In-depth insights into Alzheimer's disease by using explainable machine learning approach

HiMAL: Multimodal Hierarchical Multi-task Auxiliary Learning framework for predicting Alzheimer's disease progression

Objective

We aimed to develop and validate a novel multimodal framework Hierarchical Multi-task Auxiliary Learning (HiMAL) framework, for predicting cognitive composite functions as auxiliary tasks that estimate the longitudinal risk of transition from Mild Cognitive Impairment (MCI) to Alzheimer's Disease (AD).

Materials and Methods

HiMAL utilized multimodal longitudinal visit data including imaging features, cognitive assessment scores, and clinical variables from MCI patients in the Alzheimer's Disease Neuroimaging Initiative dataset, to predict at each visit if an MCI patient will progress to AD within the next 6 months. Performance of HiMAL was compared with state-of-the-art single-task and multitask baselines using area under the receiver operator curve (AUROC) and precision recall curve (AUPRC) metrics. An ablation study was performed to assess the impact of each input modality on model performance. Additionally, longitudinal explanations regarding risk of disease progression were provided to interpret the predicted cognitive decline.

Results

Out of 634 MCI patients (mean [IQR] age: 72.8 [67-78], 60% male), 209 (32%) progressed to AD. HiMAL showed better prediction performance compared to all state-of-the-art longitudinal single-modality singe-task baselines (AUROC = 0.923 [0.915-0.937]; AUPRC = 0.623 [0.605-0.644]; all P < .05). Ablation analysis highlighted that imaging and cognition scores with maximum contribution towards prediction of disease progression.

Discussion

Clinically informative model explanations anticipate cognitive decline 6 months in advance, aiding clinicians in future disease progression assessment. HiMAL relies on routinely collected electronic health records (EHR) variables for proximal (6 months) prediction of AD onset, indicating its translational potential for point-of-care monitoring and managing of high-risk patients.

Clinical variables contributing to the identification of biologically defined subgroups within cognitively unimpaired and mild cognitive impairment individuals

BACKGROUND

A lack of consensus exists in linking demographic, behavioral, and cognitive characteristics to biological stages of dementia, defined by the ATN (amyloid, tau, neurodegeneration) classification incorporating amyloid, tau, and neuronal injury biomarkers.

METHODS

Using a random forest classifier we investigated whether 27 demographic, behavioral, and cognitive characteristics allowed distinction between ATN-defined groups with the same cognitive profile. This was done separately for three cognitively unimpaired (CU) (112 A-T-N-; 46 A+T+N+/-; 65 A-T+/-N+/-) and three mild cognitive impairment (MCI) (128 A-T-N-; 223 A+T+N+/-; 94 A-T+/-N+/-) subgroups.

RESULTS

Classification-balanced accuracy reached 39% for the CU and 52% for the MCI subgroups. Logical Delayed Recall (explaining 16% of the variance), followed by the Alzheimer's Disease Assessment Scale 13 (14%) and Everyday Cognition Informant (10%), were the most relevant characteristics for classification of the MCI subgroups. Race and ethnicity, marital status, and Everyday Cognition Patient were not relevant (0%).

CONCLUSIONS

The demographic, behavioral, and cognitive measures used in our model were not informative in differentiating ATN-defined CU profiles. Measures of delayed memory, general cognition, and activities of daily living were the most informative in differentiating ATN-defined MCI profiles; however, these measures alone were not sufficient to reach high classification performance.

Interpreting artificial intelligence models: a systematic review on the application of LIME and SHAP in Alzheimer's disease detection

Explainable artificial intelligence (XAI) has gained much interest in recent years for its ability to explain the complex decision-making process of machine learning (ML) and deep learning (DL) models. The Local Interpretable Model-agnostic Explanations (LIME) and Shaply Additive exPlanation (SHAP) frameworks have grown as popular interpretive tools for ML and DL models. This article provides a systematic review of the application of LIME and SHAP in interpreting the detection of Alzheimer's disease (AD). Adhering to PRISMA and Kitchenham's guidelines, we identified 23 relevant articles and investigated these frameworks' prospective capabilities, benefits, and challenges in depth. The results emphasise XAI's crucial role in strengthening the trustworthiness of AI-based AD predictions. This review aims to provide fundamental capabilities of LIME and SHAP XAI frameworks in enhancing fidelity within clinical decision support systems for AD prognosis.

An explainable machine learning approach for Alzheimer's disease classification

The early diagnosis of Alzheimer's disease (AD) presents a significant challenge due to the subtle biomarker changes often overlooked. Machine learning (ML) models offer a promising tool for identifying individuals at risk of AD. However, current research tends to prioritize ML accuracy while neglecting the crucial aspect of model explainability. The diverse nature of AD data and the limited dataset size introduce additional challenges, primarily related to high dimensionality. In this study, we leveraged a dataset obtained from the National Alzheimer's Coordinating Center, comprising 169,408 records and 1024 features. After applying various steps to reduce the feature space. Notably, support vector machine (SVM) models trained on the selected features exhibited high performance when tested on an external dataset. SVM achieved a high F1 score of 98.9% for binary classification (distinguishing between NC and AD) and 90.7% for multiclass classification. Furthermore, SVM was able to predict AD progression over a 4-year period, with F1 scores reached 88% for binary task and 72.8% for multiclass task. To enhance model explainability, we employed two rule-extraction approaches: class rule mining and stable and interpretable rule set for classification model. These approaches generated human-understandable rules to assist domain experts in comprehending the key factors involved in AD development. We further validated these rules using SHAP and LIME models, underscoring the significance of factors such as MEMORY, JUDGMENT, COMMUN, and ORIENT in determining AD risk. Our experimental outcomes also shed light on the crucial role of the Clinical Dementia Rating tool in predicting AD.

Explaining graph convolutional network predictions for clinicians-An explainable AI approach to Alzheimer's disease classification

Introduction

Graph-based representations are becoming more common in the medical domain, where each node defines a patient, and the edges signify associations between patients, relating individuals with disease and symptoms in a node classification task. In this study, a Graph Convolutional Networks (GCN) model was utilized to capture differences in neurocognitive, genetic, and brain atrophy patterns that can predict cognitive status, ranging from Normal Cognition (NC) to Mild Cognitive Impairment (MCI) and Alzheimer's Disease (AD), on the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Elucidating model predictions is vital in medical applications to promote clinical adoption and establish physician trust. Therefore, we introduce a decomposition-based explanation method for individual patient classification.

Methods

Our method involves analyzing the output variations resulting from decomposing input values, which allows us to determine the degree of impact on the prediction. Through this process, we gain insight into how each feature from various modalities, both at the individual and group levels, contributes to the diagnostic result. Given that graph data contains critical information in edges, we studied relational data by silencing all the edges of a particular class, thereby obtaining explanations at the neighborhood level.

Results

Our functional evaluation showed that the explanations remain stable with minor changes in input values, specifically for edge weights exceeding 0.80. Additionally, our comparative analysis against SHAP values yielded comparable results with significantly reduced computational time. To further validate the model's explanations, we conducted a survey study with 11 domain experts. The majority (71%) of the responses confirmed the correctness of the explanations, with a rating of above six on a 10-point scale for the understandability of the explanations.

Discussion

Strategies to overcome perceived limitations, such as the GCN's overreliance on demographic information, were discussed to facilitate future adoption into clinical practice and gain clinicians' trust as a diagnostic decision support system.

Development and Validation of Data-Level Innovation Data-Balancing Machine Learning Models for Predicting Optimal Implantable Collamer Lens Size and Postoperative Vault

INTRODUCTION

There are only four sizes of implantable collamer lens (ICL) available for selection, which cannot completely fit all patients as a result of the discontinuity of ICL sizes. Sizing an optimal ICL and predicting postoperative vault are still unresolved problems. This study aimed to develop and validate innovative data-level data-balancing machine learning-based models for predicting ICL size and postoperative vault.

METHODS

The patients were randomly assigned to training and internal validation sets in a 4:1 ratio. Feature selection was performed using analysis of variance (ANOVA) and Kruskal-Wallis feature importance methods. Traditional linear regression model and machine learning-based models were used. The accuracy of models was assessed using the area under the curve (AUC) and confusion matrix.

RESULTS

A total of 564 patients (1127 eyes) were eligible for this study, consisting of 808 eyes in the training set, 202 eyes in the internal validation set, and 117 eyes in the external validation set. Compared with the traditional linear regression method, the machine learning model bagging tree showed the best performance for ICL size selection, with an accuracy of 84.5% (95% confidence interval (CI) 83.2-85.8%), and the AUC ranged from 0.88 to 0.99; the prediction accuracy of 12.1 mm and 13.7 mm ICL sizes was improved by 49% and 59%, respectively. The bagging tree model achieved the best accuracy [90.2%, (95% CI 88.9-91.5%)] for predicting the postoperative vault, and the AUC ranged from 0.90 to 0.94. The prediction accuracies of internal and external validation dataset for ICL sizing were 82.2% (95% CI 81.1-83.3%) and 82.1% (95% CI 81.1-83.1%), respectively.

CONCLUSIONS

The innovative data-level data balancing-based machine learning model can be used to predict ICL size and postoperative vault more accurately, which can assist surgeons in choosing optimal ICL size, thus reducing risks of postoperative complications and secondary surgery.

Systematic review: fluid biomarkers and machine learning methods to improve the diagnosis from mild cognitive impairment to Alzheimer's disease

Mild cognitive impairment (MCI) is often considered an early stage of dementia, with estimated rates of progression to dementia up to 80-90% after approximately 6 years from the initial diagnosis. Diagnosis of cognitive impairment in dementia is typically based on clinical evaluation, neuropsychological assessments, cerebrospinal fluid (CSF) biomarkers, and neuroimaging. The main goal of diagnosing MCI is to determine its cause, particularly whether it is due to Alzheimer's disease (AD). However, only a limited percentage of the population has access to etiological confirmation, which has led to the emergence of peripheral fluid biomarkers as a diagnostic tool for dementias, including MCI due to AD. Recent advances in biofluid assays have enabled the use of sophisticated statistical models and multimodal machine learning (ML) algorithms for the diagnosis of MCI based on fluid biomarkers from CSF, peripheral blood, and saliva, among others. This approach has shown promise for identifying specific causes of MCI, including AD. After a PRISMA analysis, 29 articles revealed a trend towards using multimodal algorithms that incorporate additional biomarkers such as neuroimaging, neuropsychological tests, and genetic information. Particularly, neuroimaging is commonly used in conjunction with fluid biomarkers for both cross-sectional and longitudinal studies. Our systematic review suggests that cost-effective longitudinal multimodal monitoring data, representative of diverse cultural populations and utilizing white-box ML algorithms, could be a valuable contribution to the development of diagnostic models for AD due to MCI. Clinical assessment and biomarkers, together with ML techniques, could prove pivotal in improving diagnostic tools for MCI due to AD.

c-Diadem: a constrained dual-input deep learning model to identify novel biomarkers in Alzheimer's disease

BACKGROUND

Alzheimer's disease (AD) is an incurable, debilitating neurodegenerative disorder. Current biomarkers for AD diagnosis require expensive neuroimaging or invasive cerebrospinal fluid sampling, thus precluding early detection. Blood-based biomarker discovery in Alzheimer's can facilitate less-invasive, routine diagnostic tests to aid early intervention. Therefore, we propose "c-Diadem" (constrained dual-input Alzheimer's disease model), a novel deep learning classifier which incorporates KEGG (Kyoto Encyclopedia of Genes and Genomes) pathway constraints on the input genotyping data to predict disease, i.e., mild cognitive impairment (MCI)/AD or cognitively normal (CN). SHAP (SHapley Additive exPlanations) was used to explain the model and identify novel, potential blood-based genetic markers of MCI/AD.

METHODS

We developed a novel constrained deep learning neural network which utilizes SNPs (single nucleotide polymorphisms) and microarray data from ADNI (Alzheimer's Disease Neuroimaging Initiative) to predict the disease status of participants, i.e., CN or with disease (MCI/AD), and identify potential blood-based biomarkers for diagnosis and intervention. The dataset contains samples from 626 participants, of which 212 are CN (average age 74.6 ± 5.4 years) and 414 patients have MCI/AD (average age 72.7 ± 7.6 years). KEGG pathway information was used to generate constraints applied to the input tensors, thus enhancing the interpretability of the model. SHAP scores were used to identify genes which could potentially serve as biomarkers for diagnosis and targets for drug development.

RESULTS

Our model's performance, with accuracy of 69% and AUC of 70% in the test dataset, is superior to previous models. The SHAP scores show that SNPs in PRKCZ, PLCB1 and ITPR2 as well as expression of HLA-DQB1, EIF1AY, HLA-DQA1, and ZFP57 have more impact on model predictions.

CONCLUSIONS

In addition to predicting MCI/AD, our model has been interrogated for potential genetic biomarkers using SHAP. From our analysis, we have identified blood-based genetic markers related to Ca2+ ion release in affected regions of the brain, as well as depression. The findings from our study provides insights into disease mechanisms, and can facilitate innovation in less-invasive, cost-effective diagnostics. To the best of our knowledge, our model is the first to use pathway constraints in a multimodal neural network to identify potential genetic markers for AD.

XGBoost-SHAP-based interpretable diagnostic framework for alzheimer's disease

BACKGROUND

Due to the class imbalance issue faced when Alzheimer's disease (AD) develops from normal cognition (NC) to mild cognitive impairment (MCI), present clinical practice is met with challenges regarding the auxiliary diagnosis of AD using machine learning (ML). This leads to low diagnosis performance. We aimed to construct an interpretable framework, extreme gradient boosting-Shapley additive explanations (XGBoost-SHAP), to handle the imbalance among different AD progression statuses at the algorithmic level. We also sought to achieve multiclassification of NC, MCI, and AD.

METHODS

We obtained patient data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database, including clinical information, neuropsychological test results, neuroimaging-derived biomarkers, and APOE-ε4 gene statuses. First, three feature selection algorithms were applied, and they were then included in the XGBoost algorithm. Due to the imbalance among the three classes, we changed the sample weight distribution to achieve multiclassification of NC, MCI, and AD. Then, the SHAP method was linked to XGBoost to form an interpretable framework. This framework utilized attribution ideas that quantified the impacts of model predictions into numerical values and analysed them based on their directions and sizes. Subsequently, the top 10 features (optimal subset) were used to simplify the clinical decision-making process, and their performance was compared with that of a random forest (RF), Bagging, AdaBoost, and a naive Bayes (NB) classifier. Finally, the National Alzheimer's Coordinating Center (NACC) dataset was employed to assess the impact path consistency of the features within the optimal subset.

RESULTS

Compared to the RF, Bagging, AdaBoost, NB and XGBoost (unweighted), the interpretable framework had higher classification performance with accuracy improvements of 0.74%, 0.74%, 1.46%, 13.18%, and 0.83%, respectively. The framework achieved high sensitivity (81.21%/74.85%), specificity (92.18%/89.86%), accuracy (87.57%/80.52%), area under the receiver operating characteristic curve (AUC) (0.91/0.88), positive clinical utility index (0.71/0.56), and negative clinical utility index (0.75/0.68) on the ADNI and NACC datasets, respectively. In the ADNI dataset, the top 10 features were found to have varying associations with the risk of AD onset based on their SHAP values. Specifically, the higher SHAP values of CDRSB, ADAS13, ADAS11, ventricle volume, ADASQ4, and FAQ were associated with higher risks of AD onset. Conversely, the higher SHAP values of LDELTOTAL, mPACCdigit, RAVLT_immediate, and MMSE were associated with lower risks of AD onset. Similar results were found for the NACC dataset.

CONCLUSIONS

The proposed interpretable framework contributes to achieving excellent performance in imbalanced AD multiclassification tasks and provides scientific guidance (optimal subset) for clinical decision-making, thereby facilitating disease management and offering new research ideas for optimizing AD prevention and treatment programs.

The anti-Alzheimer potential of novel spiroindolin-1,2-diazepine derivatives as targeted cholinesterase inhibitors with modified substituents

In this study, a new series of spiro indolin-1,2-diazepine were designed, synthesized, and screened for their cholinesterase inhibitory activities. A novel, green, high-yielding approach was constructed to synthesize spiro indolin-1,2-diazepine derivatives through a cascade reaction of different isatins, malononitrile and 1,1-enediamines (EDAMs) via sequential four-component reactions to produce the target compounds with good to excellent yields. Next the inhibitory potencies of all derivatives were determined spectroscopically at 415 nm using the modified Ellman method. The results of the in vitro screening indicated that 5l with spiroindolin-1,2-diazepine core bearing 5-NO₂ at R¹ and 4-OH at R² was the most potent and selective AChE inhibitor with an IC₅₀ value of 3.98 ± 1.07 µM with no significant inhibition against BChE while 5j was the most active analog against both AChE and BChE enzymes. The structure-activity relationships suggested the variation in the inhibitory activities of derivatives was affected by different substitutions on the indolinone ring as well as the phenyl moiety. The enzyme kinetic studies of the most potent compound 5l at five different concentrations and acetylthiocholine substrate (0.1-1 mM) by Ellman's method revealed that it inhibited AChE in a mixed mode with a K_i of 0.044 μM. A molecular docking study was performed via induced fit docking protocol to predict the putative binding interaction. It was shown that the moieties used in the initial structure design play a fundamental role in interacting with the enzyme's binding site. Further, molecular dynamics simulations with the Schrödinger package were performed for 5l in a complex with AChE and revealed that compound 5l formed the stable complex with the enzyme. The MTT toxicity assessments against the neuroblastoma cell line were executed, and no toxicity was seen for 5l under the tested concentrations.

A cross-sectional study of explainable machine learning in Alzheimer's disease: diagnostic classification using MR radiomic features

Introduction

Alzheimer's disease (AD) even nowadays remains a complex neurodegenerative disease and its diagnosis relies mainly on cognitive tests which have many limitations. On the other hand, qualitative imaging will not provide an early diagnosis because the radiologist will perceive brain atrophy on a late disease stage. Therefore, the main objective of this study is to investigate the necessity of quantitative imaging in the assessment of AD by using machine learning (ML) methods. Nowadays, ML methods are used to address high dimensional data, integrate data from different sources, model the etiological and clinical heterogeneity, and discover new biomarkers in the assessment of AD.

Methods

In this study radiomic features from both entorhinal cortex and hippocampus were extracted from 194 normal controls (NC), 284 mild cognitive impairment (MCI) and 130 AD subjects. Texture analysis evaluates statistical properties of the image intensities which might represent changes in MRI image pixel intensity due to the pathophysiology of a disease. Therefore, this quantitative method could detect smaller-scale changes of neurodegeneration. Then the radiomics signatures extracted by texture analysis and baseline neuropsychological scales, were used to build an XGBoost integrated model which has been trained and integrated.

Results

The model was explained by using the Shapley values produced by the SHAP (SHapley Additive exPlanations) method. XGBoost produced a f1-score of 0.949, 0.818, and 0.810 between NC vs. AD, MC vs. MCI, and MCI vs. AD, respectively.

Discussion

These directions have the potential to help to the earlier diagnosis and to a better manage of the disease progression and therefore, develop novel treatment strategies. This study clearly showed the importance of explainable ML approach in the assessment of AD.

Radiomics for Alzheimer's Disease: Fundamental Principles and Clinical Applications

Alzheimer's disease is a neurodegenerative disease with a huge impact on people's quality of life, life expectancy, and morbidity. The ongoing prevalence of the disease, in conjunction with an increased financial burden to healthcare services, necessitates the development of new technologies to be employed in this field. Hence, advanced computational methods have been developed to facilitate early and accurate diagnosis of the disease and improve all health outcomes. Artificial intelligence is now deeply involved in the fight against this disease, with many clinical applications in the field of medical imaging. Deep learning approaches have been tested for use in this domain, while radiomics, an emerging quantitative method, are already being evaluated to be used in various medical imaging modalities. This chapter aims to provide an insight into the fundamental principles behind radiomics, discuss the most common techniques alongside their strengths and weaknesses, and suggest ways forward for future research standardization and reproducibility.

Neuropsychiatric Symptoms and Commonly Used Biomarkers of Alzheimer's Disease: A Literature Review from a Machine Learning Perspective

There is a growing interest in the application of machine learning (ML) in Alzheimer's disease (AD) research. However, neuropsychiatric symptoms (NPS), frequent in subjects with AD, mild cognitive impairment (MCI), and other related dementias have not been analyzed sufficiently using ML methods. To portray the landscape and potential of ML research in AD and NPS studies, we present a comprehensive literature review of existing ML approaches and commonly studied AD biomarkers. We conducted PubMed searches with keywords related to NPS, AD biomarkers, machine learning, and cognition. We included a total of 38 articles in this review after excluding some irrelevant studies from the search results and including 6 articles based on a snowball search from the bibliography of the relevant studies. We found a limited number of studies focused on NPS with or without AD biomarkers. In contrast, multiple statistical machine learning and deep learning methods have been used to build predictive diagnostic models using commonly known AD biomarkers. These mainly included multiple imaging biomarkers, cognitive scores, and various omics biomarkers. Deep learning approaches that combine these biomarkers or multi-modality datasets typically outperform single-modality datasets. We conclude ML may be leveraged to untangle the complex relationships of NPS and AD biomarkers with cognition. This may potentially help to predict the progression of MCI or dementia and develop more targeted early intervention approaches based on NPS.