京都大学 / 新制・課程博士 / 博士(医学) / 甲第24498号 / 医博第4940号 / 新制||医||1064(附属図書館) / 京都大学大学院医学研究科医学専攻 / (主査)教授 中本 裕士, 教授 森本 尚樹, 教授 大森 孝一 / 学位規則第4条第1項該当 / Doctor of Medical Science / Kyoto University / DFAM

Purpose: Quality improvement project to improve diabetic retinopathy education and screening in a rural primary care clinic to meet the standard of care. Aims: To improve the delinquency rate of diabetic retinopathy screening. Processes: Participants included those with type 1 and type 2 diabetes ages 18 and up in the rural health clinic. Diabetic retinopathy screening importance education was displayed in the clinic and provided to each applicable patient in the form of a handout. A diabetic eye camera was brought to the rural health primary care clinic to offer more convenient access and free eye exams to clinic patients with diabetes. The project was deemed quality improvement by the IRB. Results: (To be determined after project implementation – results anticipated to be excellent based on the number of patients who are signed up to participate in this day.) There are 486 patients with a diagnosis of diabetes in the clinic. ___ were delinquent in eye exam prior to implementation and ___ were delinquent after. Limitations: Project performed in only one clinic; project leader is employed at the clinic in this study. Conclusions: Implementation of the eye exam day improved the delinquency rate of diabetic retinopathy screening in the clinic and proved to be a valuable means of enhancing patient compliance and satisfaction of routine eye health monitoring in patients with diabetes.

Healthcare analytics leverages extensive patient data for data-driven decision-making, enhancing patient care and results. Diabetic Retinopathy (DR), a complication of diabetes, stems from damage to the retina’s blood vessels. It can affect both type 1 and type 2 diabetes patients. Ophthalmologists employ retinal images for accurate DR diagnosis and severity assessment. Early detection is crucial for preserving vision and minimizing risks. In this context, we utilized a Kaggle dataset containing patient retinal images, employing Python’s versatile tools. Our research focuses on DR detection using deep learning techniques. We used a publicly available dataset to apply our proposed neural network and transfer learning models, classifying images into five DR stages. Python libraries like TensorFlow facilitate data preprocessing, model development, and evaluation. Rigorous cross-validation and hyperparameter tuning optimized model accuracy, demonstrating their effectiveness in early risk identification, personalized healthcare recommendations, and improving patient outcomes.

Yes / Inequities in access to diabetic retinopathy (DR) services particularly in rural and remote Fiji is concerning. This is because DR when left undiagnosed and untreated for long, can lead to vision loss and permanent blindness. Appropriate channels must be explored to strengthen services and ensure equitable access to healthcare for everyone. This study describes the development and implementation of DR awareness training for community health workers (CHWs) and their subsequent engagement to raise awareness and scale-up DR screening for communities throughout Fiji. As part of a programme to reduce the incidence of avoidable blindness due to diabetes amongst people living in the Pacific, DR training for primary level nurses was developed and implemented. As these primary level nurses were already inundated by clinical duties and competing health priorities, a shifting of the task was proposed to engage the CHWs who would instead educate communities on diabetes and DR and make referrals for DR screening. A one-day DR awareness training was developed and implemented by the Pacific Eye Institute with funding from the Fred Hollows Foundation New Zealand. At the end of the DR programme in 2019, the team had achieved their target and trained a total of 823 CHWs giving an 81.32% coverage of the total 1012 registered CHW in the MHMS register. Anecdotal evidence showed a spike in DR referrals and screenings recorded at health facilities. Three key themes emerged related to the involvement of CHWs which include engagement of CHWs, benefits of the engagement, and health system-related challenges. The use of CHWs who are already integrated into the health system was considered a sustainable intervention to strengthen diabetes and DR services at the primary level of care, particularly if it involves community awareness, health education, and health services facilitation The future of the CHWs will depend on their being integrated more systematically into local health services with strengthened management and supervision. / We acknowledge Fred Hollows Foundation New Zealand for granting this project.

published_or_final_version / Medical Sciences / Master / Master of Medical Sciences

Introduction: Diabetic retinopathy (a diabetes complication that affects eyes) is one of the leading causes of blindness and low vision in the US. More than 90% of vision loss caused by diabetes can be prevented by a routine annual eye examination and early treatment. However, data shows that about half of people with diabetes in the US do not receive the recommended annual eye screening exams, and there is a scarcity of literature assessing the specific role of health insurance. This study aimed to assess if having health insurance had an impact on eye screening. Methods: The nationally representative 2021 Behavioral Risk Factor Surveillance System (BRFSS) was used to examine having an eye exam within the past year among individuals 18 years of age and older who self-reported living with diabetes. Those who reported having some form of health insurance were considered as having access to health insurance and those who reported no, or don’t know or refused or missing responses were considered as having no access to insurance. Meeting the national recommendations of having a dilated eye exam within the past year was the primary outcome of interest. Those who reported having an eye exam within the past year were considered as meeting the recommendations and who reported no, or don’t know or more than one year ago were considered as not having the recommended service. Other independent variables were defined according to the Andersen Model of Healthcare Services Utilization (predisposing factors, enabling factors, need factors, environment, and health behavior. Chi-square analysis and multivariable logistic regression with OR and 95% CI were used to determine the association between eye screening and health insurance adjusting for other covariates. Results and conclusions: Ninety-one percent (91.3%, 53,919) of the adults reported having some form of health insurance, as compared to 8.7%(3,697) who reported having no form of insurance coverage. Approximately 66.2% of the study population had an eye exam at least once within the past year. A higher proportion of adults who had health insurance reported having an eye exam compared to those with no health insurance (68.6 vs. 44.8%; p=0.000). Among those older than 65 years, 73.9% had eye exam as compared to 42.7% among those younger than 35 years (p=$50,000, 71% had eye exam as compared to 59.9% in those earning

No description available.

Made available in DSpace on 2016-01-26T12:51:35Z (GMT). No. of bitstreams: 1 carloseduardocuryjunior_dissert.pdf: 414169 bytes, checksum: 77abecaf5a67d52db441c24d19b9c2af (MD5) Previous issue date: 2010-12-15 / Diabetic retinopathy (DR) is one of the most frequent causes of legal blindness worldwide and the most common microvascular complication of the disease. During the first two decades, almost all patients of type I and more than 60% of the patients of type II have developed the disease. Studies to determinate the prevalence of DR in a certain population are an important measure to delineate screening programs. Objective: To determine the prevalence of Diabetic Retinopathy in public health care units of São José do Rio Preto-SP-Brazil. Material and methods: Population-based cross-sectional study. The study sample, of 710 patients, was derived from the HIPERDIA (Diabetes and High-blood pressure social health care program) of São José do Rio Preto. Participants were also interviewed and examined to determine their demographic characteristics, medical conditions and the realization of previous fundoscopic eye examination All patients, known to have diabetes, underwent an eye examination by indirect ophthalmoscope to check for any signs of DR through dilated pupils.. Statistical studies were done with t-Student test, Fisher test or chi-square test.. Results: The prevalence of DR were 16,3%. Patients were divided in two groups: Group I, patients with DR 112 (16,3%) and Group II , patients without microvascular complication of diabetes 597 (83,7%) . In Group I 90 (80,4%) demonstrated non-proliferative and (22) 19,6% with proliferative diabetic retinopathy. Only 143 patients (68,7%) had a history of previous fundoscopic eye examination. Conclusions: The prevalence of DR in São José do Rio Preto is 16,3%. The main risk factors associated with DR were time of disease and glicemic control. Type of DM and nephropathy were considered secondary risk factors. The presence of high blood pressure, in this study, was not a risk factor associated with DR. / A retinopatia diabética (RD) é uma das principais causas de cegueira em todo o mundo e a principal complicação microvascular da doença. Durante as duas primeiras décadas da evolução da doença, praticamente todos os pacientes com diabetes do tipo 1 e mais de 60% dos pacientes com diabetes do tipo 2 desenvolvem retinopatia. Estudos para determinar a prevalência da RD em uma determinada população são uma importante medida. Estes facilitam o planejamento de campanhas para a prevenção e a detecção da doença.Objetivo: Determinar a prevalência e o estadiamento da retinopatia diabética (RD) em unidades básicas de saúde de São José do Rio Preto-SP - Brasil.Casuística e métodos: Estudo epidemiológico descritivo transversal, no qual foram examinados 710 pacientes diabéticos, cadastrados no programa HIPERDIA (Hipertensos e Diabéticos) da Secretaria Municipal de Saúde de SJRP. Os pacientes responderam a questionário, que incluía: idade, tempo de duração do diabetes, medicação utilizada para o controle glicêmico, tratamento para hipertensão arterial sistêmica, hiperlipidemia ou nefropatia e realização de exame fundoscópico prévio. Os dados complementares, como o valor da HbA1c e como o tipo do diabetes (tipos 1 ou 2), foram extraídos dos respectivos prontuários. Após a dilatação pupilar, foi realizado o exame de fundo de olho, por oftalmoscopia indireta. Os métodos estatísticos utilizados para a análise foram: teste t-Student, teste de Fisher ou teste qui-quadrado. Em todos os testes estatísticos, o nível de significância adotado foi de 5%.Resultados: A prevalência da RD foi de 16,3%. Os pacientes estudados foram divididos em dois grupos: Grupo I, de pacientes com RD 112 (16,3%) e Grupo II, de pacientes sem a complicação microvascular do diabetes 597 (83,7%). Com relação à classificação da RD, apresentada pelos pacientes do Grupo I, verificou-se que noventa (80,4%) dos pacientes apresentaram a forma não proliferativa da doença (RDNPF). Do total de pacientes, 68,7% foram anteriormente submetidos ao exame de fundoscopia. Conclusões: A prevalência da RD, em São José do Rio Preto, está estimada em 16,3%. Os principais fatores de risco associados à RD foram o tempo de doença e o controle glicêmico. O tipo de DM e a presença de nefropatia foram considerados fatores de risco secundários para o desenvolvimento da RD. Neste estudo, a presença de HAS não foi considerada fator de risco associado a RD.

[EN] The World Health Organization estimates that in 2010 there were 285 million people visually impaired in the world. It is calculated that the 80\% of these cases are preventable or treatable. In addition, aging population and chronic disease increase are two factors that predict a higher number of blindness cases in the future. Hypertension, diabetic retinopathy (DR), age-related macular degeneration (AMD) and glaucoma are the most common pathologies in the current society that provoke retinal damage and can be directly related to blindness and vision loss. The early diagnosis of these diseases allows, through appropriate treatment, to reduce costs generated when they are in advanced states and may become chronic. This fact justifies screening campaigns. However, a screening campaign requires a heavy workload for trained experts in the analysis of anomalous patterns of each disease, which in addition to the increase of population at risk, makes these campaigns economically unfeasible. Therefore, the need of automatic screening system developments is highlighted. The final goal of this thesis is the implementation of novel methods that allow the analysis and processing of fundus images to implement an automatic screening of four of the most important diseases that affect world population. In particular, the main objective of the thesis is to build up algorithms for the characterization of the retinal structures and the retina background in order to assist in the discrimination between a ``normal" and pathological retina. Mathematical morphology along with other operators are used for the detection of the retinal vessels and the optic disk. The proposed methods work properly on databases with a large degree of variability. Not only have the main structures been segmented, but significant features have also been extracted from them to be used in a computer aided diagnosis software for hypertensive risk determination. The texture of the retina background is also analyzed in this work by means of local binary patterns with the aim of identifying DR and AMD and avoiding the need of segmentation of the characteristic retinal lesions of each disease. The results are promising above all for AMD diagnosis. / [ES] La Organización Mundial de la Salud estima que en 2010 había 285 millones de personas con alguna discapacidad visual en el mundo. Se calcula que el 80\% de estos casos son evitables o tratables. Además, el envejecimiento de la población y el aumento de las enfermedades crónicas son dos factores que hacen prever un número todavía mayor de casos de ceguera en el futuro. La hipertensión, la retinopatía diabética (RD), la degeneración macular asociada a la edad (DMAE) y el glaucoma son las enfermedades más comunes que provocan daños en la retina y, por tanto, están directamente relacionadas con la ceguera y con la pérdida de visión. El diagnóstico de estas enfermedades en estadios tempranos permite, mediante el tratamiento adecuado, reducir los costes que generan en estados ya avanzados y que en la mayoría de los casos acaban convirtiéndose en crónicas, lo que justifica la realización de campañas de cribado. Sin embargo, una campaña de cribado exige una gran carga de trabajo de personal experto entrenado en el análisis de los patrones anómalos propios de cada enfermedad, lo que sumado al aumento de la población de riesgo, hace que estas campañas sean inviables económicamente. Por lo tanto, se evidencia la necesidad del desarrollo de sistemas de cribado automáticos. El objetivo final del presente trabajo es la implementación de métodos novedosos de análisis de imágenes de fondo de ojo para usarlos en un sistema de cribado de cuatro de las enfermedades más importantes que afectan a la población actual. En concreto, el objetivo principal de la tesis es el desarrollo de algoritmos para la caracterización de las estructuras y del fondo retiniano, los cuales servirán de ayuda para discriminar una retina ``normal" de otra patológica. Para la detección de los vasos retinianos y del disco óptico, se ha usado morfología matemática además de otros operadores. Se ha demostrado que los métodos propuestos para este fin funcionan adecuadamente en bases de datos con un alto grado de variabilidad. No sólo se han segmentado las principales estructuras retinianas, sino que, además, se han extraído sus características más significativas para determinar el riesgo hipertensivo. En este trabajo, también se han analizado las texturas presentes en el fondo de la retina por medio de la teoría de los patrones binarios locales con el objetivo de identificar la RD y la DMAE a la vez que se evita la necesidad de la segmentación de las lesiones específicas de cada enfermedad. Los resultados son prometedores, sobre todo, para la detección de la DMAE. / [CAT] L'Organització Mundial de la Salut estima que en 2010 havia 285 milions de persones amb alguna discapacitat visual en el món. Es calcula que el 80\% d'aquests casos són evitables o tractables. A més, l'envelliment de la població i l'augment de les malalties cròniques són dos factors que fan preveure un número encara major de casos de ceguera en el futur. La hipertensió, la retinopatia diabètica (RD), la degeneració macular associada a l'edat (DMAE) i el glaucoma són les malalties més comuns que provoquen danys en la retina i, per tant, estan directament relacionades amb la ceguera i amb la pèrdua de visió. El diagnòstic d'aquestes malalties en estadis primerencs permet, per mitjà del tractament adequat, reduir els costos que generen en estats ja avançats i que en la majoria dels casos acaben convertint-se en cròniques, la qual cosa justifica la realització de campanyes de garbellament. No obstant això, una campanya de garbellament exigix una gran càrrega de treball de personal expert entrenat en l'anàlisi dels patrons anòmals propis de cada malaltia, que si es suma a l'augment de la població de risc, fa que aquestes campanyes siguen inviables econòmicament. Per tant, s'evidencia la necessitat del desenrotllament de sistemes de garbellament automàtics. L'objectiu final del present treball és la implementació de mètodes nous d'anàlisi d'imatges de fons d'ull per a usar-los en un sistema de garbellament de quatre de les malalties més importants que afecten la població actual. En concret, l'objectiu principal de la tesi és el desenvolupament d'algoritmes per a la caracterització de les estructures i del fons retinià, els quals serviran d'ajuda per a discriminar una retina ``normal" d'una altra patològica. Per a la detecció dels vasos retinians i del disc òptic, s'ha usat morfologia matemàtica a més d'altres operadors. S'ha demostrat que els mètodes proposats per a aquest fi funcionen adequadament en bases de dades amb un alt grau de variabilitat. No sols s'han segmentat les principals estructures retinianes, sinó que, a més, s'han extret les seues característiques més significatives per a determinar el risc hipertensiu. En aquest treball, també s'han analitzat les textures presents en el fons de la retina per mitjà de la teoria dels patrons binaris locals amb l'objectiu d'identificar la RD i la DMAE al mateix temps que s'evita la necessitat de la segmentació de les lesions específiques de cada malaltia. Els resultats són prometedors, sobretot, per a la detecció de la DMAE. / Morales Martínez, S. (2015). Fundus characterization for automatic disease screening through retinal image processing [Tesis doctoral]. Editorial Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/53933 / TESIS

published_or_final_version / abstract / Anatomy / Doctoral / Doctor of Philosophy