Hasil Pencarian  ::  Simpan CSV :: Kembali

Hasil Pencarian

Ditemukan 20024 dokumen yang sesuai dengan query
cover
Hanung Adi Nugroho
"World Health Organisation (WHO) has predicted 300 million peoples will suffer of diabetic in 2025. Long-term diabetics can lead to diabetic retinopathy that can cause blindness in developing countries. One of the abnormalities of diabetic retinopathy is exudate. Exudates are classified into two categories, i.e. hard and soft exudates. This paper proposes feature extraction based on texture for distinguishing hard, soft and non-exudates. The green channel of the original images is enhanced by CLAHE and followed by median filtering and thresholding in red channel to detect and remove the optic disc. The enhanced image is segmented based on clustering to obtain the region of interest of exudates. Feature extraction based on texture is conducted by using GLCM and lacunarity. Results show that classification based on NaïveBayes algorithm achieves accuracy, specificity and sensitivity of 92.13%, 96% and 87.18%, respectively."
Depok: Faculty of Engineering, Universitas Indonesia, 2015
UI-IJTECH 6:2 (2015)
Artikel Jurnal  Universitas Indonesia Library
cover
Alif Karnadi Yulvianto
"Retinopati Diabetik adalah salah satu penyakit pada retina disebabkan oleh komplikasi diabetes yang dapat berujung pada kebutaan. Retinopati Diabetik tidak bisa dideteksi langsung secara kasat mata karena tanda-tandanya berada di bagian syaraf retina. Dari beberapa penelitian yang telah dilakukan pendeteksian Retinopati Diabetik dimungkinkan dapat dilakukan dengan melakukan klasifikasi menggunakan data citra retina atau yang biasa disebut sebagai citra fundus.
Dalam penelitian ini diterapkan metode segmentasi citra yaitu Watershed dan Efficient Graph-Based beserta metode klasifikasi yaitu K-Nearest Neighbor dan Support Vector Machine dalam pendeteksian Retinopati Diabetik. Dari hasil implementasi, metode untuk segmentasi Efficient Graph-Based menggunakan data citra fundus dari DIARETDB0 diperoleh nilai akurasi, recall, dan precision lebih tinggi dibandingkan dengan metode segmentasi Watershed.

Diabetic Retinopathy is one of disease on retina because of Diabetic complication that can cause blindness. Diabetic Retinopathy cant detected directly from the eyes because sign of Diabetic Retinopathy itself is in the eyes nerve. From several research that has been done prove that Diabetic Retinopathy can be detected by using retinas image or usually called fundus image.
In this research use segmentation method that is Watershed and Efficient Graph-Based with classification method that is K-Nearest Neighbor and Support Vector Machine for detection of Diabetic Retinopathy. From the implementation result, the Efficient Graph-Based segmentation method using fundus image data from the DIARETDB0 obtained that the accuracy, recall, and precision score is higher than Watershed segmentation method.
"
Depok: Fakultas Matematika dan Ilmu Pengetahuan Alam Universitas Indonesia, 2019
S-Pdf
UI - Skripsi Membership  Universitas Indonesia Library
cover
Pray Somaldo
"ABSTRAK
Diabetik Retinopati adalah kelainan retina akibat komplikasi diabetes yang menyebabkan kebutaan. Seiring berkembangnya teknologi pengolahan citra, pendeteksian Diabetik Retinopati DR dimungkinkan melalui gambar retina yang disebut citra fundus dengan menggunakan ekstraksi ?tur. Dalam penelitian ini, diusulkan metode ekstraksi ?tur menggunakan Gray Level Co-occurrence Matrix GLCM . Penelitian ini mengusulkan sebuah metode dengan enam ?tur tekstur GLCM dengan klasi?kasi Naive Bayes. Dengan menggunakan tiga metode pengujian dan offset GLCM untuk dibandingkan, offset GLCM menghasilkan hasil yang lebih baik dengan accuracy 82.05 pada metode pengujian 70 train 30 test, accuracy 80 pada metode pengujian 5-Fold Cross Validation, accuracy 80.77 pada metode pengujian 10-Fold Cross Validation. Hasil ini akan menjelaskan seberapa akurat Naive Bayes untuk mengklasi?kasikan citra fundus normal atau citra DR.

ABSTRAK
Diabetic Retinopathy is retinal disorders resulting from diabetes complications that lead to blindness. As the development of technology in image processing, detection of Diabetic Retinopathy DR was possible through retinal images called fundus image using feature extraction. In this paper, a feature extraction method using Gray Level Co occurrence Matrix GLCM is proposed. This paper proposed a method with six textural features of GLCM with Naive Bayes classifier. Using three testing methods and offset of GLCM to compare with, the offset of GLCM achieves a better result with an Accuracy of 82.05 for 70 training data and 30 testing data method, Accuracy of 80.00 for 5 fold Cross Validation method, Accuracy of 80.77 for 10 fold Cross Validation method. These results will explain how accurate Naive Bayes to classify normal fundus image or DR fundus image."
2017
S69377
UI - Skripsi Membership  Universitas Indonesia Library
cover
Dian Farikha
"Tujuan: Untuk mengetahui pengaruh suplementasi pycnogenol 150 mg perhari selama 8 minggu terhadap amplitudo dan waktu implisit pada gelombang b dan oscillatory potential (OP) ERG skotopik retinopati diabetik nonproliferatif ringan dan sedang.
Metode: Uji klinik acak tersamar. Empat puluh subjek dengan retinopati diabetik nonproliferatif ringan sedang diacak dan dibagi menjadi dua kelompok, 20 subjek mendapat pycnogenol, 20 subjek mendapat pycnogenol. Pengukuran objektif dilakukan sebelum pemberian suplementasi dan 8 minggu setelahnya, yang meliputi amplitudo gel.b, waktu implisit gel.b, amplitudo sum OP, waktu implisit sum OP .
Hasil: Pada kelompok pycnogenol sebelum perlakuan, amp gel.b 397,9±109,6μV, waktu implisit gel.b 48,7 (44,3-68,2) ms, amp sum OP 193,05 (15,2-498,9) μV dan waktu implisit sum OP 126,18± 7,8ms. Setelah 8 minggu pada kelompok pycnogenol, amp gel.b 396,2±115,7 μV, waktu implisit gel.b 47,8 (43,4-58,4)ms, amp sum OP 228,45 (16,3-511,8) μV dan waktu implisit sum OP 126,2 (118,2-137) ms. Pada kelompok plasebo sebelum intervensi, amp gel.b 349± 79 μV, waktu implisit gel.b 48,7 (44,3-68,2) ms, amp sum OP 101,45 (28,3-301,2) μV dan waktu implisit sum OP 130 (121,6-163,5) ms. Setelah 8 minggu pada kelompok plasebo, amp gel.b 334,65±70,3 μV, waktu implisit gel.b 49,15 (44,3 -68,2) ms, amp sum OP 124,9 (51,3-303,8)μV dan waktu implisit sum OP 130 (121,6-163,5) ms. Tidak terdapat perbedaan bermakna secara statistik pada semua keluaran.
Kesimpulan: Tidak terdapat perbedaan yang bermakna secara statistik parameter amplitudo gel.b, waktu implisit gel.b, amplitudo sum OP, waktu implisit sum OP dari pemberian pycnogenol 150 mg sehari selama 8 minggu pada retinopati diabetik nonproliferatif ringan sedang.

Objective: This study is to evaluate the effect of eight weeks supplementation of 150 mg pycnogenol, to b-wave amplitude, b-wave implicit time, sum Oscillatory Potential (OP) amplitude and sum Oscillatory Potential (OP) implicit time on Electroretinography (ERG) result of mild - moderate nonproliferative diabetic retinopathy (NPDR) patient, compared to plasebo.
Methods: Randomized clinical trial of 40 mild - moderate NPDR patients, which further equally divided into two groups. The b-wave amplitude (amp), b-wave implicite time (it), sum OP amplitude (amp), sum OP implicit time (it) ERG were evaluated before and after eight weeks pycnogenol supplementation
Results:The ERG results of pycnogenol group before intervention were as follows: b wave amp 397,9±109,6μV, b-wave it 48,7 (44,3-68,2) ms, sum OP amp 193,05 (15,2-498,9) μV and sum OP it 126,18± 7,8ms. After 8 weeks in pycnogenol group, b wave amp 396,2±115,7 μV, b wave it 47,8 (43,4-58,4)ms, sum OP amp 228,45 (16,3-511,8) μV and sum OP it 126,2 (118,2-137) ms. Meanwhile in placebo group before intervention, the b wave amp was 349± 79 μV, b-wave it 48,7 (44,3-68,2) ms, sum OP amp 101,45 (28,3-301,2) μV and sum OP it 130,8±8,4 ms. After 8 weeks in placebo group, b wave amp 334,65±70,3 μV, b-wave it 49,15 (44,3 -68,2) ms, sum OP amp 124,9 (51,3-303,8)μV and sum OP it 130 (121,6-163,5) ms. No statistical significant differences in all outcome
Conclusions: No significant differences in b-wave amplitude, b-wave implicite time, sum OP amplitude and sum OP implicit time ERG after 150 mg pycnogenol supplementation for 8 weeks in mild-moderate NPDR compare with placebo."
Jakarta: Fakultas Kedokteran Universitas Indonesia, 2015
T-Pdf
UI - Tesis Membership  Universitas Indonesia Library
cover
Gitalisa Andayani
"Retinopati diabetik (DR) merupakan komplikasi mikrovaskular diabetes melitus (DM). Fenofibrat oral dapat mencegah progresivitas DR dengan mekanisme pengaturan kadar lipid lipid-related dan mekanisme lain nonlipid-related, antara lain dengan mencegah disfungsi endotel, mengurangi inflamasi, dan angiogenesis. Penelitian ini bertujuan mengetahui efek fenofibrat oral terhadap ketebalan makula sentral (CMT) dan volume makula, serta pengaruhnya pada kadar penanda biologis serum disfungsi endotel eNOS, inflamasi (VCAM-1), dan angiogenesis (VEGF) pada penyandang DR dengan dislipidemia.
Penelitian prospektif ini menggunakan disain uji klinis acak tersamar ganda dengan membagi subjek menjadi kelompok intervensi simvastatin dan fenofibrat dan kontrol simvastatin dan plasebo. Penelitian berlangsung sejak Nopember 2016 hingga Oktober 2017, di Klinik Vitreo-retina, Departemen Medik Mata ndash;RSCM Kirana, melibatkan 60 mata dari 30 pasien penyandang DR non-proliferatif NPDR dengan dislipidemia. Penelitian pada tiap subjek dilakukan selama tiga bulan dengan evaluasi klinis, foto fundus, dan spectral domain optical coherence tomography (SD-OCT) makula tiap bulan. Pengukuran kadar eNOS, VCAM-1, dan VEGF, serta HbA1c dan profil lipid dilakukan sebelum dan setelah tiga bulan pengobatan.Sebelum intervensi, pada kedua kelompok tidak didapatkan perbedaan karakteristik demografik, klinik, dan penanda biologis serum. Tidak didapatkan perbedaan bermakna pada CMT kelompok simvastatin fenofibrat 248,0 40,4 m dibandingkan kelompok simvastatin plasebo 265,8 40,8 m, namun CMT lebih rendah secara bermakna pada bulan ke-1 pada kelompok simvastatin fenofibrat. Pada subjek dengan edema makula diabetik DME pemberian simvastatin fenofibrat setelah tiga bulan menunjukkan CMT lebih rendah secara bermakna. Volume makula setelah tiga bulan pemberian obat 10086 886,4 m3 pada kelompok simvastatin fenofibrat dan 10307 1058,6 m3 pada simvastatin plasebo. Perbedaan tersebut tidak bermakna, namun pada subjek dengan regulasi glukosa darah yang baik HbA1c 7 didapatkan volume makula lebih rendah pada bulan ke-2. Kadar penanda biologis serum setelah tiga bulan pemberian obat menunjukkan rerata kadar eNOS dan median VEGF sebesar 3878,8 873,33 pg/mL dan 242,8 86 - 1123,3 pg/mL pada kelompok simvastatin fenofibrat, dibandingkan 4031,2 742,56 pg/mL dan 370 134,8 - 810,6 pg/mL pada kelompok simvastatin plasebo, yang tidak berbeda bermakna, namun penurunan kadar VCAM-1 serum lebih besar secara bermakna pada kelompok simvastatin fenofibrat 50,7 pg/mL, 32,5 - 223,4 pg/mL vs. 40,4 pg/mL, 27,9 - 94,2 pg/mL . Pada subjek dengan kontrol glukosa darah ketat HbA1c 6,5 kadar VEGF 128,7 114,5 - 145,2 pg/mL, lebih rendah secara bermakna dibandingkan 423 86 - 1233,3 pg/mL pada subjek dengan HbA1c > 6,5 .Disimpulkan pemberian simvastatin fenofibrat selama tiga bulan pada subjek DR dengan dislipidemia secara umum tidak menurunkan CMT dan volume makula, namun menurunkan CMT khusus pada subjek DR dengan DME. Pemberian simvastatin fenofibrat pada subjek DR tidak mencegah penurunan kadar eNOS, peningkatan kadar VCAM-1 dan VEGF, namun pengendalian gula darah yang baik dapat mencegah peningkatan kadar VEGF. Simvastatin fenofibrat dapat dipertimbangkan sebagai terapi ajuvan pada penyandang DR dengan DME yang disertai dislipidemia. Pengontrolan glukosa yang baik merupakan manajemen utama pada DR.

Diabetic retinopathy (DR) is a microvascular complication of diabetes mellitus (DM) due to structural and biochemical changes. Previous studies showed that oral fenofibrate prevents DR progression through lipid-regulating and nonlipid-related mechanisms, including preventing endothelial dysfunction, reducing inflammation and angiogenesis. This study aims to investigate the effects of oral fenofibrate on central macular thickness CMT and macular volume, and on specific biomarkers of endothelial dysfunction eNOS, inflammation VCAM-1 , and angiogenesis VEGF in DR individuals with dyslipidemia.
This is a prospective, double-blind randomized clinical trial, with subjects divided into intervention group simvastatin fenofibrate and control group simvastatin placebo. This study was conducted from November 2016 to October 2017 at the Vitreo-retina Clinic, Department of Ophthalmology ndash; RSCM Kirana, involving 60 eyes from 30 non-proliferative DR patients NPDR with dyslipidemia that met inclusion criteria. Each subject was observed for three months, with monthly clinical evaluation, fundus photo, and macular spectral domain optical coherence tomography SD-OCT . Serum eNOS, VCAM-1, and VEGF biomarkers, as well as HbA1c and lipid profile, were examined before and after intervention.Before intervention, there were no differences in demographic and clinical characteristics, and serum biomarker levels between two groups. After three months of treatment, there was no significant difference between CMT in the intervention group and the control group 248 40.4 ? m vs. 265.8 40.8 ? m , but a significantly lower CMT was observed in the intervention group at the first month. There was also a significantly lower CMT compared to the control group 294 39,2 vs 263 24,4, p=0,045 in eyes with diabetic macular edema DME . Macular volume after three-month treatment was 10086 886.4 ? m3 in the intervention group and 10307 1058.6 ? m3 in the control group, this difference was not significant. However, in all subjects with good blood glucose regulation HbA1c 7 , macular volume in the second month was significantly lower compared to subjects with HbA1c > 7 . Serum biologic marker levels after three-month treatment showed no significant difference between control and intervention group, respectively, in mean eNOS 3878.8 873.33 pg/mL vs 4031.2 742.56 pg/mL and median VEGF levels 242.8 86 - 1123.3 pg/mL vs 370 134.8 - 810.6 pg/mL . Nonetheless, the decrease in VCAM-1 level was significantly higher in the intervention group 50.7 pg/mL, 32.5 - 223.4 pg/mL vs. 40.4 pg/mL, 27.9 - 94.2 pg/mL . In subjects with tighter blood glucose control HbA1c 6.5 , serum VEGF level was 128.7 114.5 - 145.2 pg/mL, which was significantly lower compared to 423 86 - 1233.3 pg/mL in subjects with HbA1c > 6.5 .In conclusion, three-month treatment with simvastatin fenofibrate does not reduce CMT and macular volume in overall DR subjects with dyslipidemia, but it reduces CMT in subjects with DME. Simvastatin fenofibrate treatment in DR subjects does not prevent lowering of serum eNOS levels, elevation of VCAM-1 levels, and elevation of VEGF levels, but tight blood sugar control prevents elevation of serum VEGF. Although good glucose control remains the most essential in the management of DR, simvastatin fenofibrate may be considered as adjuvant therapy for DR with dyslipidemia and DME."
Jakarta: Fakultas Kedokteran Universitas Indonesia, 2018
D-pdf
UI - Disertasi Membership  Universitas Indonesia Library
cover
Nourma Nurillah Hayati
"[ABSTRAK
Latar Belakang: Pendidikan kesehatan gigi mulut berperan penting untuk pencegahan komplikasi diabetes terhadap gigi mulut. Tujuan: Mengetahui perbedaan pengetahuan pada penderita diabetes melitus tipe 2 sebelum dan sesudah diberikan edukasi. Metode: Subjek penelitian diberikan perlakuan berupa buku berisi materi komprehensif kesehatan gigi mulut dilakukan evaluasi pra dan pasca perlakuan dengan kuesioner dan hasil evaluasi dianalisis secara statistik. Hasil: Terdapat perbedaan tingkat pengetahuan signifikan sebelum dan sesudah pemberian perlakuan mengenai dampak diabetes terhadap gigi mulut sebesar 30,75%. Kesimpulan: Terdapat perbedaan pengetahuan penderita diabetes melitus tipe 2 saat sebelum dan sesudah edukasi, ditandai dengan peningkatan pengetahuan dampak diabetes terhadap gigi dan mulut.;Background: Oral health education play an important role to prevent oral complications in diabetic people.
ABSTRACT
Objective: To investigate the efficacy of oral health education to increase knowledge of type 2 diabetic patients. Methods: This Respondents were given intervention by using comprehensive booklet then knowledge of both groups was evaluated by questionnaire. Results of questionnaire then analyzed using statistical test. Results: There were significant knowledge improvements of education group remarked by the 30,75% improvement on effects of diabetes towards oral health item. Conclusion: There were differences of knowledge before and after education, marked by effects of diabetes towards oral health, Background: Oral health education play an important role to prevent oral complications in diabetic people. Objective: To investigate the efficacy of oral health education to increase knowledge of type 2 diabetic patients. Methods: This Respondents were given intervention by using comprehensive booklet then knowledge of both groups was evaluated by questionnaire. Results of questionnaire then analyzed using statistical test. Results: There were significant knowledge improvements of education group remarked by the 30,75% improvement on effects of diabetes towards oral health item. Conclusion: There were differences of knowledge before and after education, marked by effects of diabetes towards oral health]"
Fakultas Kedokteran Gigi Universitas Indonesia, 2015
S-Pdf
UI - Skripsi Membership  Universitas Indonesia Library
cover
Putri Anggarani Idham
"ABSTRAK
Edema makula diabetik (EMD) merupakan salah satu penyebab utama kebutaan pada pasien diabetes. Saat ini terapi utama pada pasien edema makula diabetik adalah injeksi intravitreal anti VEGF. Pada beberapa keadaan, hal ini menjadi kendala karena 50% pasien yang menjalani rangkaian injeksi intravitreal anti VEGF memiliki edema makula yang refrakter. Vitrektomi pars plana dan internal limiting membran (ILM) peeling diharapkan dapat menjadi alternatif terapi pada EMD refrakter. Penelitian ini bertujuan menilai hasil terapi tindakan vitrektomi dan ILM peeling pada pasien non proliferative diabetic retiopathy (NPDR) dengan EMD refrakter. Penelitian ini merupakan penelitian uji klinis dengan intervensi single arm. Subjek dengan NPDR dan EMD refrakter menjalani tindakan vitrektomi dan ILM peeling. Nilai ketebalan makula sentral (CMT) dan tajam penglihatan diukur sebelum, 1 bulan, 2 bulan, dan 3 bulan sesudah tindakan. Komplikasi pasca tindakan juga dinilai pada setiap kunjungan yang direncanakan. Rentang usia 62,5 (39-72) tahun, lama menderita diabetes 10 (3-18) tahun, kadar HbA1C 6,4 (5,5 -10,8)%. Nilai CMT sebelum, 1 bulan, 2 bulan dan 3 bulan sesudah tindakan adalah [492,0 (303-895) : 277,5 (97-809) : 264 (147-608) : 264,0 (142-660) µm] (p=<0,001). Tajam penglihatan terbaik adalah [1,02 (0,60-1,30) : 1,04 (0,60-1,70) : 1,06 (0,52-2,00) : 1,04 (0,52-2,00) LogMAR] (p=0,635). Terdapat komplikasi pasca tindakan pada pengamatan bulan kedua meliputi retinal detachment dan macular hole. Pada penelitian ini, tindakan vitrektomi dan ILM peeling pada pasien NPDR dengan EMD refrakter memberikan perubahan CMT yang bermakna. Tidak terdapat perubahan yang bermakna secara statistik pada nilai tajam penglihatan namun mayoritas subjek menunjukkan stabilitas tajam penglihatan.

ABSTRACT
Diabetic macular edema (DME) is one of the leading causes of blindness in diabetic patients. The main therapy of DME, up until now is intravitreal injection of anti-vascular endothelial growth factor (VEGF). In certain situation, medical dilemma appeared as in such circumstances 50% patients that underwent series of intravitreal injection of anti VEGF experienced the refractory DME. Pars plana vitrectomy and internal limiting membrane (ILM) peeling is expected to be an alternative treatment in refractory DME. The aim of this study was to assess the result of vitrectomy and ILM peeling in patients with non-proliferative diabetic retinopathy (NPDR) with refractory DME. This study was a clinical trial with single arm intervention. The patients with NPDR with DME underwent vitrectomy and ILM peeling surgery. The assessment of the central macular thickness (CMT) and the visual acuity was conducted before the treatment and 1 month, 2 months and 3 months after. The complication after the treatment was assessed in each scheduled visit. The average age was 62.5 years old with range of 39-72 years old, the history duration of diabetes mellitus was 10 years (3-18) years, level of HbA1C was 6.4 (5.5-10.8)%. The CMT before treatment, 1 month, 2 months and 3 months after treatment were [492,0 (303-895) : 277,5 (97-809) : 264 (147-608) : 264,0 (142-660) µm] (p=<0,001). The best corrected visual acuity was [1,02 (0,60-1,30) : 1,04 (0,60-1,70) : 1,06 (0,52-2,00) : 1,04 (0,52-2,00) LogMAR] (p=0,635). The recorded complication after the treatment was retinal detachment and macular hole. These complications were found on the 2nd month. This study concluded that there was a significant CMT changes in patients with NPDR and refractory DME who underwent vitrectomy and ILM peeling. There was no statistically significant changes in the visual acuity yet majority of the subjects showed a stable visual acuity after the treatment."
Jakarta: Fakultas Kedokteran Universitas Indonesia, 2019
T58740
UI - Tugas Akhir  Universitas Indonesia Library
cover
Rizka Amalia
"Retinopati diabetik adalah kelainan vaskular retina yang disebabkan oleh diabetes jangka panjang. Deteksi dini retinopati diabetik pada pasien diabetes diperlukan karena tidak ada gejala yang terlihat selama tahap awal penyakit. Para peneliti mengembangkan metode berbasis komputer untuk membantu dokter dalam proses deteksi dini. Dokter dapat menggunakan output dari metode tersebut sebagai pertimbangan dalam mediagnosis tipe retinopati diabetik yang diderita pasien. Salah satu metode yang populer adalah deep learning. Pada penelitian ini, dibangun gabungan dua algoritma deep learning, yaitu Convolutional Neural Network (CNN)-Long Short-Term Memory (LSTM) untuk deteksi retinopati diabetik dengan output berupa caption yang menjelaskan kondisi yang ada pada citra fundus pasien. CNN digunakan untuk mengekstraksi fitur lesi retinopati diabetik pada citra fundus, dan LSTM digunakan untuk membuat caption berdasarkan fitur lesi tersebut. Penelitian ini menggunakan empat model CNN, yakni AlexNet, pre-trained AlexNet, GoogleNet, dan pre-trained GoogleNet. Simulasi gabungan algoritma CNN-LSTM dilakukan dengan proporsi data yang berbeda menggunakan data set dari Rumah Sakit Cipto Mangunkusumo. Hasil simulasi menunjukkan bahwa gabungan algortima CNN-LSTM dapat mendeteksi fitur lesi dan membuat caption dengan rata-rata kinerja akurasi tertinggi sebesar 91.69% untuk model pre-trained GoogleNet-LSTM dan proporsi data 80% data training dan 20% data testing.

Diabetic retinopathy is a retinal vascular disorder caused by long-term diabetes. Early diabetic retinopathy detection in diabetes patients is needed because no symptoms can be seen during the early stage of disease. The researchers developed a computer-based method to assist ophthalmologists in the early detection process. Ophthalmologists can use the output of the method as a consideration in diagnosing the type of diabetic retinopathy. One of the popular methods is deep learning. In this study, a combination of two deep learning algorithms, namely Convolutional Neural Network (CNN)-Long Short-Term Memory (LSTM), was constructed for diabetic retinopathy detection with the output in the form of a caption that explains the condition present in the patient’s fundus images. CNN is used to extract features of diabetic retinopathy lesions on fundus images, and LSTM is used to generate a caption based on those lesion features. This study used four CNN models that are AlexNet, pre-trained AlexNet, GoogleNet, and pre-trained GoogleNet. Simulation of a combined CNN-LSTM algorithm has been done with the different proportions of data using a data set from Cipto Mangunkusumo National General Hospital. The simulation results show that a combined CNN-LSTM algorithm can detect lesion features and generate caption with the highest average performance accuracy of 91.69% for pre-trained GoogleNet-LSTM and the proportion 80% training data and 20% testing data."
Depok: Fakultas Matematika dan Ilmu Pengetahuan Alam Universitas Indonesia, 2021
T-pdf
UI - Tesis Membership  Universitas Indonesia Library
cover
Patricia Felia Budijarto
"Keterbatasan glomerulus filtration rate (eGFR) dan urine albumin creatinine ratio (uACR) sebagai acuan menyebabkan keterlambatan diagnosis dan prognosis penyakit ginjal diabetes. Perkembangan diabetes mengarah pada kerusakan ginjal dicerminkan oleh penanda (biomarker) yang ditemukan dalam spesimen biologis. Penelitian ini bertujuan mencari metabolit potensial sebagai biomarker pada populasi Indonesia dengan membandingkan metabolit dalam urin pasien diabetes dengan risiko ginjal rendah (n=16) dan tinggi (n=16) menurut klasifikasi KDIGO2022. Analisis metabolomik dilakukan menggunakan liquid chromatography/mass spectrometry quadrupole time-of-flight (LC/MS-QTOF) dengan analisis statistik data menggunakan software Metaboanalyst5,0. Metabolit diidentifikasi menggunakan database Human Metabolome Database (HMDB), Metlin, dan Pubchem. Diskriminasi antar 2 kelompok divisualisasikan dengan Principal Component Analysis (PCA) dan Partial Least Squares-Discriminant Analysis (PLS-DA). Signifikansi metabolit antar 2 kelompok ditentukan dengan T-test (p<0,05), variable importance for projection (VIP>1), dan fold change (log2(FC)>1,2). Metabolit yang dipilih hanya metabolit endogen yang diketahui jalur metabolismenya. Dari berbagai parameter tersebut, metabolit yang potensial sebagai biomarker harus memenuhi nilai area under curve (AUC)>0,65. Berdasarkan karakteristik dasar dan klinis, tidak terdapat perbedaan bermakna karakteristik dasar (usia, jenis kelamin, indeks massa tubuh, durasi menderita DMT2, frekuensi olahraga, kebiasaan merokok, penyakit lain, kepatuhan minum obat, regimen terapi metformin-glimepirid) dan pemeriksaan klinis (HbA1c, tekanan darah sistol, dan diastol) antara kedua kelompok (p>0,05). Ditemukan 23 metabolit yang memenuhi parameter VIP, p-value, dan fold change. Disimpulkan, tiga metabolit teratas dengan AUC>0,65 merupakan biomarker potensial yang membedakan kedua kelompok, yaitu indoksil glukuronida, N-asetilserotonin glukuronida, dan gliserofosfokolin. Indoksil glukuronida dan N-asetilserotonin glukuronida terlibat dalam metabolisme triptofan dan glukuronat, sedangkan gliserofosfokolin terlibat dalam jalur metabolisme gliserofosfolipid dan eter lipid.

The limited utility of glomerulus filtration rate (eGFR) dan urine albumin creatinine ratio (uACR) as the gold standard lead to late diagnosing and prognosing of diabetic kidney disease. Diabetes progression contributes to kidney damage and is reflected by biomarkers in patients' biological samples. This study aims to identify potential endogenous metabolite biomarkers for improved diagnosis and prognosis by comparing metabolites in the urine of diabetic patients with low (n=16) and high (n=16) kidney disease risk in the Indonesian population according to the KDIGO2022 classification. Metabolomic analysis was conducted using liquid chromatography/mass spectrometry quadrupole time-of-flight (LC/MS-QTOF) with Metaboanalyst5.0 software. Metabolites were identified using the Human Metabolome Database, Metlin, and PubChem. Discrimination between the two groups was visualized using principal component analysis (PCA) and Partial Least squares discriminant analysis (PLS-DA). Based on patients' characteristics, no significant differences were observed in baseline characteristics (age, gender, body mass index, duration of type 2 diabetes mellitus, exercise frequency, smoking habits, comorbidities, medication adherence, metformin-glimepiride therapy regimen) and clinical characteristics (HbA1c, systolic and diastolic blood pressure) between two groups (p>0.05). According to the findings of the T-test (p<0.05), fold change (log2(FC)>1.2), and variables important for the projection (VIP>1), there were 23 metabolites substantially different between the two groups. In conclusion, the top 3 metabolites with the area under curve (AUC) value>0.65 demonstrated potential biomarker differentiating among two groups; these are indoxyl glucuronide, N-acetylserotonin glucuronide, and glycerophosphocholine. Indoxyl glucuronide and N-acetylserotonin glucuronide involved in tryptophan metabolism and glucuronate interconversion. Glycerophsophocholine involved in glycerophospholipid and ether lipid metabolism."
Depok: Fakultas Farmasi Universitas Indonesia, 2023
S-pdf
UI - Skripsi Membership  Universitas Indonesia Library
cover
Rani Lisa Indra
"Cairan NaCl 3% pada penelitian sebelumnya terbukti mampu menarik kelebihan eksudat dan mengurangi bau luka karena bersifat hipertonik. Penelitian eksperimen dengan penyamaran ganda dilakukan untuk mengetahui efektivitas perawatan luka dengan cairan NaCl 3% terhadap penurunan jumlah eksudat dan bau ulkus diabetik. Intervensi dilakukan selama 14 hari terhadap 15 sampel yang dibagi menjadi kelompok NaCl 0,9% dan NaCl 3% melalui randomisasi blok.
Tidak terdapat perbedaan signifikan jumlah eksudat setelah intervensi antara kedua kelompok namun terdapat perbedaan signifikan pada skor bau luka. Perawatan ulkus diabetik dengan NaCl 3% tidak lebih efektif dalam menurunkan jumlah eksudat luka dibandingkan NaCl 0,9% namun lebih efektif NaCl 3% dalam menurunkan skor bau.

Previous studies on wound care had proved that NaCl 3% solution able to absorbs the wound exudate and reduces the odor because it is hypertonic. A randomized controlled trial with double blinded technique was conducted to determine the effectiveness of wound care using NaCl 3% solution to decrease amount of exudate and odor of diabetic ulcers. Interventions performed for 14 days on 15 subjects blocked randomly allocated to NaCl 0,9% and NaCl 3% groups.
The result showed that there was no significant difference in the amount of exudate between the groups, however there was significant difference in the odor score. Wound care using NaCl 3% is no more effective to reduce the amount of exudate than NaCl 0,9%, however NaCl 3% is effective to reduce the odor score of diabetic ulcer.
"
Depok: Fakultas Ilmu Keperawatan Universitas Indonesia, 2015
T44545
UI - Tesis Membership  Universitas Indonesia Library
<<   1 2 3 4 5 6 7 8 9 10   >>