AI-assisted cEEG Diagnosis of Neonatal Seizures in Neonatal Intensive Care Unit

NCT04991779 | Withdrawn

• 1 other identifier: CHFudanU_NNICU16
• Study Type: observational
• Target: N/A
• Locations: 1 country
• Sites: 3

Brief Summary

A diagnostic accuracy study on Artificial intelligence assisted continue EEG diagnostic tool is to carried out comparing with manually EEG interpretation as the golden standard for neonatal seizure.

Conditions

Neonatal Seizure

Outcome Measures

Primary Outcomes (1)

• The accuracy of AI-assisted cEEG diagnostic tool in evaluating the neonatal seizure

  The accuracy of includes sensitivity and specificity. The reference standard is the electrographic seizures interpreted by 3 clinicians who had attended the uniformly training program and were certified by the Chinese Anti-Epilepsy Association. Sensitivity is defined as: The proportion of neonates with seizures is successfully screened out by AI-assisted cEEG diagnostic tool. Specificity is defined as: The proportion of neonates without seizures who are not recognized as seizures by AI-assisted cEEG diagnostic tool.

  within 7 days since the end of cEEG monitoring during hospitalization

Study Arms (1)

The neonates with suspected seizures or high risk of seizures

The neonates with suspected seizures or high risk of seizures are monitored by continuous electroencephalogram (cEEG) at least 12 hours since admission. The cEEG will be interpreted by AI-assisted cEEG diagnostic tool at the end of cEEG monitoring. At the same time, the same cEEG will be manually reported according the reference standard.

Diagnostic Test: AI-assisted cEEG detection tool

Interventions

AI-assisted cEEG detection tool DIAGNOSTIC_TEST

This study is an observational study to evaluate the accuracy of AI-assisted cEEG diagnostic tool with routine care. All patients from the cohort accept cEEG monitoring and AI-assisted cEEG detection tool. The tool included a quantitive EEG neural signal processing pipeline to extract features from the original signal datasets, machine learning models based on gradient boosted model for prediction. The reference standard is the electrographic seizures interpreted by 3 clinicians who had attended the uniformly training program and were certified by the Chinese Anti-Epilepsy Association.

The neonates with suspected seizures or high risk of seizures

Eligibility Criteria

• Age: 0 Days - 28 Days
• Sex: all
• Healthy Volunteers: No
• Age Groups: Child (0-17)
• Sampling Method: Non-Probability Sample

Study Population

Neonates with suspected seizures and high risk of seizures

You may qualify if:

• Postnatal age \< or = 28 days;
• cEEG monitoring at least 12hours monitoring;
• Suspected seizures;
• Risk of Intracranial hemorrhage;
• Abnormality of MRI or ultrasound before cEEG;
• Neonates diagnosed with encephalopathy or suspected of encephalopathy;
• Hypoxic-ischemic encephalopathy or suspected hypoxic-ischemic encephalopathy;
• Metabolic disturbances (Hypoglycemia, Hypocalcemia, Hypomagnesemia, Inborn errors of metabolism);
• Central nervous system (CNS) or systemic infections;
• Postsurgical neonatal within 3 days;
• Suspected genetic disease or Positive genetic diagnoses;

You may not qualify if:

• The neonates with head scalp defect, scalp hematoma, edema and other contraindications which are not suitable for cEEG monitoring during hospitalization.

Sponsors & Collaborators

• Children's Hospital of Fudan University: lead
• Chengdu Women's and Children's Central Hospital: collaborator
• Xiamen Children's Hospital: collaborator
• Kunming Children's Hospital: collaborator

Study Sites (3)

Henan Children's Hospital

Zhengzhou, Henan, China

Location

Children Hospital of Fudan University

Shanghai, Shanghai Municipality, 201102, China

Location

Chengdu Women's and Children's Central Hospital

Chengdu, Sichuan, China

Location

Related Publications (3)

• Rennie JM, de Vries LS, Blennow M, Foran A, Shah DK, Livingstone V, van Huffelen AC, Mathieson SR, Pavlidis E, Weeke LC, Toet MC, Finder M, Pinnamaneni RM, Murray DM, Ryan AC, Marnane WP, Boylan GB. Characterisation of neonatal seizures and their treatment using continuous EEG monitoring: a multicentre experience. Arch Dis Child Fetal Neonatal Ed. 2019 Sep;104(5):F493-F501. doi: 10.1136/archdischild-2018-315624. Epub 2018 Nov 24.

  PMID: 30472660 RESULT

• Shellhaas RA, Chang T, Tsuchida T, Scher MS, Riviello JJ, Abend NS, Nguyen S, Wusthoff CJ, Clancy RR. The American Clinical Neurophysiology Society's Guideline on Continuous Electroencephalography Monitoring in Neonates. J Clin Neurophysiol. 2011 Dec;28(6):611-7. doi: 10.1097/WNP.0b013e31823e96d7. No abstract available.

  PMID: 22146359 RESULT

• Hoodbhoy Z, Masroor Jeelani S, Aziz A, Habib MI, Iqbal B, Akmal W, Siddiqui K, Hasan B, Leeflang M, Das JK. Machine Learning for Child and Adolescent Health: A Systematic Review. Pediatrics. 2021 Jan;147(1):e2020011833. doi: 10.1542/peds.2020-011833. Epub 2020 Dec 15.

  PMID: 33323492 RESULT

Study Officials

• Wenhao Zhou, Ph.D

  Children's Hospital of Fudan University

  STUDY CHAIR

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: PROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: July 28, 2021
• First Posted: August 5, 2021
• Study Start: March 16, 2022
• Primary Completion: May 16, 2022
• Study Completion: May 16, 2022
• Last Updated: December 29, 2023

Record last verified: 2023-12

Locations

CN (3)