ABSTRACT
Type 2 Diabetes, a metabolic disorder disease, is becoming a fast growing health crisis worldwide. It reduces the quality of life, and increases mortality and health care costs unless managed well. After-meal blood glucose level measure is considered as one of the most fundamental and well-recognized steps in managing Type 2 diabetes as it guides a user to make better plans of their diet and thus control the diabetes well. In this paper, we propose a data-driven approach to predict the 2 h after meal blood glucose level from the previous discrete blood glucose readings, meal, exercise, medication, & profile information of Type 2 diabetes patients. To the best of our knowledge, this is the first attempt to use discrete blood glucose readings for 2 h after meal blood glucose level prediction using data-driven models. In this study, we have collected data from five prediabetic and diabetic patients in free living conditions for six months. We have presented comparative experimental study using different popular machine learning models including support vector regression, random forest, and extreme gradient boosting, and two deep layer techniques: multilayer perceptron, and convolutional neural network. We present also the impact of different features in blood glucose level prediction, where we observe that meal has some modest and medication has a good influence on blood glucose level.
ABSTRACT
Deep Learning (DL) techniques have recently been used in medical image segmentation and the reconstruction of 3D anatomies of a human body. In this work, we propose a semi-supervised DL (SSDL) approach utilizing a CNN-based 3D U-Net model for femur segmentation from sparsely annotated quantitative computed tomography (QCT) slices. Specifically, QCT slices at the proximal end of the femur forming ball and socket joint with acetabulum were annotated for precise segmentation, where a segmenting binary mask was generated using a 3D U-Net model to segment the femur accurately. A total of 5474 QCT slices were considered for training among which 2316 slices were annotated. 3D femurs were further reconstructed from segmented slices employing polynomial spline interpolation. Both qualitative and quantitative performance of segmentation and 3D reconstruction were satisfactory with more than 90% accuracy achieved for all of the standard performance metrics considered. The spatial overlap index and reproducibility validation metric for segmentation-Dice Similarity Coefficient was 91.8% for unseen patients and 99.2% for validated patients. An average relative error of 12.02% and 10.75% for volume and surface area, respectively, were computed for 3D reconstructed femurs. The proposed approach demonstrates its effectiveness in accurately segmenting and reconstructing 3D femur from QCT slices.
Subject(s)
Deep Learning , Imaging, Three-Dimensional , Humans , Imaging, Three-Dimensional/methods , Image Processing, Computer-Assisted/methods , Reproducibility of Results , Femur/diagnostic imagingABSTRACT
OBJECTIVES: Chronic suppurative otitis media is a major cause of acquired hearing impairment, especially in children of developing countries. The study sought to explore the bacteriological profile and their antimicrobial susceptibility among patients of chronic suppurative otitis media from a tertiary care hospital in Bangladesh. METHODS: A cross sectional microbiological study was conducted at the Department of Microbiology, Rajshahi Medical College, Bangladesh from January to December 2019. Aural swabs were collected aseptically from clinically suspected patients irrespective of age and gender attending the ear, nose and throat outpatient department of Rajshahi Medical College Hospital. Aerobic bacterial culture was done and isolates were identified through standard bacteriological identification scheme. Antimicrobial susceptibility testing of isolates was done by modified Kirby-Bauer disk diffusion method following Clinical and Laboratory Standards Institute guidelines. RESULTS: Of 96 swabs, culture yielded a total of 73 bacterial isolates from 68(70.8%) culture-positive plates including 63 (65.6%) unimicrobial and 5 (5.2%) polymicrobial (mixed growth of a pair of bacteria) growths. Frequency distribution revealed, 40(55%) gram-negative and 33(45%) gram-positive bacteria with Staphylococcus aureus was the leading isolate (37%) followed by Pseudomonas aeruginosa (31.5%), Escherichia coli (13.7%), coagulase-negative Staphylococcus (8.2%), Klebsiella pneumoniae (5.5%) and Proteus spp. (4.1%). Gram-positive bacteria were found to be highly susceptible (100%) to Linezolid and Vancomycin followed by Imipenem (83 to 96.3%), while moderate to high resistance (44 to 67%) was observed against Ciprofloxacin, Ceftriaxone, Ceftazidime, Amoxicillin/Clavulanate and Clindamycin. For gram-negative bacteria, susceptibility ranged from 67 to 100% to Imipenem, 67 to 96% to Piperacillin/Tazobactam and 67 to 83% to Gentamicin, while moderate to high resistance (50 to 75%) was observed against Ciprofloxacin, Ceftriaxone, Ceftazidime and Amoxicillin/Clavulanate. CONCLUSION: Moderate to high level of multidrug-resistance especially to 3rd generation cephalosporins, Ciprofloxacin and Amoxicillin/Clavulanate is an alarming situation. It warns reinforcement of judicious antibiotic prescription and introduction of antibiotic stewardship program in the tertiary care hospitals.
ABSTRACT
OBJECTIVES: Successful treatment of gonorrhea has always been jeopardized by the emergence of resistance to antibiotics recommended as first-line therapies. The present investigation was carried out to demonstrate the current status of antimicrobial susceptibility of N. gonorrhoeae with a special reference to azithromycin and ceftriaxone. METHODS: Microscopical detection in Gram-stained smear and isolation by culture in Thayer-Martin medium were done for 60 clinically suspected gonorrhea patients using urethral discharge or prostatic secretion for male and endocervical secretion for female. Isolates of N. gonorrhoeae were subjected to antimicrobial susceptibility testing by modified Kirby Bauer disk diffusion method against eight antimicrobial drugs including azithromycin and ceftriaxone. RESULTS: Culture yielded a total of 25(42%) isolates of N. gonorrhoeae from 60 clinically suspected patients of both sexes; 21 from male (17 from urethral discharge and 04 from prostatic secretion) and 04 from female (endocervical secretion). Isolates of N. gonorrhoeae showed moderate to high resistance (60 to 88%) to penicillin, tetracycline, cotrimoxazole, erythromycin, ciprofloxacin and cefixime. While resistance to azithromycin and ceftriaxone was 60% and 48% respectively, which was also moderate. CONCLUSION: Our findings indicate moderate to the high resistance of N. gonorrhoeae to conventional antibiotics. It also showed moderate resistance to azithromycin and ceftriaxone, current dual therapy recommended by the WHO for the treatment of genital gonorrhea, which is alarming.