This article presents a summary of recent advances in the development and use of complex systems using artificial intelligence (AI) in neuro-ophthalmology. The aim of the following article is to present the principles of AI and algorithms that are currently being used or are still in the stage of evaluation or validation within the neuro-ophthalmology environment. For the purpose of this text, a literature search was conducted using specific keywords in available scientific databases, cumulatively up to April 2023. The AI systems developed across neuro-ophthalmology mostly achieve high sensitivity, specificity and accuracy. Individual AI systems and algorithms are subsequently selected, simply described and compared in the article. The results of the individual studies differ significantly, depending on the chosen methodology, the set goals, the size of the test, evaluated set, and the evaluated parameters. It has been demonstrated that the evaluation of various diseases will be greatly speeded up with the help of AI and make the diagnosis more efficient in the future, thus showing a high potential to be a useful tool in clinical practice even with a significant increase in the number of patients.

BACKGROUND: Disconjugate eye movements are essential for depth perception in frontal-eyed species, but their underlying neural substrates are largely unknown. Lesions in the midbrain can cause disconjugate eye movements. While vertically disconjugate eye movements have been linked to defective visuo-vestibular integration, the pathophysiology and neuroanatomy of horizontally disconjugate eye movements remains elusive.
METHODS: A patient with a solitary focal midbrain lesion was examined using detailed clinical ocular motor assessments, binocular videooculography and diffusion-weighted MRI, which was co-registered to a high-resolution cytoarchitectonic MR-atlas.
RESULTS: The patient exhibited both vertically and horizontally disconjugate eye alignment and nystagmus. Binocular videooculography showed a strong correlation of vertical and horizontal oscillations during fixation but not in darkness. Oscillation intensities and waveforms were modulated by fixation, illumination, and gaze position, suggesting shared visual- and vestibular-related mechanisms. The lesion was mapped to a functionally ill-defined area of the dorsal midbrain, adjacent to the posterior commissure and sparing nuclei with known roles in vertical gaze control.
CONCLUSIONS: A circumscribed region in the dorsal midbrain appears to be a key node for disconjugate eye movements in both vertical and horizontal planes. Lesioning this area produces a unique ocular motor syndrome mirroring hallmarks of developmental strabismus and nystagmus. Further circuit-level studies could offer pivotal insights into shared pathomechanisms of acquired and developmental disorders affecting eye alignment.

This article presents a  summary of recent advances in the development and use of complex systems using artificial intelligence (AI) in neuroophthalmology. The aim of the following article is to present the principles of AI and algorithms that are currently being used or are still in the stage of evaluation or validation within the neuro-ophthalmology environment. For the purpose of this text, a literature search was conducted using specific keywords in available scientific databases, cumulatively up to April 2023. The AI systems developed across neuro-ophthalmology mostly achieve high sensitivity, specificity and accuracy. Individual AI systems and algorithms are subsequently selected, simply described and compared in the article. The results of the individual studies differ significantly, depending on the chosen methodology, the set goals, the size of the test, evaluated set, and the evaluated parameters. It has been demonstrated that the evaluation of various diseases will be greatly speeded up with the help of AI and make the diagnosis more efficient in the future, thus showing a high potential to be a useful tool in clinical practice even with a significant increase in the number of patients.

OBJECTIVE: To evaluate the effects of COVID-19 lockdown in Italy on the features of Acute Acquired Concomitant Esotropia (AACE).
METHODS: Patients of the Polyclinic Hospital of Bari diagnosed with AACE between January 2018 and December 2021, subdivided in pre-lockdown group - diagnosed before March 2020 - and post-lockdown group.
METHODS: Medical records were reviewed, and statistical analysis performed. Deviation size was assessed in the 9 cardinal positions of gaze with refractive correction. Wilcoxon test for unpaired samples was used to compare data of age, near maximum deviation and best corrected visual acuity (BCVA) for each eye; Student\'s t test was used to compare far maximum deviation, difference far/near maximum deviation and spherical equivalent data. Fisher exact test was used to compare subtype cases (Bielschowsky vs Non-Bielschowsky) in the two groups. A p-value lower than 0.05 was considered statistically significant.The primary outcome measure was the difference in AACE subtypes between the two groups.
RESULTS: Nineteen patients were included, of which 12 males (63.2%); 7 belong to the pre-lockdown group and 12 to the post-lockdown group. The difference in types between the two groups proved to be statistically significant (p = 0.01977).The differences in the mean of age, right BCVA, right spherical equivalent and mean spherical equivalent between the two groups proved to be statistically significant (p < 0.05).
CONCLUSIONS: After the COVID-19 pandemic, the profile of the typical patient with AACE has probably changed, and now it is more probably myopic and elderly than before. Thus, we observed an increase in the Bielschowsky subtype.

Amblyopia is a developmental visual disorder resulting from atypical binocular experience in early childhood that leads to abnormal visual cortex development and vision impairment. Recovery from amblyopia requires significant visual cortex neuroplasticity, i.e. the ability of the central nervous system and its synaptic connections to adapt their structure and function. There is a high level of neuroplasticity in early development and, historically, neuroplastic responses to changes in visual experience were thought to be restricted to a \"critical period\" in early life. However, as our review now shows, the evidence is growing that plasticity of the adult visual system can also be harnessed to improve vision in amblyopia. Amblyopia treatment involves correcting refractive error to ensure clear and equal retinal image formation in both eyes, then, if necessary, promoting the use of the amblyopic eye by hindering or reducing visual input from the better eye through patching or pharmacologic therapy. Early treatment in children can lead to visual acuity gains and the development of binocular vision in some cases; however, many children do not respond to treatment, and many adults with amblyopia have historically been untreated or undertreated. Here we review the current evidence on how dichoptic training can be used as a novel binocular therapeutic approach to facilitate visual processing of input from the amblyopic eye and can simultaneously engage both eyes in a training task that requires binocular integration. It is a novel and promising treatment for amblyopia in both children and adults.

The Dynamic Gait Index (DGI) is a useful tool that has been evaluated for its reliability in patients with vestibular disorders, elderly people and, in chronic stroke population. Present study was aimed to evaluate the intrarater and interrater reliability of the DGI to measure dynamic balance and gait performance in stroke patients with eye movement disorders.
A sample of 30 stroke patients suffering from eye movement disorders were recruited. Two Physical therapists assessed the intrarater and interrater reliability of the DGI in two testing sessions three days apart. In the later session, two raters assessed the patients\' performance simultaneously on the DGI. The reliability was calculated using the intra-class correlation coefficient (ICC2, 1). Standard error of measurement (SEM) and minimal detectable change (MDC95) at 95% confidence interval were also calculated. A significance level was set at p-value <0.05.
The (ICC2, 1) for intrarater and interrater reliability of total DGI scores was 0.86 and 0.91 respectively. While (ICC2, 1) for intrarater and interrater reliability of individual items ranged from 0.73 to 0.91 to 0.73-0.93, respectively. The (SEM) and (MDC95) for intrarater reliability of total DGI scores were 0.76 and 2.10, respectively. Corresponding values for interrater reliability were 0.62 and 1.71, respectively.
The DGI is a reliable tool for evaluating the dynamic balance and gait performance in stroke patients with eye movement disorders. This tool showed good to excellent intrarater and interrater reliability of total DGI scores and moderate to good intrarater and interrater reliability of individual items of the DGI.

BACKGROUND: Eye movement abnormalities are commonplace in neurological disorders. However, unaided eye movement assessments lack granularity. Although videooculography (VOG) improves diagnostic accuracy, resource intensiveness precludes its broad use. To bridge this care gap, we here validate a framework for smartphone video-based nystagmography capitalizing on recent computer vision advances.
METHODS: A convolutional neural network was fine-tuned for pupil tracking using > 550 annotated frames: ConVNG. In a cross-sectional approach, slow-phase velocity of optokinetic nystagmus was calculated in 10 subjects using ConVNG and VOG. Equivalence of accuracy and precision was assessed using the \"two one-sample t-test\" (TOST) and Bayesian interval-null approaches. ConVNG was systematically compared to OpenFace and MediaPipe as computer vision (CV) benchmarks for gaze estimation.
RESULTS: ConVNG tracking accuracy reached 9-15% of an average pupil diameter. In a fully independent clinical video dataset, ConVNG robustly detected pupil keypoints (median prediction confidence 0.85). SPV measurement accuracy was equivalent to VOG (TOST p < 0.017; Bayes factors (BF) > 24). ConVNG, but not MediaPipe, achieved equivalence to VOG in all SPV calculations. Median precision was 0.30°/s for ConVNG, 0.7°/s for MediaPipe and 0.12°/s for VOG. ConVNG precision was significantly higher than MediaPipe in vertical planes, but both algorithms\' precision was inferior to VOG.
CONCLUSIONS: ConVNG enables offline smartphone video nystagmography with an accuracy comparable to VOG and significantly higher precision than MediaPipe, a benchmark computer vision application for gaze estimation. This serves as a blueprint for highly accessible tools with potential to accelerate progress toward precise and personalized Medicine.

The CTNNB1 Syndrome is a rare neurodevelopmental disorder associated with developmental delay, intellectual disability, and delayed or absent speech. The aim of the present study is to systematically review the available data on the prevalence of clinical manifestations and to evaluate the correlation between phenotype and genotype in published cases of patients with CTNNB1 Syndrome. Studies were identified by systematic searches of four major databases. Information was collected on patients\' genetic mutations, prenatal and neonatal problems, head circumference, muscle tone, EEG and MRI results, dysmorphic features, eye abnormalities, early development, language and comprehension, behavioral characteristics, and additional clinical problems. In addition, the mutations were classified into five groups according to the severity of symptoms. The study showed wide genotypic and phenotypic variability in patients with CTNNB1 Syndrome. The most common moderate-severe phenotype manifested in facial dysmorphisms, microcephaly, various motor disabilities, language and cognitive impairments, and behavioral abnormalities (e.g., autistic-like or aggressive behavior). Nonsense and missense mutations occurring in exons 14 and 15 were classified in the normal clinical outcome category/group because they had presented an otherwise normal phenotype, except for eye abnormalities. A milder phenotype was also observed with missense and nonsense mutations in exon 13. The autosomal dominant CTNNB1 Syndrome encompasses a wide spectrum of clinical features, ranging from normal to severe. While mutations cannot be more generally categorized by location, it is generally observed that the C-terminal protein region (exons 13, 14, 15) correlates with a milder phenotype.

BACKGROUND: Impaired vision is one of the commonest and most disabling consequence following stroke. Among all visual impairments, eye movement disorders are found in 70% of stroke patients which include nystagmus, strabismus, gaze palsies, disconjugate eye movements and cranial nerve palsies. They have a wide ranging impact on balance and activities of daily livings by creating difficulties in maintaining normal alignment and appropriate movement of eyes. The purpose of this study was to examine the effects of visual scanning exercises in addition to task specific approach on balance and activities of daily livings in post stroke patients with eye movement disorders.
METHODS: This study is a randomized controlled trial and was conducted in the University of Lahore Teaching Hospital from May 2019 to October 2020. A sample of 64 patients was recruited and randomly allocated into experimental and control group. 32 patients in experimental group were treated with visual scanning exercises along with task specific approach and 32 patients in control group were treated with task specific approach alone. Pre and post assessment of balance and activities of daily livings was assessed on BERG BALANCE SCALE and BARTHEL INDEX SCALE at baseline and at 4th week.
RESULTS: Intra-group analysis of BERG BALANCE SCALE in experimental group showed statistically significant result (p < 0.05) in all items except in items 4, 13 and 14 respectively. Intra-group analysis of BERG BALANCE SCALE in control group showed statistically significant result (p < 0.05) in items 3, 5, 8 and 12 respectively, whereas remaining all items showed statistically insignificant result. Intra-group analysis of BARTHEL INDEX SCALE in experimental group showed statistically significant result in all items (p < 0.05) except in items 9 and 10 respectively. Intra-group analysis of BARTHEL INDEX in control group showed statistically significant result (p < 0.05) in items 1, 3, 4 and 8 respectively whereas remaining all items showed statistically insignificant result. Inter-group analysis showed statistically significant result in total scores of BERG BALANCE SCALE (p = 0.000) and BARTHEL INEX SCALE (p = 0.033).
CONCLUSIONS: Visual scanning exercises along with task specific approach were found to be more effective in comparison to task specific approach alone.
BACKGROUND: Trial registration number: [IRCT20190717044237N1], trial registration date: 10/11/2019.

Inborn errors of metabolism are genetic disorders that need to be recognized as early as possible because treatment may be available. In late-onset forms, core symptoms are movement disorders, psychiatric symptoms, and cognitive impairment. Eye movement disorders are considered to be frequent too, although specific knowledge is lacking. We describe and analyze eye movements in patients with an inborn error of metabolism, and see whether they can serve as an additional clue in the diagnosis of particularly late-onset inborn errors of metabolism. Demographics, disease characteristics, and treatment data were collected. All patients underwent a standardized videotaped neurological examination and a video-oculography. Videos are included. We included 37 patients with 15 different inborn errors of metabolism, including 18 patients with a late-onset form. With the exception of vertical supranuclear gaze palsy in Niemann-Pick type C and external ophthalmolplegia in Kearns-Sayre syndrome, no relation was found between the type of eye movement disorder and the underlying metabolic disorder. Movement disorders were present in 29 patients (78%), psychiatric symptoms in 14 (38%), and cognitive deficits in 26 patients (70%). In 87% of the patients with late-onset disease, eye movement disorders were combined with one or more of these core symptoms. To conclude, eye movement disorders are present in different types of inborn errors of metabolism, but are often not specific to the underlying disorder. However, the combination of eye movement disorders with movement disorders, psychiatric symptoms, or cognitive deficits can serve as a diagnostic clue for an underlying late-onset inborn error of metabolism.