Macular Holes, Epiretinal Membrane, Retinal Detachment, Macular Dystrophies
Conditions
Keywords
vitreoretinal surgery, machine learning, decisional support systems
Brief summary
The aim of the study is to identify morphological and functional biomarkers of post-operative recovery after vitreoretinal surgery, using decisional support systems (DSS), based on multimodal big-data analysis by means of machine learning techniques in daily clinical practice
Detailed description
The aim of the study is to identify morphological and functional biomarkers of post-operative recovery after vitreoretinal surgery. Identifying the biomarkers and assessing the predictivity of recovery will make it possible to highlight the categories of patients who can benefit most from surgical treatment, and to target the patient more precisely for personalised medicine and surgery. The introduction of new decisional support systems (DSS), based on multimodal big-data analysis through machine learning techniques in daily clinical practice, is providing new useful information in patient assessment for personalised surgery.
Interventions
DIAGNOSTIC_TESTBiometry
Biometric measurements performed with IOL Master, if executable Contact or immersion echobiometry if IOL Master cannot be performed
DIAGNOSTIC_TESTRetinography (Color) + Autofluorescence (AF)
Colour + AF: EIDON, if available (60° not modulable) Colour: COBRA (60° non-modifiable) AF: Spectralis-Heidelberg (choose 55°) Other if available (choose posterior pole examination between 50-60°)
DIAGNOSTIC_TESTOCT B-scan and OCT angiography (OCTA)
OCT B-scan: 2 scans (6 mm) 1 cross line OCTA: 3x3 mm + 6x6 mm centred on the fovea 4.5 mm centred on the optic nerve
DIAGNOSTIC_TESTMicroperimetry
1\) fixation pattern 2) retinal sensitivity map
DIAGNOSTIC_TESTElectrophysiological exams
Layer-by-layer assessment of the retina using focal ERG and pattern ERG according to standardised and published methods , For patients with visus \< 3/10 and unstable fixation a protocol based on component analysis of the photopic ERG from diffuse flash will be used.
Sponsors
Fondazione Policlinico Universitario Agostino Gemelli IRCCS
Study design
Observational model
COHORT
Time perspective
PROSPECTIVE
Eligibility
Sex/Gender
ALL
Age
18 Months to No maximum
Healthy volunteers
No
Inclusion criteria
* All patients to undergo vitreo-retinal surgery for: 1. Macular hole 2. Epiretinal membranes 3. Retinal detachment 4. Macular dystrophies (retinal pre-prosthesis)
Exclusion criteria
* Patients under 18 years of age will be excluded; patients in whom morphological examinations cannot be performed due to poor cooperation or opacity of the dioptric media (e.g. corneal pathology). Quality of morphological images inadequate for post acquisition processing (\<6/10).
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Predictivity of morphological-functional radiomic data | 3 years | Rate of predictivity of morphological-functional radiomic data to establish the grade of recovery in the post-operative period by means of an artificial intelligence (AI) machine learning model. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Identify predictive differences according to diagnosis | 3 years | Subdivision into subgroups in order to identify predictive differences according to diagnosis |
| Correlating with the age of patients | 3 years | Identify predictive differences according to diagnosis and correlate them with the age of patients |
| Correlate with age of onset of disease | 3 years | Identify predictive differences according to diagnosis and correlate them with the age of onset of disease |
Countries
Italy
Contacts
Primary ContactMaria Cristina Savastano, MD,PhD
Backup ContactAlfonso Savastano, MD,PhD
Outcome results
None listed