An Explainable Self-Attention Deep Neural Network for Detecting Mild Cognitive Impairment Using Multi-input Digital Drawing Tasks

Ruengchaijatuporn, Natthanan; Chatnuntawech, Itthi; Teerapittayanon, Surat; Sriswasdi, Sira; Itthipuripat, Sirawaj; Chotibut, Thiparat; Chunharas, Chaipat

doi:10.1101/2021.12.15.472738

Cited by 4 publications

(13 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…8. Even though some studies used XAI tools in AD prediction, they did not consider disease biomarkers such as MRI volumetry, cortical thickness, etc., which correlate well with dementia [117,119]. 9.…”

Section: Xai Researchers Often Resort To Self-intuition To De-mentioning

confidence: 83%

“…All models were trained and evaluated on ADNI, AIBL and OASIS datasets. Deep learning models have been created by Natthanan et al [117] to classify MCI and AD utilizing tasks like the traditional clock drawing, cube-copying, and trail-making test. Multiple drawing task images are used as input and have proved to have significantly improved the classification performance between HC and AD.…”

Section: Resultsmentioning

confidence: 99%

“…Ruengchaijatuporn et al [117] proposed a two-way classification for differentiating MCI vs. HC patients using the VGG16 and custom CNN architecture incorporating a self-attention mechanism (Conv-Att). The authors considered digital drawings (clock, cube, and trail making) collected from HC and MCI patients to train the models.…”

Section: Global Posthoc Model Agnosticmentioning

confidence: 99%

“…Combining the localized scores creates a high-resolution and classdiscriminative visualization. Natthanan et al [117] use images of bedside tasks like clock drawing tests, cubecopying and tail-making tests to classify between HC and AD patients in a deep neural network. For improving interpretation, convolutional self-attention and output of class probability as a soft label is applied with the GradCAM tool to visualise the model for essential input regions.…”

Section: Global Posthoc Model Agnosticmentioning

confidence: 99%

“…The authors focused on using AI, HCI, and XAI in healthcare. There have been several noteworthy applications of XAI in AD classification too [113,114,115,116,117,118,119,120,121,122,123,124,125,126,127] However, an exclusive systematic review article on XAI for AD classification that points to various XAI frameworks and Blackbox models used inside these frameworks is yet to be proposed by the research community.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Application of Explainable Artificial Intelligence in Alzheimer's Disease Classification: A Systematic Review

Vimbi¹,

Shaffi²,

Mahmud

et al. 2023

Preprint

View full text Add to dashboard Cite

Context: Artificial Intelligence (AI) in the medical domain has achieved remarkable results on various metrics primarily due to recent advancements in computational capabilities. However, AI models used for Computer Aided Diagnosis (CAD) have limited acceptance and trust due to their typical {Blackbox} nature. Consequently, explainable AI (XAI) is needed to justify the trustworthiness of the machine's predictions. Approach: In this work, we undertake a systematic review based on PRISMA guidelines on research articles investigating Alzheimer's Disease (AD) prediction with XAI for the past decade. The review was driven by carefully formulated research questions (RQ) which helped categorize AI models into different XAI methods(Post-hoc, Ante-hoc, Model-Agnostic, Model-Specific, etc) and frameworks (LIME, SHAP, GradCAM, LRP, etc.). Summary: This categorisation provides broad coverage of the interpretation spectrum from intrinsic (model-specific, ante-hoc models) to complex patterns (model-agnostic, post-hoc models) and by taking local explanations to a global scope. Additionally, the study categorizes merit in terms of different forms of interpretation to provide in-depth insight into the factors that support the clinical diagnosis of AD. Finally, limitations and open research challenges are outlined, and possible prospects are presented.

show abstract

Section: Xai Researchers Often Resort To Self-intuition To De-mentioning

confidence: 83%

Section: Resultsmentioning

confidence: 99%

Section: Global Posthoc Model Agnosticmentioning

confidence: 99%

Section: Global Posthoc Model Agnosticmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Application of Explainable Artificial Intelligence in Alzheimer's Disease Classification: A Systematic Review

Vimbi¹,

Shaffi²,

Mahmud

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

Explainable Artificial Intelligence in Alzheimer’s Disease Classification: A Systematic Review

Viswan,

Shaffi,

Mahmud

et al. 2023

Cogn Comput

View full text Add to dashboard Cite

The unprecedented growth of computational capabilities in recent years has allowed Artificial Intelligence (AI) models to be developed for medical applications with remarkable results. However, a large number of Computer Aided Diagnosis (CAD) methods powered by AI have limited acceptance and adoption in the medical domain due to the typical blackbox nature of these AI models. Therefore, to facilitate the adoption of these AI models among the medical practitioners, the models' predictions must be explainable and interpretable. The emerging field of explainable AI (XAI) aims to justify the trustworthiness of these models' predictions. This work presents a systematic review of the literature reporting Alzheimer's disease (AD) detection using XAI that were communicated during the last decade. Research questions were carefully formulated to categorise AI models into different conceptual approaches (e.g., Post-hoc, Ante-hoc, Model-Agnostic, Model-Specific, Global, Local etc.) and frameworks (Local Interpretable Model-Agnostic Explanation or LIME, SHapley Additive exPlanations or SHAP, Gradient-weighted Class Activation Mapping or GradCAM, Layer-wise Relevance Propagation or LRP, etc.) of XAI. This categorisation provides broad coverage of the interpretation spectrum from intrinsic (e.g., Model-Specific, Ante-hoc models) to complex patterns (e.g., Model-Agnostic, Post-hoc models) and by taking local explanations to a global scope. Additionally, different forms of interpretations providing in-depth insight into the factors that support the clinical diagnosis of AD are also discussed. Finally, limitations, needs and open challenges of XAI research are outlined with possible prospects of their usage in AD detection.

show abstract

Combination of Paper and Electronic Trail Making Tests for Automatic Analysis of Cognitive Impairment: Development and Validation Study

Zhang¹,

Zheng²,

Tang³

et al. 2023

J Med Internet Res

View full text Add to dashboard Cite

Background Computer-aided detection, used in the screening and diagnosing of cognitive impairment, provides an objective, valid, and convenient assessment. Particularly, digital sensor technology is a promising detection method. Objective This study aimed to develop and validate a novel Trail Making Test (TMT) using a combination of paper and electronic devices. Methods This study included community-dwelling older adult individuals (n=297), who were classified into (1) cognitively healthy controls (HC; n=100 participants), (2) participants diagnosed with mild cognitive impairment (MCI; n=98 participants), and (3) participants with Alzheimer disease (AD; n=99 participants). An electromagnetic tablet was used to record each participant’s hand-drawn stroke. A sheet of A4 paper was placed on top of the tablet to maintain the traditional interaction style for participants who were not familiar or comfortable with electronic devices (such as touchscreens). In this way, all participants were instructed to perform the TMT-square and circle. Furthermore, we developed an efficient and interpretable cognitive impairment–screening model to automatically analyze cognitive impairment levels that were dependent on demographic characteristics and time-, pressure-, jerk-, and template-related features. Among these features, novel template-based features were based on a vector quantization algorithm. First, the model identified a candidate trajectory as the standard answer (template) from the HC group. The distance between the recorded trajectories and reference was computed as an important evaluation index. To verify the effectiveness of our method, we compared the performance of a well-trained machine learning model using the extracted evaluation index with conventional demographic characteristics and time-related features. The well-trained model was validated using follow-up data (HC group: n=38; MCI group: n=32; and AD group: n=22). Results We compared 5 candidate machine learning methods and selected random forest as the ideal model with the best performance (accuracy: 0.726 for HC vs MCI, 0.929 for HC vs AD, and 0.815 for AD vs MCI). Meanwhile, the well-trained classifier achieved better performance than the conventional assessment method, with high stability and accuracy of the follow-up data. Conclusions The study demonstrated that a model combining both paper and electronic TMTs increases the accuracy of evaluating participants’ cognitive impairment compared to conventional paper-based feature assessment.

show abstract

An Explainable Self-Attention Deep Neural Network for Detecting Mild Cognitive Impairment Using Multi-input Digital Drawing Tasks

Cited by 4 publications

References 22 publications

Application of Explainable Artificial Intelligence in Alzheimer's Disease Classification: A Systematic Review

Application of Explainable Artificial Intelligence in Alzheimer's Disease Classification: A Systematic Review

Explainable Artificial Intelligence in Alzheimer’s Disease Classification: A Systematic Review

Combination of Paper and Electronic Trail Making Tests for Automatic Analysis of Cognitive Impairment: Development and Validation Study

Contact Info

Product

Resources

About