AI assisted reader evaluation in acute CT head interpretation (AI-REACT): protocol for a multireader multicase study.

INTRODUCTION: A non-contrast CT head scan (NCCTH) is the most common cross-sectional imaging investigation requested in the emergency department. Advances in computer vision have led to development of several artificial intelligence (AI) tools to detect abnormalities on NCCTH. These tools are intended to provide clinical decision support for clinicians, rather than stand-alone diagnostic devices. However, validation studies mostly compare AI performance against radiologists, and there is relative paucity of evidence on the impact of AI assistance on other healthcare staff who review NCCTH in their daily clinical practice. METHODS AND ANALYSIS: A retrospective data set of 150 NCCTH will be compiled, to include 60 control cases and 90 cases with intracranial haemorrhage, hypodensities suggestive of infarct, midline shift, mass effect or skull fracture. The intracranial haemorrhage cases will be subclassified into extradural, subdural, subarachnoid, intraparenchymal and intraventricular. 30 readers will be recruited across four National Health Service (NHS) trusts including 10 general radiologists, 15 emergency medicine clinicians and 5 CT radiographers of varying experience. Readers will interpret each scan first without, then with, the assistance of the qER EU 2.0 AI tool, with an intervening 2-week washout period. Using a panel of neuroradiologists as ground truth, the stand-alone performance of qER will be assessed, and its impact on the readers' performance will be analysed as change in accuracy (area under the curve), median review time per scan and self-reported diagnostic confidence. Subgroup analyses will be performed by reader professional group, reader seniority, pathological finding, and neuroradiologist-rated difficulty. ETHICS AND DISSEMINATION: The study has been approved by the UK Healthcare Research Authority (IRAS 310995, approved 13 December 2022). The use of anonymised retrospective NCCTH has been authorised by Oxford University Hospitals. The results will be presented at relevant conferences and published in a peer-reviewed journal. TRIAL REGISTRATION NUMBER: NCT06018545.

Neonatal hypoxic-ischaemic encephalopathy: Motor impairment beyond cerebral palsy.

BACKGROUND: Research investigating neuromotor function in the absence of cerebral palsy (CP) for children who had neonatal HIE is limited. AIMS: To investigate school-age neurological and neuromotor function, and correlations with attention, neonatal Magnetic Resonance Imaging (MRI), and neuromotor assessments at toddler age. METHODS: Twenty-seven children with neonatal HIE without CP who underwent hypothermia treatment and a comparison group of 20 children were assessed at age 5-7 years for Minor Neurological Dysfunction (MND; simplified Touwen), motor skills (Movement Assessment Battery for Children-2; MABC-2), parental concern over motor function (MABC Checklist), general cognition (Wechsler Preschool and Primary Scale of Intelligence-IV, WPPSI), and attention (DuPaul ADHD Rating Scale). Neurological examination and motor development, using Bayley-3 scales, at age 24-months was extracted from the clinical database. Clinical neonatal MRI was assessed for hypoxic-ischaemic injury. RESULTS: In the HIE group, MND was more prevalent (p = 0.026) and M-ABC performance (total score p = 0.006; balance subtest p = 0.008) was worse; parents were more concerned about children's motor function (p = 0.011). HIE group inattention scores were higher (p = 0.032), which correlated with lower MABC-2 scores (rs = -0.590, p = 0.004). Neurological examination at 24-months correlated with MND (rs = 0.437, p = 0.033); Bayley-3 motor scores did not correlate with M-ABC-2 scores (rs = 368, p = 0.133). Neonatal MRI findings were not associated with school-age MND (rs = 0.140, p = 0.523) or MABC-2 (rs = 0.300, p = 0.165). CONCLUSIONS: Children with neonatal HIE, without CP, treated with hypothermia may be more likely to develop MND and motor difficulties than typically developing peers. Inattention may contribute to motor performance. In the absence of CP, neonatal MRI and toddler age assessment of motor development have limited predictive value for school-age outcome. Since this was an exploratory study with a small sample size, findings should be confirmed by a definite larger study.