21 CFR 892.8200 — Radiological Software System For Delivery Date Prediction

Radiology (RA) · De Novo Classifications · § 892.8200

Identification

Delivery Date AI is a post-processing software designed to analyze pregnancy ultrasound images using machine learning techniques. It analyzes raw images to provide healthcare practitioners (HCPs) with a Predicted Delivery Date (PDD) in women 18 years of age or older with a singleton pregnancy at or beyond 14 0/7 weeks through 36 6/7 weeks gestation who lack a reliable Estimated Delivery Date (EDD) due to unreliable LMP or no first-trimester ultrasound. The software should be used as an aid in clinical judgment, alongside standard methods for assessing gestational age.

Classification Rationale

FDA has determined that the device can be classified in Class II with the establishment of special controls for Class II. FDA believes that Class II (special) controls provide reasonable assurance of the safety and effectiveness of the device type.

Product Codes

Special Controls

SHE — Radiological Software System For Delivery Date Prediction

In combination with the general controls of the FD&C Act, the radiological software system for delivery date prediction is subject to the following special controls: - (1) Data obtained from clinical performance validation testing acquired under anticipated conditions of use must demonstrate that the device performs as intended when used in the intended patient population. Documentation must include the following: - (i) A clear description of the patient population the device is intended to analyze. - (ii) A clear description of the clinical environment and context of use in which the device is intended to be used. - (iii) A description of the dataset(s) used, including detailed annotation methods and important cohorts (e.g., subsets defined by patient demographics, clinically relevant confounders, and image acquisition characteristics). Validation must contain a sufficient number of cases from important cohorts (i.e., subsets defined by clinically relevant demographics, confounders, effect modifiers, concomitant diseases, challenging cases, and subsets defined by image acquisition characteristics) such that the performance estimates and confidence intervals of the device for these individual subsets can be characterized for the intended use population and imaging equipment. The test dataset must be independent of the data used in the training/development of the device. - (iv) A description of prespecified performance testing protocols (including but not limited to the study objectives, study endpoints, statistical hypotheses, performance goals, sample size calculation, and statistical analyses). Performance goals used to determine success of the clinical validation study must be clinically justified and must be based on appropriate objective performance measures comparing the device output to known delivery information on sampled patients (e.g., Bland-Altman plots, error metrics). - (v) Performance testing should capture inter- and intra- patient variability and ranges of agreement between the device predictions and reference standard, as well as other relevant sources of variation. - (2) Device design characteristics must ensure that information and limitations in special control (4)(i) and 4(vii) are featured in the software user interface. - (3) Software verification, validation, and hazard analysis must be provided. Software documentation must include a detailed technical description of all image analysis algorithms, including the algorithm inputs and outputs, each major component or block, and any algorithm limitations. - (4) Labeling must include: - (i) A description of the meaning of the date predicted by the device and the relationship of the date to other calculated dates used in clinical practice (e.g., estimated delivery date); - (ii) A description of the intended patient population, the intended user, clinical environment, and context of use, including information on interpretation of outputs within the intended clinical workflow; - (iii) A description of the device inputs and outputs; - (iv) A description of compatible imaging hardware and imaging protocols; - (v) A summary of the development data and clinical validation data, including sources of data, study sites, samples sizes, demographics and other relevant characteristics of the study participants; - (vi) A summary of performance testing including test methods, dataset characteristics, reference standard, testing environment, results (with confidence intervals), and a summary of clinical performance for all demographic subgroups and relevant confounders from testing dataset(s); - (vii) Limiting statements that indicate: - (A) The output is not intended to predict or assess the risk of pre-term birth; - (B) A description of situations in which the device may fail or may not operate at its expected performance level (e.g., poor image quality or for certain subpopulations), as applicable; and - (C) A warning that users should use the device in conjunction with other clinical and diagnostic findings, including information obtained by alternative methods and clinical evaluation, as appropriate. - (5) The device manufacturer must develop and implement a post-market performance management plan that ensures regular assessment of the generalizability and device performance in the intended patient population in real-world use. The plan must include: - (i) Data collection, analysis methods, and procedures for: - (A) Monitoring relevant performance characteristics and detecting changes in performance; - (B) Identifying sources of performance changes between validation and real-world environment over time; and - (C) Assessing the results from the performance testing on safety and effectiveness; - (ii) Procedures for communicating the device's current performance to the users.

De Novo Order DEN250007