Hybrid Machine Learning Framework for Multistage Parkinson's Disease Classification Using Acoustic Features of Sustained Korean Vowels.

Recent research has achieved a great classification rate for separating healthy people from those with Parkinson's disease (PD) using speech and the voice. However, these studies have primarily treated early and advanced stages of PD as equal entities, neglecting the distinctive speech impairments and other symptoms that vary across the different stages of the disease. To address this limitation, and improve diagnostic precision, this study assesses the selected acoustic features of dysphonia, as they relate to PD and the Hoehn and Yahr stages, by combining various preprocessing techniques and multiple classification algorithms, to create a comprehensive and robust solution for classification tasks. The dysphonia features extracted from the three sustained Korean vowels /아/(a), /이/(i), and /우/(u) exhibit diversity and strong correlations. To address this issue, the analysis of variance F-Value feature selection classifier from scikit-learn was employed, to identify the topmost relevant features. Additionally, to overcome the class imbalance problem, the synthetic minority over-sampling technique was utilized. To ensure fair comparisons, and mitigate the influence of individual classifiers, four commonly used machine learning classifiers, namely random forest (RF), support vector machine (SVM), k-nearest neighbor (kNN), and multi-layer perceptron (MLP), were employed. This approach enables a comprehensive evaluation of the feature extraction methods, and minimizes the variance in the final classification models. The proposed hybrid machine learning pipeline using the acoustic features of sustained vowels efficiently detects the early and mid-advanced stages of PD with a detection accuracy of 95.48%, and with a detection accuracy of 86.62% for the 4-stage, and a detection accuracy of 89.48% for the 3-stage classification of PD. This study successfully demonstrates the significance of utilizing the diverse acoustic features of dysphonia in the classification of PD and its stages.

Machine Learning-Based Hearing Aid Fitting Personalization Using Clinical Fitting Data.

The initial software fitting prescribed by the fitting formula largely depends on the patient's hearing loss, which may not be the optimal preference for a particular user. Certain criteria must also be readjusted by an audiologist to meet the user-specific requirements. Therefore, this study focuses on the novel application of a neural network (NN) technique to build a suitable fitting algorithm with prescribed hearing loss and the corresponding preferred gain to minimize the gap between optimized fittings. The algorithm intended to learn the hearing preferences of an individual user such that the initial fitting may be optimized. These findings demonstrate the efficiency of the algorithm, with and without additional features. Using the clinical fitting data, the average mean square error (MSE) for the simple NN algorithm was 5.4183%. By adding additional features to the data, the algorithm performed better, and the average MSE was as low as 5.2530%. However, the algorithm outperformed Company A fitting software, as the MSE was the highest at 5.4748%. As the company's automatic fitting has a noticeable discrepancy with clinical fitting records, the impeccable results from this study can lead to a better path towards fitting satisfaction, thus benefiting the hearing-impaired community to a larger extent.

CONSERVATION. Genetic assignment of large seizures of elephant ivory reveals Africa's major poaching hotspots.

Poaching of elephants is now occurring at rates that threaten African populations with extinction. Identifying the number and location of Africa's major poaching hotspots may assist efforts to end poaching and facilitate recovery of elephant populations. We genetically assign origin to 28 large ivory seizures (≥0.5 metric tons) made between 1996 and 2014, also testing assignment accuracy. Results suggest that the major poaching hotspots in Africa may be currently concentrated in as few as two areas. Increasing law enforcement in these two hotspots could help curtail future elephant losses across Africa and disrupt this organized transnational crime.

Parathyroid failure following thyroid surgery.

This cross-sectional study was done to see the association of post thyroidectomy parathyroid failure with thyroid disease and type of surgery. It was carried out in the Department of Otolaryngology-Head and Neck Surgery, Bangabandhu Sheikh Mujib Medical University, Dhaka during the period of July 2008 to June 2010. Total 50 cases of thyroid malignancy and multinodular goiter who had undergone total or near total thyroidectomy with or without neck dissection were studied. In this study highest number of cases were found in 3rd decade of age (28%) and there was female predominance (M:F=1:3.54). Overall frequency of post operative hypocalcaemia was 30% (26% was temporary hypocalcaemia and 4% was permanent). Hypocalcaemia revealed clinically in 20% cases and remained subclinical in 10% cases. Hypocalcaemia developed in 42.30% cases of malignant thyroid disease and 16.66% cases of benign thyroid disease (p<0.05). It was found in 54.54% cases with neck dissection and 23.07% cases without neck dissection (p<0.05). Hypocalcaemia developed in 62.5% cases where parathyroid gland were not identified and 23.8% cases where parathyroid gland was identified. Hypocalcaemia developed most commonly on the 2nd post operative day (73.33%). There is a significance difference with development of parathyroid failure after thyroid surgery between benign and malignant thyroid disease and also between thyroid surgery with or without neck dissection.

A comparative study among laparoscopically assisted vaginal hysterectomy, vaginal hysterectomy and abdominal hysterectomy: experience in a tertiary care hospital in Bangladesh.

The study was undertaken to compare the efficiency and outcome of laparoscopically assisted vaginal hysterectomy (LAVH), total abdominal hysterectomy (TAH) and vaginal hysterectomy (VH) in terms of operative time, cost, estimated blood loss, hospital stay, quantity of analgesia use, intra- and postoperative complications rate and patients recovery. A total of 750 patients were prospectively collected in the study period from January 2005 through January 2009 in a tertiary care hospital. The mean estimated blood loss in LAVH and VH group were significantly lower compared with the TAH group. As to postoperative pain, significantly less diclofenac was required in the LAVH and VH group vs the TAH group. LAVH, VH is clinically and economically comparable with TAH, with patients' benefits of less estimated blood loss; less analgesia use; less intra- and postoperative complication rates; less postoperative pain; rapid patient recovery and shorter hospital stay. The study concludes that thus, LAVH, VH is clinically and economically comparable with TAH.

Evaluation of the results of posterior decompression, posterolateral fusion and stabilization by pedicle screw and rod in traumatic thoracolumbar fractures.

This study is to evaluate the clinical and radiological success of posterior decompression, posterolateral fusion and stabilization by pedicle screw and rod in the management of traumatic thoracolumbar fractures. It is a prospective interventional study which is carried out in Bangabandhu Sheikh Mujib Medical University and different private hospitals in Dhaka city from January 2008 to December 2010. Total 16 patients were selected according to the inclusion and exclusion criteria. There were 10 male patients and 06 female within a age range of 21-40 years. Mean age was 33.32 years. Total 08 cases involved L1, 03 cases involved at D12, 02 cases involved at D1, and at L2 each whereas 01 case at L3. Total 10 cases were of compression fracture and remainder 06 burst fractures. Ten (10) patients presented with paraparesis, 05 patients with incomplete paraplegia and 01 patient with complete paraplegia. All the patients were followed up for minimum 1 year. Patients with paraparesis fully recovered neurologically and could walk without support. All the 05 patients with incomplete paraplegia also recovered fully except 01 which gained partial improvement and walks with aids. One patient with complete paraplegia remained unchanged. Our results show that posterior decompression posterolateral fusion and stabilization by pedicle screw and rod provides a safe and effective surgical option for management of traumatic thoracolumbar fractures.