Artificial neural networks in the discrimination of Alzheimer's disease using biomarkers data

Aljović, Almir; Badnjević, Almir; Gurbeta, Lejla

doi:10.1109/meco.2016.7525762

Cited by 47 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generally speaking, with the increasing popularity of artificial intelligence, telemedicine service systems show great potential [42,43]. Online remote fetal cardiac monitoring technology has become a popular area for research in recent years.…”

Section: Discussionmentioning

confidence: 99%

Application of remote fetal heart rate monitoring via internet in late pregnancy during the COVID-19 pandemic

Zhou

Jin

Jiang

et al. 2023

THC

View full text Add to dashboard Cite

BACKGROUND: Internet-related technologies have rapidly developed and started to impact the traditional medical practices, which combined wireless communication technology as well as “cloud service” technology with electronic fetal heart monitoring have become a mainstream tendency. OBJECTIVE: To investigate the clinical application value of remote fetal heart rate monitoring mode (RFHRM) on late pregnancy during the coronavirus disease (COVID-19) pandemic. METHODS: From March 2021 to February 2022, we recruited 800 cases of pregnant women received prenatal examination at the Anhui Province Maternity and Child Healthcare Hospital. These pregnant women were randomly divided into two groups: the control group (n= 400), which was given traditional management, and the observation group (n= 400), which received remote monitoring technology on this basis. The two groups were compared with neonatal asphyxia, pregnancy outcomes, Edinburgh postnatal depression scale (EPDS), prenatal examination expenses and total time consumption. RESULTS: There were no statistically significant differences between the groups in pregnancy outcome and neonatal outcome (P> 0.05). However, total EPDS score of 12.5% pregnant women in TPE group were higher than 12. The TPE group had significantly higher mean EPDS scores compared with the RFHRM group (7.79 ± 3.58 vs 5.10 ± 3.07; P< 0.05). The results showed a significant difference in maternity expenses (2949.83 ± 456.07 vs 2455.37 ± 506.67; P< 0.05) and total time consumption (42.81 ± 7.60 vs 20.43 ± 4.16; P< 0.05) between the groups. CONCLUSION: Remote fetal heart rate monitoring via Internet served as an innovative, acceptable, safe and effective reduced-frequency prenatal examination model without affecting the outcome of perinatology of pregnant women with different risk factors.

show abstract

Section: Discussionmentioning

confidence: 99%

Application of remote fetal heart rate monitoring via internet in late pregnancy during the COVID-19 pandemic

Zhou

Jin

Jiang

et al. 2023

THC

View full text Add to dashboard Cite

show abstract

“…But that model is train with limited number of MRI images. Deep neural network is developed for feature extraction by [22].…”

Section: Related Workmentioning

confidence: 99%

“…MRI techniques are costly. In addition, patients also need to have their brain scanned many times to review the changes in their structure during the whole process, raising the cost even further [22]. User defined discriminate features are extracted for the classification of AD from the brain imaging data by using these methods.…”

Section: Related Workmentioning

confidence: 99%

Diagnosis of Alzheimer’s Disease using Comparative Study on Machine Learning Models

Zohra

Akram²,

Din

2021

VFAST trans. softw. eng.

View full text Add to dashboard Cite

The method of diagnosing and treating diseases can be improved by identifying the genes that cause diseases. Alzheimer’s disease (AD) is one of the neurodegenerative disease that slowly destroys memory as well as thinking abilities. It’s important to diagnose Alzheimer’s disease (AD) early on so that adequate treatment can be given to patient. That article compares various machine learning models for identify Alzheimer’s Disease and proves that which algorithm gives the most reliable results in detecting AD in advance. Machine learning is a backbone of technology and everything in our life related to machine learning technologies. In this study various biomarkers are developed based on different machine learning classifiers like Random Forest, K-NN, Support Vector Machine, AdaBoost and XgBoost for AD gene detection. Genome data is extracted from NCBI related to Alzheimer disease. After that features are extracted from this genome data. Then above machine learning classifiers are train on these features. Different results are obtained by using Self-Consistency test and 10 Cross Validation test. Random Forest in both test gives 100% results. KNN gives 73.17% and 86.33%, SVM gives 100% and 97% AdaBoost gives 74.02% and 87.42%, XgBoost gives 86.04%and 92.56%accuracy for self-consistency and 10 Cross Validation test respectively.

show abstract

“…Developing a new AD diagnostic model with a different approach than existing studies, Sun et al (2022) obtained the area under the curve (AUC) value of 0.953 and accuracy value of 0.914 by using the ANN model with the data they accessed from the Gene Expression Omnibus (GEO) database. Again with a different approach, in the study of Aljović et al (2016), it was stated that an accurate classification was made by using biomarkers in the cerebrospinal fluid together with the ANN methodology, with an accuracy of 95.5% with demented test data and 91.43% with nondemented test data. In the study, the material and method are explained in the second part.…”

Section: Introductionmentioning

confidence: 99%

Ann Based Early Detection of Alzheimer Disease on Selected Features

YILDIZ,

YILDIZ

2023

Mühendislik Bilimleri Ve Tasarım Dergisi

View full text Add to dashboard Cite

Alzheimer's Disease (AD) is a type of dementia, also called cognitive impairment. In cases where measures are not taken against the disease, it may result in a decrease in the quality of life of the person and result in very serious consequences. While it presents with neurological consequences such as decreased functions of thinking and memory, it may result in death in advanced cases. The fact that the treatment is not completely possible makes the place of early diagnosis and intervention important for AD. As a result of the researches carried out in the study, it was seen that there are many studies and scientific content within the framework of AD. A method for early diagnosis of the disease was evaluated by using an open source shared dataset, which includes some disease-specific values and demographic characteristics. By using Artificial Neural Networks (ANN) model, which is one of the machine learning methods, it is aimed to be useful for other studies to take precautions for early detection of the disease. With the ANN, which was classified as dementia and non-dementia individuals, Root Mean Square Error (RMSE) value 0.2302, Mean Absolute Error (MAE) value 0.1899 and accuracy rate of 98.5% was obtained.

show abstract

Artificial neural networks in the discrimination of Alzheimer's disease using biomarkers data

Cited by 47 publications

References 15 publications

Application of remote fetal heart rate monitoring via internet in late pregnancy during the COVID-19 pandemic

Application of remote fetal heart rate monitoring via internet in late pregnancy during the COVID-19 pandemic

Diagnosis of Alzheimer’s Disease using Comparative Study on Machine Learning Models

Ann Based Early Detection of Alzheimer Disease on Selected Features

Contact Info

Product

Resources

About