Wos İndeksli Açık & Kapalı Erişimli Yayınlar

Permanent URI for this communityhttps://hdl.handle.net/11727/10751

Browse

Search Results

Now showing 1 - 6 of 6
  • Item
    CNN-Based Severity Prediction Of Neurodegenerative Diseases Using Gait Data
    (2022) Erdas, Cagatay Berke; Sumer, Emre; Kibaroglu, Seda; https://orcid.org/0000-0003-3467-9923; 35111334; AGA-5711-2022
    Neurodegenerative diseases occur because of degeneration in brain cells but can manifest as impairment of motor functions. One of the side effects of this impairment is an abnormality in walking. With the development of sensor technologies and artificial intelligence applications in recent years, the disease severity of patients can be estimated using their gait data. In this way, decision support applications for grading the severity of the disease that the patient suffers in the clinic can be developed. Thus, patients can have treatment methods more suitable for the severity of the disease. The presented research proposes a deep learning-based approach using gait data represented by a Quick Response code to develop an effective and reliable disease severity grading system for neurodegenerative diseases such as amyotrophic lateral sclerosis, Huntington's disease, and Parkinson's disease. The two-dimensional Quick Response data set was created by converting each one-dimensional gait data of the subjects with a novel representation approach to a Quick Response code. This data set was regressed with the convolutional neural network deep learning method, and a solution was sought for the problem of grading disease severity. Further, to demonstrate the success of the results obtained with the novel approach, native machine learning approaches such as Multilayer Perceptron, Random Forest, Extremely Randomized Trees, and K-Nearest Neighbours, and ensemble machine learning methods, such as voting and stacking, were applied on one-dimensional data. Finally, the results obtained on the prediction of disease severity by testing one-dimensional gait data with a convolutional neural network architecture that operates on one-dimensional data were included. The results showed that, in most cases, the two-dimensional convolutional neural network approach performed the best among all methods.
  • Item
    Neutrophil to lymphocyte ratio, stroke severity and short term clinical outcomes in acute ischemic stroke
    (2021) Iyigundogdu, Ilkin; Derle, Eda; Kibaroglu, Seda; Can, Ufuk; 0000-0001-7860-040X; 0000-0002-3964-268X; AAJ-2053-2021; AAJ-2956-2021
    Background: Neutrophil to lymphocyte ratio is an easily evaluated systemic inflammation indicator. However, there are limited reports on neutrophil to lymphocyte ratio and functional outcome in ischemic stroke. In this study, we aimed to evaluate the association of neutrophil to lymphocyte ratio and stroke severity, short term functional outcomes and mortality in patients with acute ischemic stroke. Methods: The clinical data of patients who were > 18 age-old and hospitalized with acute ischemic stroke in Baskent University Hospital, Ankara, Turkey between January 2018 and May 2019 were studied retrospectively. Neutrophil to lymphocyte ratio were measured. The neutrophil to lymphocyte ratio and National Institute of Health Stroke Scale (NIHSS) score at admission, mortality during hospitalization and Modified Rankin Scale (mRS) score at discharge of the patients with acute ischemic stroke were correlated. Results: Among the acute ischemic stroke patients due to the exclusion criteria, the data of 134 patients were evaluated. Median age of the patients were 76 +/- 12.5 years and 82 patients (61.2%) were male. The median NIHSS scores of the patients at admission was 5 +/- 4.5. Mortality during the hospitalization was seen in 8 patients (6%). The median neutrophil to lymphocyte ratio value of the patients at admission were found to be 2.6 +/- 3.4. Neutrophil to lymphocyte ratio and NIHSS scores of the patients at admission, duration of the hospitalization, mRS scores at discharge and mortality during hospitalization were found to be positively correlated. Conclusion: Neutrophil to lymphocyte ratio is a simple and easily measured marker and can be used as a potential indicator for prognosis in acute ischemic stroke. However further prospective multicenter investigations are required to confirm the role of neutrophil to lymphocyte ratio for predicting the prognosis in acute ischemic stroke patients.
  • Item
    Neurologic Complications in Heart Transplant Recipients Readmitted to the Intensive Care Unit
    (2021) Sahinturk, Helin; Yurtsever, Beyza Meltem; Ersoy, Ozgur; Kibaroglu, Seda; Zeyneoglu, Pinar; 34926017
    Introduction Neurologic complications after transplantation surgery are major causes of morbidity, and the incidence of neurologic complications among heart transplant recipients varies from 7% to 81%. In our study, we aimed to determine the incidence, etiologies, and risk factors of neurologic complications among patients readmitted to the intensive care unit (ICU) after heart transplantation. Method In this retrospective cohort study, the medical records of all patients who underwent cardiac transplantation from February 2003 to July 2019 were reviewed, and those admitted to the ICU due to neurologic complications during the early and late postoperative period were evaluated. The patients were divided into two groups based on the development of neurologic complications to compare demographic and other characteristics. Results A total of 130 heart transplant recipients were analyzed. We excluded 33 patients from the study because they either had neurologic complications or died postoperatively without discharge from the intensive care unit. The mean age of the cohort was 35.4 +/- 18.5 years, and 74 (76.3%) were male. Out of those 97 heart transplant recipients, 22 (22.7%) developed neurologic complications. Five patients (22.7% ) were admitted to the ICU in the first month, six patients (27.3%) were admitted to the ICU between one and six months, and 11 patients (50%) were admitted to the ICU six months after transplantation due to neurologic complications. The most common diagnosis was posterior reversible encephalopathy syndrome (PRES) (n = 6, 27.3%). The other diagnoses were calcineurin inhibitor toxicity (n = 5, 22.7%), intracranial hemorrhage (n = 3, 13.6%), seizures (n = 2, 9.2%), stroke (n = 2, 9.2%), femoral neuropathy (n = 1, 4.5%), myopathy (n = 1, 4.5%), phrenic nerve damage (n = 1, 4.5%), and cerebral abscess (n = 1, 4.5%). The rate of neurologic complications was higher in males when compared with females (p = 0.03). Both groups were similar in terms of the etiologies of cardiac failure, coexisting disease, and anticoagulant and immunosuppressive usage. The requirement for mechanical ventilation, renal replacement therapy, and the incidence of acute kidney injury were similar in both groups (p > 0.05). The incidence of sepsis was significantly higher in patients with neurologic complications (n = 8, 36.4%, versus n = 5, 6.7%; p < 0.001). The mean length of hospital stay was significantly higher in patients with neurologic complications (21.4 +/- 15.8 versus 11.1 +/- 13.3 days, p = 0.01). The risk of developing neurologic complications is 3.036 times higher in males, and this is statistically significant (odds ratio (OR), 3.036; 95% confidence interval (CI), 1.078-8.444; p = 0.036). Conclusion Our results suggest that neurologic complications develop in 22.7% of heart transplant recipients admitted to the ICU, and half of them are seen after six months postoperatively. PRES was the most frequent (27.3%) neurologic complication. The risk of neurologic complications is three times higher for males. The mean length of hospital stay and incidence of sepsis were significantly higher in heart transplant recipients who developed neurologic complications.
  • Thumbnail Image
    Item
    Intrathecal Methotrexate-Induced Posterior Reversible Encephalopathy Syndrome (PRES)
    (2014) Guler, Tulay; Cakmak, Ozden Yener; Toprak, Selami Kocak; Kibaroglu, Seda; Can, Ufuk; 24764745
  • Thumbnail Image
    Item
    Clinical results of carotid artery stenting versus carotid endarterectomy
    (2016) Derle, Eda; Akinci, Tuba; Kibaroglu, Seda; Harman, Ali; Kural, Feride; Cinar, Pinar; Kilinc, Munire; Akay, Hakki T.; Can, Ufuk; Benli, Ulku S.; 0000-0002-7386-7110; 0000-0002-4226-4034; 0000-0002-9975-3170; 0000-0003-2122-1016; 0000-0002-3964-268X; 0000-0001-8689-417X; 27744460; AAI-8830-2021; AAJ-2956-2021; K-9824-2013; AAL-9808-2021; AAJ-4403-2021; AAJ-2999-2021
    Objective: To review our results of carotid artery stenting (CAS) and carotid endarterectomy (CEA). Methods: We evaluated the medical records of patients undergoing carotid artery revascularization procedure, between 2001 and 2013 in Baskent University Hospital, Ankara, Turkey. Carotid artery stenting or CEA procedures were performed in patients with asymptomatic carotid stenosis (=70%) or symptomatic stenosis (=50%). Demographic data, procedural details, and clinical outcomes were recorded. Primary outcome measures were in 30-day stroke/transient ischemic attacks (TIA)/amaurosis fugax or death. Secondary outcome measures were nerve injury, bleeding complications, length of stay in hospital, stroke, restenosis (ICA patency), and all-cause death during long-term follow-up. Results: One hundred ninety-four CEA and 115 CAS procedures were performed for symptomatic and/or asymptomatic carotid artery stenosis. There is no significant differences 30-day mortality and neurologic morbidity between CAS (13%) and CEA procedures (7.7%). Length of stay in hospital were significantly longer in CEA group (p=0.001). In the post-procedural follow up, only in symptomatic patients, restenosis rate was higher in the CEA group (p=.045). The other endpoints did not differ significantly. Conclusions: Endovascular stent treatment of carotid artery atherosclerotic disease is an alternative for vascular surgery, especially for patients that are high risk for standard CEA. The increasing experience, development of cerebral protection systems and new treatment protocols increases CAS feasibility.
  • Thumbnail Image
    Item
    The Assessment of Efficiency of Traditional and Complementary Medicine Practices in Neurology
    (2018) Kibaroglu, Seda; Caglayan, Hale Zeynep Batur; Ataoglu, Esra Erkoc
    Traditional, complementary, and alternative medicine practices are used in the prevention, diagnosis, and treatment of a wide variety of diseases in the world. Such practices in Turkey are regulated by the "Regulation of Traditional and Complementary Medicine Practice" issued by the Ministry of Health in the Official Gazette of the Republic of Turkey (Issue: 29158, 27th October 2014). The appendix of this regulation defines 15 practices that can be applied in units and practice centers. These applications include; 1. Acupuncture, 2. Apitherapy, 3. Phytotherapy, 4. Hypnosis, 5. Leech therapy (Hirudotherapy), 6. Homeopathy, 7. Chiropractic, 8. Cupping, 9. Maggot therapy, 10. Mesotherapy, 11. Prolotherapy, 12. Osteopathy, 13. Ozone therapy, 14. Reflexology, and 15. Music therapy. In this review, the indications of these 15 applications in the field of neurology are examined and current opinions of the evidence-based medical data are summarized.