Are artificial intelligence chatbots a reliable source of information about contact lenses?

INTRODUCTION: Artificial Intelligence (AI) chatbots are able to explain complex concepts using plain language. The aim of this study was to assess the accuracy of three AI chatbots answering common questions related to contact lens (CL) wear. METHODS: Three open access AI chatbots were compared: Perplexity, Open Assistant and ChatGPT 3.5. Ten general CL questions were asked to all AI chatbots on the same day in two different countries, with the questions asked in Spanish from Spain and in English from the U.K. Two independent optometrists with experience working in each country assessed the accuracy of the answers provided. Also, the AI chatbots' responses were assessed if their outputs showed any bias towards (or against) any eye care professional (ECP). RESULTS: The answers obtained by the same AI chatbots were different in Spain and the U.K. Also, statistically significant differences were found between the AI chatbots for accuracy. In the U.K., ChatGPT 3.5 was the most and Open Assistant least accurate (p < 0.01). In Spain, Perplexity and ChatGPT were statistically more accurate than Open Assistant (p < 0.01). All the AI chatbots presented bias, except ChatGPT 3.5 in Spain. CONCLUSIONS: AI chatbots do not always consider local CL legislation, and their accuracy seems to be dependent on the language used to interact with them. Hence, at this time, although some AI chatbots might be a good source of information for general CL related questions, they cannot replace an ECP.

Comparative study of the glistening between four intraocular lens models assessed by OCT and deep learning.

PURPOSE: To evaluate the glistening in 4 different models of intraocular lenses (IOLs) using optical coherence tomography (OCT) and deep learning (DL). SETTING: Centro Internacional de Oftalmología Avanzada (Madrid, Spain). DESIGN: Cross-sectional study. METHODS: 325 eyes were assessed for the presence and severity of glistening in 4 IOL models: ReSTOR+3 SN6AD1 (n = 41), SN60WF (n = 110), PanOptix TFNT (n = 128) and Vivity DFT015 (n = 46). The presence of glistening was analyzed using OCT, identifying the presence of hyperreflective foci (HRF) in the central area of the IOL. A manual and an original DL-based quantification algorithm designed for this purpose was applied. RESULTS: Glistening was detected in 22 (53.7%) ReSTOR SN6AD1, 44 (40%) SN60WF, 49 (38.3%) PanOptix TFNT, and 4 (8.7%) Vivity DFT015 IOLs, when any grade was considered. In the comparison of the different types of IOLs, global glistening measured as total HRF was 17.3 ± 25.9 for the ReSTOR+3; 9.3 ± 15.7 for the SN60WF; 6.9 ± 10.5 for the PanOptix; and 1.2 ± 2.6 for the Vivity ( P < .05). There was excellent agreement between manual and DL-based quantification (≥0.829). CONCLUSIONS: It is possible to quantify, classify and compare the glistening severity in different IOL models using OCT images in a simple and objective manner with a DL algorithm. In the comparative study, the Vivity presented the lowest severity of glistening.

Repeatability of choriocapillaris flow voids by optical coherence tomography angiography in central serous chorioretinopathy.

PURPOSE: To assess the repeatability of flow signal voids (FSV) measurements of the choriocapillaris (CC) and choroid (CH) in central serous chorioretinopathy (CSCR) by Swept-Source optical coherence tomography angiography (SS-OCTA). METHODS: Cross-sectional study including 104 eyes of 52 patients with unilateral CSCR. Two consecutive macular 6x6 mm SS-OCTA scans (Plex Elite 9000; Zeiss, Dublin, CA) were obtained from the affected eyes with persistent subretinal fluid (SRF) (CSCR group) and the fellow unaffected eyes (control group). FSV area and the number of contours measurements were analyzed using three slabs: inner CC, outer CC and CH. The repeatability of the measurements was assessed with intraclass correlation coefficients (ICC) and coefficients of variation (CV). RESULTS: In the CSCR group, ICCs for the FSV area in the three slabs were all ≥0.859, observing higher values for the outer CC and the CH (0.959 and 0.964) than for the inner CC (0.859). Similar ICC values were obtained for the FSV area in control eyes, observing the highest values for the outer CC (0.949), followed by the CH (0.932) and inner CC (0.844). Regarding the FSV number of contours measurements, ICCs were higher for the outer CC and CH (0.949 and 0.932) than for inner CC (0.844). CV for the FSV area was 4.7%, 3.8% and 8.6% in the CSCR eyes and 4.8%, 3.9% and 9.3% in the control group for the inner CC, outer CC and CH respectively. CONCLUSION: SS-OCTA offers good repeatability to quantify macular FSV in CSCR eyes and fellow eyes.

Prediction of the response to photodynamic therapy in patients with chronic central serous chorioretinopathy based on optical coherence tomography using deep learning.

PURPOSE: To assess the prediction of the response to photodynamic therapy (PDT) in chronic central serous chorioretinopathy (CSCR) based on spectral-domain optical coherence tomography (SD-OCT) images using deep learning (DL). METHODS: Retrospective study including 216 eyes of 175 patients with CSCR and persistent subretinal fluid (SRF) who underwent half-fluence PDT. SD-OCT macular examination was performed before (baseline) and 3 months after treatment. Patients were classified into groups by experts based on the response to PDT: Group 1, complete SRF resorption (n = 100); Group 2, partial SRF resorption (n = 66); and Group 3, absence of any SRF resorption (n = 50). This work proposes different computational approaches: 1st approach compares all groups; 2nd compares groups 1 vs. 2 and 3 together; 3rd compares groups 2 vs. 3. RESULTS: The mean age was 55.6 ± 10.9 years and 70.3% were males. In the first approach, the algorithm showed a precision of up to 57% to detect the response to treatment in group 1 based on the initial scan, with a mean average accuracy of 0.529 ± 0.035. In the second model, the mean accuracy was higher (0.670 ± 0.046). In the third approach, the algorithm showed a precision of 0.74 ± 0.12 to detect the response to treatment in group 2 (partial SRF resolution) and 0.69 ± 0.15 in group 3 (absence of SRF resolution). CONCLUSION: Despite the high clinical variability in the response of chronic CSCR to PDT, this DL algorithm offers an objective and promising tool to predict the response to PDT treatment in clinical practice.

Early changes in choriocapillaris flow voids as an efficacy biomarker of photodynamic therapy in central serous chorioretinopathy.

PURPOSE: To assess the early changes produced in the choriocapillaris (CC) and choroidal vasculature using swept-source optical coherence tomography angiography (SS-OCTA) in patients with persistent central serous chorioretinopathy (CSCR) as predictors of the efficacy after photodynamic therapy (PDT). METHODS: Prospective observational study in 52 eyes of 52 patients with persistent subretinal fluid (SRF). SS-OCTA scans of the 6 × 6 mm macular region were assessed before; 2-3 days, one month and three months after half-fluence PDT. Vessel occlusion in the CC and choroid was measured as flow signal voids (FSV). RESULTS: A 3.67 ± 4.12 and 2.76 ± 3.63 fold increase in CC and CH FSV, due to vessel occlusion, was observed at 2-3 days after PDT versus baseline. There was less SRF at 3 months in patients with an increase in FSV (≥1-fold) compared to those without this increase (<1-fold) after PDT (p ≤ 0.003). An association between the increase in CC and choroidal FSV at the early control (2-3 days) and the height of SRF at 1 month was found (R=-0.405; p = 0.002 and R=-0.356; p = 0.008 respectively). In a multivariate model, the SRF at one month was not associated with age, gender, visual acuity, or FSV (p ≥ 0.288). At 3 months, flow restoration was achieved in the choroid versus the baseline (p = 0.619), but there was a persistent increase in the CC FSV (p = 0.008). CONCLUSIONS: Early vessel occlusion by OCTA after PDT in CSCR was associated with good treatment response. Therefore, an increase in FSV immediately after PDT could be a biomarker to predict SRF resorption.