Search Results

Daylight is a prescription device delivering Cognitive Behavioral Therapy and can be made available on the order of a licensed healthcare provider. Daylight is a digital therapeutic intended to treat generalized anxiety disorder (GAD) by improving a patient's GAD symptoms as an adjunct to usual care in patients aged 22 years and older.

Daylight is a digital therapeutic designed to address the symptoms of adults with generalized anxiety disorder (GAD) through the use of Cognitive Behavioral Therapy (CBT) techniques. The Daylight program is has been demonstrated to help improve symptoms of GAD, if followed correctly, and is supported by evidence from peer-reviewed studies and clinical trials. The program is delivered digitally through the Daylight iOS/Android apps, giving users easy access to effective techniques.

The document provided focuses on asserting the substantial equivalence of the Daylight device to a predicate device (Somryst) for regulatory clearance, primarily based on the similarity of their intended use, technological characteristics, and a clinical study demonstrating the efficacy of Daylight for its specific indication (Generalized Anxiety Disorder).

This type of submission document (510(k) Summary) does not typically contain detailed information about specific acceptance criteria for device performance in the same way one might describe the performance of a diagnostic AI algorithm against a set of quantitative metrics. Instead, "acceptance criteria" here refer to the overall regulatory requirements for establishing substantial equivalence and demonstrating safety and effectiveness for a digital therapeutic. The primary "proof" of the device meeting these criteria is via the clinical trial results.

Below is an interpretation of "acceptance criteria" in the context of this 510(k) and the information provided to substantiate that the device meets these criteria.

Acceptance Criteria and Device Performance for Daylight

Based on the 510(k) summary, the "acceptance criteria" are implicitly tied to demonstrating safety and effectiveness for the device's intended use and establishing substantial equivalence to a predicate device. For a digital therapeutic, effectiveness is primarily demonstrated through clinical outcomes.

1. Table of Acceptance Criteria and Reported Device Performance

Given the nature of the device (a digital therapeutic delivering CBT for GAD), the acceptance criteria are not in the form of typical quantitative performance metrics like sensitivity/specificity for a diagnostic device. Instead, they relate to:

• Clinical Efficacy: Improvement in GAD symptoms.
• Safety: Acceptable adverse event profile.
• Substantial Equivalence: Alignment with predicate device in terms of intended use, technology, and risk profile.

2. Sample Size and Data Provenance

• Test Set (Clinical Trial Data):
  • Sample Size: 351 adults, randomized 1:1, with 175 assigned to Daylight and 176 to online anxiety psychoeducation.
  • Data Provenance: Participants were recruited from across the United States via social media. The study was a two-arm, parallel group, randomized controlled trial (RCT), indicating prospective data collection.

3. Number of Experts and their Qualifications (for Ground Truth)

• Not applicable in this context. The device is a digital therapeutic for generalized anxiety disorder, and the "ground truth" for its effectiveness is based on patient-reported outcomes (GAD-7, PHQ-8, SCI-8, OASIS), and clinician-reported outcomes (CGI-I, CGI-S) from a Randomized Controlled Trial, rather than expert interpretation of images or other data typically requiring consensus for ground truth. The "experts" involved would be the clinicians conducting the CGI assessments and diagnosing GAD, but the document does not specify their number or qualifications.

4. Adjudication Method for the Test Set

• Not applicable in this context. As the effectiveness is measured through standardized questionnaires and clinical scales in an RCT, there is no need for expert adjudication of cases/data points in the same way as, for example, reviewing medical images.

5. MRMC Comparative Effectiveness Study

• No, this was not an MRMC study. This was a randomized controlled trial (RCT) comparing a digital therapeutic (Daylight) to an active control (online anxiety psychoeducation).
• Effect Size of Human Readers Improvement: This concept is not relevant to this type of device or study. The study investigates the effect of the digital therapeutic on patient symptoms, not how AI assists human readers in a diagnostic task. The "human readers" in this context are the patients interacting with the digital therapeutic.

6. Standalone Performance Study

• Yes, in the sense that the clinical trial evaluated the performance of the Daylight algorithm/program as a standalone therapeutic intervention. The study compared Daylight (the intervention) to a psychoeducation control. The device is a "Software as a Medical Device (SaMD)" intended to treat GAD. Its performance is its ability to improve GAD symptoms.
• The study design evaluated the device's direct therapeutic effect on participants, not its ability to assist a human in performing a diagnostic or interpretive task.

7. Type of Ground Truth Used

• Clinical Outcomes / Patient-Reported Outcomes (PROs) and Clinician-Reported Outcomes (CROs):
  • Primary:
    • Generalized Anxiety Disorder 7-item questionnaire (GAD-7) for patient-reported symptom severity.
    • Clinical Global Impression - Improvement scale (CGI-I) for remission (scores of 1 or 2).
  • Secondary:
    • Patient Health Questionnaire (PHQ-8) for depression symptoms.
    • Sleep Condition Indicator (SCI-8) for insomnia symptoms.
    • Clinical Global Impression - Severity (CGI-S) for anxiety severity.
    • Overall Anxiety Severity and Impairment Scale (OASIS).
  • Diagnosis of GAD at baseline according to DSM-5 criteria.

8. Sample Size for the Training Set

• Not explicitly stated in the 510(k) summary. For digital therapeutics based on established CBT principles, a traditional "training set" for a machine learning model might not be applicable in the same way it is for image-based AI diagnostics. The device's "training" might refer to the development and refinement of the CBT content and delivery structure, which is typically based on clinical psychology principles and past research, rather than a data-driven machine learning training set of patient data to optimize an algorithm. The clinical trial serves as the primary validation.

9. How Ground Truth for the Training Set Was Established

• Not applicable / Not detailed in the document. As mentioned above, the "training set" concept is different for this type of device. The "ground truth" for developing the therapeutic content of Daylight would be the established principles of Cognitive Behavioral Therapy for anxiety, supported by decades of psychological and clinical research. The document highlights that Daylight "is supported by evidence from peer-reviewed studies and clinical trials," implying that its efficacy framework is built upon existing scientific understanding of CBT. The GATE trial served as the definitive evaluation of the product's effectiveness as developed.

Ask a specific question about this device

Sleepio is a digital therapeutic intended for the treatment of chronic insomnia disorder as an adjunct to usual care in patients aged 18 and older. Sleepio is a prescription device delivering Cognitive Behavioral Therapy for Insomnia (CBT-I) and can be made available on the order of a licensed healthcare provider.

Sleepio is a digital therapeutic for the treatment of chronic insomnia / insomnia disorder. Sleepio treats chronic insomnia disorder by delivering evidence-based techniques targeting the cognitive and behavioral factors that maintain insomnia and chronic sleep problems. Patient experience is tailored based on symptoms and daily sleep tracking. In addition to core therapeutic components, there is in-the-moment therapeutic content for help falling asleep. Content is delivered via smartphone and tablet applications (iOS and Android), as well as via web. Sleepio is intended as an adjunct to usual care treatment for chronic insomnia / insomnia disorder by a healthcare provider. Healthcare providers have access to a dashboard to track patient engagement with Sleepio.

Based on the provided text, the device in question is Sleepio, a digital therapeutic for the treatment of chronic insomnia disorder. Here's a breakdown of the acceptance criteria and the study proving the device meets them:

Disclaimer: The provided document is an FDA 510(k) summary, which focuses on demonstrating substantial equivalence to a predicate device rather than setting explicit acceptance criteria for this specific device's performance in a new, de novo fashion. The clinical data presented serves to support the substantial equivalence claim by showing similar or superior performance to standard care (Sleep Hygiene Education, SHE) and implicitly, to the predicate. Therefore, the "acceptance criteria" table below is inferred from the goals of the clinical study and the claims made about the device's efficacy in the context of demonstrating substantial equivalence for an FDA 510(k) submission.

1. Table of inferred acceptance criteria and the reported device performance

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

• Test set sample size: The clinical effectiveness was evaluated in the CrEDIT trial, a two-arm, parallel group, randomized controlled trial (RCT) with 336 adults.
  • Sleepio group (n=168)
  • Online sleep hygiene education (SHE) group (n=168)
• Data provenance: Participants were recruited from across the United States via social media. The study was prospective (Randomized Controlled Trial).

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

The document does not specify the use of human experts to establish ground truth for the test set in the conventional sense of image or diagnostic adjudication. The ground truth for insomnia was established clinically based on self-reported patient assessments using standardized questionnaires (Insomnia Severity Index, ISI) and sleep diaries (SOL, WASO), and a DSM-5 diagnosis of insomnia disorder as criteria for study inclusion. The study evaluated the effectiveness of a therapeutic intervention, not the diagnostic accuracy of an AI model against expert consensus.

4. Adjudication method for the test set

Not applicable. As noted above, this study measures the therapeutic effectiveness of Sleepio based on patient-reported outcomes, not the performance of a diagnostic or classification algorithm that would require an adjudication method 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

No, an MRMC comparative effectiveness study was not done. This was a clinical trial evaluating a digital therapeutic directly delivered to patients for treatment, not an AI-assisted diagnostic tool for human readers. Therefore, the concept of "human readers improve with AI vs without AI assistance" does not apply.

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

Yes, in a way. Sleepio is a digital therapeutic that delivers Cognitive Behavioral Therapy for Insomnia (CBT-I) directly to patients via smartphone/tablet apps and web. While it's a "prescription device" and "can be made available on the order of a licensed healthcare provider" who "have access to a dashboard to track patient engagement," the core therapeutic delivery and patient interaction are directly from the algorithm/software. The study design directly assesses the effect of this standalone digital intervention compared to sleep hygiene education.

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

The ground truth or clinical endpoints were based on patient-reported outcomes data derived from:

• Insomnia Severity Index (ISI) scores: A standardized, self-reported questionnaire.
• Sleep diary data: Self-reported sleep onset latency (SOL) and wake after sleep onset (WASO).
• DSM-5 diagnosis of insomnia disorder: Used as an inclusion criterion for participants.
• Sleep Condition Indicator (SCI-8): A secondary outcome measure.

8. The sample size for the training set

The document does not specify a training set sample size in the context of an AI/ML model for this device. Sleepio delivers Cognitive Behavioral Therapy for Insomnia (CBT-I), which is an evidence-based therapeutic approach. The "training" for such a device would typically relate to the development of the CBT-I content and algorithms based on established clinical guidelines and research in psychology and sleep medicine, rather than a machine learning training dataset in the typical sense for image recognition or diagnostic AI. The software verification and validation are noted, but this refers to engineering and quality assurance processes, not a machine learning training curriculum.

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

Not applicable directly, as this is not described as a device that uses a trained AI model in the sense of predictive or diagnostic capabilities. Sleepio is a digital delivery mechanism for an established therapy (CBT-I). The "ground truth" for its therapeutic approach is the established principles and efficacy of CBT-I as validated in clinical literature and practice over many years. The clinical study (CrEDIT trial) served as a validation study to demonstrate that Sleepio's digital implementation of CBT-I is effective, rather than a study to establish ground truth for a novel AI algorithm's training.

Ask a specific question about this device