Pediatric Neurogenetic Diagnosis Support Platform (DIAGEN-IA)

Diagnostic Support Platform for the Identification of Pediatric Genetic Neurological Diseases Through a Machine Learning-Based Recommendation System

This study evaluates a diagnostic support platform, DIAGEN-IA, designed to identify pediatric neurological diseases with a genetic basis. Conducted at Carlos Van Buren Hospital in Chile, it aims to determine if the platform reduces inappropriate referrals to clinical geneticists, improves diagnostic evaluations, enhances referral quality, and increases user satisfaction. A prospective before-and-after design will compare outcomes across two phases: baseline data collection and an intervention phase using DIAGEN-IA. Healthcare professionals will use the platform to guide referrals and diagnostic studies. Outcomes include referral appropriateness, completeness of evaluations, quality of referrals, and user satisfaction.

Study Overview

• Status: Recruiting
• Conditions: Genetic Disease; Neurogenetic Disorders
• Intervention / Treatment: Device: Web-Based Application

Detailed Description

This study aims to evaluate the DIAGEN-IA diagnostic support platform, developed to assist in the identification of pediatric neurological diseases with a genetic basis. The primary objective is to assess whether the platform reduces the proportion of inappropriate referrals to clinical geneticists. Secondary objectives include improving the completeness of initial diagnostic evaluations, enhancing the quality of referral requests, and evaluating user satisfaction with the platform.

The study will be conducted at Carlos Van Buren Hospital in Valparaíso, a high-complexity hospital serving over 486,000 individuals. Using a prospective before-and-after design, the study is divided into two phases. The initial 6-month phase will collect baseline data on referrals, their appropriateness, and the completeness of initial diagnostic evaluations. Interobserver variability among geneticists will also be analyzed. In the 6-month intervention phase, healthcare professionals will use DIAGEN-IA during consultations, and the same outcomes will be reassessed.

Participants include healthcare providers from primary and secondary care centers who manage pediatric patients and are responsible for referring cases to clinical geneticists. Eligible participants must be Spanish-speaking professionals with advanced proficiency, working with children under 18 years old, and involved in diagnosing rare diseases. Data will be anonymized, and demographic information such as age, gender, specialty, years of practice, and specific training in genetics or metabolic disorders will be collected.

DIAGEN-IA is a platform co-designed with input from neuropediatricians and geneticists, integrating the Orphanet ontologies (ORDO, HPO, and HOOM) to ensure comprehensive diagnostic support. The application employs a Bayesian network model to recommend differential diagnoses and appropriate tests based on phenotypic characteristics. This AI-driven approach enables interpretable decision-making and models uncertainty inherent in rare disease diagnosis. The platform operates on a client-server architecture and supports seamless integration into clinical workflows.

Primary outcomes include the proportion of referrals deemed inappropriate, assessed using a 5-point Likert scale by clinical geneticists. Secondary outcomes focus on referral quality, evaluated against standardized criteria, and user satisfaction, measured with the validated CSQ-8 questionnaire. User satisfaction will be assessed at one and six months during the intervention phase. Results will inform strategies to optimize referral processes and diagnostic accuracy in pediatric care.

• Study Type: Interventional
• Enrollment (Estimated): 9
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Nicole Nakousi-Capurro, MD; Phone Number: +56 32 2364000; Email: nnakousi@gmail.com
• Study Contact Backup: Name: Carla Taramasco, PhD; Phone Number: +56 32 284 5904; Email: carla.taramasco@unab.cl

Study Locations

• Chile
  • Valparaíso, Chile, 2341131
    • Recruiting
    • Hospital Carlos Van Buren
    • Contact: Nicole Nakousi-Capurro, MD; Phone Number: +56 32 2364000; Email: nnakousi@gmail.com

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Child; Adult; Older Adult
• Accepts Healthy Volunteers: Yes

Description

Inclusion Criteria:

• Neuropediatricians working in the Carlos Van Buren Hospital.
• Participants providing care to pediatric patients (under 18 years of age).
• Native Spanish speakers or those with certified C1-level Spanish proficiency according to the Common European Framework of Reference for Languages.
• Professionals responsible for referring pediatric patients with suspected rare diseases to a clinical geneticist.

Exclusion Criteria:

• Refusal to participate.

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Diagnostic
• Allocation: N/A
• Interventional Model: Single Group Assignment
• Masking: None (Open Label)

Number of Arms

1

Arms and Interventions

Participant Group / Arm

Intervention / Treatment

Experimental: Web-Based Application; The intervention involves the use of the DIAGEN-IA platform, a diagnostic support application designed to assist in identifying pediatric neurological diseases with a genetic basis. DIAGEN-IA employs a Bayesian network model, integrating ontologies such as ORDO, HPO, and HOOM to link phenotypic characteristics entered by physicians with suggested diagnoses and recommended tests. Participating pediatric neurologists will receive training to use the application during the 6-month intervention phase. The platform enables clinicians to input clinical data and complementary test results, generating a list of potential diagnoses and corresponding diagnostic tests. The results can be exported in PDF format for integration into the patient's medical record. Throughout the intervention, platform usage will be monitored, including login frequency, duration of use, and the number of evaluations performed.

Device: Web-Based Application; The intervention involves the DIAGEN-IA platform, a diagnostic support tool designed to identify pediatric neurological diseases with a genetic basis. Using a Bayesian network model and integrating ontologies such as ORDO, HPO, and HOOM, DIAGEN-IA links phenotypic data entered by physicians to suggested diagnoses and tests. Pediatric neurologists will be trained to use the platform during a 12-month intervention. DIAGEN-IA allows clinicians to input clinical and diagnostic data, generating differential diagnoses and recommended tests, with results exportable in PDF for integration into medical records. Platform usage will be tracked, including login frequency, time spent, and evaluations performed.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Proportion of Inappropriate Referrals	The primary outcome of this study is the proportion of referrals deemed inappropriate by clinical geneticists. Appropriateness is assessed using a 5-point Likert scale, where referrals scoring 1 or 2 are classified as inappropriate. This evaluation considers all referral requests received during the study period, regardless of whether an in-person evaluation occurred.	6 months

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Completeness of Initial Diagnostic Evaluations	The completeness of evaluations in this study is assessed using Morera's scale, adapted for the study's objectives. This scale evaluates whether essential components such as clinical history, findings from physical examinations, relevant diagnostic tests, and a clear presumptive or differential diagnosis are sufficiently detailed to justify the referral. Referrals are categorized into four levels: Very Poor (minimal or no relevant data), Poor (some clinical or test data but insufficient for a justified referral), Normal (adequate data with a basic diagnostic judgment), and Very Good (comprehensive history, examination, and tests with a clear diagnostic justification).	6 months
User Satisfaction	User satisfaction will be evaluated using the Client Satisfaction Questionnaire (CSQ-8), a validated tool widely used in healthcare settings. The CSQ-8 consists of eight questions, each scored on a 4-point Likert scale, assessing users' perceptions of the utility, quality, and impact of the service provided. Scores range from 8 to 32, with higher scores indicating greater satisfaction. The questionnaire is designed to be self-administered and has undergone extensive linguistic validation, including in Spanish.	1 and 6 months

Collaborators and Investigators

• Sponsor: Universidad Nacional Andres Bello
• Collaborators: Hospital Carlos Van Buren; Sociedad Chilena de Pediatría
• Investigators: Study Director: Nicole Nakousi-Capurro, MD, Hospital Carlos Van Buren

Publications and helpful links

Helpful Links

• Study application website.

Study record dates

Study Major Dates

• Study Start (Actual): December 10, 2024
• Primary Completion (Estimated): October 30, 2025
• Study Completion (Estimated): December 30, 2025

Study Registration Dates

• First Submitted: December 5, 2024
• First Submitted That Met QC Criteria: December 5, 2024
• First Posted (Actual): December 10, 2024

Study Record Updates

• Last Update Posted (Actual): May 29, 2025
• Last Update Submitted That Met QC Criteria: May 22, 2025
• Last Verified: May 1, 2025

More Information

Terms related to this study

• Keywords: Pediatrics; Genetic disease; Clinical Decision Support Systems; Referral and Consultation; Neurogenetic disorders; Bayesian Network
• Additional Relevant MeSH Terms: Genetic Diseases, Inborn
• Other Study ID Numbers: UNAB-006; FONDEF ID23I10327 (Other Grant/Funding Number: Agencia Nacional de Investigación y Desarrollo)

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: UNDECIDED

IPD Plan Description

The data is highly contextual, reflecting practices, healthcare infrastructure, and referral patterns unique to the Valparaíso-San Antonio Health Service network. External researchers may misinterpret or misuse the data without understanding the local healthcare dynamics and cultural nuances.

As the DIAGEN-IA platform is an innovative diagnostic tool still under evaluation, premature sharing of study data could lead to misrepresentation of its efficacy or functionality. Retaining control ensures proper validation and dissemination of accurate findings before broader analysis or application by others.

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No
• product manufactured in and exported from the U.S.: No