Layer recurrent neural network-based diagnosis of Parkinson's disease using voice features.

Parkinson's disease (PD), a slow-progressing neurological disease, affects a large percentage of the world's elderly population, and this population is expected to grow over the next decade. As a result, early detection is crucial for community health and the future of the globe in order to take proper safeguards and have a less arduous treatment procedure. Recent research has begun to focus on the motor system deficits caused by PD. Because practically most of the PD patients suffer from voice abnormalities, researchers working on automated diagnostic systems investigate vocal impairments. In this paper, we undertake extensive experiments with features extracted from voice signals. We propose a layer Recurrent Neural Network (RNN) based diagnosis for PD. To prove the efficiency of the model, different network models are compared. To the best of our knowledge, several neural network topologies, namely RNN, Cascade Forward Neural Networks (CFNN), and Feed Forward Neural Networks (FFNN), are used and compared for voice-based PD detection for the first time. In addition, the impacts of data normalization and feature selection (FS) are thoroughly examined. The findings reveal that normalization increases classifier performance and Laplacian-based FS outperforms. The proposed RNN model with 300 voice features achieves 99.74% accuracy.

Early diagnosis of Parkinson's disease using machine learning algorithms.

Parkinson's disease is caused by the disruption of the brain cells that produce substance to allow brain cells to communicate with each other, called dopamine. The cells that produce dopamine in the brain are responsible for the control, adaptation and fluency of movements. When 60-80%of these cells are lost, then enough dopamine is not produced and Parkinson's motor symptoms appear. It is thought that the disease begins many years before the motor (movement related) symptoms and therefore, researchers are looking for ways to recognize the non-motor symptoms that appear early in the disease as early as possible, thereby halting the progression of the disease. In this paper, machine learning based diagnosis of Parkinson's disease is presented. The proposed diagnosis method consists of feature selection and classification processes. Feature Importance and Recursive Feature Elimination methods were considered for feature selection task. Classification and Regression Trees, Artificial Neural Networks, and Support Vector Machines were used for the classification of Parkinson's patients in the experiments. Support Vector Machines with Recursive Feature Elimination was shown to perform better than the other methods. 93.84% accuracy was achieved with the least number of voice features for Parkinson's diagnosis.

Artificial and natural sialic acid precursors influence the angiogenic capacity of human umbilical vein endothelial cells.

N-acetylneuraminic acid (Neu5Ac) represents the most common terminal carbohydrate residue in many mammalian glycoconjugates and is directly involved in a number of different physiological as well as pathological cellular processes. Endogenous sialic acids derive from the biosynthetic precursor molecule N-acetyl-D-mannosamine (ManNAc). Interestingly, N-acyl-analogues of D-mannosamine (ManN) can also be incorporated and converted into corresponding artificial sialic acids by eukaryotic cells. Within this study, we optimized a protocol for the chemical synthesis of various peracetylated ManN derivatives resulting in yields of approximately 100%. Correct molecular structures of the obtained products ManNAc, N-propanoyl-ManN (ManNProp) and N-butyl-ManN (ManNBut) were verified by GC-, ESI-MS- and NMR-analyses. By applying these substances to human umbilical vein endothelial cells (HUVECs), we could show that each derivative was metabolized to the corresponding N-acylneuraminic acid variant and subsequently incorporated into nascent glycoproteins. To investigate whether natural and/or artificial sialic acid precursors are able to modulate the angiogenic capacity of HUVECs, a spheroid assay was performed. By this means, an increase in total capillary length has been observed when cells incorporated N-butylneuraminic acid (Neu5But) into their glycoconjugates. In contrast, the natural precursor ManNAc inhibited the growth of capillaries. Thus, sialic acid precursors may represent useful agents to modulate blood vessel formation.

Mortality and associated factors in a thoracic surgery ICU.

OBJECTIVE: To assess mortality and identify mortality risk factors in patients admitted to a thoracic surgery ICU. METHODS: We retrospectively evaluated 141 patients admitted to the thoracic surgery ICU of the Denizli State Hospital, located in the city of Denizli, Turkey, between January of 2006 and August of 2008. We collected data regarding gender, age, reason for admission, invasive interventions and operations, invasive mechanical ventilation, infections, and length of ICU stay. RESULTS: Of the 141 patients, 103 (73.0%) were male, and 38 (23.0%) were female. The mean age was 52.1 years (range, 12-92 years), and the mortality rate was 16.3%. The most common reason for admission was trauma. Mortality was found to correlate with advanced age (p < 0.05), requiring invasive mechanical ventilation (OR = 42.375; p < 0.05), prolonged ICU stay (p < 0.05), and specific reasons for admission-trauma, gunshot wound, stab wound, and malignancy (p < 0.05 for all). CONCLUSIONS: Among patients in a thoracic surgery ICU, the rates of morbidity and mortality are high. Increased awareness of mortality risk factors can improve the effectiveness of treatment, which should reduce the rates of morbidity and mortality, thereby providing time savings and minimizing costs.

Mortalidade e fatores associados em uma UTI de cirurgia torácica / Mortality and associated factors in a thoracic surgery ICU

OBJETIVO: Determinar a mortalidade e identificar fatores de riscos associados em pacientes em uma UTI de cirurgia torácica. MÉTODOS: Foram avaliados retrospectivamente 141 pacientes admitidos na UTI de cirurgia torácica do Hospital Estadual de Denizli, localizado na cidade de Denizli, Turquia, entre janeiro de 2006 e agosto de 2008. Foram coletados dados sobre gênero, idade, causa de admissão, intervenções invasivas e operações, status de ventilação mecânica invasiva, infecções e tempo de permanência na UTI. RESULTADOS: Dos 141 pacientes, 103 (73,0 por cento) eram do sexo masculino e 38 (23,0 por cento) do sexo feminino. A média de idade foi de 52,1 anos (variação: 12-92 anos), e a taxa de mortalidade foi de 16,3 por cento. A causa de admissão mais frequente foi trauma. A mortalidade correlacionou-se com idade avançada (p < 0,05), uso de ventilação mecânica invasiva (OR = 42,375; p < 0,05), longa permanência na UTI (p < 0,05) e causas de admissão específicas - trauma, injúria por arma de fogo, injúria por arma branca e malignidade (p < 0,05 para todos). CONCLUSÕES: Os pacientes em uma UTI de cirurgia torácica têm alta morbidade e mortalidade. Um conhecimento maior dos fatores de risco de mortalidade pode melhorar a eficiência do tratamento, resultando em diminuição da morbidade e mortalidade, o que gerará economia de tempo e reduzirá os custos financeiros.

OBJECTIVE: To assess mortality and identify mortality risk factors in patients admitted to a thoracic surgery ICU. METHODS: We retrospectively evaluated 141 patients admitted to the thoracic surgery ICU of the Denizli State Hospital, located in the city of Denizli, Turkey, between January of 2006 and August of 2008. We collected data regarding gender, age, reason for admission, invasive interventions and operations, invasive mechanical ventilation, infections, and length of ICU stay. RESULTS: Of the 141 patients, 103 (73.0 percent) were male, and 38 (23.0 percent) were female. The mean age was 52.1 years (range, 12-92 years), and the mortality rate was 16.3 percent. The most common reason for admission was trauma. Mortality was found to correlate with advanced age (p < 0.05), requiring invasive mechanical ventilation (OR = 42.375; p < 0.05), prolonged ICU stay (p < 0.05), and specific reasons for admission-trauma, gunshot wound, stab wound, and malignancy (p < 0.05 for all). CONCLUSIONS: Among patients in a thoracic surgery ICU, the rates of morbidity and mortality are high. Increased awareness of mortality risk factors can improve the effectiveness of treatment, which should reduce the rates of morbidity and mortality, thereby providing time savings and minimizing costs.