Mobile Video Education and Machine Learning-Based Risk Prediction in Neonatal Seizure Management

Neonatal seizures are among the most common neurological emergencies occurring within the first 28 days of life and are associated with significant risks for both short- and long-term neurodevelopmental outcomes. After discharge from the neonatal intensive care unit, seizure recurrence and antiepileptic drug management may create substantial uncertainty and anxiety, particularly for families of high-risk infants. Although the medical management of neonatal seizures and the psychological experiences of parents have been examined separately in the literature, there is a lack of comprehensive approaches that combine technology-based risk prediction with targeted educational interventions.

This study aims to identify infants at high risk of seizure recurrence after discharge by using a machine learning model developed from retrospective clinical data and to evaluate the effect of mobile video-supported education provided to mothers of these infants on their knowledge and anxiety levels.

The study is designed as a mixed-methods study and will be conducted in three phases. In the first phase, retrospective clinical data of infants discharged from the neonatal intensive care unit will be used to develop a machine learning-based risk prediction model for seizure recurrence after discharge. In the second phase, qualitative interviews will be conducted with mothers of high-risk infants to determine their educational needs, concerns, and experiences regarding neonatal seizure management. The findings obtained from these interviews will be used to develop the content of the mobile video-supported education program. In the third phase, mothers of high-risk infants will be randomly assigned to intervention and control groups in a randomized controlled experimental design. The intervention group will receive mobile video-supported education in addition to standard discharge education, while the control group will receive standard discharge education only. The effects of the education program on mothers' knowledge and anxiety levels will be evaluated during the follow-up period.

This study is expected to contribute to the early identification of high-risk infants, support the personalization of nursing care, improve parental knowledge regarding seizure management, and reduce anxiety among mothers caring for infants at risk of seizure recurrence after discharge.

Keywords: Neonatal seizure, machine learning, mobile video education, parental anxiety, knowledge level.

Inclusion criteria

• The infant is classified as high risk according to the machine learning-based risk prediction model developed in the first phase of the study.
• The infant is planned to be discharged home from the Neonatal Intensive Care Unit of Başakşehir Çam and Sakura City Hospital.
• The mother is 18 years of age or older.
• The mother is the primary caregiver responsible for the infant's care.
• The mother is able to read, write, and communicate in Turkish.
• The mother has access to a smartphone and active internet connection, either mobile data or Wi-Fi.
• The mother is able to use a smartphone and basic communication applications such as WhatsApp.
• The mother voluntarily agrees to participate in the study and signs the informed consent form.

Exclusion criteria

• The infant is transferred to another center before completion of the study process or during the discharge period.
• The infant dies during the study period.
• The mother has a diagnosed cognitive or psychiatric condition that may prevent her from understanding the educational materials or managing the study process.
• The mother has a visual or hearing impairment that may prevent her from following the video content.
• Significant connection problems occur during the qualitative interview process that prevent completion of the interview.
• The mother is unable to access or complete the mobile video education within the first 72 hours after discharge due to technical reasons.
• The mother wishes to withdraw from the study at any stage.