International Journal of Telemedicine and Clinical Practices (8 papers in press)
MINIMUM REDUNDANCY MAXIMUM RELEVANCE WITH MEAN BASED RANKING FOR BIOMARKER GENE SELECTION IN AUTISM
by Prema Ramasamy, Premalatha Kandhasamy
Abstract: Autism is the most commonly occurring form of Autism Spectrum Disorder. Analysis of gene expression data is important in Autism in order to retrieve the required information. Gene expression data generally contain a large number of genes but a small number of samples. The complicated relations among the different genes make analysis more difficult, and removing the irrelevant genes will improve the quality of the results. This paper presents a feature selection method based on Minimum Redundancy Maximum Relevance with Mean based Ranking (mRMR-μR) to identify the genes associated with Autism or potential susceptibility regions in the genome. To assess the performance of the proposed method, it is applied on Autism gene expression data. The classifiers Support Vector Machine (SVM), k-Nearest-Neighbor (kNN) and Artificial Neural Network (ANN) are used to identify the accuracy of selected features. The experimental results show that the proposed feature selection method gives 100% average classification accuracy for the top twenty-five selected genes.
Keywords: Autism; Gene Expression Data; Feature Selection; Classification; Minimum Redundancy Maximum Relevance.
Improving efficiency and effectiveness of the telemedicine system between a Remote Clinic and a Super Specialty Hospital - A case study and its key determining factors
by Ponraj Vellaichamy, Selvakumar K
Abstract: This paper focuses on accessibility of healthcare through telemedicine ICT Software implementation and bring process and performance improvements. For achieving efficacy of the hypothesis, this paper studies the key determining factors such as challenges, adoption of technologies and standards, process refinement, reliability, safety and security of the patient records, and performance improvements. This pilot study ensures the success of quality healthcare delivery outreach to remote/rural patients through telemedicine in a C2H (Clinic to Hospital) environment between NLC Remote Clinic to SRMC Super Specialty Hospital for ensuring the efficacy of the tele-medicine system software through ICT. During implementation, delays due to generation and resolution side of the healthcare delivery were identified and suitable policy measures, technology adoption at all levels of healthcare delivery system from both the ends of C2H was advocated.
Keywords: Keywords: Telemedicine; C2H; Remote Clinic to Hospital; Clinic to Hospital; Teleradiology; DICOM; SIP; Spring Security; https; EMR; HMIS; LIS; RIS; PACS; DICOM; EMR; EHR; telehealth; ehealth.
EPR data hiding in MRI head volumes for telemedicine using rectangular box embedding method
by T. Kalaiselvi, K. Somasundaram, S. Vijayalakshmi, P. Sriramakrishnan
Abstract: Mapping of electronic patient report (EPR) text file to magnetic resonance imaging (MRI) volumes increases burden to diagnosis over telemedicine. In this paper, we propose a high capacity, robust technique to select slices of interest (SOI) from a MRI volume that to embed EPR and transfer on a network. Embedding EPR along with selected slices is used to removal of mapping procedure at the receiver end. Initially brain extraction algorithm (BEA) is used to focus the region and ease of pathology detection in the slices. Then the embedding scheme uses the technique of rectangular box mapping (RBM) where it takes care of sensitive part of medical image. EPR data is encrypted and embedded for security purpose. Experimental results on security and robustness have been tested against various images. The proposed method can store longer EPR string along with better authenticity and confidentiality properties while satisfying all the requirements of medical data transfer and has achieved 51% reduction in bit rate than the traditional methods.
Keywords: magnetic resonance images; head scans; biomedical imaging; data communication; EPR hiding; telemedicine; brain extraction algorithm; rectangular box mapping; RBM; slices of interest; SOI; region of interest; ROI.
Cell nuclei detection in multispectral histology images using K-means and expectation-maximisation segmentations
by Mohamed Bouzid, Ali Khalfallah, Sana Lafi, Med Salim Bouhlel
Abstract: Histology images contain a lot of relevant information which are useful in the diagnostic (cells, cell compartments such as nuclei…). In this topic, the main goal of computer-based image analysis is to identify structures or nuclei in histology images with high accuracy and robustness. Current methods and systems based on colour images give results with a lot of errors. We suggest using multispectral imaging system with a programmable light source (PLS). With the new acquisition system, a 3-band colour image (MS3), a 5-band multispectral image (MS5), a 10-band multispectral image (MS10) and a 25-band multispectral image (MS25) from 450 nm to 700 nm are acquired. After the acquisition, two unsupervised segmentation methods are applied: the expectation-maximisation (EM) and the K-means (KM). Firstly, each band is segmented separately; secondly a fusion of bands is used. A comparison has been drawn between the two segmentation methods. The results show a small superiority of EM segmentation against KM segmentation. It is also noted that the fuse of selected bands from MS5 ensures the best F-measure of cell nuclei detection.
Keywords: histology; nuclei detection; multispectral images; segmentation; K-means; expectation-maximisation.
Some considerations of common spatial pattern for better classification in brain-computer interfaces
by June-Hyoung Kim, Yeon-Mo Yang
Abstract: EEG-based motor imagery signal classification is very important in brain-computer interface (BCI) technology. In this work, we develop a common spatial pattern (CSP) technique for feature extraction in a BCI system. To confirm classification improvement, classification accuracy was analysed by using four statistics, namely mean, variance, skewness, and kurtosis within the CSP paradigm. The data from the dataset III of BCI competition II were used and simulated using MATLAB. The results show that the best classification accuracy is obtained when the CSP algorithm uses the variance statistic for feature extraction.
Keywords: brain-computer interface; BCI; motor imagery; common spatial pattern; CSP; neural signal classification; statistical signal processing.
The feasibility of cross-sector videoconferences in discharge planning among stroke patients: a mixed-methods study scrutinising patient and staff perspectives
by Simone Hofman Rosenkranz, Anne Argir Falster, Tina Strid Carstensen, Lone Lundbak Mathiesen, Helle Klingenberg Iversen, Charlotte Kira Kimby
Abstract: We tested the quality and effectiveness of cross-sector videoconferences in planning the discharge of stroke patients. Throughout the trial, time registration and structured patient interviews were conducted. During intervention, a self-administered questionnaire and semi-structured focus group interviews were conducted among staff. Patient and staff questionnaires revealed high satisfaction with discharge videoconferences, and substantial savings on transport was registered among municipalities. Through focus groups, detailed workflow descriptions, ongoing staff education, detailed care-plans, the availability of a 'super user', and a suitable conference room were important when conducting a videoconference. Additionally, interviews revealed concern among staff regarding whether communication and observation through videoconferencing is sufficient to ensure that rehabilitation meets the patient's needs. This study offers opportunities to overcome geographical and economic challenges in discharge planning without compromising quality of care. Furthermore, the results create a foundation for further exploration of how discharge videoconferences affect workflow, communication, and quality of care.
Keywords: patient discharge; videoconferencing; discharge videoconferences; stroke rehabilitation; cross-sector cooperation; continued care.
Study on the efficacy of tele-medicine system implementation at SRMC
by Vellaichamy Ponraj, K. Selvakumar
Abstract: Majority of the tele-medicine implementations are not effective in healthcare delivery hence slowly it loses its significance due to various factors, which ultimately defeat the purpose of tele-medicine intervention. Hence, this paper examines the existing tele-medicine implementation and understands its challenges, studies the efficacy of the system and suggests the alternative system with technological and process improvements to improve its efficacy, quality and sustainability. By reviewing the process involved in getting the expert opinion from super specialty hospital, it was found out that there are many bottlenecks in the system, process, technology and access in delivering the quality healthcare services on time. This study carried out between SRMC and NLC Clinic has further helped to suggest a software architecture involving the overall process of electronic medical record flow in association with tele-medicine, tele-radiology and hospital management information system connectivity to improve the efficiency of the tele-medicine.
Keywords: telemedicine; efficacy of telemedicine; hardware-based video conference; tele-health; DICOM; PACS; SIP; tele-radiology; information and communication technologies; ICT.
Special Issue on: Internet of Things and Big Data for Smart Health Services
A framework for predicting malaria using naïve Bayes classifier
by Aminu Aliyu, Rajesh Prasad, Mathias Fonkam
Abstract: Malaria, a life-threatening parasite contained in the spittle of mosquitoes, and is transmitted via a bite. This study designs a framework for predicting malaria using a probabilistic classifier: naïve Bayes. The study classifies the incoming patient into two phases. In the first phase, it first classifies patients as either having malaria or not, then in the second phase it proceeds to further classify the level of severity. The framework has been tested on a sample dataset of 700 records obtained from a hospital located in Yola, Adamawa State of Nigeria. The result proved that the model can classify any given patients successfully, having provided the required input symptoms at both classification phases. The accuracy of the model was checked using confusion matrix and ROC.
Keywords: malaria; data mining; classification; naïve Bayes; prediction; performance measure.