PREDICTING POST-OPERATIVE INTRAOCULAR LENS (IOL) TILT USING PREOPERATIVE IOL MEASUREMENTS AND A MACHINE LEARNING ALGORITHM
Published 2023
- 27th ESCRS Winter Meeting
Reference: MP3
| Type: Presented Poster & Poster Submission
| DOI:
10.82333/qs49-8104
Authors:
Klemens Waser* 1
, Andreas Honeder 1
, Peter Laubichler 1
, Haidar Khalil 1
, Leon Pomberger 1
, Matthias Bolz 1
, Nino Hirnschall 1
1Department of Ophthalmology and Optometry, Johannes Kepler University, Linz, Austria,Linz,Austria
Purpose
Intraocular lens (IOL) tilt reduces visual performance, if it exceeds the amount of physiological tilt. Aim of this study was to use preoperative biometry data to predict the post-operative amount and orientation of tilt.
Setting
Department of Ophthalmology and Optometry, Johannes Kepler University, Linz, Austria
Methods
In total, 200 eyes scheduled for cataract surgery were included in this prospective study. Preoperatively, anterior segment imaging was performed using swept source optical coherence tomography measurements (IOL Master 700; Carl Zeiss Meditec AG, Germany and Casia 2; Tomey, Japan). These measurements were repeated 8 weeks after surgery together with autorefraction and subjective refraction. Random forest plot and Bayesian statistics were used to develop a tilt prediction model.
Results
Results: The crystalline lens (preoperative) showed a mean IOL tilt of 4.7° (±1.4°) and a mean tilt orientation of 111.4 ° (± 56.3°). The mean postoperative IOL tilt was 4.3° (±1.6) with a mean orientation of 111.4° (±56.9°). In 85% of all cases the tilt orientation changed less than 15° from pre- to post-operatively. The prediction algorithm showed very good predictability of the post-operative orientation of tilt and a moderate predictive power regarding the amount of IOL tilt.
Conclusion
Conclusions: Post-operative IOL tilt is predictable and this information could be helpful for further improvement in IOL power calculation concepts.