About The Formula

The Postoperative spherical Equivalent prediction using ARtificial Intelligence and Linear algorithms (PEARL) project aims to assess the potential of Artificial Intelligence (AI) techniques in the IOL calculation field, to determine the optimal architecture of those formulas, and to encourage open research in this field by publishing the experiments and the related code under an open-source license. It was initiated in 2017 in the Anterior Segment and Refractive Surgery Department at Rothschild Foundation by the authors of this chapter.

The PEARL-DGS calculator was developed using the methodology described in the paper "The PEARL-DGS formula: the development of an open-source machine learning-based thick IOL calculation formula", by Debellemanière G, Dubois M, Gauvin M, Wallerstein A, Brenner Luis F, Rampat R, Saad A, Gatinel D. American Journal of Ophthalmology. 2021 May 13:S0002-9394(21)00276-2. doi: 10.1016/j.ajo.2021.05.004.

The PEARL formula is based on thick lens equations and uses machine learning models to predict the posterior corneal radius and the theoretical internal lens position (TILP).

The Python code allowing to understand the development methodology is available on Github.

Guillaume Debellemanière, MD

Rothschild Foundation,Paris,

Anterior Segment and Refractive Surgery Department.

Cabinet d'Ophtalmologie de Moorea - Moorea, Windwards Islands, French Polynesia. Centre Laser Vision de Tahiti, Papeete - Cofounder

Damien Gatinel, MD, PhD

Rothschild Foundation, Paris,

Head of the Anterior Segment and Refractive Surgery Department.‌

Institut Laser Vision Noémie de Rothschild

Alain Saad, MD                        

Rothschild Foundation, Paris,

Anterior Segment and Refractive Surgery Department.

Institut Laser Vision Noémie de Rothschild

Collaborators

Mathieu Dubois, MD

Rothschild Foundation,Paris,

Anterior Segment and Refractive Surgery Department.

Radhika Rampat, MD

Royal Free London NHS Foundation Trust.

United Kingdom