VAULT: vault accuracy using deep learning technology: new image-based artificial intelligence model for predicting implantable collamer lens postoperative vault.

PURPOSE: To develop an accurate deep learning model to predict postoperative vault of phakic implantable collamer lenses (ICLs). SETTING: Parkhurst NuVision LASIK Eye Surgery, San Antonio, Texas. DESIGN: Retrospective machine learning study. METHODS: 437 eyes of 221 consecutive patients who underwent ICL implantation were included. A neural network was trained on preoperative very high-frequency digital ultrasound images, patient demographics, and postoperative vault. RESULTS: 3059 images from 437 eyes of 221 patients were used to train the algorithm on individual ICL sizes. The 13.7 mm size was excluded because of insufficient data. A mean absolute error of 66.3 µm, 103 µm, and 91.8 µm were achieved with 100%, 99.0%, and 96.6% of predictions within 500 µm for the 12.1 mm, 12.6 mm, and 13.2 mm sizes, respectively. CONCLUSIONS: This deep learning model achieved a high level of accuracy of predicting postoperative ICL vault with the overwhelming majority of predictions successfully within a clinically acceptable margin of vault.

A Comprehensive Retrospective Analysis of EVO/EVO+ Implantable Collamer Lens: Evaluating Refractive Outcomes in the Largest Single Center Study of ICL Patients in the United States.

Purpose: We evaluate visual outcomes in patients with EVO/EVO+™ (posterior chamber phakic intraocular lens with a central port) within approved United States (US) age and refractive range indications. Patients and Methods: This single-center retrospective study evaluated one-month, single-center postoperative data for 225 eyes meeting inclusion criteria and undergoing EVO/EVO+ implantation from April to October 2022. Data included lens size (mm), lens power (diopters of spherical and cylindrical power), preoperative best corrected visual acuity, preoperative spherical equivalent from manifest refraction, achieved postoperative uncorrected visual acuity, postoperative refraction, intraocular pressure (mmHg), and adverse events. Results: A total of 225 eyes underwent EVO/EVO+ Implantable Collamer Lens (ICL) implantation from April to October 2022, with 51.5% receiving toric lenses. The most common ICL size was 12.6mm (56.4%), followed by 13.2mm (27.5%), 12.1mm (15.1%), and 13.7mm (0.9%). Among patients with preoperative BCVA of 20/20 or better (149 eyes), 95.2% achieved postoperative UCVA of 20/20 or better, and 99.3% achieved UCVA of 20/25 or better at postoperative month one. About 75% of eyes were within a spherical equivalent target of ±0.50 D and 94% within ±1.00 D. Toric ICLs were implanted in 116 eyes (51.8%). Of these, anticipated residual cylinder >1 diopter was seen in 21 eyes (18.1%) resulting in three rotations, three explants, and three laser vision correction (LVC) enhancements. The postoperative adjustment rate (including rotations, exchanges, and LVC enhancement) was minimal (4.8%). Incidence of major adverse events was 0%. Conclusion: Our study, the largest US single-center analysis of EVO/EVO+ ICL implantation, demonstrates strong early results and infrequent adverse events, supporting ICL safety and effectiveness. High predictability and favorable visual outcomes, including 20/20 or better, highlight the reliability of this technology. Despite study limitations, our findings underscore this technology's effectiveness. Future research should refine patient criteria and assess long-term outcomes in this evolving landscape.

Retinoids induce integrin-independent lymphocyte adhesion through RAR-α nuclear receptor activity.

Oxidative metabolites of vitamin A, in particular all-trans-retinoic acid (atRA), have emerged as key factors in immunity by specifying the localization of immune cells to the gut. Although it is appreciated that isomers of retinoic acid activate the retinoic acid receptor (RAR) and retinoid X receptor (RXR) family of nuclear receptors to elicit cellular changes, the molecular details of retinoic acid action remain poorly defined in immune processes. Here we employ a battery of agonists and antagonists to delineate the specific nuclear receptors utilized by retinoids to evoke lymphocyte cell adhesion to ADAM (adisintegrin and metalloprotease) protein family members. We report that RAR agonism is sufficient to promote immune cell adhesion in both immortal and primary immune cells. Interestingly, adhesion occurs independent of integrin function, and mutant studies demonstrate that atRA-induced adhesion to ADAM members required a distinct binding interface(s) as compared to integrin recognition. Anti-inflammatory corticosteroids as well as 1,25-(OH)2D3, a vitamin D metabolite that prompts immune cell trafficking to the skin, potently inhibited the observed adhesion. Finally, our data establish that induced adhesion was specifically attributable to the RAR-α receptor isotype. The current study provides novel molecular resolution as to which nuclear receptors transduce retinoid exposure into immune cell adhesion.