Ischemic stroke prediction using machine learning in elderly Chinese population: The Rugao Longitudinal Ageing Study.

OBJECTIVE: Compared logistic regression (LR) with machine learning (ML) models, to predict the risk of ischemic stroke in an elderly population in China. METHODS: We applied 2208 records from the Rugao Longitudinal Ageing Study (RLAS) for ischemic stroke risk prediction assessment. Input variables included 103 phenotypes. For 3-year ischemic stroke risk prediction, we compared the discrimination and calibration of LR model and ML methods, where ML methods include Random Forest (RF), Gaussian kernel Support Vector Machines (SVM), Multilayer perceptron (MLP), K-Nearest Neighbors Algorithm (KNN), and Gradient Boosting Decision Tree (GBDT) to develop an ischemic stroke risk prediction model. RESULTS: Age, pulse, waist circumference, education level, ß2-microglobulin, homocysteine, cystatin C, folate, free triiodothyronine, platelet distribution width, QT interval, and QTc interval were significant induced predictors of ischemic stroke. For ischemic stroke prediction, the ML approach was able to tap more biochemical and ECG-related multidimensional phenotypic indicators compared to the LR model, which placed more importance on general demographic indicators. Compared to the LR model, SVM provided the best discrimination and calibration (C-index: 0.79 vs. 0.71, 11.27% improvement in model utility), with the best performance in both validation and test data. CONCLUSION: In a comparison of LR with five ML models, the accuracy of ischemic stroke prediction was higher by combining ML with multiple phenotypes. Combined with other studies based on elderly populations in China, ML techniques, especially SVM, have shown good long-term predictive performance, inspiring the potential value of ML use in clinical practice.

Spectral-domain optical coherence tomography for evaluating palisades of Vogt in ocular surface disorders with limbal involvement.

Spectral-domain optical coherence tomography (SD-OCT) has been used to observe the morphology of the palisades of Vogt (POV) with satisfactory resolutions. In this study, we used SD-OCT to examine the microstructure of the POV in ocular surface disorders with limbal involvement. We detect subclinical limbal pathologies based on five parameters, including (1) decreased epithelial thickness, (2) loss of the sharp stromal tip, (3) loss of the smooth epithelial-stromal interface, (4) dilated stromal vessels, and (5) decreased POV density. Eighteen eyes of 10 patients with advancing wavelike epitheliopathy (AWE) and 15 eyes of 9 patients with phlyctenular keratitis/ocular rosacea were recruited. SD-OCT could detect abnormal changes in the POV in 100% of the lesion sites. In presumed-healthy areas of the diseased eyes diagnosed by slit-lamp biomicroscopy, SD-OCT detected abnormal changes in the POV in 100% of the eyes in both groups. In patients with unilateral disease, abnormal changes in the POV were detected by SD-OCT in 50% and 100% of presumed-healthy eyes diagnosed by slit-lamp biomicroscopy in the AWE group and phlyctenular keratitis/ocular rosacea group, respectively. SD-OCT is powerful in detecting POV changes in ocular surface disorders and can provide useful information that cannot be provided by slit-lamp biomicroscopy.

Neurotrophic keratitis in autoimmune polyglandular syndrome type 1: a case report.

BACKGROUND: Autoimmune polyglandular syndrome type 1 (APS-1) is a rare autosomal recessive disease. In patients with APS-1, the most frequently reported ocular manifestations are keratoconjunctivitis with dry eye and retinal degeneration. However, to our knowledge, no research studies have reported the relationship between APS-1 and neurotrophic keratitis (NK). Possible explanations such as limbus cell deficiency being the primary cause of APS-1 keratopathy are not applicable to our unusual case of the patient with APS-1 presenting as ocular surface disease with NK. Our case findings suggest a new explanation for the observed corneal pathology and a potential treatment for these patients. CASE PRESENTATION: A 27-year-old woman was referred to our hospital because of intermittent blurred vision and recalcitrant ocular surface problems in both eyes for many years. She has a history of autoimmune polyglandular syndrome type 1 (APS-1), which includes hypothyroidism, hypoparathyroidism, hypoadrenalism, and hypogonadotropic hypogonadism. In vivo confocal microscopy clearly demonstrated significant degeneration of the sub-basal nerve plexus and stromal nerve bundles in her corneas bilaterally. She was diagnosed with severe NK and ocular surface disease caused by dry eye. Treatment included the application of therapeutic soft contact lenses and punctual occlusion; however, both treatments had a limited effect. CONCLUSION: Patients with APS-1 may have ocular surface disease and severe damage to corneal nerves. Regular follow-up and treatment focusing on the regeneration of corneal nerves is particularly important in these patients.

Epithelial basement membrane dystrophy after femtosecond laser-assisted LASIK successfully treated with in vivo confocal microscopy-assisted photorefractive keratectomy.

Photorefractive keratectomy (PRK) was performed to treat corneal epithelial basement membrane dystrophy (EBMD) found after femtosecond laser-assisted laser in situ keratomileusis (FS-LASIK) in a 29-year-old man with previous silent cornea. The patient was diagnosed with post-FS-LASIK EBMD by slitlamp examination and in vivo confocal microscopy (IVCM). Initial treatment with topical lubricants and alcohol soaking was unsuccessful, and the patient continued to have blurred vision and discomfort. The patient underwent a PRK procedure, and the symptoms resolved dramatically; residual refractive errors were also corrected. IVCM revealed a characteristic presentation of EBMD before PRK and normal corneal epithelium after treatment. Patients with asymptomatic EBMD might suffer from recurrent corneal erosions after FS-LASIK. Surface ablation including PRK might lead to successful treatment outcomes, and IVCM might provide helpful information before and after treatment.

Using optical coherence tomography to assess the role of age and region in corneal epithelium and palisades of vogt.

Using spectral-domain optical coherence tomography (OCT) to observe the morphology and epithelial thickness (ET) of the palisades of Vogt (POV), and to evaluate the role of age and region on these structures.One hundred twelve eyes of 112 healthy subjects were enrolled and divided into 4 groups: A (0-19), B (20-39), C (40-59), and D (≥60 years old). RTvue-100 OCT was applied on the cornea and the limbus. The morphology of the subepithelial stroma underneath the epithelium of POV was classified into typical and atypical types. Maximum ET of POV was measured manually from OCT images.The positive rate of typical POV in superior, nasal, temporal, and inferior limbus was: Group A: 100%, 69.2%, 65.4%, 100%; Group B: 100%, 73.5%, 61.8%, 94.1%; Group C: 95.8%, 41.7%, 37.5%, 83.3%; Group D: 67.9%, 0%, 3.6%, 25%, showing a significant decreasing tendency with age. The maximum ET of POV in superior, nasal, temporal, and inferior limbus was: Group A: 103.5 ±â€Š10.1 um, 89.2 ±â€Š9.7 um, 87.9 ±â€Š13.6 um, 104.7 ±â€Š14.1 um; Group B: 111.4 ±â€Š15.8 um, 85.3 ±â€Š9.9 um, 88.2 ±â€Š8.6 um, 112.6 ±â€Š19.7 um; Group C: 116.4 ±â€Š16.4 um, 82.8 ±â€Š11.6 um, 87.0 ±â€Š11.6 um, 120.0 ±â€Š25.6 um; Group D: 96.3 ±â€Š17.9 um, 73.8 ±â€Š15.9 um, 79.2 ±â€Š16.7 um, 87.4 ±â€Š18.5 um. Age-dependent change was observed. In general, the maximum ET of POV in superior/inferior quadrants was thicker than the other 2 quadrants.Spectral-domain OCT is a useful tool to observe the limbal microstructure and provide invaluable information. Aging and anatomic regions had significant effects on the microstructure of these areas.

Aspheric Ablation Depth as the Target Depth for Enhanced Wavefront-Guided Myopic Retreatments After Laser-Assisted In Situ Keratomileusis.

PURPOSE: To propose a new adjustment method and present the clinical result of wavefront-guided myopic laser-assisted in situ keratomileusis (LASIK) retreatment with an aspheric program-targeted central ablation depth to avoid refractive overcorrection. METHODS: Thirty-two eyes (of 20 consecutive patients) that underwent wavefront-guided LASIK myopic retreatment between January 2009 and February 2012 after primary wavefront-guided LASIK for myopia were included. Wavefront-guided retreatments were performed using the Bausch and Lomb Technolas 217z100 excimer laser system. Wavefront-guided retreatments were adjusted by setting the ablation depth corresponding to the ablation depth determined by the aspheric program. The refractive outcome, visual outcome, and outcome of high-order aberrations (HOAs) were analyzed. Linear mixed models were also used to evaluate the predicting factors for retreatment offset. RESULTS: Mean age was 29.5 ± 3.1 years. Spherical equivalent (SE) before retreatment was -1.0 ± 0.44 diopters (D) (range, -2.25 to -0.5). Twelve months postoperatively, SE was -0.03 ± 0.12 D, and 31 of 32 eyes had an uncorrected visual acuity 20/20 or better. All eyes were within ±0.5 D. None of the eyes had lost >2 lines of Snellen visual acuity. Safety and efficacy indices were 1.03 and 1.00, respectively. Total HOA, coma, and trefoil were reduced significantly (P = 0.028, P = 0.036, P = 0.034, respectively). Predictive factors for the amount of offset required are significantly related to preoperative SE (P = 0.006) and spherical aberration (P = 0.03, adjusted by SE). CONCLUSIONS: Setting the target ablation depth using the aspheric program provided high refractive predictability with a satisfactory visual outcome, significant reduction of HOAs, and no overcorrections.

Changes of Ocular Surface and the Inflammatory Response in a Rabbit Model of Short-Term Exposure Keratopathy.

PURPOSE: To evaluate the ocular surface change and the inflammatory response in a rabbit model of short-term exposure keratopathy. METHODS: Short term exposure keratopathy by continuous eyelid opening was induced in New Zealand white rabbits for up to 4 hours. Ultrasound pachymetry was used to detect central total corneal thickness. In vivo confocal microscopy and impression cytology were performed to evaluate the morphology of ocular surface epithelium and the infiltration of inflammatory cells. Immunohistochemistry for macrophage,neutrophil, CD4(+) T cells, and CD8(+) T cells were performed to classify the inflammatory cells. Scanning electron microscopy(SEM) was performed to detect ocular surface change.The concentrations of IL-8, IL-17, Line and TNF-αwere analyzed by multiplex immunobead assay. TUNEL staining was performed to detect cellular apoptosis. RESULTS: Significant decrease ofcentral total cornealthickness were found within the first 5 minutes and remained stable thereafter, while there were no changes of corneal epithelial thickness.No significant change of corneal, limbal and conjunctival epithelial morphology was found by in vivo confocal microscopy except the time dependent increase of superficial cellular defects in the central cornea. Impression cytology also demonstrated time dependent increase of sloughing superficial cells of the central cornea. Aggregations ofinflammatory cells were found at 1 hour in the limbal epithelium, 2 hours in the perilimbal conjunctival epithelium, and 3 hours in the peripheral corneal epithelium.In eyes receiving exposure for 4 hours, the infiltration of the inflammatory cells can still be detected at 8 hours after closing eyes.Immunohistochemical study demonstrated the cells to be macrophages, neutrophils, CD4-T cells and CD-8 T cells.SEM demonstrated time-depending increase of intercellular border and sloughing of superficial epithelial cells in corneal surface. Time dependent increase of IL-8, IL-17 and TNF-α in tear was found.TUNEL staining revealed some apoptotic cells in the corneal epithelium and superficial stroma at 3 hours after exposure. CONCLUSIONS: Short term exposure keratopathy can cause significant changes to the ocular surface and inflammatory response. Decrease of central total corneal thickness, aggregation of inflammatory cells, and cornea epithelial cell and superficial keratocyte apoptosis were found no less than 4 hours following the insult.

In vivo confocal microscopic evaluation of corneal wound healing after epi-LASIK.

PURPOSE: To study the healing of corneal wounds after epikeratome laser-assisted in situ keratomileusis (epi-LASIK). METHODS: Twenty-seven patients who had undergone epi-LASIK for the treatment of myopia or myopic astigmatism in 46 eyes were enrolled. A single intraoperative application of 0.02% mitomycin C (MMC) for 20 to 30 seconds was used in 24 eyes with a refraction of no less than -6.0 D (MMC group). MMC was not given to eyes with myopia less than -6.0 D (non-MMC group). The eyes were examined by in vivo confocal microscopy at 1, 3, and 7 days after surgery and then weekly during the first month and once each at 3 and 6 months. Selected images of the corneal basal-apical surface epithelia and stromal reactions quantified by z-scan profile were evaluated. RESULTS: In vivo confocal microscopy showed that cells in most of the epithelial flaps were damaged during the first few days after surgery and were rapidly replaced by new growing cells. In the MMC and non-MMC groups, the corneal basal epithelial cells returned to their preoperative morphology in 0% and 13.6% of the eyes after 1 week, 37.5% and 36.4% after 2 weeks, and 87.5% and 86.3% after 1 month, respectively. The corneal apical surface epithelial cells in the MMC and non-MMC groups recovered their squamous morphology in 12.5% and 13.6% of the eyes at 2 weeks, 37.5% and 54.5% at 1 month, and 52.4% and 57.9% at 6 months, respectively. There was no difference in the stromal reaction between the groups at 1, 3, and 6 months after surgery. CONCLUSIONS: Damage of the epithelial flaps after epi-LASIK was observed by in vivo confocal microscopy. MMC usage may cause more damage to the epithelial flaps. There was no difference in stromal reaction between the groups with and without MMC.