A Review of Machine Learning Techniques for Keratoconus Detection and Refractive Surgery Screening

ABSTRACT

Various machine learning techniques have been developed for keratoconus detection and refractive surgery screening. These techniques utilize inputs from a range of corneal imaging devices and are built with automated decision trees, support vector machines, and various types of neural networks. In general, these techniques demonstrate very good differentiation of normal and keratoconic eyes, as well as good differentiation of normal and form fruste keratoconus. However, it is difficult to directly compare these studies, as keratoconus represents a wide spectrum of disease. More importantly, no public dataset exists for research purposes. Despite these challenges, machine learning in keratoconus detection and refractive surgery screening is a burgeoning field of study, with significant potential for continued advancement as imaging devices and techniques become more sophisticated.     

Incidence and pattern of dry eye after cataract surgery

Purpose

The objectives of the study were to identify the incidence and pattern of dry eye after phacoemulsification and manual small incision cataract surgeries.

Validation of the Italian version of the Charcot‐Marie‐Tooth disease Pediatric Scale

The Charcot‐Marie‐Tooth disease Pediatric Scale (CMTPedS) is a Rasch‐built clinical outcome measure of disease severity. It is valid, reliable, and responsive to change for children and adolescents aged 3 to 20 years. The aim of this study was to translate and validate an Italian version of the CMTPedS using a validated framework of transcultural adaptation. The CMTPedS (Italian) was translated and culturally adapted from source into Italian by two experts in CMT with good English language proficiency. The two translations were reviewed by a panel of experts in CMT. The agreed provisional version was back translated into English by a professional translator. The definitive Italian version was developed during a consensus teleconference by the same panel. CMT patients were assessed with the final version of the outcome measure and a subset had a second assessment after 2 weeks to evaluate test‐retest reliability. Seventeen patients with CMT aged 5 to 20 years (eight female) were evaluated with the CMTPedS (Italian), and test‐retest was performed in three patients. The CMTPedS (Italian) showed a high test‐retest reliability. No patient had difficulty in completing the scale. The instructions for the different items were clearly understood by clinicians and therefore the administration of the outcome measure was straight forward and easily understood by the children assessed. The CMTPedS (Italian) will be used for clinical follow‐up and in clinical research studies in the Italian population. The data is fully comparable to that obtained from the English language version.     

Assessment of heavy metals by ICP-OES and their impact on insulin stimulating hormone and carbohydrate metabolizing enzymes

Arsenic (As) and cadmium (Cd) have recently emerged as major health concerns owing to their strong association with diabetes mellitus (DM). We aimed to investigate the heavy metals exposure towards incidence of DM at various enzymatic and hormonal levels. Additionally, association of As and Cd with Zinc (Zn, essential metal) was also evaluated. Spot urine samples were collected to assess As, Cd and Zn through ICP-OES. Serum was analyzed by assay method for fasting blood glucose, liver and renal function biomarkers. ELISA was performed to investigate the impact of heavy metals on HbA1c, α-amylase, DPP-IV, IGF-1, leptin, GSH, MDA, SOD, HDL, FFA, TG and interleukin (IL)-6. Association of heavy metals with DM was measured by odds ratio (OR) and level of significance was assessed by Chi-squared test. Unpaired student's t-test was used to compare DM-associated risk factors in heavy metals-exposed and unexposed participants. As and Cd were detectable in 75.4% and 83% participants with mean concentration of 75.5 ppb and 54.5 ppb, respectively. For As exposure, OR in the third quartile was maximum ie 1.34 (95% CI, 0.80 to 2.23), however the result was not statistically significant (P > .05). For Cd exposure, OR in the fourth quartile was considerably high, 1.62 (95% CI, 1.00 to 2.61), with a significant probability value (P < .05). Urinary Cd was negatively associated with Zn. As and Cd exposure increases the incidence of DM in the general population. Impaired hormonal and enzymatic levels in diabetic and non-diabetic exposed participants reflect the multiple organ damage by heavy metal exposure.