Residual Partial Least Squares Learning: Brain Cortical Thickness Simultaneously Predicts Eight Non-pairwise-correlated Behavioural and Disease Outcomes in Alzheimer's Disease.

Alzheimer's Disease (AD) is the leading cause of dementia. It results in cortical thickness changes and is associated with a decline in cognition and behaviour. Such decline affects multiple important day-to-day functions, including memory, language, orientation, judgment and problem-solving. Recent research has made important progress in identifying brain regions associated with single outcomes, such as individual AD status and general cognitive decline. The complex projection from multiple brain areas to multiple AD outcomes, however, remains poorly understood. This makes the assessment and especially the prediction of multiple AD outcomes - each of which may unveil an integral yet different aspect of the disease - challenging, particularly when some are not strongly correlated. Here, uniting residual learning, partial least squares (PLS), and predictive modelling, we develop an explainable, generalisable, and reproducible method called the Residual Partial Least Squares Learning (the re-PLS Learning) to (1) chart the pathways between large-scale multivariate brain cortical thickness data (inputs) and multivariate disease and behaviour data (outcomes); (2) simultaneously predict multiple, non-pairwise-correlated outcomes; (3) control for confounding variables (e.g., age and gender) affecting both inputs and outcomes and the pathways in-between; (4) perform longitudinal AD disease status classification and disease severity prediction. We evaluate the performance of the proposed method against a variety of alternatives on data from AD patients, subjects with mild cognitive impairment (MCI), and cognitively normal individuals (n=1,196) from the Alzheimer's Disease Neuroimaging Initiative (ADNI). Our results unveil pockets of brain areas in the temporal, frontal, sensorimotor, and cingulate areas whose cortical thickness may be respectively associated with declines in different cognitive and behavioural subdomains in AD. Finally, we characterise re-PLS' geometric interpretation and mathematical support for delivering meaningful neurobiological insights and provide an open software package (re-PLS) available at https://github.com/thanhvd18/rePLS.

Comparison of non-pharmaceutical treatments for evaporative dry eye: a randomised controlled study protocol.

INTRODUCTION: The lipid layer of the tear film is critical to maintaining the integrity of the tear film and absence in the tear film lipid layer (TFLL) is one of the main causes of evaporative dry eye (EDE) in dry eye disease patients, resulting in excessive evaporation (so-called hyperevaporative dry eye). This study protocol will be designed to assess and compare the effects of intense pulsed light (IPL), heated eye mask (HEM), vectored thermal pulsation system (VTPS) and eyelid massage device (EMD) for improving signs and symptoms of EDE. METHODS AND ANALYSIS: Patients with EDE will be randomly divided into IPL, HEM, VTPS and EMD groups and will be followed up for 6 weeks. The primary outcome measure will be non-invasive tear breakup time (NITBUT). The secondary outcome measures will include, TFLL score, meibomian gland quality and expressibility change from baseline conjunctivocorneal staining with fluorescein and lissamine, tear meniscus height, conjunctival hyperaemia (redness score) and ocular surface disease index questionnaire. Additionally, adverse events will be monitored and documented. ETHICS AND DISSEMINATION: Ethics approval number: IRB(2023)K019.01. The findings will be shared regardless of the effect's direction. TRIAL REGISTRATION NUMBER: NCT05923528.

A Novel Method for the Measurement of Retinal Arteriolar Bifurcation.

INTRODUCTION: The purpose of this research was to develop protocols for evaluating the bifurcation parameters of retinal arteriole and establish a reference range of normal values. METHODS: In this retrospective study, we measured a total of 1314 retinal arteriolar bifurcations from 100 fundus photographs. We selected 200 from these bifurcations for testing inter-measurer and inter-method agreement. Additionally, we calculated the normal reference range for retinal arteriolar bifurcation parameters and analyzed the effects of gender, age, and anatomical features on retinal arteriolar bifurcation. RESULTS: The measurement method proposed in this study has demonstrated nearly perfect consistency among different measurers, with interclass correlation coefficient (ICC) for all bifurcation parameters of retinal arteriole exceeding 0.95. Among healthy individuals, the retinal arteriolar caliber was narrowest in young adults and increased in children, teenagers, and the elderly; retinal arteriolar caliber was greater in females than in males; and the diameter of the inferior temporal branch exceeded that of the superior temporal branch. The angle between the two branches of retinal arteriolar bifurcation was also greater in females than in males. When using the center of the optic disc as a reference point, the angle between the two branches of the retinal arteriole at the proximal or distal ends increased. In contrast, the estimated optimum theoretical values of retinal arteriolar bifurcation were not affected by these factors. CONCLUSIONS: The method for the measurement of retinal arteriolar bifurcation in this study was highly accurate and reproducible. The diameter and branching angle of the retinal arteriolar bifurcation were more susceptible to the influence of gender, age, and anatomical features. In comparison, the estimated optimum theoretical values of retinal arteriolar bifurcation were relatively stable. Video available for this article.

Association of 10 Genetic Variations and 10 Environmental Factors with Myopia of Different Severities in Different Age Groups of People in Northeast China.

BACKGROUND: To investigate the association of 10 genetic variations and 10 environmental factors with myopia of different severities in different age groups of children and adolescents in northeast China. METHODS: Parental history and genetic testing for myopia-related susceptibility genes were carried out in a cohort of children and adolescents aged 2-17 years. In addition, 10 single nucleotide polymorphism (SNP) sites for genotyping and 10 environmental risk factors were selected, and the differences between site variation and environmental factors in different age groups with different degrees of myopia were explored. RESULTS: A total of 2497 volunteers were recruited, including 2023 myopes and 474 non-myopes in the control group. From the cohort, 1160 subjects were sequenced for myopia SNP sites. Compared with the non-myopic group, the myopia of parents, outdoor activity less than 60 min per day, and a high-sugar diet were risk factors for developing myopia. Two syntrophin beta 1 (SNTB1) sites, rs4455882 and rs6469937 were found to be significantly associated with moderate myopia; fibroblast growth factor 10 (FGF10) rs339501 was significantly correlated with high myopia; and insulin-like growth factor 1 (IGF1) rs5742714 was significantly correlated with different degrees of myopia in the age group of <6 years. Finally, the FGF10 gene rs339501 SNP was significantly associated with moderate myopia and mild myopia in the 6- to 12-year-old age group. CONCLUSIONS: Our results indicate that myopia is affected by both environmental and genetic factors. To prevent and control myopia, attention should be paid to the parental history of myopia, a high-sugar diet should be avoided, and outdoor time should be adjusted according to the average daily sunshine. In addition, it is necessary to pay attention to the increased risk of myopia in school-age children caused by SNTB1 rs4455882, FGF10 rs339501, and IGF1 rs5742714.

A protocol for a single center, randomized, controlled trial comparing the clinical efficacy of 3% diquafosol and 0.1% hyaluronic acid in diabetic patients with dry eye disease.

BACKGROUND: The global prevalence of diabetes mellitus (DM) continues to rise and 70% of diabetic individuals have dry eye disease (DED) that leads to subsequent abnormalities of the corneal epithelium, corneal nerves, tear film, or corneal endothelium. In addition, persons with diabetes produce fewer tear secretions than healthy individuals. While several anti-inflammatory drug-based therapies for dry eye in diabetic individuals are currently being administered, their efficacy has not been studied in detail. Therefore, the aim of this study was to compare the effectiveness of 3% diquafosol (DQS) vs 0.1% hyaluronic acid (HA) eye drops in diabetic dry eye patients. METHODS: This triple-blind randomized, control trial will include 202 diabetic-related DED and will be assigned to DQS (n = 101) and HA (n = 101) one drop, six times per day for 8 weeks. Tear film lipid layer, non-invasive breakup time, conjunctivocorneal staining score, corneal sensitivity, tear MMP-9 levels, meibomian gland expression and quality, tear meniscus height, corneal nerves, immune/inflammatory cell change, conjunctival hyperemia, and ocular surface disease index questionnaire score will be assessed and compared at baseline, week 4, and week 8. DISCUSSION: This study will be a standardized, scientific, clinical trial designed to evaluate the therapeutic effects and safety of DQS and HA for diabetic dry eye treatment. TRIAL REGISTRATION: ClinicalTrials.govNCT05682547. Registered on December 05, 2022.

Protocol for a parallel assignment prospective, randomised, double-blinded, placebo-controlled trial to evaluate the efficacy of 0.01% atropine for near work-induced transient myopia and myopic progression in China.

INTRODUCTION: Assessment of near work-induced transient myopia (NITM) is important for permanent myopia development and progression. Atropine eye drop has been reported to be beneficial in reducing initial NITM and slowing down myopic progression. This study aimed to investigate the efficacy of 0.01% atropine in treating NITM and its possible association with the progression of refractive change in Chinese myopic children. METHODS AND ANALYSIS: The study is designed as a parallel assignment prospective, randomised, double-blinded, placebo-controlled trial conducted at He Eye Specialist Hospital in Shenyang, China. One hundred fifty participants will be randomly assigned in a 1:1 ratio to receive 0.01% atropine or placebo eye drop once nightly bilaterally for 1 year. Initial NITM, cycloplegic refraction, axial length, best-corrected visual acuity, intraocular pressure and pupil diameter will be measured at baseline, 4 weeks, 12 weeks, 24 weeks, 36 weeks and 48 weeks. Visual Function Questionnaire will be administered at baseline and each follow-up visit. Adverse events also will be monitored and documented at each subsequent follow-up visit. ETHICS AND DISSEMINATION: A parallel assignment prospective, randomised, double-blinded, placebo-controlled trial to evaluate the efficacy of 0.01% atropine for near work-induced transient myopia and myopic progression registered on 10 September 2023. Ethics approval number: IRB (2023) K025.01. The study's findings will be shared regardless of the effect's direction. TRIAL REGISTRATION NUMBER: NCT06034366.

Effects of Diquafosol Sodium Ophthalmic Solution on Tear Film Matrix Metallopeptidase-9 and Corneal Nerve Density in Patients with Type 2 Diabetic Dry Eye.

Purpose: Diabetes mellitus has been associated with increased dry eye disease (DED) and exacerbates DED's pathology. This preliminary short-term study aimed to evaluate the effects of 3% Diquafosol Sodium ophthalmic solution (DQS) on ocular surface inflammation and corneal nerve density in diabetic dry eye (DDE) patients. Methods: In this perspective, participants used 1 drop of 3% DQS (Diquas; Santen Pharmaceutical Co., Ltd., Osaka, Japan) 6 times daily for 8 weeks. Non-invasive tear breakup time (NITBUT), tear film lipid layer (TFLL), conjunctival hyperemia [redness score (RS)], corneoconjunctival staining (CFS), corneal sensitivity (CS), Meibomian gland quality (MGQ) and Meibomian gland expressibility (MGEx), corneal nerve fiber density (CNFD), and Standard Patient Evaluation Eye Dryness (SPEED) questionnaire were assessed at baseline, at weeks 4, and up to 8 weeks. Matrix metalloproteinase-9 (MMP-9) of tear samples was measured at baseline and weeks 8. Results: The mean age was 61.27 ± 11.68 years. At baseline NITBUT = 5.89 ± 2.81 s, tear meniscus height = 0.17 ± 0.05 mm, TFLL = 2.74 ± 0.51, CFS = 4.35 ± 0.68, CS = 53.83 ± 9.63 mm, MMP-9 = 49.10 ± 10.42 ng/mL, RS = 1.65 ± 0.44, MGEx = 1.85 ± 0.72, MGQ = 2.65 ± 0.50, CNFD = 20.36 ± 8.20 no./mm2, and SPEED = 12.62 ± 3.91. At week 4, significant improvements were found in all parameters except RS (1.59 ± 0.46, P = 0.172) and CNFD (21.46 ± 8.41, P = 0.163). Finally, at week 8, all parameters had significant improvements. Conclusion: Preliminary short-term findings suggest that treatment of DDE patients with DQS was found to be safe and efficacious in improving dry eye parameters. In addition, inflammatory marker and corneal nerve density were significantly improved. This study was registered with ClinicalTrials.gov (NCT05193331).

Effects of insomnia on symptomatic dry eye during COVID-19 in China: An online survey.

Sleep is an essential determinant of health and quality of life. This study aimed to evaluate sleep disorders and symptomatic dry eye (DE) occurrence. This study was a cross-sectional survey of 1393 participants in China. The insomnia severity index (ISI) Questionnaire was used to evaluate sleep quality, and the ocular surface disease index (OSDI) questionnaire was used to assess DE symptoms. Subjects were divided into 2 groups based on subjects with and without symptomatic DE. The patients who had DE (10.48 ±â€…7.27) had substantially lower ISI scores compared to those without DE (3.57 ±â€…5.10) (P = .003). Furthermore, each ISI item and total ISI score was significantly correlated with OSDI dry eye severity and total OSDI dry eye score. Higher prevalence of insomnia was found in participants with symptomatic DE, and insomnia correlated significantly with DE symptoms. The present results suggest that clinicians and healthcare workers need to remember that DE and insomnia are highly co-existing health issues.

The influence of pupil diameter upon and subjective quality of vision following implantable collamer lens (ICL V4c) implantation: An observational study.

This study aimed to assess the change in pupil size and its influence on subjective quality of vision (QoV) in subjects with implanted collamer lenses (ICLs). This retrospective study assessed 53 participants (53 eyes) implanted with ICL (V4c) and categorized them into incremental groups according to pupil diameter. Preoperative and postoperative photopic and mesopic pupil diameter, uncorrected distance visual acuity (UDVA), and QoV questionnaire scores were assessed and compared. Postoperatively, at 3 months, UDVA was -0.10 ± 0.06 logarithm of the minimum angle of resolution (LogMAR), and mean QoV for day and night was 9.34 ± 0.76 and 8.58 ± 1.29, respectively. The mean mesopic and photopic pupil diameters were 6.59 ± 0.79 mm and 4.61 ± 0.74 mm, respectively. Photopic pupil diameter negatively correlated with "QoV day" (Rs = -0.413, P = .001), positively correlated with "haloes" (Rs = 0.568*, P < .001) and "blurred vision" (Rs = 0.243, P = .04) respectively. Mesopic pupil diameter negatively correlated with "QoV night" (Rs = -0.426, P = .001), positively correlated with "haloes" (Rs = 0.624*, P < .001), "starburst" (Rs = 0.233, P = .046) and "difficulty focusing" (Rs = 0.27, P = .025), respectively. Participants had excellent VA at 3-month follow-up. Photopic and mesonic pupil diameter negatively correlated with QoV day and QoV night scores, respectively. Pupil diameter was found to have a more significant effect on visual symptoms at night, and lower QoV due to larger pupil size was more noticeable at night. Further investigation is needed to explore the importance of pupil diameter and its impact on the QoV in ICL implanted patients.

Relationship between ocular surface pain and corneal nerve loss in dry eye diabetics: a cross-sectional study in Shenyang, China.

BACKGROUND: Diabetes mellitus has been associated with increased dry eye disease (DED) and exacerbates DED pathology. OBJECTIVE: To investigate the potential relationship between corneal nerve loss and ocular pain among diabetic patients with dry eye (DE). DESIGN: A cross-sectional study. SETTING: He Eye Specialist Hospital, Shenyang, China. PARTICIPANTS: This study recruited 124 eyes of 62 diabetic patients diagnosed with DED between August and October 2022. MAIN OUTCOME MEASURES: Best-corrected visual acuity, intraocular pressure, non-invasive tear breakup time, tear meniscus height, tear film lipid layer, conjunctival hyperaemia (redness score), conjunctivocorneal epithelial staining (CS score), central corneal sensitivity and vitro confocal corneal microscopy was assessed in all subjects. The Ocular Surface Disease Index Questionnaire assessed DE symptoms and ocular pain. RESULTS: The study's final analysis included 26 patients (52 eyes) without ocular pain and 36 patients (72 eyes) with ocular pain. The corneal nerve fibre density (CNFD), corneal nerve branch density (CNBD) and corneal nerve fibre length (CNFL) in patients with ocular pain were significantly lower than those without (p<0.001, p=0.004, and p<0.001, respectively). CNFD, CNBD and CNFL negatively correlated with ocular pain (r=-0.385, r=-0.260, r=-0.358, respectively). Moreover, CNFD, CNBD and CNFL have a significant (p<0.05) positive correlation with corneal sensitivity (r=0.523, r=0.330, r=0.421, respectively). CONCLUSIONS: Corneal nerve loss was associated with ocular pain and decreased corneal sensitivity in diabetic patients with DE. Further studies into the neurological role of ocular surface diseases can elaborate diagnostics, prognosis and treatment of diabetic patients with DE. TRIAL REGISTRATION NUMBER: ClinicalTrials.gov (NCT05193331).

The Combined Impact of Intense Pulsed Light Combined and 3% Diquafosol Ophthalmic Solution on Evaporative Dry Eye: A Randomized Control Study.

INTRODUCTION: The primary objective of this study is to assess whether the combination of intense pulsed light (IPL) with 3% diquafosol (DQS) ophthalmic solution is more effective than intense pulsed light in alleviating signs and symptoms of dry eye disease (DED). METHODS: This randomized study included 66 participants with evaporative dry eye (EDE) who received IPL + DQS therapy (n = 44 eyes), IPL therapy (n = 44 eyes), or sham therapy (n = 44 eyes). All participants were examined at baseline (D0), day 14 (D14), and day 28 (D28) for non-invasive break-up time (NITBUT), tear-film lipid layer (TFLL), corneal conjunctival staining (CS), meibomian gland quality (MGQ), meibomian gland expression (MGEx), and ocular surface disease index (OSDI). RESULTS: At day 28, comparison among the IPL + DQS therapy, IPL therapy, and sham therapy found significant differences in the mean NITBUT (12.03 ± 1.27 versus 10.47 ± 3.48 versus 4.57 ± 0.46; p < 0.001), TFLL (2.09 ± 0.29 versus 2.27 ± 0.45 versus 2.89 ± 0.65; p < 0.001), CS (1.43 ± 0.82 versus 1.93 ± 1.32 versus 3.52 ± 1.00; p < 0.001), MGQ (1.55 ± 0.66 versus 1.91 ± 0.77 versus 2.66 ± 0.53; p < 0.001), MGEx (1.27 ± 0.45 versus 1.75 ± 0.44 versus 2.41 ± 0.50; p < 0.001), and OSDI score (19.36 ± 7.01 versus 24.77 ± 4.68 versus 42.61 ± 7.49; p < 0.001); significant improvements in NITBUT, TFLL, CS, MGQ, MGEx, and OSDI were found in the IPL + DQS therapy and IPL therapy, while the sham therapy had no significant improvements. CONCLUSION: Combining 3% diquafosol ophthalmic solution with intense pulsed light was superior to IPL therapy alone in relieving the signs and symptoms of patients with severe evaporative DED. TRIAL REGISTRATION: Clinical Trials Identifier: NCT05694026.

Tear Film Lipid Layer Changes Following Combined Effect of Heated Eye Mask with Intense Pulsed Light Therapy for Evaporative Dry Eye: A Randomized Control Study.

Background: Dry eye disease (DED) is a complex ocular surface inflammatory disorder with a multifactorial etiology. Therapies such as intense pulsed light (IPL) and heated eye mask (HEM) have been reported to improve the tear film lipid layer (TFLL) and signs and symptoms of DED. Methods: This randomized study aimed to compare the effects of IPL combined with HEM (IPL+HEM) group, IPL group, and control group in participants with evaporative DED. All participants were examined at baseline (D0), day 21 (D21), day 42 (D42), and day 84 (D84) for noninvasive tear breakup time (NITBUT), TFLL, corneal conjunctival staining (CS), meibomian gland quality (MGQ), meibomian gland expressibility (MGEx), and Ocular Surface Disease Index (OSDI). Results: The mean age of participants was IPL+HEM: 28.06 ± 3.88 years, IPL: 29.88 ± 4.68 years, and control: 28.52 ± 3.77 years. At D84, significant improvements in TFLL (p < 0.05), noninvasive tear breakup time (NITBUT) (p < 0.05), corneoconjunctival staining (CS) (p < 0.05), MGQ (p < 0.05), MGEx (p < 0.05), and OSDI (p < 0.05) were found in the IPL+HEM and IPL groups, whereas the control group had no significant improvements. Furthermore, ΔTFLL significantly correlated with ΔNITBUT (r = -0.678, p < 0.001), ΔCS (r = 0.321, p < 0.001), ΔMGQ (r = 0.669, p < 0.001), ΔMGEx (r = 0.598, p < 0.001), and ΔOSDI score (r = 0.649, p < 0.001). Conclusions: IPL therapy in combination with HEM and IPL therapy only can significantly improve the quality of TFLL and clinically reduce the sign and symptoms of evaporative DED. However, IPL therapy in combination with HEM was found to be more effective than IPL therapy alone.

Protocol for a parallel assignment prospective, randomised, comparative trial to evaluate the safety and efficacy of intense pulsed light (IPL) combined with 3% diquafosol (DQS) ophthalmic solution in dry eye syndrome.

INTRODUCTION: Evaporative dry eye (EDE) is common and can lead to ocular pain, decreased visual quality and reduced quality of life. Intense pulsed light (IPL) and 3% diquafosol ophthalmic solution have been found to be beneficial in reducing signs and symptoms of dry eye. METHODS AND ANALYSIS: A randomised clinical trial will be performed at He Eye Specialist Hospital in Shenyang. 360 dry eye disease patients will be equally divided randomly into the IPL group, DQS group (3% diquafosol ophthalmic solution eye-drops) and IPL+group (IPL combined with 3% diquafosol eye-drops). All groups will be followed up for 4 weeks. The primary outcome measures will be the non-invasive tear break-up time and the Ocular Surface Disease Index change from the baseline. The secondary outcome measures willincludeconjunctival and cornea staining with fluorescein and lissamine, meibomian gland function and secretion quality, tear film lipid layer score, tear meniscus height, conjunctival hyperemia (redness score) changes . Adverse events also will be monitored and documented. DISCUSSION: This study aimed to assess whether the combination of IPL with 3% diquafosol ophthalmic solution (study group), IPL+ (study group), is more effective than IPL (active control group) or DQS (active control group) in participants with EDE. ETHICS AND DISSEMINATION: Management of dry eye with IPL combined with 3% diquafosol ophthalmic solution, registered on 23 January 2023. Ethics approval number: IRB (2022) K029.01. The study's findings will be shared regardless of the effect's direction. TRIAL REGISTRATION NUMBER: NCT05694026.

Efficacy of intense pulsed light therapy on signs and symptoms of dry eye disease: A meta-analysis and systematic review.

This study reviewed the efficacy and safety of intense pulsed light (IPL) for the treatment of dry eye disease (DED). The PubMed database was used to conduct the literature search, which used the keywords "intense pulsed light" and "dry eye disease". After the authors evaluated the articles for relevancy, 49 articles were reviewed. In general, all treatment modalities were proven to be clinically effective in reducing dry eye (DE) signs and symptoms; however, the level of improvement and persistence of outcomes differed amongst them. Meta-analysis indicated significant improvement in the Ocular Surface Disease Index (OSDI) scores post-treatment with a standardized mean difference (SMD) = -1.63; confidence interval (CI): -2.42 to -0.84. Moreover, a meta-analysis indicated a significant improvement in tear break-up time (TBUT) test values with SMD = 1.77; CI: 0.49 to 3.05. Research suggests that additive therapies, such as meibomian gland expression (MGX), sodium hyaluronate eye drops, heated eye mask, warm compress, lid hygiene, lid margin scrub, eyelid massage, antibiotic drops, cyclosporine drops, omega-3 supplements, steroid drops, and warm compresses along with IPL, have been found to work in tandem for greater effectiveness; however, in clinical practice, its feasibility and cost-effectiveness have to be taken into consideration. Current findings suggest that IPL therapy is suitable when lifestyle modifications such as reducing or eliminating the use of contact lenses, lubricating eye drops/gels, and warm compresses/eye masks fail to improve signs and symptoms of DE. Moreover, patients with compliance issues have been shown to benefit well as the effects of IPL therapy is sustained for over several months. DED is a multifactorial disorder, and IPL therapy has been found to be safe and efficient in reducing its signs and symptoms of meibomian gland dysfunction (MGD)-related DE. Although the treatment protocol varies among authors, current findings suggest that IPL has a positive effect on the signs and symptoms of MGD-related DE. However, patients in the early stages can benefit more from IPL therapy. Moreover, IPL has a better maintenance impact when used in conjunction with other traditional therapies. Further research is needed to assess cost-utility analysis for IPL.

DeepFundus: A flow-cytometry-like image quality classifier for boosting the whole life cycle of medical artificial intelligence.

Medical artificial intelligence (AI) has been moving from the research phase to clinical implementation. However, most AI-based models are mainly built using high-quality images preprocessed in the laboratory, which is not representative of real-world settings. This dataset bias proves a major driver of AI system dysfunction. Inspired by the design of flow cytometry, DeepFundus, a deep-learning-based fundus image classifier, is developed to provide automated and multidimensional image sorting to address this data quality gap. DeepFundus achieves areas under the receiver operating characteristic curves (AUCs) over 0.9 in image classification concerning overall quality, clinical quality factors, and structural quality analysis on both the internal test and national validation datasets. Additionally, DeepFundus can be integrated into both model development and clinical application of AI diagnostics to significantly enhance model performance for detecting multiple retinopathies. DeepFundus can be used to construct a data-driven paradigm for improving the entire life cycle of medical AI practice.

Managing Severe Evaporative Dry Eye with Intense Pulsed Light Therapy.

INTRODUCTION: This study assessed the efficacy and safety of intense pulsed light (IPL) therapy in participants with severe evaporative dry eye disease (DED). METHODS: This randomized, controlled, single-center study included 49 adult participants (≥ 18 years) with severe evaporative DED who received either IPL therapy (n = 56 eyes) or sham therapy (n = 42 eyes) three times. The primary efficacy parameters were ocular surface disease index (OSDI) score, non-invasive tear breakup time (NITBUT), tear film lipid layer (TFLL), conjunctivocorneal staining score (CS), MG Score, meibomian gland (MG) quality, and MG expression score. RESULTS: The mean ages for the IPL group and the control group were 28.05 ± 3.41 years (57.1% female) and 28.14 ± 3.53 years (52.4% female), respectively. Comparison between the IPL group and the control group found significant differences in the mean OSDI score (22.16 ± 6.08 vs. 42.38 ± 6.60; P < 00.01), NITBUT (6.27 ± 0.84 vs. 3.86 ± 0.68; P < 0.001), TFLL (2.14 ± 0.44 vs. 3.45 ± 0.50; P < 0.001), MG Score (1.34 ± 0.55 vs. 1.88 ± 0.33; P < 0.001), MG quality (1.59 ± 0.07 vs. 2.67 ± 0.08), and MG expression (1.54 ± 0.57 vs. 2.45 ± 0.55) at 12 weeks follow-up; however, there was no significant difference in CS (3.32 ± 1.11 vs. 3.74 ± 1.04; P = 0.063). CONCLUSION: The findings suggest that IPL therapy is clinically beneficial in ameliorating the signs and symptoms of severe evaporative dry eye disease.

Impact of Diquafosol Ophthalmic Solution on Tear Film and Dry Eye Symptom in Type 2 Diabetic Dry Eye: A Pilot Study.

Purpose: Diquafosol ophthalmic solution (DQS) stimulates P2Y2 receptors on the ocular surface, which enhances mucin secretion from goblet cells. Therefore, tear film stability and hydration of the ocular surface can be achieved independent from lacrimal gland function. Methods: This prospective, open-label pilot study included 60 eyes of 30 diabetic patients diagnosed with dry eye disease (DED) and were randomly assigned to either DQS (n = 30 eyes) or hyaluronate (HA) group (n = 30 eyes). Participants in the DQS group received 3% diquafosol ophthalmic solution, whereas HA group received 0.1% sodium HA preservative-free artificial tears. The dosage for both drugs was 1 drop, 6 times per day for 4 weeks. Tear film lipid layer (TFLL), noninvasive breakup time (NITBUT), corneoconjunctival staining (CS) score, meibomian gland (MG), conjunctival hyperemia [redness score (RS)], ocular surface disease index (OSDI) was assessed and compared at baseline, day 14, and day 28. Results: Comparing baseline and day 28 measurements revealed that both groups found significant improvements in NITBUT, CS, MG quality, MG expressibility, and OSDI scores significantly (P < 0.05), in addition TFLL improvements were only found in the DQS group. At day 28, the magnitude of change in mean NITBUT was 1.74 (DQS) versus 0.31 (HA), 1.16 (DQS) versus 0.37 (HA) point grade reduction in corneoconjunctival staining score and 9.80 (DQS) versus 4.80 (HA) point grade in mean OSDI score. Conclusion: Three percent diquafosol ophthalmic solution treatment demonstrated the ability to improve the tear film dry eye parameters and clinically reduced sign and symptoms of DED in diabetic dry eye patients. Clinical Trials.gov ID: NCT04980144.

Tear film interferometry assessment after intense pulsed light in dry eye disease: A randomized, single masked, sham-controlled study.

BACKGROUND: Inadequate meibomian glands (MGs) secretion can lead to dry eye signs and symptoms. Tear film lipid layer (TFLL) secreted by MGs protects and prevents rapid evaporation of tear film. The purpose was to assess TFLL alteration and function in patients with evaporative dry eye (EDE) using tear interferometry after optimal pulse light technology (OPT) intense pulsed light (IPL). METHODS: This prospective randomized examiner-masked sham- controlled study included 86 participants (142 eyes) with DED. IPL or sham procedure was performed on day 0, 21, and 42. Ocular Surface Disease Index (OSDI), non-invasive breakup time (NITBUT), interferometric fringe pattern determined TFLL quality, fluorescein staining (FS), and meibum gland (MG) were assessed at day 0, 21, 42 and 3-month. RESULTS: At 3-month, TFLL, NITBUT, MG drop-out, MG quality, MG expressibility, FS and OSDI improved significantly (P < 0.05) in the IPL group, while the sham group had no significant improvements. Except for Meibo-score and FS, all parameters significantly correlated with the improvement in TFLL following IPL treatment. Additionally, artificial tears usage was significantly less in the IPL group from D-42 onwards. CONCLUSION: IPL treatment demonstrated the ability to improve TFLL quality and clinically reduced sign and symptoms of DED thereby reducing the frequency of artificial tears use.