Loku, Lindita and Fetaji, Bekim and Krstev, Aleksandar (2018) Automated medical data analyses of diseases using big data. Knowledge - International Journal, Scientific Papers, 28.5 (5). pp. 1719-1724. ISSN 2545-4439
Preview |
Text
KNOWLEDGE – International Journal Vol. 28.5 December, 2018.pdf Download (949kB) | Preview |
Abstract
Diagnosis of different diseases is a growing concern and one of the most difficult challenges for modern medicine. Current diagnosis technologies (e.g. magnetic resonance imaging, electroencephalogram) produce huge quantity data (in size and dimension) for detection, monitoring and treatment of neurological diseases. In general, analysis of those medical big data is performed manually by experts to identify and understand the abnormalities. It is really difficult task for a person to accumulate, manage, analyse and assimilate such large volumes of data by visual inspection. As a result, the experts have been demanding computerised diagnosis systems, called “computer-aided diagnosis (CAD)” that can automatically detect the neurological abnormalities using the medical big data. This system improves consistency of diagnosis and increases the success of treatment, save lives and reduce cost and time. Recently, there are some research works performed in the development of the CAD systems for management of medical big data for diagnosis assessment. Such data analyses to realize diagnosis is very interesting for diabetes and autism. Many companies and research groups are working to treat diabetes, but preventing the disease will have a greater impact on health in at-risk groups. A team of US researchers are using data analytics to create a precision medicine approach to prevention of diabetes that steers efforts towards those who are at highest risk of developing the disease and who would benefit most from drug treatment or preventive lifestyle strategies. The analyses yielded most important 17 factors that were assessed that could predict an individual’s risk of diabetes. Autism Spectrum Disorder (ASD) is characterized by difficulties in social communication, social interactions, and repetitive behaviors. It is diagnosed during the first three years of life. Early and intensive interventions have been shown to improve the developmental trajectory of the affected children. The earlier the diagnosis, the sooner the intervention therapy can begin, thus, making early diagnosis is set as our important research goal. Because ASD is not a neurodegenerative disorder, many of the core symptoms can improve as the individuals learn to cope with their environments under the right conditions. The earlier the age at which intervention can be started, the better their learning and daily function can be facilitated. Recent Big Data software packages and innovations in Artificial Intelligence have tremendous potential to assist with early diagnosis and improve intervention programs. The research study will focus on methodological evaluation of emerging technologies and will investigate by comparing different data sets and find a pattern that can be established as prognosis system. The research study investigated peer-reviewed studies in order to understand the current status of empirically-based evidence on the clinical applications in the diagnosis and treatment of Autism Spectrum Disorders (ASD). Also a survey and investigation on different sensing technologies for ASD like: eye trackers, movement trackers, electrodermal activity monitors, tactile sensors, vocal prosody and speech detectors. We assess their effectiveness and study their limitations. We also examine the challenges faced by this growing field that need to be addressed before these technologies can perform up to their theoretical potential In some cases, a technology is unable to deliver up to its potential, not due to the hardware but due to the inefficiency of the accompanied algorithms, as in the case of classifiers for repetitive behavior detection. Therefore, equal emphasis needs to be placed on the improvement of all aspects of a tracking technology. The nature of the sensors makes the tracked data very sensitive to experimental and systematic errors, often causing the collected data to be discarded due to unreliability. Efforts to reduce such inaccuracies can significantly improve the performance and potential of the overall technology. By collecting specific data, these sensors may be able to acquire objective measures that can be used to identify symptoms specific to ASD. The contribution of the analyses will assist not only the therapists and clinicians in their selection of suitable tools, but to also guide the developers of the technologies and devise new algorithm in prediction of autism.
| Item Type: | Article |
|---|---|
| Subjects: | Natural sciences > Computer and information sciences Engineering and Technology > Medical engineering Medical and Health Sciences > Other medical sciences Social Sciences > Other social sciences |
| Divisions: | Faculty of Computer Science |
| Depositing User: | Aleksandar Krstev |
| Date Deposited: | 06 Feb 2019 08:09 |
| Last Modified: | 06 Feb 2019 08:09 |
| URI: | https://eprints.ugd.edu.mk/id/eprint/21507 |
Actions (login required)
 |
View Item |