Romano Swarts, H. Mwamba, P. Fourie, D. van den Heever
{"title":"PANDA: Paediatric attention-deficit/hyperactivity disorder app","authors":"Romano Swarts, H. Mwamba, P. Fourie, D. van den Heever","doi":"10.1109/SAIBMEC.2018.8363190","DOIUrl":"https://doi.org/10.1109/SAIBMEC.2018.8363190","url":null,"abstract":"The development of a novel method that validates and enhances the current subjective diagnostic methods/tools for attention-deficit/hyperactivity disorder (ADHD) is investigated. The proposed method/tool is in the form of a tablet-based game with underlying artificial intelligence, such as machine learning. Two mini-games were developed, each dealing with one ADHD subtype: the inattentive subtype and the hyperactivity subtype. The objective of each mini-game is to differentiate between an ADHD individual (either from the inattentive or hyperactivity subtype) and a non-ADHD individual, based on game-play data. The design of the mini-games was based on analyzing the ADHD criteria defined by the Diagnostic and Statistical Manual of Mental Disorders (DSM-V) and converting those criteria into measurable parameters, where applicable. Those measurable parameters were then implemented in the mini-games and used as a means to gather objective data. Beta-testing was performed with a population of 40 subjects (20 ADHD-inattentive, 20 ADHD-hyperactivity) between the ages of 4 and 17 years old. A clinical study has begun following mini-games optimisation based on feedback obtained during beta-testing. The clinical study comprises a total of 200 subjects between the ages of 4 and 17 years of age. 156 subjects will be used to train and validate the proposed machine learning algorithms, while the remaining 44 will be used to test the classification accuracy of the algorithms. According to a statistical POWER analysis, it was seen that using a sample size of 156, an ADHD population could be differentiated from a non-ADHD population with 16% error. Given this fact, it is speculated that using neural networks and support vector machines, a smaller error can be expected.","PeriodicalId":165912,"journal":{"name":"2018 3rd Biennial South African Biomedical Engineering Conference (SAIBMEC)","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122656053","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Musculoskeletal modeling of crouch gait","authors":"T. Guess, Swithin S. Razu","doi":"10.1109/SAIBMEC.2018.8363188","DOIUrl":"https://doi.org/10.1109/SAIBMEC.2018.8363188","url":null,"abstract":"Crouch gait affects older adults following stroke and is common in children with cerebral palsy. Contracture, spasticity, and increased activation of the hamstrings are often implicated in pediatric crouch gait. Instrumented prosthetics have measured tibiofemoral contact forces in older adults walking in a crouched posture, but contact forces experienced during clinical crouch gait may be much higher. The effect of abnormal muscle forces on knee arthrokinematics and loading of individual knee structures is important to understanding the consequences of crouch gait on developing knees and in older patients with prosthetic components. This project used computational methods that concurrently consider knee anatomy and prosthetic geometry, muscle activation, and body motion to simulate the effect of altered muscle activations on knee loading during crouch gait for a person with an instrumented total knee prosthetic. Measured EMG signals were decomposed into muscle synergies and alterations to synergy weightings provided a means to modify neural command signals in forward dynamics simulations of crouch gait. Open-chain seated leg extension exercises were used to adjust certain muscle properties from generic values and the resulting musculoskeletal model predicted medial and lateral tibiofemoral contact forces within 0.33 and 0.38 bodyweight of measured over one crouch gait cycle. Increasing hamstring activation during stance increased knee loading, posterior tibia translation, and loading on the posterior cruciate ligament.","PeriodicalId":165912,"journal":{"name":"2018 3rd Biennial South African Biomedical Engineering Conference (SAIBMEC)","volume":"33 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125529200","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Architecture of a village small cell network for mobile health","authors":"B. Malila, Tinashe Ernest Mutsvangwa, T. Douglas","doi":"10.1109/SAIBMEC.2018.8363172","DOIUrl":"https://doi.org/10.1109/SAIBMEC.2018.8363172","url":null,"abstract":"This paper proposes the architecture of a village small cell network for rural and remote areas for enabling the delivery of healthcare services using mHealth applications and systems. The proposed architecture is based on emerging 5G technologies and is expected to address the need for cost-effective, high capacity and reliable mobile connectivity in rural areas. This will make it possible to provide more innovative video and Internet-based mHealth applications and services, in addition to the current SMS and voice-based services. Future work will include addressing issues of security, privacy and data integrity of patient health information.","PeriodicalId":165912,"journal":{"name":"2018 3rd Biennial South African Biomedical Engineering Conference (SAIBMEC)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133717032","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
T. A. Silva, M. Costa, R. Stelmach, Peter K. Bley, M. A. Gutierrez, C. Filho
{"title":"Development of a system mobile-based to assist asthma self-management","authors":"T. A. Silva, M. Costa, R. Stelmach, Peter K. Bley, M. A. Gutierrez, C. Filho","doi":"10.1109/SAIBMEC.2018.8363186","DOIUrl":"https://doi.org/10.1109/SAIBMEC.2018.8363186","url":null,"abstract":"Self-management is a major factor in the treatment of asthma and contributes to reduce morbidity in adults and children. However, adherence to self-management depends on a number of factors, including literacy and understanding of disease and health concepts. This paper proposes a system based on the use of mobile devices in order to provide tools to help with adherence to self-management, in addition to propose a narrowing between doctor and patient communication. The proposed system consists of a mobile application for the Android platform, a WEB application and online features of Firebase. In the usability evaluation of the system, most users (82%) rated it as useful and would use the system regularly to support the self-management of asthma.","PeriodicalId":165912,"journal":{"name":"2018 3rd Biennial South African Biomedical Engineering Conference (SAIBMEC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131520401","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A case of healthcare supply chain visibility in South Africa","authors":"Munyaradzi Bvuchete, S. Grobbelaar, J. van Eeden","doi":"10.1109/SAIBMEC.2018.8363179","DOIUrl":"https://doi.org/10.1109/SAIBMEC.2018.8363179","url":null,"abstract":"Statistically 8.5% of annual gross domestic (GDP) expenditure in South Africa is on healthcare but the country still experience poor healthcare outcomes. The South African public healthcare system still experience challenges such as escalated healthcare costs, and medicines stock outs. With 25%–30% of the costs emanating from the healthcare supply chain and 80% of the population dependent on the public healthcare system, undoubtedly, this represents a significant potential for more effective management and improvement of the healthcare supply chain with respect to the reduction of cost and medicines access. However, trying to create a balance between reducing healthcare supply chain costs and improving access results in healthcare supply chain complexity. The literature searched appears to suggest that supply chain visibility and demand driven supply chain management approaches can help address such complexities and challenges. Therefore it is the prime intention of this study to explore: (i) what is supply chain visibility (ii) the importance of supply chain visibility in healthcare (ii) how the Vodacom/Mezzanine ware Stock Visibility Solution (SVS) can be used as a tool to facilitate supply chain visibility (iii) how the Stock Visibility Solution can enable demand driven supply chain management.","PeriodicalId":165912,"journal":{"name":"2018 3rd Biennial South African Biomedical Engineering Conference (SAIBMEC)","volume":"371 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122923963","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Platforms in healthcare innovation ecosystems: The lens of an innovation intermediary","authors":"C. Ngongoni, S. Grobbelaar, C. Schutte","doi":"10.1109/SAIBMEC.2018.8363191","DOIUrl":"https://doi.org/10.1109/SAIBMEC.2018.8363191","url":null,"abstract":"Healthcare innovation has made progressive strides. Innovative solutions now tend to incorporate device integration, data collection and data analysis linked across a diverse range of actors building platform-centric healthcare ecosystems. The interconnectedness and inter-disciplinarity of the ecosystems bring with it a number of vital issues around how to strategically manage such a complex system. This paper highlights the importance of innovation intermediaries particularly in a platform-centric ecosystem such as the healthcare industry. It serves as a reminder of why it is important for healthcare technologists to consider proactive ways to contribute to the innovation ecosystem by creating devices with the platform perspective in mind.","PeriodicalId":165912,"journal":{"name":"2018 3rd Biennial South African Biomedical Engineering Conference (SAIBMEC)","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115802302","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Bianca Sutcliffe, L. Wiggins, D. Rubin, V. Aharonson
{"title":"Voice quality enhancement for vocal tract rehabilitation","authors":"Bianca Sutcliffe, L. Wiggins, D. Rubin, V. Aharonson","doi":"10.1109/SAIBMEC.2018.8363197","DOIUrl":"https://doi.org/10.1109/SAIBMEC.2018.8363197","url":null,"abstract":"Vocal rehabilitation devices used by patients after Laryngectomy produce an unnatural sounding speech. Our study aims at increasing the quality of these synthetically generated voices by implementing human-like characteristics. A simplified source filter model, linear predictive coding coefficients and line spectral frequencies were used to model the vocal tract and manipulate the acoustic features of their resulting speech. Two different mapping functions were employed to convert between the features of synthetically generated voice and those of a human voice: A Gaussian mixture model and a linear regression model. The models were trained on a set of 50 human and 50 synthetic voice utterances. Both mapping functions yielded significant changes in the transformed synthetic voices and their spectra were similar to the human voices. The linear regression model mapping produced slightly better results compared to the Gaussian mixture model mapping. Listeners' tests confirmed this result, but indicated that voices re-synthesized from the transformed model coefficients, improved on the synthetic voice but still sounded unnatural. This may imply that the vocal tract model is lacking in information that produces the subjective perception of “artificial speech”. Future work will investigate an elaborate model which will include the speech production excitation and radiation signals and the transformation of their features. These models have the potential to improve the conversion of synthetically generated electrolarynx voice into human sounding one.","PeriodicalId":165912,"journal":{"name":"2018 3rd Biennial South African Biomedical Engineering Conference (SAIBMEC)","volume":"75 2-3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133055084","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Development of a signal processing and feature extraction framework for the safe passage study","authors":"E. Kieser, H. Odendaal, D. van den Heever","doi":"10.1109/SAIBMEC.2018.8363193","DOIUrl":"https://doi.org/10.1109/SAIBMEC.2018.8363193","url":null,"abstract":"This work describes a framework that was developed to export and analyze maternal heartrate and uterine activity from a Monica AN24 ECG recording device. 9478 Traces from 5356 patients were processed, the mean recording length was 47 minutes. The framework implemented additional signal cleaning algorithms and extracted accelerations, decelerations, baseline traces, commonly used heartrate variability parameters, phase rectified signal average wavelets and identified beats that were missed by the Monica detection algorithm.","PeriodicalId":165912,"journal":{"name":"2018 3rd Biennial South African Biomedical Engineering Conference (SAIBMEC)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132437882","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Electrospun bioresorbable tissue repair scaffolds: From laboratory to clinic","authors":"M. Raxworthy, L. P. Serino, P. Iddon","doi":"10.1109/SAIBMEC.2018.8363177","DOIUrl":"https://doi.org/10.1109/SAIBMEC.2018.8363177","url":null,"abstract":"The healing of soft tissue wounds and injury sites is a complex process requiring the participation of many different cells, tissues, proteins and tissue components in a coordinated manner. We describe the development of regenerative, electrospun, bioresorbable advanced material tissue scaffolds providing three dimensional (3D) structure for cells involved in the repair of soft tissue injuries. One product, EktoTherix™ provides a micron-scale 3D architecture to enhance the recruitment of reparative cells onto this temporary support and in this way the body's capacity to repair itself is utilised. EktoTherix and other electrospun tissue scaffolds have been translated from early stage laboratory work through manufacturing process development and clinical investigation.","PeriodicalId":165912,"journal":{"name":"2018 3rd Biennial South African Biomedical Engineering Conference (SAIBMEC)","volume":"331 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127571746","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Hyperspectral imaging for cancer detection and classification","authors":"M. Nathan, A. S. Kabatznik, A. Mahmood","doi":"10.1109/SAIBMEC.2018.8363180","DOIUrl":"https://doi.org/10.1109/SAIBMEC.2018.8363180","url":null,"abstract":"The design and implementation of a classification system for hyperspectral images of cancer cell cultures is discussed. The ability to distinguish between different types of cancers is of particular importance in this study. This possibility allows for metastasised tumours to be identified, in the near infrared regions of 920 nm–2514 nm and thus the origin of a tumour. Using Principal Component Analysis (PCA) to find the features for Artificial Neural Networks (ANNs) and Support Vector Machines (SVMs), different cancer types could be distinguished with an overall accuracy of 87.4 % using an ANN solution whereas the SVM accuracy ranged from 73 %–88.9 % due to the One-Vs-One (OVO) multiclass technique implemented.","PeriodicalId":165912,"journal":{"name":"2018 3rd Biennial South African Biomedical Engineering Conference (SAIBMEC)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121490197","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}