Neonatal Neurological Observation With Video AI (NeoNOVA)

NeoNOVA is a multi-site, prospective, single-arm, silent observational study to determine: among (Population) infants admitted to newborn services during their inpatient hospital stay, whether (Intervention) continuous bedside non-contact high definition video running real-time AI analysis of anatomic landmarks and movement, (Comparison) compared against human-labeled video frames and standardized clinical exams, will (Outcome) accurately localize infant anatomic landmarks (primary objective; outcome median position error in pixels) and demonstrate a statistically significant association between a video-derived movement index and clinical measures of patient neurological exams (secondary objective; outcomes N-PASS and modified Sarnat exams).

Study Overview

• Status: Not yet recruiting
• Conditions: Sleep; Sedation; Hypoxic-Ischemic Encephalopathy; Neonatal Encephalopathy
• Intervention / Treatment: Device: Continuous bedside video monitoring with AI anatomic landmark tracking for neurologic monitoring

Detailed Description

Over 1.3 million infants are admitted to Neonatal Intensive Care Units (NICUs) in OECD countries every year. All NICU infants undergo cardiorespiratory monitoring allowing for expedient hemodynamic management. However, there is no analogous clinical decision support for neurologic monitoring, despite neurologic injury having the highest impact on long-term neurodevelopmental outcome. Neonatal encephalopathy (NE) is a leading cause of neurodevelopmental impairment (NDI) and death, occurring in 3 per 1000 live births; inadequate pain control and sedation is a leading risk factor for many complications in the NICU including unplanned extubation (UE), occurring at rates 1-5 UEs per 100 intubation days. Currently, neurologic changes such as NE, pain control, and sedation are primarily assessed by physical examination. However, this approach is deeply flawed since physical examination is performed at set time intervals, is highly subjective, and may not discern subtle or subacute changes.

To fill this critical gap in neonatal care, we developed and validated NeoPose, a low-cost, non-invasive, computer vision digital health tool to continuously monitor infants using real time video streams. NeoPose uses Pose Artificial Intelligence (AI) for an explainable approach to measure, quantify, and analyze infant movement. From the vectorized movement, we can accurately confirm the presence of encephalopathy and quantify the degree of sedation. Our explainable AI platform enables continuous neuromonitoring with AI-driven alerts, suspicious event replay, movement comparisons, and training on a vast dataset of normal and abnormal infant movements far beyond what any provider could witness.

The Neonatal Neurological Observation with Video AI (NeoNOVA) study is a multi-site, prospective, single-arm, pragmatic, silent observational study to evaluate the performance of NeoPose and AI-derived insights in real world settings. NeoNOVA will deploy a bedside video monitoring system (ArtemisAI Platform) that continuously, passively video records the subject from enrollment to discharge. The study will prospectively validate the AI system's tracking accuracy against ground-truth human-labeled video frames (primary objective; outcome median position error in pixels), will evaluate the association between a video-derived movement index and standardized bedside assessments of encephalopathy, pain, and sedation (secondary objective; outcomes N-PASS and modified Sarnat scales), and will support hypothesis-generating research on novel video prediction algorithms for outcomes like sepsis and need for respiratory support (tertiary objective). The study operates in "silent mode," where AI outputs are not shown to the patient's clinical team. Findings are intended to support a structured clinical evidence generation plan for a Software as a Medical Device (SaMD) designed for continuous, non-contact neurological monitoring in the NICU.

• Study Type: Observational
• Enrollment (Estimated): 200

Contacts and Locations

• Study Contact: Name: Saum Naderi, MA; Phone Number: 714-913-3641; Email: saum@artemisailabs.com
• Study Contact Backup: Name: Florian Richter, PhD; Phone Number: 773-312-3301; Email: florian@artemisailabs.com

Study Locations

• United States
  • New York
    • New York, New York, United States, 10029
      • Mount Sinai Hospital
      • Contact: Rachelle Weisman, MPH; Email: rachelle.weisman@mssm.edu
      • Contact: Klaren Ng; Phone Number: 347-525-8336; Email: klaren.ng@mssm.edu
      • Principal Investigator: Benjamin Glicksberg, PhD
    • New York, New York, United States, 10065
      • Weill Cornell Medicine / NewYork-Presbyterian Hospital
      • Contact: Martha Liu; Phone Number: 646-697-6428; Email: mal4038@med.cornell.edu
      • Principal Investigator: Sushma Krishna, MD

Participation Criteria

Eligibility Criteria

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

• Sampling Method: Non-Probability Sample

Study Population

Neonates of any sex, gestational age, demographic background, or health status admitted to newborn services, including the NICU, at a participating hospital. No diagnosis-specific criteria apply. Consent is provided by at least one parent or legally authorized representative aged 18 or older. Sites will make reasonable efforts to enroll a demographically diverse sample reflective of their local NICU populations, supporting prespecified subgroup analyses of AI performance consistency across gestational age, race/ethnicity, sex, and clinical condition. The first five participants at each site are excluded from primary and secondary endpoint analyses and serve as a technology familiarization cohort.

Description

Inclusion Criteria:

• Signed and dated informed consent from at least one parent or legally authorized representative (LAR) who is at least 18 years old.
• Parent/LAR expresses willingness to comply with study procedures for the duration of the infant's hospital stay.
• Infant of any sex (including intersex/undetermined) admitted to newborn services (including the NICU) at a participating hospital.

Exclusion Criteria:

• Parents or LAR unable to provide informed consent or are under the age of 18.
• Non-viable neonates

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort

Intervention / Treatment

NICU-Admitted Infants Undergoing Continuous Video Monitoring; Infants admitted to newborn services, including the neonatal intensive care unit (NICU), who meet eligibility criteria and undergo continuous, non-contact bedside video monitoring from enrollment until hospital discharge.

Device: Continuous bedside video monitoring with AI anatomic landmark tracking for neurologic monitoring; A non-contact, passive bedside video recording system is mounted adjacent to the infant's crib or incubator. The device continuously captures video data from enrollment to hospital discharge or withdrawal. The device runs AI models to track infant anatomic landmarks and calculate a continuous movement index. The trial runs in "silent mode," where AI outputs are not shown to the patient's clinical team and do not influence care.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
AI Anatomic Landmark Tracking Accuracy	The primary endpoint is analytical performance of the AI pose estimation system, quantified as median position error (in pixels) between AI-predicted and human-labeled anatomic landmark positions extracted from continuous bedside video. Success is defined as median position error less than typical human inter-rater variability.	At study completion, an average of 1 week.

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Movement Index - Encephalopathy measured by modified Sarnat exam	Association between a video-derived movement index and encephalopathy classification of severity from the modified Sarnat exam score, a bedside neurological exam assessed by trained clinical staff.	Through study completion, an average of 1 week.
Movement Index - N-PASS	Association between a video-derived movement index and Neonatal Pain, Agitation, and Sedation Scale (N-PASS) score (ordinal outcome), a bedside neurological exam measuring pain/sedation and assessed by trained clinical staff.	Through study completion, an average of 1 week.
Movement Index - Sedative Exposure	Association between movement index and sedative exposure, a routinely collected clinical variable that influences neonatal arousal.	Through study completion, an average of 1 week.
Movement Index - Chronological Age at Video	Association between movement index and chronological age at video, a routinely collected clinical variable that influences neonatal arousal.	Through study completion, an average of 1 week.
Movement Index - Gestational age at birth	Association between the movement index and gestational age at birth, a routinely collected clinical variable that influences neonatal arousal.	Through study completion, an average of 1 week.
Movement Index - Sleep state	Association between the movement index and sleep state, a routinely collected clinical variable that influences neonatal arousal.	Through study completion, an average of 1 week.
Movement Index - EEG evidence of cerebral dysfunction	Association between the movement index and, if obtained as part of routine clinical care, EEG evidence of cerebral dysfunction (a biomarker of encephalopathy).	Through study completion, an average of 1 week.

Other Outcome Measures

Outcome Measure	Measure Description	Time Frame
AI Anatomic Landmark Tracking - Post-Menstrual Age at Video	Assess performance of AI anatomic landmark tracking (median position error) across post-menstrual ages at the time of video recording.	At study completion, an average of 1 week.
AI Anatomic Landmark Tracking - Encephalopathy Status	Assess performance of AI anatomic landmark tracking (median position error) across encephalopathy statuses.	At study completion, an average of 1 week.
AI Anatomic Landmark Tracking - Caregiver-reported Race/Ethnicity	Assess performance of AI anatomic landmark tracking (median position error) across caregiver-reported race/ethnicity.	At study completion, an average of 1 week.
AI Anatomic Landmark Tracking - Sex	Assess performance of AI anatomic landmark tracking (median position error) and sex.	At study completion, an average of 1 week.
AI Anatomic Landmark Tracking - Lighting Conditions	Assess performance of AI anatomic landmark tracking (median position error) and lighting conditions (phototherapy, lights on/off, time of day).	At study completion, an average of 1 week.
Parent and Provider Feedback	Brief structured surveys administered to parents and clinical providers to assess acceptability, usability, and perceived burden of the bedside video monitoring system. Findings will inform system design refinements and support future bedside adoption and regulatory human factors documentation.	At baseline and study completion (Day 1 - Day 7, on average).

Collaborators and Investigators

• Sponsor: Artemis AI Labs
• Investigators: Principal Investigator: Benjamin Glicksberg, PhD, Icahn School of Medicine at Mount Sinai

Publications and helpful links

General Publications

• Feng R, Richter F, Mari E, Gleason A, Le C, Kellner CP, Shrivastava RK, Fields M, Rapoport BI, Bederson JB, Schadt EE, Glicksberg BS, Richter F, Dangayach NS. Artificial Intelligence Monitoring of Neurological Status From Patient Videos in the Neuroscience Intensive Care Unit. Neurosurgery. 2026 Jan 14. doi: 10.1227/neu.0000000000003899. Online ahead of print.
• Gleason A, Richter F, Beller N, Arivazhagan N, Feng R, Holmes E, Glicksberg BS, Morton SU, La Vega-Talbott M, Fields M, Guttmann K, Nadkarni GN, Richter F. Detection of neurologic changes in critically ill infants using deep learning on video data: a retrospective single center cohort study. EClinicalMedicine. 2024 Nov 11;78:102919. doi: 10.1016/j.eclinm.2024.102919. eCollection 2024 Dec.

Study record dates

Study Major Dates

• Study Start (Estimated): June 1, 2026
• Primary Completion (Estimated): May 31, 2027
• Study Completion (Estimated): May 31, 2029

Study Registration Dates

• First Submitted: May 26, 2026
• First Submitted That Met QC Criteria: June 1, 2026
• First Posted (Actual): June 5, 2026

Study Record Updates

• Last Update Posted (Actual): June 5, 2026
• Last Update Submitted That Met QC Criteria: June 1, 2026
• Last Verified: June 1, 2026

More Information

Terms related to this study

• Keywords: machine learning; artificial intelligence; Sedation; NICU; Neonate; AI; Neonatal; Encephalopathy; computer vision; movement analysis; neurological assessment; pose estimation; Pose AI; Video AI; neonatal monitoring; spontaneous movement
• Additional Relevant MeSH Terms: Cerebrovascular Disorders; Central Nervous System Diseases; Nervous System Diseases; Vascular Diseases; Cardiovascular Diseases; Brain Ischemia; Signs and Symptoms, Respiratory; Hypoxia, Brain; Hypoxia; Pathological Conditions, Signs and Symptoms; Signs and Symptoms; Brain Diseases; Hypoxia-Ischemia, Brain
• Other Study ID Numbers: STUDY-25-01036

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO
• IPD Plan Description: Aggregate deidentified data and results will be shared. Individual participant video data will not be shared due to PHI concerns.

Drug and device information, study documents

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