건식 뇌파 데이터를 활용한 경도인지장애 진단 인공지능 모델에 관한 연구
A Study on Artificial Intelligence Model for Diagnosis of Mild Cognitive Impairment Using Dry Electroencephalogram Data
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
치매는 기억, 인지장애를 동반하는 노인질환으로, 증상 완화와 중증화 지연을 위해선 조기진단이 매우 중요하다. 그러나 현재 치매의 진단은 큰 비용과 높은 전문성을 요구하여 조기진단 및 치료가 어려운 실정이다. 본 연구에서는 건식 방식으로 수집된 19채널 뇌파(electroencephalogram) 데이터(정상군 50명, 경도인지장애군 175명)를 머신러닝 및 딥러닝 모델의 학습 및 테스트에 사용하여 치매의 조기진단에 적합한 모델 및 하이퍼파라미터 세팅을 제안한다. 기존의 연구들이 습식 방식으로 수집된 64채널 고해상도 뇌파 데이터를 활용한 반면, 본 연구는 연구자 및 환자의 측정부담이 적은 건식 방식의 19채널 뇌파 데이터를 활용했다는 점에서 차별성을 가진다. 실험은 앙상블 기반의 AutoML 머신러닝 알고리즘인 Auto-sklearn과 딥러닝 모델 3종(ShallowFBCSPNet, Deep4Net, EEGNet)으로 이진 분류기를 훈련한 후 성능을 비교하는 방식으로 진행되었다. 그 결과, EEGNet이 가장 우수한 성능 (정확도=68.9%)을 냈다. 다음으로, 데이터 불균형으로 인한 과적합 문제를 해결하기 위해 EEGNet에 데이터 불균형 처리 알고리즘 4종(class weight, Gaussian noise, frequency shift, undersampling)을 각각 적용한 뒤 성능 개선 여부를 확인했다. 그 결과, EEGNet에 Gaussian Noise를 적용했을 때 가장 우수한 성능 (정확도=78.9%)을 냈다. 본 연구 결과는 19채널 건식 뇌파 데이터와 제안된 방법의 조합이 치매의 조기진단에 활용될 가능성이 있음을 보인다.
Abstract
Dementia, characterized by memory and cognitive impairment, necessitates early detection for symptom mitigation and progression delay. However, existing diagnostic approaches are resource-intensive, demanding both high cost and expertise, which complicates early intervention. In this study, we propose an optimal model and hyperparameter settings suitable for early dementia diagnosis using machine learning and deep learning models trained and tested on 19-channel electroencephalogram (EEG) data (50 normal subjects, 175 mild cognitive impairment subjects) collected via a dry methodology. While previous studies utilized 64-channel high-resolution EEG data acquired through a wet methodology, this study is distinct in its use of 19-channel dry EEG data, which reduces the burden on researchers and patients. The experiment was conducted by training a binary classifier using an ensemble-based AutoML algorithm, Auto-sklearn, and three deep learning models (ShallowFBCSPNet, Deep4Net, EEGNet), followed by a comparison of their respective performances. EEGNet demonstrated the best results (accuracy = 68.9%). Next, to address the overfitting problem due to data imbalance, four data imbalance processing algorithms (class weight, Gaussian noise, frequency shift, and undersampling) were applied to EEGNet. The best performance (accuracy = 78.9%) was achieved with Gaussian noise applied to EEGNet. This study’s findings suggest the potential utility of combining 19-channel dry EEG data with the proposed method for early dementia diagnosis.
참고문헌 (36)
- Klementieva, O., "Pre-plaque conformational changes in Alzheimer’s disease-linked Aβ and APP", Nature communications, 8(1), pp.14726~ (2017)
- Binder, Lester I., "Tau, tangles, and Alzheimer's disease", Biochimica et Biophysica Acta (BBA)-Molecular Basis of Disease, 1739(2-3), pp.216~223 (2005)[DOI]
- Acharya, U. Rajendra, "Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals", Computers in biology and medicine, 100, pp.270~278 (2018)
- Aboalayon, Khald Ali I, "Sleep stage classification using EEG signal analysis : a comprehensive survey and new investigation", Entropy, 18(9), pp.272~ (2016)
- Ebrahimi, Farideh, "Automatic sleep stage classification based on EEG signals by using neural networks and wavelet packet coefficients", 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (2008), IEEE
- Berka, Chris, "EEG correlates of task engagement and mental workload in vigilance, learning, and memory tasks", Aviation, space, and environmental medicine, 78(5), pp.B231~B244 (2007)[DOI]
- Malmivuo, Jaakko, "Bioelectromagnetism: principles and applications of bioelectric and biomagnetic fields" (1995), Oxford University Press
- Urigüen, Jose Antonio, "EEG artifact removal—state-ofthe-art and guidelines", Journal of neural engineering, 12(3), pp.031001~ (2015)
- Gratton, Gabriele, "Dealing with artifacts : The EOG contamination of the event-related brain potential", Behavior Research Methods, Instruments, & Computers, 30(1), pp.44~53 (1998)
- Craik, Alexander, "Deep learning for electroencephalogram(EEG)classification tasks : a review", Journal of neural engineering, 16(3), pp.031001~ (2019)
- Bos, Danny Oude, "EEG-based emotion recognition", The influence of visual and auditory stimuli, 56(3), pp.1~17 (2006)
- 손귀영, "EEG 신호 기반의 특징벡터 형성 및 감정인식을 위한 기계학습", 한국차세대컴퓨팅학회 논문지, 16(2), pp.72~79 (2020), 한국차세대컴퓨팅학회[DOI]
- 손귀영, "기계학습을 이용한 EEG 신호 기반 감정상태 평가 및 분류 검증", 한국차세대컴퓨팅학회 논문지, 18(1), pp.37~46 (2022), 한국차세대컴퓨팅학회[DOI]
- 류제우, "EEG 기반 감정인식을 위한 주석 레이블링과 EEG Topography 레이블링 기법의 비교 고찰", 한국차세대컴퓨팅학회 논문지, 15(3), pp.16~24 (2019), 한국차세대컴퓨팅학회[DOI]
- Acharya, U. Rajendra, "Automated EEG-based screening of depression using deep convolutional neural network", Computer methods and programs in biomedicine, 161, pp.103~113 (2018)
- Mazaheri, Ali, "EEG oscillations during word processing predict MCI conversion to Alzheimer's disease", NeuroImage : Clinical, 17, pp.188~197 (2018)
- Kulkarni, N. N., "Extracting salient features for EEG-based diagnosis of Alzheimer's disease using support vector machine classifier", IETE Journal of Research, 63(1), pp.11~22 (2017)
- Trambaiolli, Lucas R., "Improving Alzheimer's disease diagnosis with machine learning techniques", Clinical EEG and neuroscience, 42(3), pp.160~165 (2011)
- McBride, Joseph C., "Spectral and complexity analysis of scalp EEG characteristics for mild cognitive impairment and early Alzheimer's disease", Computer methods and programs in biomedicine, 114(2), pp.153~163 (2014)
- Anderer, P., "Discrimination between demented patients and normals based on topographic EEG slow wave activity : comparison between z statistics, discriminant analysis and artificial neural network classifiers", Electroencephalography and clinical neurophysiology, 91(2), pp.108~117 (1994)
- Pritchard, Walter S., "EEG-based, neural-net predictive classification of Alzheimer's disease versus control subjects is augmented by non-linear EEG measures", Electroencephalography and clinical Neurophysiology, 91(2), pp.118~130 (1994)
- Rodrigues, Pedro, "Artificial neural networks in the discrimination of alzheimer’s disease", ENTERprise Information Systems: International Conference, CENTERIS 2011, pp.2011~ (2011), Springer Berlin Heidelberg
- Ruiz-Gómez, Saúl J., "Automated multiclass classification of spontaneous EEG activity in Alzheimer’s disease and mild cognitive impairment", Entropy, 20(1), pp.35~ (2018)
- Ahmadlou, Mehran, "New diagnostic EEG markers of the Alzheimer’s disease using visibility graph", Journal of neural transmission, 117, pp.1099~1109 (2010)
- Ieracitano, Cosimo, "A convolutional neural network approach for classification of dementia stages based on 2D-spectral representation of EEG recordings", Neurocomputing, 323, pp.96~107 (2019)
- You, Zeng, "Alzheimer's disease classification with a cascade neural network", Frontiers in Public Health, 8, pp.584387~ (2020)
- Sazgar, Mona, "Absolute Epilepsy and EEG Rotation Review: Essentials for Trainees", pp.149~162 (2019)
- Schirrmeister, Robin Tibor, "Deep learning with convolutional neural networks for EEG decoding and visualization", Human brain mapping, 38(11), pp.5391~5420 (2017)
- Lawhern, Vernon J., "EEGNet : a compact convolutional neural network for EEG-based brain–computer interfaces", Journal of neural engineering, 15(5), pp.056013~ (2018)
- Feurer, Matthias, "Efficient and robust automated machine learning", Advances in neural information processing systems, 28 (2015)
- Feurer, Matthias, "Auto-sklearn 2. 0 : Hands-free automl via meta-learning", J Machine Learn Res, 23(261), pp.1~61 (2020)
- Chawla, Nitesh V., "SMOTE : synthetic minority over-sampling technique", Journal of artificial intelligence research, 16, pp.321~357 (2002)
- Schwabedal, Justus TC, "Addressing class imbalance in classification problems of noisy signals by using fourier transform surrogates" (2018)
- Wang, Fang, "Data augmentation for EEG-based emotion recognition with deep convolutional neural networks", MultiMedia Modeling: 24th International Conference, MMM 2018 (2018), Springer International Publishing
- Cheng, Joseph Y., "Subject-aware contrastive learning for biosignals" (2020)
- Mohsenvand, Mostafa Neo, "Contrastive representation learning for electroencephalogram classification", Machine Learning for Health. PMLR (2020)