Corneal arcus as first sign of familial hypercholesterolemia

Computational intelligence in eye disease diagnosis: a comparative study

In recent years, eye disorders are an important health issue among older people. Generally, individuals with eye diseases are unaware of the gradual growth of symptoms. Therefore, routine eye examinations are required for early diagnosis. Usually, eye disorders are identified by an ophthalmologist via a slit-lamp investigation. Slit-lamp interpretations are inadequate due to the differences in the analytical skills of the ophthalmologist, inconsistency in eye disorder analysis, and record maintenance issues. Therefore, digital images of an eye and computational intelligence (CI)-based approaches are preferred as assistive methods for eye disease diagnosis. A comparative study of CI-based decision support models for eye disorder diagnosis is presented in this paper. The CI-based decision support systems used for eye abnormalities diagnosis were grouped as anterior and retinal eye abnormalities diagnostic systems, and numerous algorithms used for diagnosing the eye abnormalities were also briefed. Various eye imaging modalities, pre-processing methods such as reflection removal, contrast enhancement, region of interest segmentation methods, and public eye image databases used for CI-based eye disease diagnosis system development were also discussed in this paper. In this comparative study, the reliability of various CI-based systems used for anterior eye and retinal disorder diagnosis was compared based on the precision, sensitivity, and specificity in eye disease diagnosis. The outcomes of the comparative analysis indicate that the CI-based anterior and retinal disease diagnosis systems attained significant prediction accuracy. Hence, these CI-based diagnosis systems can be used in clinics to reduce the burden on physicians, minimize fatigue-related misdetection, and take precise clinical decisions.

Computer-Aided Diagnosis of Anterior Segment Eye Abnormalities using Visible Wavelength Image Analysis Based Machine Learning

Eye disease is a major health problem among the elderly people. Cataract and corneal arcus are the major abnormalities that exist in the anterior segment eye region of aged people. Hence, computer-aided diagnosis of anterior segment eye abnormalities will be helpful for mass screening and grading in ophthalmology. In this paper, we propose a multiclass computer-aided diagnosis (CAD) system using visible wavelength (VW) eye images to diagnose anterior segment eye abnormalities. In the proposed method, the input VW eye images are pre-processed for specular reflection removal and the iris circle region is segmented using a circular Hough Transform (CHT)-based approach. The first-order statistical features and wavelet-based features are extracted from the segmented iris circle and used for classification. The Support Vector Machine (SVM) by Sequential Minimal Optimization (SMO) algorithm was used for the classification. In experiments, we used 228 VW eye images that belong to three different classes of anterior segment eye abnormalities. The proposed method achieved a predictive accuracy of 96.96% with 97% sensitivity and 99% specificity. The experimental results show that the proposed method has significant potential for use in clinical applications.

Treatment of homozygous familial hypercholesterolaemia in paediatric patients: A monocentric experience

Background

Homozygous familial hypercholesterolaemia is a rare life-threatening disease characterized by markedly elevated low-density lipoprotein cholesterol (LDL-C) concentrations and accelerated atherosclerosis. The presence of double gene defects in the LDL-Receptor, either the same defect (homozygous) or two different LDL-raising mutations (compound heterozygotes) or other variants, identify the homozygous phenotype (HopFH). Apheresis is a procedure in which plasma is separated from red blood cells before the physical removal of LDL-C or the LDL-C is directly removed from whole blood. It is currently the treatment of choice for patients with HopFH whose LDL-C levels are not able to be reduced to target levels with conventional lipid-lowering drug therapy.

Design

The aim of this study is to report a cohort of six paediatric patients and to evaluate the long term efficacy of combined medical therapy and LDL-apheresis on LDL-C reduction.

Methods

We collected data from six children with confirmed diagnosis of HopFH (two females and four males; age range at diagnosis 3–8 years, mean 6 ± 1 years) from a single clinical hospital in Italy from 2007 to 2017.

Results

Clinical manifestations and outcomes may greatly vary in children with HopFH. Medical therapy and LDL-apheresis for the severe form should be started promptly in order to prevent cardiovascular disease.

Conclusions

Lipoprotein apheresis is a very important tool in managing patients with HopFH at high risk of cardiovascular disease. Based on our experience and the literature data, the method is feasible in very young children, efficient regarding biological results and cardiac events, and safe with minor side-effects and technical problems. We advise treating homozygous and compound heterozygous children as soon as possible.