ABSTRACT
Depression is a common mental health problem leading to significant disability world wide. Depression is not only common but also commonly co-occurs with other mental and neurological illnesses. Parkinson's Disease gives rise to symptoms directly impairing a person's ability to function. Early diagnosis and detection of depression can aid treatment, but diagnosis typically requires an interview with a health provider or structured diagnostic questionnaire. Thus, unobtrusive measures to monitor depression symptoms in daily life could have great utility in screening depression for clinical treatment. Vocal biomarkers of depression are a potentially effective method of assessing depression symptoms in daily life, which is the focus of the current research. We have a database of 921 unique patients with Parkinson's disease and their self assessment of whether they felt depressed or not. Voice recordings from these patients were used to extract paralinguistic features, which served as inputs to machine-learning and deep learning techniques to predict depression. The results are presented here and the limitations are discussed given the nature of the recordings which lack language content. Our models achieved accuracies as high as 0.77 in classifying depressed and non-depressed subjects accurately using their voice features and PD severity. We found depression and severity of Parkinson's Disease had a correlation coefficient of 0.3936, providing a valuable feature when predicting depression from voice. Our results indicate a clear correlation between feeling depressed and the severity of the Parkinson's disease. Voice may be an effective digital biomarker to screen for depression among patients suffering from Parkinson's Disease.
ABSTRACT
OBJECTIVE: Acute appendicitis (AA) is one of the most common surgical emergencies. Despite extraordinary advances in modern investigations, the accurate diagnosis of AA remains an enigmatic challenge. The aim of this study was to compare and evaluate the diagnostic accuracy of inflammatory parameters [C-reactive protein (CRP), procalcitonin (PCT), erythrocyte sedimentation rate (ESR)], ultrasound (US) and Alvarado score (AS) in reducing the rate of negative appendectomies. MATERIAL AND METHODS: Two hundred seventy-eight patients were included in this study. Patients were separated into two main groups as the surgery group (n=184) and non-operative group (n=94). Complete blood count, ESR and PCT levels were assessed, abdominal US was performed and AS was calculated for all patients. RESULTS: In the surgery group, clinical predictive factors for histopathologic results such as AS ≥7, AA signs on US, neutrophilia and leukocytosis were significant. Neutrophilia and leukocytosis had the highest accuracy rate among these factors. Inflammatory parameters were not predictive for histopathologic results, although higher CRP and PCT levels were significant in perforated and necrotizing appendicitis. Multifactorial regression analyses showed that AS was not of significant predictive value in the non-operative group. CONCLUSION: There was no superiority of AS and/or US in the diagnosis of AA. Recent findings have shown the most reliable parameters in the diagnosis of AA to be primarily 'neutrophilia' and secondarily 'leukocytosis'. Other results of this study indicated that inflammatory parameters (CRP, PCT, ESR) were not superior to other parameters but CRP and PCT levels were significantly high in complicated cases.
ABSTRACT
BACKGROUND: In this study, we aimed to set levels of blood S100B and lactate and to determine any correlation with brain computerized tomography in minor head traumas in children and adults. METHODS: This clinical trial is a prospective study including 100 head trauma patients who applied to Ankara Training and Research Hospital emergency service. RESULTS: In this study, cut-off ranges of 0.0-0.15 ug/ml and 0.9-1.7 mmol/L for blood S100B and lactate levels, respectively, were used. S100B level was higher than the cut-off range in 42% of patients and lactate level was higher in 56% of patients. No significant differences were determined between age groups. When the relation between S100B and lactate levels with brain CT was evaluated, no statistically significant relation was determined. CONCLUSION: According to our results, in minor head traumas, the determination of elevated serum S100B and lactate levels cannot take the place of clinical examination and the use of cranial CT. Although the patients in our study group had minor head trauma, we do not consider S100B and lactate to be reliable markers for estimating progression.
