Marcello Leucci

Marcello Leucci

Auto-generated profile, based on publicly available information

Marcello Leucci

Moorfields Eye Hospital NHS Trust, London, UK

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 December 2021 in JMIR Medical Informatics
Verified
Journal Article
Open access
HMHoward Maile
Howard Maile
JLJi-Peng Olivia Li
Ji-Peng Olivia Li
DGDaniel Gore
Daniel Gore
MLMarcello Leucci
Marcello Leucci
PMPadraig Mulholland
Padraig Mulholland
NPNikolas Pontikos
Nikolas Pontikos
Background: Keratoconus is a disorder characterized by progressive thinning and distortion of the cornea. If detected at an early stage, corneal collagen cross-linking can prevent disease progression and further visual loss. Although advanced forms are easily detected, reliable identification of subclinical disease can be problematic. Several different machine learning algorithms have been used to improve the detection of subclinical keratoconus based on the analysis of multiple types of clinical measures, such as corneal imaging, aberrometry, or biomechanical measurements. Objective: The aim of this study is to survey and critically evaluate the literature on the algorithmic detection of subclinical keratoconus and equivalent definitions. Methods: For this systematic review, we performed a structured search of the following databases: MEDLINE, Embase, and Web of Science and Cochrane Library from January 1, 2010, to October 31, 2020. We included all full-text studies that have used algorithms for the detection of subclinical keratoconus and excluded studies that did not perform validation. This systematic review followed the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) recommendations. Results: We compared the measured parameters and the design of the machine learning algorithms reported in 26 papers that met the inclusion criteria. All salient information required for detailed comparison, including diagnostic criteria, demographic data, sample size, acquisition system, validation details, parameter inputs, machine learning algorithm, and key results are reported in this study. Conclusions: Machine learning has the potential to improve the detection of subclinical keratoconus or early keratoconus in routine ophthalmic practice. Currently, there is no consensus regarding the corneal parameters that should be included for assessment and the optimal design for the machine learning algorithm. We have identified avenues for further research to improve early detection and stratification of patients for early treatment to prevent disease progression.

2 June 2025 in Translational Vision Science & Technology
Verified
Journal Article
Open access
SLSiyin Liu
Siyin Liu
LKLynn Kandakji
Lynn Kandakji
ASAleksander Stupnicki
Aleksander Stupnicki
DSDayyanah Sumodhee
Dayyanah Sumodhee
MLMarcello T. Leucci
Marcello T. Leucci
NPNikolas Pontikos
Nikolas Pontikos
Fuchs endothelial corneal dystrophy (FECD) is a common, age-related cause of visual impairment. This systematic review synthesizes evidence from the literature on artificial intelligence (AI) models developed for the diagnosis and management of FECD. We conducted a systematic literature search in MEDLINE, PubMed, Web of Science, and Scopus from January 1, 2000, to June 31, 2024. Full-text studies utilizing AI for various clinical contexts of FECD management were included. Data extraction covered model development, predicted outcomes, validation, and model performance metrics. We graded the included studies using the Quality Assessment of Diagnostic Accuracies Studies 2 tool. This review adheres to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) recommendations. Nineteen studies were analyzed. Primary AI algorithms applied in FECD diagnosis and management included neural network architectures specialized for computer vision, utilized on confocal or specular microscopy images, or anterior segment optical coherence tomography images. AI was employed in diverse clinical contexts, such as assessing corneal endothelium and edema and predicting post-corneal transplantation graft detachment and survival. Despite many studies reporting promising model performance, a notable limitation was that only three studies performed external validation. Bias introduced by patient selection processes and experimental designs was evident in the included studies. Despite the potential of AI algorithms to enhance FECD diagnosis and prognostication, further work is required to evaluate their real-world applicability and clinical utility. This review offers critical insights for researchers, clinicians, and policymakers, aiding their understanding of existing AI research in FECD management and guiding future health service strategies.

1 September 2025 in Journal of Cataract & Refractive Surgery
Verified
Journal Article
Open access
SBShafi Balal
Shafi Balal
YCYijun Cai
Yijun Cai
LKLynn Kandakji
Lynn Kandakji
SLSiyin Liu
Siyin Liu
PMPádraig J. Mullholand
Pádraig J. Mullholand
BABruce Allan
Bruce Allan
Purpose: To analyze measurement precision using a contemporary tomography device (MS-39) in a large sample of patients with keratoconus. Setting: Moorfields Eye Hospital, London, United Kingdom. Design: Prospective and retrospective analyses of clinical data. Methods: For a range of key corneal tomographic indices, repeatability and reproducibility were compared in a prospective series of 1248 scans (n = 208 eyes) with 2 observers each acquiring 3 scans per eye. Measurement repeatability for single measures vs the mean of 3 consecutive measures was then compared using the same dataset. 95% repeatability coefficients were mapped at each unit interval through the measurement range in a retrospective analysis of 13 734 scans (n = 4578 eyes) to adapt progression thresholds to disease severity. Finally, keratoconus classification using alternate progression definitions was compared at 1 and 2-year time points. Results: For all corneal tomographic indices examined, no significant differences were found between MS-39 measurement repeatability and reproducibility (P > .05), repeatability was (average) 44% improved using the mean of 3 consecutive measures, and measurement repeatability deteriorated as keratoconus advanced. Progression was classified incorrectly in over 50% of cases at both time points where adaptive thresholds and repeated measures were not used. Conclusions: MS-39 measurement precision was not significantly influenced by the operator. Consecutive repeated measures and adaptive thresholds for observed change in key tomographic parameters based on device-specific precision limits tailored to disease severity are necessary for accurate classification of progression.

1 May 2026 in Ophthalmology Science
Verified
Journal Article
Open access
SBShafi Balal
Shafi Balal
LKLynn Kandakji
Lynn Kandakji
MLMarcello Leucci
Marcello Leucci
PKPearse A. Keane
Pearse A. Keane
DGDaniel Gore
Daniel Gore
BABruce D. Allan
Bruce D. Allan
To develop and validate deep learning models for predicting keratoconus progression risk using multimodal imaging and clinical data, enabling risk-stratified patient monitoring. A retrospective cohort study with external validation. We analyzed 7396 eyes of 3893 patients (internal dataset) and 963 eyes of 519 patients (external validation dataset) with keratoconus who underwent MS-39 (CSO Italia) anterior-segment OCT (AS-OCT) and Placido topography between October 2020 and June 2024. Progression was defined using the global consensus criteria requiring changes in multiple parameters above device-specific precision limits. We compared conventional machine learning, unimodal deep learning, and multimodal fusion architectures to predict 2-year progression risk from baseline data. We developed recurrent neural networks to incorporate data from sequential clinic visits. We assessed clinical utility through simulated risk-stratified triage pathways in an external validation cohort. The area under the receiver operating characteristic curve (AUROC), sensitivity, specificity, and predictive values for keratoconus progression within 2 years were measured. The multimodal model of AS-OCT, Placido, and tabular data yielded the best single-visit prediction (AUROC 0.84, 95% confidence interval [CI]: 0.83–0.85); adding sequential visits via long short-term memory boosted this to 0.93 (95% CI: 0.91–0.96). Fifty-eight percent of patients could be classified as low risk (90% chance of correctly predicting no progression in 2 years) after their baseline clinic visit, rising to 83% with inclusion of data from a second clinic visit. Artificial intelligence models can be used to develop risk-stratified pathways for monitoring keratoconus, reducing unnecessary follow-up for patients at low risk of progression while ensuring optimal resource allocation and timely intervention for those at high risk. Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

25 January 2021 in JMIR Preprints
Verified
Preprint
Open access
HMHoward Maile
Howard Maile
JLJi-Peng Olivia Li
Ji-Peng Olivia Li
DGDaniel Gore
Daniel Gore
MLMarcello Leucci
Marcello Leucci
PMPadraig Mulholland
Padraig Mulholland
NPNikolas Pontikos
Nikolas Pontikos
BACKGROUND Keratoconus is a disorder characterized by progressive thinning and distortion of the cornea. If detected at an early stage, corneal collagen cross-linking can prevent disease progression and further visual loss. Although advanced forms are easily detected, reliable identification of subclinical disease can be problematic. Several different machine learning algorithms have been used to improve the detection of subclinical keratoconus based on the analysis of multiple types of clinical measures, such as corneal imaging, aberrometry, or biomechanical measurements. OBJECTIVE The aim of this study is to survey and critically evaluate the literature on the algorithmic detection of subclinical keratoconus and equivalent definitions. METHODS For this systematic review, we performed a structured search of the following databases: MEDLINE, Embase, and Web of Science and Cochrane Library from January 1, 2010, to October 31, 2020. We included all full-text studies that have used algorithms for the detection of subclinical keratoconus and excluded studies that did not perform validation. This systematic review followed the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) recommendations. RESULTS We compared the measured parameters and the design of the machine learning algorithms reported in 26 papers that met the inclusion criteria. All salient information required for detailed comparison, including diagnostic criteria, demographic data, sample size, acquisition system, validation details, parameter inputs, machine learning algorithm, and key results are reported in this study. CONCLUSIONS Machine learning has the potential to improve the detection of subclinical keratoconus or early keratoconus in routine ophthalmic practice. Currently, there is no consensus regarding the corneal parameters that should be included for assessment and the optimal design for the machine learning algorithm. We have identified avenues for further research to improve early detection and stratification of patients for early treatment to prevent disease progression.

18 November 2024 in medRxiv
Verified
Preprint
Open access
PDF file
SLSiyin Liu
Siyin Liu
LKLynn Kandakji
Lynn Kandakji
ASAleksander Stupnicki
Aleksander Stupnicki
DSDayyanah Sumodhee
Dayyanah Sumodhee
MLMarcello Leucci
Marcello Leucci
NPNikolas Pontikos
Nikolas Pontikos
Purpose: Fuchs Endothelial Corneal Dystrophy (FECD) is a common, age-related cause of visual impairment. This systematic review synthesizes evidence from the literature on Artificial Intelligence (AI) models developed for the diagnosis and management of FECD. Methods: We conducted a systematic literature search in MEDLINE, PubMed, Web of Science, and Scopus from January 1, 2000, to June 31, 2024. Full-text studies utilizing AI for various clinical contexts of FECD management were included. Data extraction covered model development, predicted outcomes, validation, and model performance metrics. We graded included studies using the Quality Assessment of Diagnostic Accuracies Studies 2 tool. This review adheres to the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) recommendations. Results: Nineteen studies were analyzed. Primary AI algorithms applied in FECD diagnosis and management included neural network architectures specialized for computer vision, utilized on confocal or specular microscopy images, or anterior segment optical coherence tomography images. AI was employed in diverse clinical contexts, such as assessing corneal endothelium and edema, and predicting post-corneal transplantation graft detachment and survival. Despite many studies reporting promising model performance, a notable limitation was that only 3 studies performed external validation. Bias introduced by patient selection processes and experimental designs was evident in the included studies. Conclusions: Despite the potential of AI algorithms to enhance FECD diagnosis and prognostication, further work is required to evaluate their real-world applicability and clinical utility. Translational Relevance: This review offers critical insights for researchers, clinicians, and policymakers, aiding their understanding of existing AI research in FECD management and guiding future health service strategies.