):
  • Sample Size: 47 users who used the device to climb stairs (out of 85 recruited subjects).
  • Data Provenance: Retrospective, collected through a survey of actual users in Europe. Data monitored over a period of six (6) years (2015 to May 2022).
• Human Factors Engineering Study Test Set:
  • Sample Size: 11 ReWalk patient subjects and 11 companion subjects.
  • Data Provenance: Prospective, conducted under IRB Approved protocol, according to principles of Good Clinical Practice (GCP).

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

This information is not explicitly provided in the document. The studies rely on user performance and self-reported data (field survey), and observed performance (human factors study), rather than expert adjudication of a "ground truth" derived from patient data like in diagnostic device studies.

4. Adjudication Method for the Test Set:

• Clinical Performance Test Set (Field Survey): Adverse events were monitored through ReWalk's Customer Relation Management (CRM) database and reviewed by the company to determine if they were device-related. The "adjudication" was internal to the company, concluding AEs were not device-related but associated with user error or instruction non-compliance.
• Human Factors Engineering Study Test Set: Performance was observed during actual use scenarios and comprehension questions were evaluated. The document doesn't specify an external adjudication panel; the evaluation of successful task completion and correct answers likely involved researchers from the study lead by the company.

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 is not applicable. The ReWalk P6.0 is an exoskeleton device, not an AI-assisted diagnostic tool. Therefore, an MRMC comparative effectiveness study involving human readers and AI assistance was not performed.

6. If a Standalone (i.e. algorithm only without human-in-the-loop performance) was done:

This is not applicable. The ReWalk P6.0 is a physical device that requires a human user and a certified companion/therapist for operation. Its performance is inherently human-in-the-loop.

7. The Type of Ground Truth Used:

• For Clinical Performance (Field Survey): The "ground truth" was established by real-world usage data and objective tracking of adverse events. Successful use was measured by the number of stairs climbed, and safety by the incidence and nature of adverse events.
• For Human Factors Study: The "ground truth" was successful completion of predefined tasks (ascending/descending stairs and curbs) by the user/companion, as observed by study personnel, and correct answers to comprehension questions.
• For Bench Testing: The "ground truth" was the physical and functional outcomes meeting predetermined engineering specifications (e.g., mechanical integrity, walking speed verification).

8. The Sample Size for the Training Set:

This information is not provided. The document highlights that the ReWalk P6.0 with stairs functionality is identical in design, materials, and components to a previously cleared version (K200032), except for the enabled stairs function. The prior versions underwent extensive testing, and this submission focuses on validating the added stairs functionality. The "training" for the device itself would be implicitly derived from its design and engineering processes, as well as prior product generations.

9. How the Ground Truth for the Training Set was Established:

Not explicitly detailed for a "training set" in the context of machine learning. For medical devices, the "training set" would relate to the iterative design, development, and testing phases where engineers and designers establish the functional specifications and design goals. Ground truth in this context is established through engineering principles, relevant standards (e.g., IEC 60601 series), and established clinical understanding of safe and effective ambulation assistance.

Ask a specific question about this device

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.

Ask a specific question about this device

The EksoNR™ is intended to perform ambulatory functions in rehabilitations under the supervision of a trained physical therapist for the following populations:

· Individuals with multiple sclerosis (upper extremity motor function of at least one arm).

• Individuals with acquired brain injury, including traumatic brain injury and 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 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 provided text, extracting information related to acceptance criteria and the study proving the device meets them. Please note that the document is a 510(k) summary for a medical device (exoskeleton), which focuses on demonstrating substantial equivalence to a predicate device rather than presenting a formal "acceptance criteria" table as might be seen for an AI/ML diagnostic tool. Therefore, some requested information may not be directly available or applicable in the provided context.

Overview:
The document clears the EksoNR powered lower extremity exoskeleton. The primary purpose of this 510(k) submission (K220988) is to expand the indications for use of the already cleared EksoNR (predicate device K200574) to include individuals with multiple sclerosis (MS). The device itself is essentially unchanged from the predicate.

Acceptance Criteria and Device Performance

Given this is a 510(k) for an updated indication for an existing medical device (exoskeleton) rather than an AI/ML diagnostic, the concept of "acceptance criteria" isn't framed as statistical thresholds for sensitivity/specificity. Instead, the acceptance criteria are implicitly that the device is safe and effective for the expanded population, demonstrating gait ambulation effectiveness and no new safety concerns in the specified population, thus maintaining substantial equivalence to the predicate.

Table of Acceptance Criteria (Implicit) and Reported Device Performance:

• TUG scores improved significantly: from 24s at baseline to 20.61s at completion of all Ekso sessions.
• Average walking speed maintained: from 0.69m/s at baseline to 0.66m/s at completion of all Ekso sessions.
• Average cognitive MOCA scores improved slightly.

Kessler MS Study (n=8):

• TUG scores improved significantly: from 16.99s at baseline to 14.15s at completion of all Ekso sessions.
• Average walking speed maintained: from 10.37s at baseline to 10.63s at completion of all Ekso sessions (note: units here are stated as 's' which is unusual for speed, likely a typo and referring to time for a specific distance or a different test. See 6MWT below).
• Symbol digit modalities test (cognition) improved.
• 6 minute walk test (6MWT) distance increased: from 279.65m to 294.69m.
• Average functional reach test distance increased.

Overall Conclusion: "The supporting clinical data demonstrating the use of the product with patients with multiple sclerosis (MS), show that the device effectively facilitates gait ambulation in the expanded patient population." |
| Substantial Equivalence: Device remains substantially equivalent to the predicate (K200574). | "This device and the previously cleared (predicate) device (K200574) are essentially the same products."
"The device is essentially unchanged from the current (predicate) device."
"The indications for use are identical to that of the predicate device, with the addition of the following: Individuals with multiple sclerosis..."
"When used as instructed, the device is as safe to use with a broader population of patients with neurological conditions to include the already cleared ABI and SCI population and this new MS population." |

Study Details

1. Sample sizes used for the test set and the data provenance:

   • Test Sets:
     • ADEMBI MS Study: 18 subjects total used the Ekso. (n=17 for TUG post-testing, n=18 for others).
     • Kessler MS Study: 9 subjects total used the Ekso. (n=8 for pre/post testing).
   • Data Provenance: Not explicitly stated regarding country of origin, but described as "Single center, prospective parallel-assignment, single-blinded, randomized controlled study" for ADEMBI MS and "Single center, randomized study" for Kessler MS. This implies prospective data collection for these specific studies. No specific mention of retrospective vs. prospective is made for the original 7 studies that supported the predicate.

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

   • This is not an AI/ML diagnostic device where ground truth is established by expert readers interpreting images or data. For an exoskeleton, the "ground truth" for effectiveness is whether the patient can ambulate and improve functional scores, as measured by standardized clinical tests (TUG, 6MWT), and the "ground truth" for safety is the absence of adverse events/falls during supervised use.
   • The device is used under the supervision of a "trained physical therapist." While not "experts establishing ground truth" in the diagnostic sense, their training and supervision are crucial for the device's safe and effective use and thus for the clinical outcomes.

3. Adjudication method (e.g., 2+1, 3+1, none) for the test set:

   • Not applicable. This is a functional device study, not an imaging diagnostic study requiring adjudication of image interpretations for ground truth. Clinical outcomes were measured directly using standardized tests and adverse events were reported.

4. 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:

   • Not applicable. This is not an AI-assisted diagnostic tool. No MRMC study was performed or needed. The device (EksoNR) is the primary intervention.

5. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:

   • Not applicable. The device is a physical exoskeleton designed for human-in-the-loop use under therapist supervision. It does not operate as a standalone algorithm.

6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

   • Outcomes Data: The primary ground truth is established through measured clinical outcomes using validated functional assessment tools (e.g., Timed Up and Go (TUG) test, 6-minute walk test (6MWT), cognitive assessments like MOCA/Symbol Digit Modalities Test) and direct observation/reporting of adverse events (falls). This is outcomes-based evidence of safety and functional improvement.

7. The sample size for the training set:

   • Not applicable in the context of device approval for an exoskeleton. This is not an AI/ML algorithm that requires a "training set" in the computational sense. The device itself is "trained" during the manufacturing and design process, and the physical therapists are trained for its use.

8. How the ground truth for the training set was established:

   • Not applicable. As above, there is no AI/ML "training set" for this device. The physical therapists are trained users, and their "ground truth" would be established through their professional education, experience, and the specific training program provided for the EksoNR device.

Ask a specific question about this device

The GEMS-H is a robotic exoskeleton that fits orthotically on the wearer's waist and thighs, outside of clothing. The device is intended to help assist ambulatory function in rehabilitations under the supervision of a trained healthcare professional for the following population:

· Individuals with stroke who have gait deficits and exhibit gait speeds of at least 0.4 m/s and are able to walk at least 10 meters with assistance from a maximum of one person.

The trained healthcare professional must successfully complete a training program prior to use of the device. The device is not intended for sports.

The GEMS-H is a lightweight, robotic exoskeleton designed to help assist ambulatory function of stroke patients who meet the assessment criteria, in rehabilitations under the supervision of a trained healthcare professional. The GEMS-H device provides assistance to the patient during hip flexion and extension.

The device is worn over clothing around the wearer's waist and fastened with Velcro straps to assists hip flexion and extension. The device weighs 4.7 lbs (2.1 kg) and has two motors that run on a single rechargeable battery. The device is equipped with joint angle and electrical current sensors to monitor hip joint angle and torque output, respectively.

The assist torque is transmitted to the wearer's thighs via thigh support frames. A trained healthcare professional, who operates the device, can change assist settings through software that runs on the tablet PC.

This document describes the premarket notification (510(k)) for the Samsung GEMS-H, a powered lower extremity exoskeleton. The information provided primarily focuses on establishing substantial equivalence to a predicate device, rather than proving the device meets specific acceptance criteria related to an AI's performance.

Based on the provided text, the device itself (GEMS-H exoskeleton) is the subject of the regulatory review, and the "study" described is a clinical trial to assess its safety and effectiveness in assisting ambulatory function in stroke patients. There is no mention of an AI component requiring specific performance acceptance criteria for an algorithm or model.

Therefore, many of the requested points regarding AI acceptance criteria, ground truth establishment, expert adjudication, and MRMC studies are not applicable directly to this document's content, as it's not about an AI-powered diagnostic or predictive device.

However, I can extract information related to the device's clinical performance and the study design:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria for the device are defined in terms of safety and effectiveness, based on a clinical trial.

Ask a specific question about this device

The ExoAtlet-II is intended to perform ambulatory functions in rehabilitation under the supervision of a trained physical therapist for the following population with upper extremity motor function at least 4/5 in both arms:

· Individuals with spinal cord injuries at levels T4 to L5

• · Individuals with spinal cord injuries at levels of C7 to T3 (ASIA D)
  The therapist must complete a training program prior to use of the device.

The device is not intended for sports or stair climbing.

The ExoAtlet-II is intended to perform ambulatory functions in rehabilitation institutions, hospitals, or similar institutions under the supervision of a healthcare professional (HCP) such as a trained physical therapist. The ExoAtlet-II is indicated for individuals with spinal cord injuries at levels T4-L5 and individuals with spinal cord injuries at levels of C7-T3. All users must have upper extremity motor function of at least 4/5 in both arms. The ExoAtlet-II is intended for multiple users in a clinical setting (i.e., gait lab or rehabilitation center) under supervision. The ExoAtlet-II includes a battery powered exoskeleton, an ExoCrutch, and a Tablet PC.

ExoAtlet-II is designed to be operated with a trained physical therapist who has received preliminary training on the Exoskeleton operation. This therapist will be familiar with the rules of the use and operational documentation. Training is conducted in a designated medical facility that is representative of the indicated environments (e.g., hospital, outpatient physical therapy clinic or similar). The training identifies safe environments of device use and uses all of the safety features found in the subject device. The training manual will be provided with the user manual along with a trainee itinerary and a trainee certification exam. The trainee needs to pass 80% of the exam questions to obtain certification.

Here's a breakdown of the acceptance criteria and study information for the ExoAtlet-II device based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of acceptance criteria with corresponding performance metrics. Instead, it describes general performance characteristics and notes differences from the predicate device that were evaluated for safety and effectiveness through testing.

However, based on the "Comparison of Technological Characteristics" table and the "Summary of Clinical Testing" section, we can infer some key performance aspects and their reported outcomes:

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

• Sample Size (Clinical Study): 20 subjects (n=20)
• Data Provenance: The study was described as an "open label, non-randomized clinical study." The document does not specify the country of origin but implies it was internal to ExoAtlet given "ExoAtlet conducted an... clinical study." The study is prospective as it was conducted to assess the safety and effectiveness of the device.

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

The document does not mention the use of experts to establish a "ground truth" for a test set in the traditional sense of diagnostic accuracy. Instead, the clinical study involved subjects using the device under the supervision of a "trained physical therapist." The therapist's role is to supervise, and their training and certification are mentioned as a requirement for device use. The study monitors objective performance (walk tests) and subjective feedback (comfort surveys, skin assessments) directly from the subjects and observations.

4. Adjudication Method for the Test Set

Not applicable. The clinical study described is a performance and safety study involving a device for rehabilitation, not a diagnostic study requiring adjudication of expert interpretations for ground truth.

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

Not applicable. This is not an AI-assisted diagnostic device, but a powered exoskeleton for rehabilitation. Therefore, an MRMC study and effects on human reader performance are not relevant.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was Done

Not applicable. The ExoAtlet-II is a physical device intended to be used by individuals under the supervision of a trained physical therapist. It is inherently a "human-in-the-loop" device by design and intended use. There is no mention of a standalone algorithm performance test.

7. The Type of Ground Truth Used (expert consensus, pathology, outcomes data, etc.)

The clinical study assessed the device's safety and effectiveness directly through:

• Performance metrics: Successful completion of the 10 Meter Walk Test and 6-Minute Walk Test.
• User feedback: Comfort ratings via surveys.
• Medical observation: Skin assessments for adverse events.
• Overall safety and functionality: Absence of new safety issues or ineffectiveness compared to predicates.

These are direct measures of the device's functional performance and user impact, rather than a "ground truth" established through external pathological or expert consensus for a diagnostic task.

8. The Sample Size for the Training Set

The document does not provide information about a "training set" in the context of machine learning or AI. The training described is for the human therapist who uses the device.

• Training for Therapists: Not a "training set" for the device's algorithm, but a program for healthcare professionals. The therapist completes a training program and must pass 80% of an exam for certification.

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

As noted above, there is no AI/ML training set mentioned. The "training set" for therapists involves instructions, operational documentation, and an exam, but this is human training, not algorithm training data.

Ask a specific question about this device

HAL for Medical Use (Lower Limb Type) orthotically fits to the lower limbs and trunk;

HAL is a gait training device intended to temporarily help improve ambulation upon completion of the HAL gait training intervention. HAL must be used with a Body Weight Support system. HAL is not intended for sports or stair climbing. HAL gait training is intended to be used in conjunction with regular physiotherapy.

The device is intended for individuals with:

• spinal cord injury at levels C4 to L5 (ASIA C, ASIA D) and T11 to L5 (ASIA A with Zones of Partial Preservation, ASIA B);

• post stroke paresis

• paraplegia due to progressive neuromuscular diseases (spinal muscular atrophy, spinal and bulbar muscular atrophy, amyotrophic lateral sclerosis, Charcot-Marie-Tooth disease, distal muscular dystrophy, inclusion body myositis, congenital myopathy, muscular dystrophy) who exhibit sufficient residual motor and movement-related functions of the hip and knee to trigger and control HAL

In preparation for HAL gait training, the controller can be used while the exoskeleton is not donned to provide biofeedback training through the visualization of surface electromyography bioelectrical signals recorded.

HAL is intended to be used inside medical facilities while under trained medical supervision in accordance with the user assessment and training certification program

HAL for Medical Use (Lower Limb Type) is a battery powered lower extremity exoskeleton that provides assistive torque at the knee and hip joints for gait training. HAL is comprised of a controller, a main unit, and sensor shoes. The device comes in 8 size variations (4 different leg lengths and 2 different hip widths) for each of the 3 configuration types (doubleleg, right-leg, and left-leg) and weighs ~14 kg (30 lbs). The device uses legally marketed cutaneous electrodes (up to 18 electrodes) to record surface electromyography bioelectrical signals of the hip and knee extensor and flexor muscles when the device is used in Cybernic Voluntary Control (CVC) mode. This mode provides assistive torque at the corresponding ioint (e.g., hip or knee) using surface electromyography bioelectrical signals that are processed using a propriety signal processing algorithm. The propriety processing algorithm allows the device to detect surface electromyography bioelectrical signals to control the HAL device in CVC mode and provide visualization of the surface electromyography bioelectrical signals during biofeedback training. The assistive torque can be adjusted using three parameters: sensitivity level, torque turner, and balance turner. The device can also provide two additional modes: Cybernic Autonomous Control (CAC) mode and Cybernic Impedance Control (CIC) mode. CAC mode provides assistive torque leg trajectories based on postural cues and sensor shoe measurements. CIC mode provides torque to compensate for frictional resistance of the motor based on joint motion. CIC mode does not provide torque assistance for dictating joint trajectories. A trained medical professional (i.e., physician, physical therapist, etc.) can configure, operate, and monitor the device during gait training to make adjustments as needed.

The provided document is a 510(k) Summary for the HAL for Medical Use (Lower Limb Type) device. It describes the device, its intended use, and substantial equivalence to a predicate device (K171909). The document focuses on demonstrating safety and effectiveness, particularly for new patient populations.

It's important to note that this document is an FDA 510(k) summary, which typically presents summarized findings rather than a detailed breakdown of all study methodologies. Therefore, some specific details for each point requested might not be explicitly stated or might require inference from the provided text.

Here's an analysis of the provided information against your requested points:

Acceptance Criteria and Device Performance

The acceptance criteria are not explicitly stated as distinct numerical targets for each performance metric in a single table. Instead, the document demonstrates meeting acceptance criteria through compliance with recognized standards, successful bench testing, and consistent or improved clinical outcomes compared to baseline or control groups across various studies. The "results" sections for non-clinical and clinical data effectively serve as proof of meeting implicit or explicit acceptance criteria related to safety, functionality, and efficacy.

Table of Acceptance Criteria and Reported Device Performance:

Ask a specific question about this device

The Keeogo is robotic exoskeleton that fits orthotically on the user's waist, thigh, and shin, outside of clothing. The device is intended to help assist ambulatory function in rehabilitation settings under the supervision of a trained healthcare professional for the following population:

Individuals with stroke who have gait deficient hip (MMT Hip >= 3) and knee strength (MMT Knee >= 2) and who are capable of standing and initiating gait movement without assistance.

The trained healthcare professional must successfully complete a training program prior to fitting and tuning the device. The device is not intended for sports.

KeeogoTM Dermoskeleton System is an ambulatory assistive device that is fitted to the lower body, and is powered at the knee. This computer-controlled orthosis provides complementary force to the knee joint to assist with: (1) knee flexion and extension in the swing phase of gait, and (2) eccentric knee control and extension in the weight bearing phase.

KeeogoTM Dermoskeleton System does not move through a pre-determined pattern of movement, but rather integrates seamlessly with movements initiated by the user themselves, and provides assistance based on the detected activity.

Here's an analysis of the acceptance criteria and study detailed in the provided document, addressing each of your requested points:

The provided text describes the B-Temia Inc. Keeogo Dermoskeleton System, a robotic exoskeleton intended to assist ambulatory function in rehabilitation settings for individuals with stroke. The submission focuses on demonstrating substantial equivalence to a predicate device.

1. Table of Acceptance Criteria and Reported Device Performance:

The document doesn't explicitly state "acceptance criteria" in the traditional sense of pre-defined quantitative thresholds for clinical performance that the device must meet to be approved. Instead, it presents the results of a clinical trial designed to show improvement with the device, which implicitly served as evidence for effectiveness.

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

• Sample Size for Effectiveness Population: 48 subjects
• Sample Size for Safety Population: 55 subjects
• Data Provenance: Prospective. The study mentions "Trial Sites" which are:
  • The Shirley Ryan AbilityLab (Chicago, Illinois, USA)
  • Human Performance and Engineering Research (HPER) (West Orange, New Jersey, USA)
  • James J Peters VA Medical Center - Center for the Medical Consequences of Spinal Cord Injury (Bronx, New York, USA)
  • Assistive Technology Clinic (ATC) (Toronto, Ontario, Canada)
    Therefore, the data provenance includes both USA and Canada.

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

The document does not specify the number of experts used or their qualifications for establishing the ground truth measurements (e.g., Wisconsin Gait Scale scores, MMT scores). These are typically assessed by trained clinicians or researchers as part of standard clinical practice or research protocols. While "trained healthcare professional" is mentioned for device supervision, it doesn't detail the assessors of the outcome measures.

4. Adjudication Method for the Test Set:

The document does not specify any adjudication method for the test set. Clinical outcome assessments like the Wisconsin Gait Scale are typically performed by a single trained assessor at each site.

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

No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not done. This study design is typically used for diagnostic devices where multiple readers interpret images or data. The Keeogo is a therapeutic/assistive device, and the study was focused on its direct impact on patient gait, not on reader interpretation. Therefore, there's no mention of effect size of human readers improving with/without AI assistance.

6. Standalone Performance:

Yes, a standalone performance was done, in the sense that the clinical trial evaluated the performance of the device when used by participants (i.e., with human-in-the-loop) but the "performance" here refers to the patient's functional improvement. The device itself (the "algorithm only") operates in real-time to assist the user's movements based on detected activity, but its "performance" is inherently linked to the human using it. The study assesses the combined human-device system's effectiveness.

7. Type of Ground Truth Used:

The ground truth for effectiveness was established using clinical outcome assessments administered by trained personnel. Specifically, the primary outcome mentioned is the Wisconsin Gait Scale (WGS), which is a scalar measure of gait quality. Other assessments included "30SCT, TST-up, TST-down, ClinRO, PRO." The MMT (Manual Muscle Test) scores for hip and knee strength were used as inclusion criteria. Safety ground truth was based on the reporting of adverse events.

8. Sample Size for the Training Set:

The document does not mention a separate training set or its sample size for the device's algorithm. The "Training Program" described refers to the training for clinicians on how to use the device, not a data set used to train an AI model within the device. For powered exoskeletons, the "training" of the device typically happens through development and testing of its control algorithms rather than a distinct "training set" of patient data in the way a diagnostic AI would have. The mechanism described for the device is that it "does not move through a pre-determined pattern of movement, but rather integrates seamlessly with movements initiated by the user themselves, and provides assistance based on the detected activity." This implies a reactive control system, not a predictive AI model trained on a large dataset of patient movements.

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

As there is no explicit "training set" for the device's algorithm mentioned (it appears to be a reactive control system assisting human-initiated movements, rather than a predictive AI), the concept of "ground truth for the training set" as it applies to AI/ML models is not directly applicable here. The device's "training" would be through engineering design and validation of its control logic.

Ask a specific question about this device