Search Results

Parallel is a prescription-only digital therapeutic device intended to provide cognitive behavioral therapy for adults aged 22 years of age and older who have been diagnosed with Irritable Bowel Syndrome (IBS). Parallel is indicated as a 3 month treatment for patients with IBS. Parallel treats IBS by reducing the severity of symptoms and is intended to be used together with other IBS treatments.

Parallel is a web-based program designed to deliver Cognitive Behavioral Therapy (CBT) to patients with IBS who continue to have symptoms despite other forms of medical therapy. It is a responsive, web-based application that is intended to be a prescription device for use in the home for patients with IBS under the management of a qualified health care professional for the treatment of their IBS. Parallel is comprised of browser-delivered digital therapy that provides the CBT content. A desktop or laptop computer with a web browser and internet connectivity is required for use.

CBT works by targeting problematic thoughts, feelings, and behaviors, building adaptive coping skills, and interrupting the cycle that is perpetuating the targeted symptoms. CBT can be delivered in-person by a mental health practitioner with adequate training in CBT. A critical component of treatment outcome is the degree to which CBT is administered competently, reliably, and as intended. Parallel treatment uses psychoeducation and teaching behavioral and cognitive skills and techniques to alter patterns of behavior and change unhelpful thoughts.

Parallel is accessed via a secure website. Initially, the patient will receive a secure email containing an access link for the Parallel web application. Upon receiving the email invitation, the user can register electronically to begin their prescription. Once registered, patients are presented with onboarding material that introduces the program. Upon completion of reading the onboarding material, the patient can start the program.

Parallel consists of eight CBT sessions, which include interactive components. The interactive components help patients remember the guidance and concepts, reflect, and engage in the therapeutic processes of CBT. In each session, patients review key points from the previous session and review their homework, thereby reinforcing previous learning. The patient must complete the sessions in sequential order. However, a patient may go back to a previously completed session. The prescription is for 90 days and patients should complete the eight sessions within that 90-day period. After the 90 days, patients can still access the sessions that they have completed.

Here's a breakdown of the acceptance criteria and the study that proves the Parallel device meets them, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

Study Proving Device Meets Acceptance Criteria

The study that proves the Parallel device meets the acceptance criteria is the Assessing Cognitive behavioral Therapy in Irritable Bowel (ACTIB) Pivotal Trial.

Here's the detailed information regarding the study:

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

• Test Set Sample Size (Clinical Study): 558 patients were randomized in total:
  • Telephone arm: 186 patients
  • Parallel arm: 185 patients
  • TAU arm: 187 patients
  • Due to drop-out, complete cases at the end of the trial were:
    • Telephone arm: 136
    • Parallel arm: 124
    • TAU arm: 131
• Data Provenance: The study was a multicenter clinical trial. While the exact country of origin is not explicitly stated, the reference for the study ("Everitt, H., et al., Therapist telephone-delivered CBT compared with treatment as usual in refractory irritable bowel syndrome: the ACTIB three-arm RCT. Health Technol Assess, 2019. 23(17): p. 1-154.") suggests it was likely conducted in the UK, as "Health Technology Assessment" is a journal associated with the UK's National Institute for Health Research (NIHR). The study design was prospective (Randomized Multicenter Clinical Trial).

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

• The ground truth for the effectiveness of the therapy was based on the IBS-Symptom Severity Score (IBS-SSS), a validated patient-reported outcome measure. Therefore, there wasn't a separate panel of experts establishing ground truth for individual cases; rather, the "ground truth" of symptom severity was derived from patient self-reporting using a standardized, validated questionnaire.
• The therapy in the "Telephone" arm was provided by "a therapist with training in CBT." No specific number or qualifications for these therapists (e.g., years of experience, specific certifications) are provided in the document. For the Parallel arm, the therapy is delivered by the software itself, with "three 30-minute telephone support calls" not explicitly stated to be therapeutic in nature but rather for ensuring adequate website resource use.

4. Adjudication Method for the Test Set:

• There was no explicit "adjudication method" described for the test set in the conventional sense of expert review of individual cases to determine a definitive outcome. The primary outcome measure (IBS-SSS) is a patient-reported questionnaire scored objectively.
• The clinical significance of the IBS-SSS change was defined based on a previously published Minimum Clinically Important Difference (MCID) of 50 points, which was agreed upon by the FDA.

5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study was done:

• No, a Multi Reader Multi Case (MRMC) comparative effectiveness study was not explicitly done in the context of comparing human readers' performance with and without AI assistance for tasks like image interpretation. This device is a therapeutic software, not a diagnostic imaging AI.
• The study was a comparative effectiveness study, comparing the device (Parallel) to telephone-delivered CBT and Treatment As Usual (TAU).
  • Effect Size of Human Readers (Therapists) with vs. without AI assistance: Not applicable in this context, as the "human readers" were therapists delivering CBT (Telephone arm) or providing support (Parallel arm), not interpreting data in an "AI-assisted" diagnostic workflow.
  • However, if we broadly interpret "human readers" as "human therapists," the study does compare purely human-delivered therapy (Telephone CBT) to AI-assisted/delivered therapy (Parallel, which has minimal human support).
    • Telephone (Human-delivered CBT) vs. TAU:
      • 3 months: 69 points
      • 6 months: 58 points
      • 12 months: 62 points
    • Parallel (AI-delivered CBT with minimal human support) vs. TAU:
      • 3 months: 53 points (meets MCID of 50)
      • 6 months: 35.7 points (does not meet MCID)
      • 12 months: 35.5 points (does not meet MCID)
    • Comparison of Human-delivered CBT vs. AI-delivered CBT (Parallel):
      • At 3 months, human-delivered CBT yielded a 69-point improvement, while Parallel yielded a 53-point improvement. This indicates that the purely human-delivered CBT had a larger effect size at 3 months (difference of 16 points). The human-delivered CBT continued to show a significant effect at 6 and 12 months, whereas Parallel's effect diminished below the MCID after 3 months.

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

• Yes, to a significant extent, the Parallel arm represents a standalone (or near-standalone) algorithm-only performance. Patients in the Parallel arm were asked to complete the website program "at home on their own time." While they received "three 30-minute telephone support calls," these were "intended to ensure that participants were adequately using the website resources, and were not equivalent to the therapy sessions provided to the Telephone arm." This suggests the primary therapeutic delivery was via the algorithm without significant human intervention for the CBT itself. The 53-point improvement at 3 months for the Parallel arm is the standalone (or near-standalone) performance.

7. The Type of Ground Truth Used:

• The ground truth for the clinical effectiveness outcome (reduction in IBS symptoms) was based on patient-reported outcomes (PROs) using a validated psychometric scale (IBS-SSS). The clinical significance was determined by an agreed-upon Minimum Clinically Important Difference (MCID).

8. The Sample Size for the Training Set:

• The document does not explicitly state a separate "training set" sample size for the Parallel device in the context of how the AI/CBT algorithm was initially developed or optimized.
• The ACTIB trial focuses on the validation of the implemented device. CBT models are typically developed based on established psychological principles and clinical experience, not necessarily through a "training set" in the machine learning sense from a specific clinical trial.
• The document mentions "access to the Parallel software in an earlier pilot trial" as an exclusion criterion, implying there might have been prior studies or development phases, but details regarding these are not provided.

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

• As a therapeutic device providing CBT, the "training set" and "ground truth" for developing the CBT content likely came from:
  • Established psychological and medical literature: The principles of CBT for IBS, its mechanisms of action, and session targets detailed in the device description are well-documented clinical practices.
  • Expert consensus/clinical experience: The design of the eight sessions and their content likely reflects the input of clinical experts in CBT and IBS.
  • Prior pilot studies (implied): The exclusion criterion regarding prior access to Parallel suggests there were earlier developmental or pilot phases where efficacy and user experience may have been iteratively improved, thereby establishing a de facto "training" or optimization process. However, specific details on how ground truth was established within these phases are not provided in this document.

Ask a specific question about this device

1. Non-Inflammatory degenerative joint disease including osteoarthritis and avascular necrosis
2. Rheumatoid arthritis
3. Correction of functional deformity
4. Treatment of non-union, femoral neck fracture, and trochanteric fractures of the proximal femur with head involvement, unmanageable by other techniques.
5. Revision of previous failed total hip arthroplasty.

The Parallel-Sided Extensively Coated Femoral Stems are for uncemented applications only.

The Parallel-Sided Extensively Coated Femoral Stem is designed to replace the patural femoral hip component due to disease or accident. The femoral hip prosthesis is made from wrought titanium alloy (Ti-6AI-4V) (ASTM F136) and has a porous coat, designed to be used in uncemented applications. The stem diameters and lengths are within the range of the previously cleared predicates. In addition to the cylindrical stem design, the Parallel-Sided Extensively Coated Femoral Stem offers a lateralized offset for optimal patient fit.

The provided document describes a 510(k) premarket notification for the "Parallel-Sided Extensively Coated Femoral Stem" device. Upon review of the document, the following observations can be made regarding acceptance criteria and supporting studies:

1. Acceptance Criteria and Reported Device Performance:

   The document does not explicitly define specific quantitative acceptance criteria for the device's performance. Instead, it states that "Non-clinical laboratory testing was performed to determine substantial equivalence. The results indicated that the device was functional within its intended use." This approach is typical for 510(k) submissions, where the primary goal is to demonstrate "substantial equivalence" to a legally marketed predicate device rather than meeting pre-defined quantitative performance thresholds.

   Acceptance Criteria	Reported Device Performance
   Demonstration of "substantial equivalence" to predicate devices (Reach® Revision System- K982367, AML® Hip Stem- K012364, XR-Series Bi-Metric® Femoral Stems- K052089)	"The technological characteristics (materials, design, sizing, and indications) of the Parallel-Sided Extensively Coated Femoral Stem are similar or identical to the predicate devices or to other previously cleared devices."
   "Functional within its intended use" based on non-clinical testing. (Intended use: femoral hip component replacement due to disease or accident, uncemented applications).	"Non-clinical laboratory testing was performed to determine substantial equivalence. The results indicated that the device was functional within its intended use." (However, specific performance metrics or thresholds are not detailed in this summary).
   Material composition (wrought titanium alloy (Ti-6AI-4V) (ASTM F136)) and porous coating for uncemented applications.	The device is made from "wrought titanium alloy (Ti-6AI-4V) (ASTM F136)" and "has a porous coat, designed to be used in uncemented applications."
   Stem diameters and lengths within the range of previously cleared predicates.	"The stem diameters and lengths are within the range of the previously cleared predicates."
   Presence of a lateralized offset (as an additional feature).	"In addition to the cylindrical stem design, the Parallel-Sided Extensively Coated Femoral Stem offers a lateralized offset for optimal patient fit." (This is a design feature, not a performance metric per se, but supports "optimal patient fit" as an intended functional outcome).

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

   The document explicitly states: "Clinical Testing: None provided as a basis for substantial equivalence." This means there was no human-patient-based test set with associated data provenance for this specific 510(k) submission. The evaluation relied solely on non-clinical (laboratory) testing and comparison to predicate devices.

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

   Not applicable, as no clinical test set was used, and therefore, no expert-established ground truth for a test set was required for this submission.

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

   Not applicable, as no clinical test set was used.

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 device is a physical orthopedic implant, not an AI or imaging diagnostic tool. Therefore, MRMC studies involving human readers and AI assistance are not relevant to its evaluation.

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

   Not applicable. This device is a physical orthopedic implant.

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

   For the "non-clinical laboratory testing," the ground truth would be established by engineering standards, material specifications, mechanical testing protocols (e.g., fatigue, static strength, wear), and performance benchmarks derived from the predicate devices. This would involve objective measurements and comparisons against established industry and regulatory standards for orthopedic implants.

8. The sample size for the training set:

   Not applicable in the context of clinical data for AI/ML. For the non-clinical testing, the "sample size" would refer to the number of devices tested in laboratory experiments (e.g., how many stems were subjected to fatigue testing). This information is not provided in the summary.

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

   Not applicable in the context of clinical data for AI/ML. For the non-clinical testing, the "ground truth" or validation data would be established through adherence to national and international standards for medical device testing (e.g., ASTM, ISO standards for hip implants), recognized testing methodologies, and comparison to the known performance characteristics of the predicate devices.

Ask a specific question about this device