(155 days)
The EarliPoint Assessment device is indicated as a tool to aid qualified clinicians in the diagnosis and assessment of Autism Spectrum Disorder (ASD) in children ages 16 months through 95 months (7 years), who are at risk based on concerns identified by a parent, caregiver, or healthcare provider.
The EarliPoint assessment uses an eye tracker to measure the patient's looking behavior while viewing a series of videos. The system then remotely analyzes the looking behavior data using software and outputs a diagnosis of the patient's ASD status and associated developmental delay indices.
The EarliPoint System device consists of the following:
- Eye-tracking module and a separate Operator Module that can control the Eye-tracking module remotely. The patient sits on a chair and the Eye-tracking module is adjusted by the operator such that the patient's eyes are within the specification of the eye-tracking window.
- Eye-tracking module captures the patient visual response to social information provided in the form of a series of age-appropriate videos.
- Operator's module is used to initiate and monitors the session remotely
- WebPortal securely stores all patient information, analyzes the eye-tracking data, and outputs the results. Users can retrieve the results directly from the web portal.
- Software analyzes the eye-tracking data and provides a diagnosis for ASD. In addition, it also outputs 3 developmental delay indices (called EarliPoint Severity Indices) that proxy validated ASD instruments
Here's an analysis of the acceptance criteria and the study that proves the device meets them, based on the provided FDA 510(k) clearance letter for the EarliPoint Assessment device.
1. Table of Acceptance Criteria and Reported Device Performance
The acceptance criteria are implicitly derived from the performance of the predicate device and the new clinical study for the expanded age range. The primary metrics are Sensitivity, Specificity, Positive Predictive Value (PPV), Negative Predictive Value (NPV), and Accuracy, compared to the expert clinical diagnosis (reference standard). The "Comparison" column in the provided table states "Substantially Equivalent" for all metrics, indicating that the performance of the subject device in the expanded age range (and the combined age range) meets the implicit acceptance criteria based on its predicate.
| Performance Measure | Acceptance Criteria (Implicit, based on Predicate K243891 16-30 months) | Reported Device Performance (EarliPoint System 16 to <96 months) |
|---|---|---|
| Sensitivity | 78.0% (70.5 - 84.3) | 80.2% (75.6 - 84.3) |
| Specificity | 85.4% (79.5 - 90.2) | 81.3% (76.7 - 85.3) |
| Positive Predictive Value | 81.3% (73.9 - 87.3) | 81.2% (76.6 - 85.2) |
| Negative Predictive Value | 82.7% (76.6 - 87.8) | 80.4% (75.7 - 84.4) |
| Accuracy | 82.1% (77.6 - 86.0) | 80.8% (77.6 - 83.7) |
Note: The predicate values for the 16-30 month age range, when reanalyzed with the borderline range, showed slightly different (and in the case of sensitivity, higher) performance. The performance of the subject device across the combined age range appears to maintain substantial equivalence. The document explicitly states, "clinical data from the expanded age range demonstrates the safety and effectiveness of the device without raising new or different questions of safety and effectiveness."
2. Sample Size Used for the Test Set and Data Provenance
- Test Set Sample Sizes:
- 16-30 months (original study): The table "EarliPoint System 16-30 months" shows a total of 335 participants for the predicate device. For the subject device (with borderline range implemented), the performance figures are based on 307 participants after excluding borderline cases from sensitivity/specificity calculations.
- 31 to <96 months (new study): The table "EarliPoint System 31 to <96 months" shows performance figures based on 369 participants (when borderline cases are excluded). Initial count for the entire population was 477 (when borderline was considered ASD-negative).
- Combined 16 to <96 months: A total of 676 participants (when borderline cases are excluded). Initial count for the entire population was 812 (when borderline was considered ASD-negative).
- Data Provenance: The studies were prospective, double-blind, multi-center, within-subject comparison, US, pivotal studies. This means the data was collected specifically for this evaluation, from multiple centers within the United States.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of those Experts
The document states:
- "All patients were evaluated for ASD by ... expert clinician diagnosis (current best practice for diagnosis of ASD)."
- "robust convergent validity in comparison with Reference Standard assessments of social disability, verbal ability, and nonverbal cognitive ability made by highly trained experts at leading expert centers."
The exact number of experts is not specified. Their qualifications are described as "expert clinician" and "highly trained experts at leading expert centers," implying specialized training and experience in ASD diagnosis, likely including child psychiatrists, developmental pediatricians, or licensed psychologists with expertise in ASD.
4. Adjudication Method for the Test Set
The document does not explicitly state the adjudication method (e.g., 2+1, 3+1). However, it highlights the challenge of "clinical uncertainty" in ASD diagnosis, noting that even clinicians are sometimes less than fully certain of their diagnoses. It states: "EarliPoint clinical trial procedures worked effectively to reduce and minimize, to the extent possible, clinician uncertainty in the reference standard diagnosis." This suggests that efforts were made to achieve a high degree of confidence in the ground truth, but the specific process (e.g., multiple independent diagnoses followed by a consensus meeting or a tie-breaker by a more senior expert) is not detailed.
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
The study described is a standalone (algorithm only) performance study, comparing the device's output directly against expert clinical diagnosis (reference standard). It is not an MRMC comparative effectiveness study where human readers' performance with and without AI assistance is measured. Therefore, there is no information provided about the effect size of human readers improving with AI assistance.
6. If a Standalone (i.e. algorithm only without human-in-the loop performance) was Done
Yes, a standalone study was done. The entire premise of the clinical study is to evaluate the "EyeTracking System diagnosis relative to the expert clinical diagnosis" and quantify its sensitivity, specificity, and other metrics. The device "outputs a diagnosis of the patient's ASD status," implying a direct algorithmic output without human intervention for the primary outcome.
7. The Type of Ground Truth Used
The primary ground truth used is expert clinician diagnosis, specifically described as "current best practice for diagnosis of ASD." This diagnosis also includes assessments using "validated ASD instruments" like ADOS-2, and Mullen/DAS-II, as referenced for correlating the EarliPoint Severity Indices.
8. The Sample Size for the Training Set
The document does not provide any information regarding the size or characteristics of the training set used to develop the EarliPoint Assessment algorithm. The clinical studies described are for validation/testing of the device's performance, not for its training.
9. How the Ground Truth for the Training Set Was Established
Since information on the training set's sample size is not provided, the method for establishing its ground truth is also not specified in this document.
FDA 510(k) Clearance Letter - EarliPoint Assessment
Page 1
U.S. Food & Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993
www.fda.gov
Doc ID # 04017.08.04
March 5, 2026
Earlitec Diagnostics
℅ Amy Wolbeck
Regulatory Consultant
Rqm+
2790 Mosside Blvd.
Pittsburgh, Pennsylvania 15146
Re: K253442
Trade/Device Name: EarliPoint Assessment
Regulation Number: 21 CFR 882.1491
Regulation Name: Pediatric Autism Spectrum Disorder Diagnosis Aid
Regulatory Class: Class II
Product Code: QPF
Dated: February 3, 2026
Received: February 3, 2026
Dear Amy Wolbeck:
We have reviewed your section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (the Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database available at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.
If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.
Page 2
K253442 - Amy Wolbeck
Page 2
Additional information about changes that may require a new premarket notification are provided in the FDA guidance documents entitled "Deciding When to Submit a 510(k) for a Change to an Existing Device" (https://www.fda.gov/media/99812/download) and "Deciding When to Submit a 510(k) for a Software Change to an Existing Device" (https://www.fda.gov/media/99785/download).
Your device is also subject to, among other requirements, the Quality Management System Regulation (QMSR) (21 CFR Part 820), which includes, but is not limited to, ISO 13485 clause 7.3 (Design controls), ISO 13485 clause 8.3 (Nonconforming product), and ISO 13485 clause 8.5 (Corrective and preventative action). Please note that regardless of whether a change requires premarket review, the QMSR requires device manufacturers to review and approve changes to device design and production (ISO 13485 clause 7.3 and 21 CFR 820.70) and document changes and approvals in the Medical Device File (21 CFR 820.181).
Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting (reporting of medical device-related adverse events) (21 CFR Part 803) for devices or postmarketing safety reporting (21 CFR Part 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reporting-combination-products); good manufacturing practice requirements as set forth in the Quality Management System Regulation (QMSR) (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR Part 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR Parts 1000-1050.
All medical devices, including Class I and unclassified devices and combination product device constituent parts are required to be in compliance with the final Unique Device Identification System rule ("UDI Rule"). The UDI Rule requires, among other things, that a device bear a unique device identifier (UDI) on its label and package (21 CFR 801.20(a)) unless an exception or alternative applies (21 CFR 801.20(b)) and that the dates on the device label be formatted in accordance with 21 CFR 801.18. The UDI Rule (21 CFR 830.300(a) and 830.320(b)) also requires that certain information be submitted to the Global Unique Device Identification Database (GUDID) (21 CFR Part 830 Subpart E). For additional information on these requirements, please see the UDI System webpage at https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-assistance/unique-device-identification-system-udi-system.
Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-devices/medical-device-safety/medical-device-reporting-mdr-how-report-medical-device-problems.
For comprehensive regulatory information about medical devices and radiation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-
Page 3
K253442 - Amy Wolbeck
Page 3
assistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).
Sincerely,
Patrick Antkowiak -S
for
Jay Gupta
Assistant Director
DHT5A: Division of Neurosurgical,
Neurointerventional, and
Neurodiagnostic Devices
OHT5: Office of Neurological and
Physical Medicine Devices
Office of Product Evaluation and Quality
Center for Devices and Radiological Health
Enclosure
Page 4
FORM FDA 3881 (6/20)
Page 1 of 1
PSC Publishing Services (301) 443-6740 EF
DEPARTMENT OF HEALTH AND HUMAN SERVICES
Food and Drug Administration
Indications for Use
Form Approved: OMB No. 0910-0120
Expiration Date: 06/30/2023
See PRA Statement below.
510(k) Number (if known): K253442
Device Name: EarliPoint Assessment
Indications for Use (Describe)
The EarliPoint Assessment device is indicated as a tool to aid qualified clinicians in the diagnosis and assessment of Autism Spectrum Disorder (ASD) in children ages 16 months through 95 months (7 years), who are at risk based on concerns identified by a parent, caregiver, or healthcare provider.
Type of Use (Select one or both, as applicable)
☒ Prescription Use (Part 21 CFR 801 Subpart D)
☐ Over-The-Counter Use (21 CFR 801 Subpart C)
CONTINUE ON A SEPARATE PAGE IF NEEDED.
This section applies only to requirements of the Paperwork Reduction Act of 1995.
DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.
The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:
Department of Health and Human Services
Food and Drug Administration
Office of Chief Information Officer
Paperwork Reduction Act (PRA) Staff
PRAStaff@fda.hhs.gov
"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."
Page 5
510(K) SUMMARY - K253442
510(k) Information
| Field | Value |
|---|---|
| 510(k) Number | K253442 |
| 510(k) Type | Traditional 510(k) |
| Date Prepared | 3 February 2026 |
Submitter Information
510(k) Submitter: Ryan Bormann, Director of Quality and Operations
EarliTec Diagnostics, Inc.
13895 Industrial Park Blvd, Suite 140
Tel: +1-833-504-9937
Email: rbormann@earlitecdx.com
Primary Correspondent: Amy Wolbeck
Regulatory Consultant
RQM+
5000 Centregreen Way, Suite 100
Cary, NC 27513
Tel: +1-707-291-3457
Email: awolbeck@rqmplus.com
EarliPoint System Device Information
| Field | Value |
|---|---|
| Trade Name (Common Name) | EarliPoint Assessment |
| Device Classification Name | Pediatric Autism Spectrum Disorder Diagnostic Aid |
| Classification Regulation | 21 CFR 882.1491 |
| Class | II |
| Panel | Neurology Devices Panel |
| Product Code | QPF |
| Predicate Device | EarliPoint System K243891 |
Device Description: The EarliPoint assessment uses an eye tracker to measure the patient's looking behavior while viewing a series of videos. The system then remotely analyzes the looking behavior data using software and outputs a diagnosis of the patient's ASD status and associated developmental delay indices.
The EarliPoint System device consists of the following:
- Eye-tracking module and a separate Operator Module that can control the Eye-tracking module remotely. The patient sits on a chair and the Eye-tracking module is adjusted by the operator such that the patient's eyes are within the specification of the eye-tracking window.
- Eye-tracking module captures the patient visual response to social information provided in the form of a series of age-appropriate videos.
- Operator's module is used to initiate and monitors the session remotely
- WebPortal securely stores all patient information, analyzes the eye-tracking data, and outputs the results. Users can retrieve the results directly from the web portal.
Page 6
- Software analyzes the eye-tracking data and provides a diagnosis for ASD. In addition, it also outputs 3 developmental delay indices (called EarliPoint Severity Indices) that proxy validated ASD instruments
| Field | Value |
|---|---|
| Intended Use | Intended for use as an aid in the diagnosis of Autism Spectrum Disorder in pediatric patients |
| Indications for Use | The EarliPoint Assessment device is indicated as a tool to aid qualified clinicians in the diagnosis and assessment of Autism Spectrum Disorder (ASD) in children ages 16 months through 95 months (7 years), who are at risk based on concerns identified by a parent, caregiver, or healthcare provider. |
EarliPoint System Nonclinical Data (unchanged from predicate device)
| Test Category | Description |
|---|---|
| Performance Testing | EarliPoint was verified to meet the electrical safety standards and the software were designed and tested per IEC 62304. |
| Mechanical/Electrical Safety and Electromagnetic Compatibility (EMC) | Mechanical/electrical safety and EMC testing were conducted on the EarliPoint device. The EarliPoint device is classified as Class I for protection against electric shock with Type B applied part and is intended for continuous mode of operation. Compliance testing shows that the EarliPoint device complies with all the applicable tests of IEC 60601-1 standard for mechanical/electrical safety and the IEC 60601-1-2 standard for EMC. |
EarliPoint System Software Testing
| Test Category | Description |
|---|---|
| Software Verification and Validation | Software verification and validation testing were successfully completed. |
EarliPoint System Clinical Testing for Expanded Age Range
Clinical Studies: The safety and effectiveness of the EarliPoint Assessment in collecting eye-tracking data and analyzing the data for diagnosing the presence of ASD was evaluated in a pivotal study in children ages 31 months to 7 years (<96 months).
All patients were evaluated for ASD by both the EarliPoint system and by expert clinician diagnosis (current best practice for diagnosis of ASD) to evaluate the sensitivity and specificity of the EarliPoint System diagnosis relative to the expert clinical diagnosis. The study also correlated the three EarliPoint Severity Indices of social disability, verbal ability and nonverbal ability against validated ASD instruments.
The EarliPoint evaluation was safe (no serious adverse events or device-related adverse events) and effective: it had strong sensitivity and specificity in comparison with Reference Standard categorical diagnoses (sensitivity 77.1% and specificity 78.6%) and has robust convergent validity in comparison with Reference Standard assessments of social disability, verbal ability, and nonverbal cognitive ability made by highly trained experts at leading expert centers. These results augment EarliPoint's
Page 7
previously cleared indication for use in children ages 16 through 30 months.
Comparison to Predicate Device
Intended Use/Indications for Use Comparison
The subject device and the predicate have the same intended use. Specifically, both devices are intended for use as an aid in the diagnosis of Autism Spectrum Disorder (ASD) in pediatric patients. The subject device and the predicate have the same indications for use with the exception being the subject device expands the age range from 16-30 months to 31-95 months of age. Clinical testing conducted in the expanded age range demonstrated that the device is as safe and effective as the predicate. The expanded age range does not raise new questions of safety or effectiveness. Clinical data has been provided to support the modified indications for use.
Technological Characteristics
The subject device has the same technological characteristics as the predicate as outlined in the table below.
Substantial Equivalent Comparison
| Device Characteristic | Predicate Device K243891 EarliPoint System | Subject Device K253442 EarliPoint Assessment |
|---|---|---|
| Intended Use | Intended for use as an aid in the diagnosis of Autism Spectrum Disorder in pediatric patients | Same as predicate |
| Indications for Use | The EarliPoint System device is indicated as a tool to aid qualified clinicians in the diagnosis and assessment of Autism Spectrum Disorder (ASD) in children ages 16 months through 30 months, who are at risk based on concerns identified by a parent, caregiver, or healthcare provider. | The EarliPoint Assessment device is indicated as a tool to aid qualified clinicians in the diagnosis and assessment of Autism Spectrum Disorder (ASD) in children ages 16 months through 95 months (7 years), who are at risk based on concerns identified by a parent, caregiver, or healthcare provider. |
| Prescription Use | Yes | Same as predicate |
| Product Code and Regulation Number | QPF 882.1491 | Same as predicate |
| Device Components | • Eye-tracking module captures the patient visual response to social information provided in the form of a series of age-appropriate videos.• Operator's module is used to initiate and monitor the session remotely• WebPortal securely stores all patient information, analyzes the eye tracking data, and outputs the results. Users can retrieve the results directly from the web portal. | Same as predicate, except for the number of device output labels (positive, negative, and borderline for the subject device vs. only positive and negative for the predicate). This does not adversely impact the safety and effectiveness of the subject device as compared to the predicate. |
Page 8
| Device Characteristic | Predicate Device K243891 EarliPoint System | Subject Device K253442 EarliPoint Assessment |
|---|---|---|
| • Software analyzes the eye-tracking data and provides diagnostic scores with labels to aid in ASD diagnosis. In addition, it also outputs 3 developmental delay indices (called EarliPoint Severity Indices) that proxy validated ASD instruments | ||
| Electrical Safety Testing | Meets electrical safety standards per:• IEC 60601-1:2005/AMD1:2012/AMD2:2020• IEC 60601-1-2:2014/AMD1:2020 | Same as predicate |
| Software | Compliant to ISO 62304 | Same as predicate |
| Clinical data | Pivotal trials provide safety and effectiveness data. | Same as predicate |
| Risk level of the device | Low risk device, non-invasive | Same as predicate |
Clinical Studies
The safety and effectiveness of the EarliPoint System in diagnosing the presence of ASD was evaluated in 2 prospective, double-blind, multi-center, within-subject comparison, US, pivotal studies. The first study evaluated 16-30-month-old children and supported the original 510(k) clearance of the device (K213882). The second study evaluated 31 to <96 month-old children.
All study subjects in both clinical studies were evaluated for ASD by both the EarliPoint system and by expert clinician diagnosis (current best practice for diagnosis of ASD) to evaluate the sensitivity and specificity of the EarliPoint System diagnosis relative to the expert clinical diagnosis. These studies also correlated the three EarliPoint Severity Indices of social disability, verbal ability and nonverbal ability against the corresponding expert clinical instruments of ADOS-2, and Mullen/DAS-II.
As autism is defined as a spectrum disorder, the distinction between autism spectrum disorder (ASD) and non-ASD presentations is at times nuanced and clinicians frequently encounter challenges in delineating clear boundaries between individuals with ASD and individuals who do not have ASD. The subject device includes implementation of a borderline range for EarliPoint diagnostic scores close to the threshold delineating ASD-positive from ASD-Negative, as such borderline cases may require additional observation from a clinician to determine the appropriate diagnosis.
EarliPoint outputs a Diagnostic Index Score for each session, typically ranging from -30 to +30. Based on this score, EarliPoint provides one of the following diagnoses:
- Consistent with autism - Scores ≤0
- Borderline Range - Scores >0 and ≤3
- Not Consistent with autism - Scores >3
Scores between 0 and 3 are considered borderline. Further assessment is advised to determine presence or absence of autism.
Page 9
Clinical Study Safety and Effectiveness
The pivotal studies showed that the EarliPoint device was safe and effective in the diagnosis of ASD in children. There was no reported serious adverse event related to the use of the EarliPoint system. When compared to the predicate, the sensitivity and specificity of the EarliPoint device was found to be substantially equivalent to the subject device.
The data from the original clinical study for the 16-30-month-old children is provided in the table below under the predicate device column. As the original device did not include a borderline output, the clinical trial data was reanalyzed with the implementation of the borderline range in the table below under the subject device column, EarliPoint System 16-30 months. Data from the second clinical study evaluating 31 to <96 month old children is provided in the table below EarliPoint System 31 to <96 months. The last column in the table below provides the data from the 2 clinical studies, EarliPoint System 16 to <96 months.
| Performance Measure | Predicate Device (K243891) EarliPoint System 16-30 months | Subject Device EarliPoint System 16-30 months | EarliPoint System 31 to <96 months | EarliPoint System 16 to <96 months | Comparison |
|---|---|---|---|---|---|
| Sensitivity | 78.0% (70.5 - 84.3) 117/150 | 84.8% (77.7 - 90.3) 117/138 | 77.1% (70.7 - 82.7) 155/201 | 80.2% (75.6 - 84.3) 272/339 | Substantially Equivalent |
| Specificity | 85.4% (79.5 - 90.2) 158/185 | 84.0% (77.6 - 89.2) 142/169 | 78.6% (71.6 - 84.5) 132/168 | 81.3% (76.7 - 85.3) 274/337 | Substantially Equivalent |
| Positive Predictive Value | 81.3% (73.9 - 87.3) 117/144 | 81.3% (73.9 - 87.3) 117/144 | 81.2% (74.9 - 86.4) 155/191 | 81.2% (76.6 - 85.2) 272/335 | Substantially Equivalent |
| Negative Predictive Value | 82.7% (76.6 - 87.8) 158/191 | 87.1% (81.0 - 91.8) 142/163 | 74.2% (67.1 - 80.4) 132/178 | 80.4% (75.7 - 84.4) 274/341 | Substantially Equivalent |
| Accuracy | 82.1% (77.6 - 86.0) 275/335 | 84.4% (79.8 - 88.2) 259/307 | 77.8% (73.2 - 81.9) 287/369 | 80.8% (77.6 - 83.7) 546/676 | Substantially Equivalent |
Each cell gives the performance measure as percentage with corresponding two-sided 95% confidence interval, together with participant counts for each measure.
Note: All confidence intervals (CI) calculated as two-sided 95% CI, estimated using the Clopper-Pearson (exact) approach.
Reference Standard Clinical Uncertainty
As noted in the existing clinical literature in autism (McDonnell et al, JADD, 2019 and Klaiman et al, JADD, 2024), current best practice diagnosis of autism is challenging, and clinicians are sometimes less than fully certain that their own diagnoses are accurate. McDonnell et al found that clinicians were only fully certain of the accuracy of their diagnoses in 60% of cases (40% uncertain), while Klaiman et al documented 29.5% uncertainty.
In the EarliPoint studies there were 252 uncertain diagnoses out of a total of 1064 subjects (23.7%), which is less than rates reported in the literature, evidence of the fact that the EarliPoint clinical trial procedures worked effectively to reduce and minimize, to the extent possible, clinician uncertainty in the reference standard diagnosis.
Page 10
Stratum-Specific Likelihood Ratios (SSLR)
The Stratum-Specific Likelihood Ratios (SSLR) provided in demonstrates that participants who receive EarliPoint scores in the Borderline range are meaningfully distinct from those who receive scores in the ASD (positive) or Non-ASD (negative) range. The non-overlapping SSLR confidence intervals demonstrate that the Borderline group does not represent a probabilistic blend of positive and negative outcomes, but instead constitutes a distinct profile. This separation supports EarliPoint's ability to identify Borderline cases with a meaningful degree of diagnostic specificity.
In practice, this supports the clinical interpretation of a Borderline EarliPoint result as an intermediate risk category. These cases warrant closer clinical review, integration with additional clinical information, and additional evaluation, rather than being interpreted as clearly positive or negative.
Stratum-Specific Likelihood Ratios for Clinical Trial Borderline Range
| Performance Measure | EarliPoint System 16-30 months (K243891) | EarliPoint System 31 - <96 months (K253442) | Entire age range 16 - <96 months |
|---|---|---|---|
| Positive (ASD) SSLR (95% CI) | 5.34 (3.73, 7.65) | 4.11 (3.01, 5.62) | 4.58 (3.61, 5.81) |
| Borderline Range SSLR (95% CI) | 0.92 (0.45, 1.89) | 0.63 (0.45, 0.89) | 0.72 (0.53, 0.99) |
| Negative (Non-ASD) SSLR (95% CI) | 0.18 (0.12, 0.27) | 0.18 (0.12, 0.27) | 0.26 (0.21, 0.33) |
¹ The 95% CI for SSLR is based on the formula introduced by Peirce and Cornell (1993).
² Positive: EarliPoint diagnostic scores ≤ 0; Borderline: EarliPoint diagnostic scores > 0 and ≤ 3; Negative: EarliPoint diagnostic scores > 3.
Performance Results with and without Borderline Range
Ages 16-30 Months are captured in Table 5-1 below. All certain diagnoses by clinical reference standard (uncertain diagnoses were not included in performance analysis, n=140 for 16-30 months):
Table 5-1: Certain Diagnoses by Reference Standard (16-30 Months)
| Population (16 to 30 months) | Sensitivity | Specificity |
|---|---|---|
| EarliPoint, borderline range not implemented, predicate K243891 N=335 | 78.0% (117/150) 95% CI: 70.7%, 83.9% | 85.4% (158/185) 95% CI: 79.5%, 90.2% |
| EarliPoint, with borderline range implemented as separate output*, predicate K243891 N=307 | 84.8% (117/138) 95% CI: 77.7%, 90.3% | 84.0% (142/169) 95% CI: 77.6%, 89.2% |
Page 11
* Borderline cases were not included in sensitivity/specificity calculations given the device's intended use
Ages 31 to <96 Months are captured in Table 5-2 below. All certain diagnoses by clinical reference standard (uncertain diagnoses were not included in performance analysis, n=112 for 31 to <96 months):
Table 5-2 Certain Diagnoses by Reference Standard (31 - <96 Months)
| Population (31 to <96 months) | Sensitivity | Specificity |
|---|---|---|
| EarliPoint, borderline range considered ASD-negative* N=477 | 63.5% (155/244) 95% CI: 57.1%, 69.6% | 84.5% (197/233) 95% CI: 79.3%, 88.9% |
| EarliPoint, with borderline range implemented as a separate output** N=369 | 77.1% (155/201) 95% CI: 70.7%, 82.7% | 78.6% (132/168) 95% CI: 71.6%, 84.5% |
* In this row, borderline cases were considered ASD-negative, consistent with the predicate device (borderline range not implemented). However, in the intended use of EarliPoint, scores in the borderline range, close to the threshold delineating ASD-positive from ASD-Negative (>0 and ≤3), will not be labeled as either "ASD-positive" or "ASD-negative". These patients who fall in the borderline range have results that are not clearly consistent with either "ASD-positive" or "ASD-negative" and may require additional observation from a clinician to determine the appropriate diagnosis.
** Borderline cases were not included in sensitivity/specificity calculations given the device's intended use
Ages 16 to <96 Months are captured in Table 5-3 below. All certain diagnoses by clinical reference standard (uncertain diagnoses were not included in performance analysis, n=252 for 16 to <96 months):
Table 5-3 Certain Diagnoses by Reference Standard (16 - <96 Months)
| Population (16 to <96 months) | Sensitivity | Specificity |
|---|---|---|
| EarliPoint, borderline range considered ASD-negative* N=812 | 69.0% (272/394) 95% CI: 64.2%, 73.6% | 84.9% (355/418) 95% CI: 81.1%, 88.2% |
| EarliPoint, with borderline range implemented as separate output** N=676 | 80.2% (272/339) 95% CI: 75.6%, 84.3% | 81.3% (274/337) 95% CI: 76.7%, 85.3% |
* In this row, borderline cases were considered ASD-negative, consistent with the predicate device (borderline range not implemented). However, in the intended use of EarliPoint, scores in the borderline range, close to the threshold delineating ASD-positive from ASD-Negative (>0 and ≤3), will not be labeled as either "ASD-positive" or "ASD-negative". These patients who fall in the borderline range have results that are not clearly consistent with either "ASD-positive" or "ASD-negative" and may require additional observation from a clinician to determine the appropriate diagnosis.
** Borderline cases were not included in sensitivity/specificity calculations given the device's intended use
Note: All confidence intervals (CI) calculated as two-sided 95% CI, estimated using the Clopper-Pearson (exact) approach.
Page 12
CONCLUSION
Both devices have the same intended use and technological characteristics. The modification to the indications for use statement of the subject device is to expand the age range for use with children through 95 months of age. Clinical data from the expanded age range demonstrates the safety and effectiveness of the device without raising new or different questions of safety and effectiveness. The conclusions drawn from the nonclinical, software testing and clinical studies support the safety and effectiveness of the device. Hence, the subject device is substantially equivalent to the predicate device.
§ 882.1491 Pediatric Autism Spectrum Disorder diagnosis aid.
(a)
Identification. A pediatric Autism Spectrum Disorder diagnosis aid is a prescription device that is intended for use as an aid in the diagnosis of Autism Spectrum Disorder in pediatric patients.(b)
Classification. Class II (special controls). The special controls for this device are:(1) Clinical performance testing must demonstrate that the device performs as intended under anticipated conditions of use, including an evaluation of sensitivity, specificity, positive predictive value, and negative predictive value using a reference method of diagnosis and assessment of patient behavioral symptomology.
(2) Software verification, validation, and hazard analysis must be provided. Software documentation must include a detailed, technical description of the algorithm(s) used to generate device output(s), and a cybersecurity assessment of the impact of threats and vulnerabilities on device functionality and user(s).
(3) Usability assessment must demonstrate that the intended user(s) can safely and correctly use the device.
(4) Labeling must include:
(i) Instructions for use, including a detailed description of the device, compatibility information, and information to facilitate clinical interpretation of all device outputs; and
(ii) A summary of any clinical testing conducted to demonstrate how the device functions as an interpretation of patient behavioral symptomology associated with Autism Spectrum Disorder. The summary must include the following:
(A) A description of each device output and clinical interpretation;
(B) Any performance measures, including sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV);
(C) A description of how the cutoff values used for categorical classification of diagnoses were determined; and
(D) Any expected or observed adverse events and complications.
(iii) A statement that the device is not intended for use as a stand-alone diagnostic.