Characterization by Automated System on Infantile Spasmes — REASSESS  

Infantile Spasm Clinical Trial

Official title: Characterization by Automated System on Infantile Spasmes

Status Recruiting

Clinical Trial Summary

Infantile spasms are defined by the occurrence of epileptic episodes characterized by the appearance of very specific motor seizures, made up of rapid, repeated contractions in flexion or extension known as spasms. This syndrome is of high concern as it will lead to mental retardation if it is not early identified and treated. Most often, spasms are characterized by sudden contractions of the body in flexion. More rarely, spasms occur in extension: the neck and legs suddenly tense, and the arms move upwards or sideways. Spasms may be accompanied by eye revulsion. They are brief, lasting 0.5 to 2 seconds each. At the start of the attack, they may be isolated, but then may occur in series lasting up to several tens of minutes. Because of its nature and duration, infantile spasm is often difficult to identify and is often confused with benign motor manifestations in children, such as hiccups or muscular jerks. This difficulty often leads to delays in diagnosis. Indeed, patients are often seen at the stage when cognitive regression has set in. The gold standard for diagnosing infantile spasms is to capture them on video-EEG to confirm the ictal correlate of the seizure. Although multiple variations are known, the ictal correlation is often a diffuse slow wave of high amplitude with subsequent electrodecrement. Yet continuous video electroencephalogram is an expensive and time-consuming resource often unavailable in developing countries and in many parts of the developed world. Furthermore, in an appropriate clinical scenario, continuous video-EEG may be unnecessary. For example, a home video examination with typical spasms combined with a definitively epileptic ambulatory EEG may certainly be adequate for the diagnosis of infantile spasms As part of Mr. Diop's thesis, the study team have developed a system for analyzing videos acquired in 2 dimensions from a simple smartphone or webcam and highlighting the existence of spasms in a child. The principle is to use computer vision and computer learning model to identify the spasms from these videos. The first prototype of this system achieved a positive predictive value of 77%, which is very good considering the small sample used (< 100) but quite insufficient to obtain a diagnostic prediction for medical use, for which we hope for sensitivity and specificity of around 95%. The aim is to achieve a sensitivity and specificity of over 95% so that we can offer this detection system to healthcare professionals and parents of children who do not have rapid access to diagnosis. The aim is to develop a system enabling broad screening at the population level so that identified children can be more rapidly directed towards the healthcare system and appropriate treatment for their disease. To achieve this goal, we need access to a standardized reference database that currently exists in the various pediatric electrophysiology laboratories of the Assistance Publique - Hôpitaux de Paris and the Île-de-France region. we propose using the films stored in these laboratories to teach the computer to recognize spasms that have already been formally identified by electrophysiologists and by ictal concordance.

Clinical Trial Description

There is insufficient evidence to determine whether other forms of corticosteroids are as effective as adrenocorticotropic hormone (ACTH) for the short-term treatment of infantile spasms. However, low-dose ACTH is probably as effective as high-dose ACTH. ACTH is more effective than vigabatrin (VGB) for the short-term treatment of children with infantile spasms (with the exception of those with tuberous sclerosis complex). There is insufficient evidence to show that other agents and combination therapy are effective for the short-term treatment of infantile spasms. A short time to treatment leads to a better long-term developmental outcome. Successful short-term treatment of cryptogenic infantile spasms with ACTH or prednisolone leads to better long-term developmental outcomes than treatment with VGB. Current recommendations are that a low dose of ACTH should be considered for the treatment of infantile spasms. ACTH or VGB may be useful for short-term treatment of infantile spasms, with ACTH preferred to VGB. Hormone therapy (ACTH or prednisolone) may be considered in preference to VGB in infants with cryptogenic infantile spasms to improve developmental outcomes potentially. A shorter delay before treating infantile spasms with hormone therapy or VGB may improve long-term developmental outcomes. In summary, the management of infantile spasms presents several issues. Diagnosis is often delayed due to the particular symptomatology and difficulty accessing diagnostic means: specialized consultation and video EEG. This delay represents a loss of opportunity for patients, as appropriate treatment may be delayed. There is still disagreement between clinicians on the characterization of infantile spasms, with little agreement, particularly at the level of electroencephalographic analysis. The aim of this science thesis is to identify infantile spasms using simple video analysis, enabling a monitoring routine to be set up at home or using a smartphone. Initially, luminance analysis is used to estimate the amount of movement. Computer vision systems for medical diagnosis are undergoing exponential development thanks to recent advances in computer science and automated learning. We are using classic techniques in this field to diagnose spasms in children. To obtain consistent results, we need to start from the gold standard today, the video electroencephalogram acquired in the neurophysiology laboratory. Therefore, we propose using the films stored in these laboratories to teach the computer to recognize spasms that have already been formally identified by electrophysiologists and by ictal concordance. Organisation and security: This work aims to enable spasms to be recognized reliably by an automated system, making it possible to direct children more rapidly towards appropriate and effective disease management. Funder: same as data controller Data Protection Officer: Ms Vincente lecomte; Data Protection Officer AP-HP Université Paris Saclay; Hôpitaux Antoine-Béclère - Maritime de Berck; Bicêtre - Paul-Brousse - Ambroise-Paré; Sainte-Périne - Raymond-Poincaré - vincente.lecomte@aphp.fr ] The centers participating in the project are the Neurophysiology laboratories of the APHP teaching hospitals: Hôpital Kremlin Bicêtre, Hôpital Raymond Poincaré, Hôpital Necker, Hôpital Trousseau, Hôpital Robert Debré and that of the Fondation Adolphe de Rothschild. The aim of the project is to develop a system for detecting spasm-type seizures in children. The aim is to achieve a level of sensitivity and specificity that will enable it to be used as a tool for early detection of seizures, and as a monitoring tool for the general public and healthcare professionals, using consumer video acquisition systems (smartphones, webcams, etc.). The benefits of the project are twofold. The benefits are twofold. It should enable patients to gain earlier access to specialized care, thanks to the earlier identification or suspicion of the disease through the use of a smartphone or webcam. It should enable patients undergoing treatment to be monitored and the therapies used to treat them to be assessed. Transparency and publication of results: the results obtained will be published in a peer-reviewed journal. Measures taken to scientific integrity and quality of the studies: the methodology methodology adopted is a learning process on part of the cohort and a randomized sample of patients. Part of the database obtained from the various centers will be used for machine machine learning. A sample of this same database and/or a naive sample sample will be selected to test the performance of the detection system. The patients included are pediatric patients who have undergone video EEG in one of the electrophysiology centers of ile-de-France. Patients diagnosed as having spasms will be included, as well as patients with other types of epilepsy. The aim is to be able to detect spasms as they occur. The patient is his or her own witness. In fact, spasms are discrete manifestations occurring against a background of "normal" activity. The background of activity represents the true negative, and the spasm(s) presented by the patient the true positive. Obtaining examinations of other types of seizure will enable us to refine the search for and identification of spasms, by checking whether the system in place is capable of differentiating spasms from other types of seizure. The study is based on retrospective data. The aim is to demonstrate the system's proof-of-concept before attempting to set up a prospective study. The aim of this request is to be authorized to use the films coupled with electroencephalograms acquired in the various electrophysiology centers in the Ile-de-France region (Assistance Publique - Hôpitaux de Paris and Fondation Rothschild ), so as to be able to implement machine learning on the analysis of the videos. Indeed, in this type of project, we need to be able to compare ourselves with the reference examination, which today is the electroencephalogram coupled with a video. The various laboratories keep a collection of films of children with epileptic spasms, coupled with electroencephalograms, which make it possible to characterize the spasm as epileptic with relative certainty. These films have already been screened by neurophysiologists, and are therefore of the highest quality. Each film may contain several spasms, each of which represents a different event enabling the system to learn to recognize a spasm. ;

Related Conditions & MeSH terms

• Infantile Spasm
• Spasms, Infantile

• NCT number: NCT06266234
• Study type: Observational
• Source: Assistance Publique - Hôpitaux de Paris
• Contact: Samuel Diop, PhD
• Phone: + 33 1 47 10 79 00
• Email: snfdiop@outlook.com
• Status: Recruiting
• Start date: February 1, 2024
• Completion date: January 2026