Performance of ChatGPT in Diagnosis of Corneal Eye Diseases.

PURPOSE: The aim of this study was to assess the capabilities of ChatGPT-4.0 and ChatGPT-3.5 for diagnosing corneal eye diseases based on case reports and compare with human experts. METHODS: We randomly selected 20 cases of corneal diseases including corneal infections, dystrophies, and degenerations from a publicly accessible online database from the University of Iowa. We then input the text of each case description into ChatGPT-4.0 and ChatGPT-3.5 and asked for a provisional diagnosis. We finally evaluated the responses based on the correct diagnoses, compared them with the diagnoses made by 3 corneal specialists (human experts), and evaluated interobserver agreements. RESULTS: The provisional diagnosis accuracy based on ChatGPT-4.0 was 85% (17 correct of 20 cases), whereas the accuracy of ChatGPT-3.5 was 60% (12 correct cases of 20). The accuracy of 3 corneal specialists compared with ChatGPT-4.0 and ChatGPT-3.5 was 100% (20 cases, P = 0.23, P = 0.0033), 90% (18 cases, P = 0.99, P = 0.6), and 90% (18 cases, P = 0.99, P = 0.6), respectively. The interobserver agreement between ChatGPT-4.0 and ChatGPT-3.5 was 65% (13 cases), whereas the interobserver agreement between ChatGPT-4.0 and 3 corneal specialists was 85% (17 cases), 80% (16 cases), and 75% (15 cases), respectively. However, the interobserver agreement between ChatGPT-3.5 and each of 3 corneal specialists was 60% (12 cases). CONCLUSIONS: The accuracy of ChatGPT-4.0 in diagnosing patients with various corneal conditions was markedly improved than ChatGPT-3.5 and promising for potential clinical integration. A balanced approach that combines artificial intelligence-generated insights with clinical expertise holds a key role for unveiling its full potential in eye care.

Performance of ChatGPT in Diagnosis of Corneal Eye Diseases.

Introduction: Assessing the capabilities of ChatGPT-4.0 and ChatGPT-3.5 for diagnosing corneal eye diseases based on case reports and compare with human experts. Methods: We randomly selected 20 cases of corneal diseases including corneal infections, dystrophies, degenerations, and injuries from a publicly accessible online database from the University of Iowa. We then input the text of each case description into ChatGPT-4.0 and ChatGPT3.5 and asked for a provisional diagnosis. We finally evaluated the responses based on the correct diagnoses then compared with the diagnoses of three cornea specialists (Human experts) and evaluated interobserver agreements. Results: The provisional diagnosis accuracy based on ChatGPT-4.0 was 85% (17 correct out of 20 cases) while the accuracy of ChatGPT-3.5 was 60% (12 correct cases out of 20). The accuracy of three cornea specialists were 100% (20 cases), 90% (18 cases), and 90% (18 cases), respectively. The interobserver agreement between ChatGPT-4.0 and ChatGPT-3.5 was 65% (13 cases) while the interobserver agreement between ChatGPT-4.0 and three cornea specialists were 85% (17 cases), 80% (16 cases), and 75% (15 cases), respectively. However, the interobserver agreement between ChatGPT-3.5 and each of three cornea specialists was 60% (12 cases). Conclusions: The accuracy of ChatGPT-4.0 in diagnosing patients with various corneal conditions was markedly improved than ChatGPT-3.5 and promising for potential clinical integration.

Femtosecond laser-assisted laser in situ keratomileusis for the correction of high myopia in Meesmann corneal dystrophy: a case report / Femto-LASIK para correção de alta miopia na distrofa corneana de Meesmann: relato de caso

ABSTRACT The patient was a 26-year-old woman who had manifest refraction and uncorrected and corrected distance visual acuities of -7.00 × -4.50 at 175°, 20/400, and 20/25, respectively, in the right eye, and -3.25 × -5.25 at 179°, 20/200, and 20/25, respectively, in the left eye. In the right and left eyes, the mean corneal thicknesses were 733 and 749 µm, and the maximum epithelial thicknesses were 70 and 68 µm, respectively. Myriads of intraepithelial cysts were observed in the slit-lamp examination. At 30 months after femtosecond laser-assisted laser in situ keratomileusis (femto-LASIK), the manifest refraction and uncorrected and corrected distance visual acuities were respectively 0.00 × -1.25 at 55°, 20/25, and 20/20 in right eye, and 0.00 × -0.50 at 135°, 20/20, and 20/20 in the left eye. In this case of Meesmann dystrophy, myopia was successfully treated with thick flap femto-LASIK without complications or ectasia.

RESUMO A paciente era uma mulher de 26 anos com refração manifesta, acuidade visual para longe não corrigida e corrigida de -7,00 × -4,50 a175°, 20/400 e 20/25 no olho direito e -3,25 × -5,25 a 179°, 20/200 e 20/25 no olho esquerdo. A espessura média da córnea foi de 733 e 749 µm, e a espessura epitelial máxima foi de 70 e 68 µm, respectivamente no olho direito e no esquerdo. Inúmeros cistos intraepiteliais foram observados no exame com lâmpada de fenda. Trinta meses após o femto-LASIK, a refração manifesta, a acuidade visual para longe não corrigida e corrigida eram respectivamente de 0,00 × -1,25 a 55°, 20/25 e 20/20 no olho direito e 0,00 × -0,50 a 135°, 20/20 e 20/20 no olho esquerdo. Neste caso de distrofia de Meesmann, a miopia foi tratada com sucesso com femto-LASIK de retalho espesso sem complicações ou ectasia.

Variability of CLMI-X parameters, zonal Kmax, and single-point Kmax in keratoconus progression.

OBJECTIVES: To compare the repeatability of Cone Location and Magnitude Index expanded (CLMI.X) parameters of 2 mm diameter zone of greatest corneal curvature (Cspot-Axi) and 1 mm diameter zone of thinnest pachmymetry (Spot-Pach) with the maximum single point keratometry (Kmax), 3 mm Zonal Kmax (Z-Kmax3), and thinnest single point pachymetry (TP) in keratoconus (KC). METHODS: In this Comparative repeatability study, data from 36 eyes of 36 normal individuals and 72 eyes of 72 KC patients (28 eyes with ≤50.0D and 44 eyes with >50.0D Z-Kmax3) were analyzed. For each enrolled eye, imaging was done 6 times (3 consecutive acquisitions with a half hour break). For each parameter, the within-subject standard deviation (Sw) was calculated from the data of the six exams. RESULTS: In the normal group, Cspot-Axi-Sw was different from Kmax-Sw (p = 0.0004). Also, Z-Kmax3-Sw was different from Kmax-Sw (p = 0.0297). The difference between Cspot-Axi-Sw and Z-Kmax3-Sw was statistically significant (p = 0.0482). In the KC group, Sw were significantly different between Cspot-Axi and Kmax (p < 0.0001), and between Z-Kmax3 and Kmax (p < 0.0001). In the Z-Kmax3 ≤ 50.0D subgroup, Sw were different between Cspot-Axi and Kmax (p = 0.0002). In the Z-Kmax3 > 50.0D subgroup, Sw were different between Cspot-Axi and Kmax (p < 0.0001), and between Z-Kmax3 and Kmax (p < 0.0001). Sw differences between Spot-Pach and TP were not significant in any of the study groups (all P > 0.05). CONCLUSIONS: In the diagnosis and follow up of KC, the zonal averages of Cspot-Axi and Z-Kmax3 are more reliable than the single point Kmax. The repeatability of Spot-Pach is similar to TP and both variables should suit the purpose equally.

Corneal Biomechanics After SMILE, Femtosecond-Assisted LASIK, and Photorefractive Keratectomy: A Matched Comparison Study.

Purpose: To evaluate the change in corneal stiffness after small incision lenticule extraction (SMILE), femtosecond laser-assisted in situ keratomileusis (FS-LASIK), and photorefractive keratectomy (PRK). Methods: Age, gender, spherical equivalent, and central corneal thickness (CCT)-matched cases undergoing SMILE with a 120-µ cap, FS-LASIK with a 110-µ flap, and PRK were enrolled. One-year change in the stress-strain index, stiffness parameter at first applanation, integrated inverse radius, deformation amplitude ratio at 2 mm, and deformation amplitude ratio at 1 mm were compared between the surgical groups by linear mixed-effect models. Results: Within each surgical group, 120 eyes completed 1 year of follow-up. The residual stromal bed (RSB) thickness and (RSB/CCTpostop) were 348.1 ± 35.0 (0.74), 375.4 ± 31.0 (0.77) and 426.7 ± 2 µm (0.88) after SMILE, FS-LASIK, and PRK, respectively. The 1-year change in all biomechanical indices was significant, except the stress-strain index with PRK (P = 0.884). The change in all indices with SMILE were significantly greater than with FS-LASIK and with PRK (all P < 0.01), except the deformation amplitude ratio at 1 mm change between SMILE and FS-LASIK (P = 0.075). The changes in all indices with FS-LASIK were significantly greater than with PRK (all P < 0.05). Conclusions: Although SMILE preserves the greatest amount of anterior cornea with a cap thickness of 120 µ, this also produces the smallest RSB and the greatest decrease in stiffness. Thus, the RSB is shown to be the predominant determinant of stiffness decreases, rather than the preserved anterior cornea. We recommend using a thinner cap to achieve a thicker RSB and a lesser decrease in the corneal stiffness in the SMILE procedure. Translational Relevance: After refractive surgery, RSB is predominant determinant of stiffness decreases, rather than the preserved anterior cornea.

A Student-Centered, Entrepreneurship Development (ASCEND) Undergraduate Summer Research Program: Foundational Training for Health Research.

Increasing the participation of students of African descent and other minoritized populations in the scientific workforce is imperative in generating a more equitable biomedical research infrastructure and increasing national research creativity and productivity. Undergraduate research training programs have shown to be essential tools in retaining underrepresented minority (URM) students in the sciences and attracting them into STEM and biomedical careers. This paper describes an innovative approach to harness students' entrepreneurial desire for autonomy and creativity in a Summer Research Institute (SRI) that has served as an entry point into a multiyear, National Institutes of Health Building Infrastructure Leading to Diversity (NIH BUILD)-funded research training program. The SRI was designed as an 8-week, student-centered and course-based research model in which students select their own research topics. We test here the effects of SRI training on students' science self-efficacy and science identity, along with several other constructs often associated with academic outcomes in the sciences. The data shown here comprise analysis of four different training cohorts throughout four subsequent summers. We show significant gains in students' science self-efficacy and science identity at the conclusion of SRI training, as well as academic adjustment and sense of belonging. SRI participants also displayed substantially improved retention in their science majors and graduation rates.

Femtosecond laser-assisted laser in situ keratomileusis for the correction of high myopia in Meesmann corneal dystrophy: a case report.

The patient was a 26-year-old woman who had manifest refraction and uncorrected and corrected distance visual acuities of -7.00 × -4.50 at 175°, 20/400, and 20/25, respectively, in the right eye, and -3.25 × -5.25 at 179°, 20/200, and 20/25, respectively, in the left eye. In the right and left eyes, the mean corneal thicknesses were 733 and 749 µm, and the maximum epithelial thicknesses were 70 and 68 µm, respectively. Myriads of intraepithelial cysts were observed in the slit-lamp examination. At 30 months after femtosecond laser-assisted laser in situ keratomileusis (femto-LASIK), the manifest refraction and uncorrected and corrected distance visual acuities were respectively 0.00 × -1.25 at 55°, 20/25, and 20/20 in right eye, and 0.00 × -0.50 at 135°, 20/20, and 20/20 in the left eye. In this case of Meesmann dystrophy, myopia was successfully treated with thick flap femto-LASIK without complications or ectasia.

Non-Cycloplegic and Cycloplegic Autorefraction with Retinomax: An Agreement Study in Preschoolers in Los Angeles, California.

PURPOSE: To evaluate the agreement between non-cycloplegic autorefraction (NCAR) and cycloplegic autorefraction (CAR) in an ethnically diverse population of preschool-aged children and the validity of the screening criteria used to refer for further evaluation. METHODS: This study included data from 7,073 preschoolers who underwent NCAR and CAR, which enabled refractive error classification based on the American Association for Pediatric Ophthalmology and Strabismus (AAPOS) 2013 criteria. Right eye data of sphere and cylinder were used to compare NCAR to CAR via paired t-testing and vector analyses, and left eye data for an analysis on anisometropia. The sensitivity and specificity of screening referral criteria for refractive error were calculated. RESULTS: Mean values of sphere differed between NCAR and CAR by 1.95 ± 1.45 D (p < .05) with 95% limits of agreement (LoA) of -0.94 to 4.85 D, with less discrepancy found in myopic eyes. The mean values of cylinder differed by -0.08 ± 0.43 D (p < .05) with 95% LoA of -0.93 to 0.77 D. Power vector results reflected a similar lack of agreement. The sensitivity and specificity of our screening referral criteria were, respectively, 66% and 84% for myopia, 66% and 98% for hyperopia, and 98% and 58% for astigmatism. CONCLUSION: NCAR is insufficient in preschoolers for spherical refractive error referrals. Level of agreements was lower for spherical (15.5% within 0.5D) and higher for cylindrical refractive errors (89.6%) compared to CAR. In the absence of cycloplegic examination, screening programs using NCAR should utilize low referral thresholds for spherical refractive error.

Small CBPR Grants Program: An Innovative Model to Build Sustainable Academic-Community Partnerships.

Community-based participatory research (CBPR) is an effective approach for addressing health disparities by integrating diverse knowledge and expertise from both academic and community partners throughout the research process. However, more is needed to invest in the foundational infrastructure and resources that are necessary for building and maintaining lasting trusting research partnerships and supporting them to generate impactful CBPR-based research knowledge and solutions. Small CBPR Grants Program is a CBPR-seed-funding program that may be particularly helpful to minority-serving institutions' and universities' goal to invest in genuine community-engaged participatory research. Between 2016 and 2019, the Morgan State University Prevention Sciences Research Center, in collaboration with other community and academic organizations, provided 14 small CBPR awards to new partnerships, and evaluated the success and challenges of the program over a period of three years. To achieve our goal, technical support and training were provided to these partnerships to help with their growth and success. The expected outcomes included trusting relationships and equitable partnerships, as well as publications, presentations, and new proposals and awards to work on mutually identified issues. The program's resulted in continued partnerships beyond the program (in most cases), a founded CBPR Center namely ASCEND, and several secured additional fundings. Keys to the program's success were supporting the formation of research partnerships through networking opportunities and information sessions, as well as providing small grants to incentivize the development of innovative concepts and projects. A learning network and local support group were also created to enhance productivity and the overall impact of each project.

An Innovative Biomedical Research Training Model: Rationale, Design, and Evaluation.

Much is told regarding the need for greater diversity in the biomedical research workforce in terms of race, ethnicity, and socioeconomic status. However, there are few evidence-based models that are tested and can have significant effects in this regard. Thus, there is a need for development and evaluation of innovative models that may help train a more diverse biomedical research workforce. In this study, we provided the rationale, conceptual model, and preliminary evaluation of a program called "A Student-Centered Entrepreneurship Development (ASCEND)". This training program was designed, implemented, and evaluated between 2017 and 2020 at Morgan State University, Baltimore, Maryland, United States. The program's conceptual model is based on four stages: Attraction and Inspiration, Ideation and Innovation, Research Implementation, and Career Growth. Results of the comparative survey between 50 students who participated in ASCEND and 86 non-member controls showed an increase in science identity, academic self-concept, science self-efficacy, and peer support. The only domain that did not show a larger increase in participants in our program compared to controls was social self-concept. In addition, a total of 59 students submitted 48 research concepts, and 16 undergraduate student projects were funded. Of participants in the Health Research Concepts Competition, 39 students graduated, and 13 were pursuing graduate programs in STEM fields at the time of evaluation. The number of research projects and trainees who started a graduate degree were also reported. The ASCEND training model fosters an entrepreneurial mindset among undergraduate students. Such a program might be effective in diversifying the biomedical research workforce. While this preliminary evaluation indicates the efficacy of the ASCEND model, there is a need for further long-term and multi-center evaluations with the trainees' research productivity and receipt of independent funding as outcomes.

Long-Term Results of Laser In Situ Keratomileusis in Myopic Patients with Topographic Indices outside Suggested Ranges.

INTRODUCTION: To investigate the long-term results of laser in situ keratomileusis (LASIK) in patients with one or more topographic indices outside the suggested range preoperatively. METHODS: Patients who had conventional or femtosecond laser-assisted LASIK for myopia correction between 2011 and 2015, and had at least one preoperative corneal topographic index outside the suggested range were contacted for a follow-up examination. Ranges were based on the cutoffs suggested for subclinical keratoconus: thinnest pachymetry (TP) < 497.50 µm, maximum keratometry (Kmax) > 47.20 D, maximum 8 mm best-fit-sphere anterior elevation (MaxAE) > 9.50 µm, maximum 8 mm best-fit-sphere posterior elevation (MaxPE) > 20.50 µm, and Belin/Ambrósio enhanced ectasia display-total deviation (BAD-D) > 1.60. RESULTS: Two hundred thirty patients (377 eyes) were enrolled; their mean age at baseline and at follow-up was 30.78 ± 8.16 and 9.06 ± 1.91 years, respectively. Mean ± SD was 484.36 ± 11.49 for TP (n = 133), 48.17 ± 0.83 for Kmax (n = 133), 16.33 ± 5.39 for MaxAE (n = 35), 27.87 ± 7.86 for MaxPE (n = 34), and 1.97 ± 0.36 for BAD-D (n = 162). Post-LASIK and suspected ectasia was found in one (0.26%) and two (0.53%) eyes, respectively. In the remaining 374, the efficacy and safety indices were 0.96 ± 0.14 and 1.01 ± 0.08, respectively. Uncorrected distance visual acuity (UDVA) was not reduced in any eyes, and corrected distance visual acuity (CDVA) was reduced one line in 1.9% of the cases; 79.9% of the cases were emmetropic. The long-term changes in UDVA, CDVA, and spherical equivalent were not different between groups with one, two, or three out-of-range topographic indices (all P > 0.05). CONCLUSION: A single out-of-range topographic index is not a strong predictor for postoperative complications, and one should consider the combination of topographic and clinical findings, or the pattern they create in tandem. Developing a scoring system that would take a combination of indices and topographic patterns may help improve the predictive accuracy of these indices.

COVID-19 cases, hospitalizations and deaths after vaccination: a cohort event monitoring study, Islamic Republic of Iran.

Objective: To investigate the incidence of coronavirus disease 2019 (COVID-19) cases, hospitalizations and deaths in Iranians vaccinated with either AZD1222 Vaxzevria, CovIran® vaccine, SARS-CoV-2 Vaccine (Vero Cell), Inactivated (lnCoV) or Sputnik V. Methods: We enrolled individuals 18 years or older receiving their first COVID-19 vaccine dose between April 2021 and January 2022 in seven Iranian cities. Participants completed weekly follow-up surveys for 17 weeks (25 weeks for AZD1222) to report their COVID-19 status and hospitalization. We used Cox regression models to assess risk factors for contracting COVID-19, hospitalization and death. Findings: Of 89 783 participants enrolled, incidence rates per 1 000 000 person-days were: 528.2 (95% confidence interval, CI: 514.0-542.7) for contracting COVID-19; 55.8 (95% CI: 51.4-60.5) for hospitalization; and 4.1 (95% CI: 3.0-5.5) for death. Compared with SARS-CoV-2 Vaccine (Vero Cell), hazard ratios (HR) for contracting COVID-19 were: 0.70 (95% CI: 0.61-0.80) with AZD1222; 0.73 (95% CI: 0.62-0.86) with Sputnik V; and 0.73 (95% CI: 0.63-0.86) with CovIran®. For hospitalization and death, all vaccines provided similar protection 14 days after the second dose. History of COVID-19 protected against contracting COVID-19 again (HR: 0.76; 95% CI: 0.69-0.84). Diabetes and respiratory, cardiac and renal disease were associated with higher risks of contracting COVID-19 after vaccination. Conclusion: The rates of contracting COVID-19 after vaccination were relatively high. SARS-CoV-2 Vaccine (Vero Cell) provided lower protection against COVID-19 than other vaccines. People with comorbidities had higher risks of contracting COVID-19 and hospitalization and should be prioritized for preventive interventions.

Comparative Contralateral Randomized Clinical Trial of Standard (3 mW/cm2) Versus Accelerated (9 mW/cm2) CXL in Patients With Down Syndrome: 3-Year Results.

PURPOSE: To compare the long-term results of accelerated corneal cross-linking (CXL) (9 mW/cm2, 10 min) with standard CXL (3 mW/cm2, 30 min) in patients with Down syndrome who had keratoconus. METHODS: In this contralateral randomized clinical trial, 27 patients with Down syndrome aged 15.78 ± 2.46 years (range: 10 to 19 years) were enrolled. CXL was performed using the KXL System (Avedro, Inc) under general anesthesia, and patients were followed up for 3 years. The main outcome measure was a change in average keratometry in the 3-mm zone around the steepest point (zonal Kmax-3mm). Secondary outcomes were changes in Corvis ST (Oculus Optikgeräte GmbH) biomechanical parameters and vision, refraction, and corneal tomography measurements. RESULTS: Mean 3-year changes in zonal Kmax-3mm were not significantly different between the accelerated and standard groups (-0.06 ± 0.75 and -0.35 ± 0.94 diopters [D], respectively, P = .727). Despite the contralateral design of the study, based on most baseline biomechanical indices, corneas in the standard group were weaker before treatment. The standard group also showed significantly fewer 3-year changes in the stress-strain index (-0.11 ± 0.21 vs -0.30 ± 0.32), integrated radius (+0.99 ± 3.48 vs +3.14 ± 2.84), and deformation amplitude ratio-2mm (-1.38 ± 1.33 vs +0.30 ± 1.75) (all P < .0167). Corneal stiffness in the accelerated group was stable for 2 years, and the decline mainly occurred during the third year. CONCLUSIONS: In young patients with Down syndrome who had keratoconus, accelerated and standard CXL showed a similar flattening effect. Standard CXL is better able to maintain corneal stiffness in weaker corneas. With accelerated CXL, despite stable results for 2 years, there was decreased corneal stiffness in the third year. Longer follow-up periods are warranted to study the decreased efficacy on keratoconus progression. [J Refract Surg. 2022;38(6):381-388.].

Best Indicators for Detecting Keratoconus Progression in Children: A Report From the Shahroud Schoolchildren Eye Cohort Study.

PURPOSE: The purpose of this study was to investigate 3-year changes in keratoconus (KC) indices to determine the indicators of KC progression compared with age-related changes in children aged 6 to 12 years. METHODS: In this report of the Shahroud Schoolchildren Eye Cohort Study, KC was diagnosed based on vision, refraction, tomography, and slitlamp examination findings. KC progression was defined as changes in refractive astigmatism or zonal maximum keratometry (Zonal Kmax-3 mm). Then, 3-year changes (Δ) in vision, refraction, and tomographic indices were compared between progressive KC and normal eyes. The best set of ∆parameters for distinguishing KC progression from age-related changes were determined using the area under curve (AUC). RESULTS: Eighteen KC eyes and 10,422 normal eyes were analyzed. All KC cases showed progression after 3 years. Δindices were statistically different between the 2 groups except corrected distance visual acuity, anterior radius of curvature, irregularity index, and KC percentage index. The best Δindices, in descending order of AUC value, were index of height decentration, Zonal Kmax-3 mm, refractive astigmatism, single point Kmax, and index of vertical asymmetry (all AUC > 0.9), followed by inferior-superior asymmetry, index of surface variance, minimum corneal thickness, index of height asymmetry, KC index, posterior radius of curvature, and Belin/Ambrósio total Deviation (AUC = 0.8-0.9). CONCLUSIONS: According to our findings, changes in index of height decentration, Zonal Kmax-3 mm, refractive astigmatism, single point Kmax, and index of vertical asymmetry are the best indices for detecting KC progression in children younger than 12 years.

Interocular Symmetry Analysis of Corneal Elevation Using the Fellow Eye as the Reference Surface and Machine Learning.

Unilateral corneal indices and topography maps are routinely used in practice, however, although there is consensus that fellow-eye asymmetry can be clinically significant, symmetry studies are limited to local curvature and single-point thickness or elevation measures. To improve our current practices, there is a need to devise algorithms for generating symmetry colormaps, study and categorize their patterns, and develop reference ranges for new global discriminative indices for identifying abnormal corneas. In this work, we test the feasibility of using the fellow eye as the reference surface for studying elevation symmetry throughout the entire corneal surface using 9230 raw Pentacam files from a population-based cohort of 4613 middle-aged adults. The 140 × 140 matrix of anterior elevation data in these files were handled with Python to subtract matrices, create color-coded maps, and engineer features for machine learning. The most common pattern was a monochrome circle ("flat") denoting excellent mirror symmetry. Other discernible patterns were named "tilt", "cone", and "four-leaf". Clustering was done with different combinations of features and various algorithms using Waikato Environment for Knowledge Analysis (WEKA). Our proposed approach can identify cases that may appear normal in each eye individually but need further testing. This work will be enhanced by including data of posterior elevation, thickness, and common diagnostic indices.

Corneal ectasia in mothers of Down syndrome children.

In this study, corneal findings regarding keratoconus (KC) and early KC among mothers with Down syndrome children (MDS) and a group of age-at-delivery-matched mothers with normal children (MNC) were compared. KC was diagnosed based on the presence of a clinical sign and at least one abnormal tomographic or biomechanical criterion. Early KC was defined as having no clinical sign in the presence of at least one abnormal tomographic or biomechanical criterion. The normal subgroups in each group were compared in terms tomographic and biomechanical parameters. In MDS and MNC, the prevalence rates were 6.5% and 1.6% for KC (P = 0.047), and 30.9% and 14.3% for early KC (P = 0.014), respectively. Comparison between the two normal subgroups showed significant differences in mean index of height asymmetry, irregularity index, anterior asphericity, pentacam random forest index, corneal stiffness parameters at first applanation, deformation amplitude ratios, integrated radius-1 mm, highest concavity deflection amplitude, biomechanical corrected IOP, peak distance, and radius (all P < 0.05). This study showed that MDS are more likely to have KC and also to have thinner, steeper and softer corneas compared to MNC. This results support the need for further work for determining the risk of delivering a child with DS.