Computer-aided diagnosis of Alzheimer’s type dementia combining support vector machines and discriminant set of features

MVPAlab: A machine learning decoding toolbox for multidimensional electroencephalography data

BACKGROUND AND OBJECTIVE

The study of brain function has recently expanded from classical univariate to multivariate analyses. These multivariate, machine learning-based algorithms afford neuroscientists extracting more detailed and richer information from the data. However, the implementation of these procedures is usually challenging, especially for researchers with no coding experience. To address this problem, we have developed MVPAlab, a MATLAB-based, flexible decoding toolbox for multidimensional electroencephalography and magnetoencephalography data.

METHODS

The MVPAlab Toolbox implements several machine learning algorithms to compute multivariate pattern analyses, cross-classification, temporal generalization matrices and feature and frequency contribution analyses. It also provides access to an extensive set of preprocessing routines for, among others, data normalization, data smoothing, dimensionality reduction and supertrial generation. To draw statistical inferences at the group level, MVPAlab includes a non-parametric cluster-based permutation approach.

RESULTS

A sample electroencephalography dataset was compiled to test all the MVPAlab main functionalities. Significant clusters (p<0.01) were found for the proposed decoding analyses and different configurations, proving the software capability for discriminating between different experimental conditions.

CONCLUSIONS

This toolbox has been designed to include an easy-to-use and intuitive graphic user interface and data representation software, which makes MVPAlab a very convenient tool for users with few or no previous coding experience. In addition, MVPAlab is not for beginners only, as it implements several high and low-level routines allowing more experienced users to design their own projects in a highly flexible manner.

Diagnosis of Alzheimer's disease and behavioural variant frontotemporal dementia with machine learning-aided neuropsychological assessment using feature engineering and genetic algorithms

BACKGROUND

Neuropsychological assessment is considered a valid tool in the diagnosis of neurodegenerative disorders. However, there is an important overlap in cognitive profiles between Alzheimer's disease (AD) and behavioural variant frontotemporal dementia (bvFTD), and the usefulness in diagnosis is uncertain. We aimed to develop machine learning-based models for the diagnosis using cognitive tests.

METHODS

Three hundred and twenty-nine participants (170 AD, 72 bvFTD, 87 healthy control [HC]) were enrolled. Evolutionary algorithms, inspired by the process of natural selection, were applied for both mono-objective and multi-objective classification and feature selection. Classical algorithms (NativeBayes, Support Vector Machines, among others) were also used, and a meta-model strategy.

RESULTS

Accuracies for the diagnosis of AD, bvFTD and the differential diagnosis between them were higher than 84%. Algorithms were able to significantly reduce the number of tests and scores needed. Free and Cued Selective Reminding Test, verbal fluency and Addenbrooke's Cognitive Examination were amongst the most meaningful tests.

CONCLUSIONS

Our study found high levels of accuracy for diagnosis using exclusively neuropsychological tests, which supports the usefulness of cognitive assessment in diagnosis. Machine learning may have a role in improving the interpretation and test selection.

Robust EEG Based Biomarkers to Detect Alzheimer's Disease

Biomarkers to detect Alzheimer's disease (AD) would enable patients to gain access to appropriate services and may facilitate the development of new therapies. Given the large numbers of people affected by AD, there is a need for a low-cost, easy to use method to detect AD patients. Potentially, the electroencephalogram (EEG) can play a valuable role in this, but at present no single EEG biomarker is robust enough for use in practice. This study aims to provide a methodological framework for the development of robust EEG biomarkers to detect AD with a clinically acceptable performance by exploiting the combined strengths of key biomarkers. A large number of existing and novel EEG biomarkers associated with slowing of EEG, reduction in EEG complexity and decrease in EEG connectivity were investigated. Support vector machine and linear discriminate analysis methods were used to find the best combination of the EEG biomarkers to detect AD with significant performance. A total of 325,567 EEG biomarkers were investigated, and a panel of six biomarkers was identified and used to create a diagnostic model with high performance (≥85% for sensitivity and 100% for specificity).

Denouements of machine learning and multimodal diagnostic classification of Alzheimer's disease

Alzheimer's disease (AD) is the most common type of dementia. The exact cause and treatment of the disease are still unknown. Different neuroimaging modalities, such as magnetic resonance imaging (MRI), positron emission tomography, and single-photon emission computed tomography, have played a significant role in the study of AD. However, the effective diagnosis of AD, as well as mild cognitive impairment (MCI), has recently drawn large attention. Various technological advancements, such as robots, global positioning system technology, sensors, and machine learning (ML) algorithms, have helped improve the diagnostic process of AD. This study aimed to determine the influence of implementing different ML classifiers in MRI and analyze the use of support vector machines with various multimodal scans for classifying patients with AD/MCI and healthy controls. Conclusions have been drawn in terms of employing different classifier techniques and presenting the optimal multimodal paradigm for the classification of AD.

Integrative blockwise sparse analysis for tissue characterization and classification

The topic of sparse representation of samples in high dimensional spaces has attracted growing interest during the past decade. In this work, we develop sparse representation-based methods for classification of clinical imaging patterns into healthy and diseased states. We propose a spatial block decomposition method to address irregularities of the approximation problem and to build an ensemble of classifiers that we expect to yield more accurate numerical solutions than conventional sparse analyses of the complete spatial domain of the images. We introduce two classification decision strategies based on maximum a posteriori probability (BBMAP), or a log likelihood function (BBLL) and an approach to adjusting the classification decision criteria. To evaluate the performance of the proposed approach we used cross-validation techniques on imaging datasets with disease class labels. We first applied the proposed approach to diagnosis of osteoporosis using bone radiographs. In this problem we assume that changes in trabecular bone connectivity can be captured by intensity patterns. The second application domain is separation of breast lesions into benign and malignant categories in mammograms. The object classes in both of these applications are not linearly separable, and the classification accuracy may depend on the lesion size in the second application. Our results indicate that the proposed integrative sparse analysis addresses the ill-posedness of the approximation problem and produces very good class separation for trabecular bone characterization and for breast lesion characterization. Our approach yields higher classification rates than conventional sparse classification and previously published convolutional neural networks (CNNs) that we fine-tuned for our datasets, or utilized for feature extraction. The BBLL technique also produced higher classification rates than learners using hand-crafted texture features, and the Bag of Keypoints, which is a sophisticated patch-based method. Furthermore, our comparative experiments showed that the BBLL function may yield more accurate classification than BBMAP, because BBLL accounts for possible estimation bias.

Laryngopharyngeal reflux image quantization and analysis of its severity

Laryngopharyngeal reflux (LPR) is a prevalent disease affecting a high proportion of patients seeking laryngology consultation. Diagnosis is made subjectively based on history, symptoms, and endoscopic assessment. The results depend on the examiner's interpretation of endoscopic images. There are still no consistent objective diagnostic methods. The aim of this study is to use image processing techniques to quantize the laryngeal variation caused by LPR, to judge and analyze its severity. This study proposed methods of screening sharp images automatically from laryngeal endoscopic images and using throat eigen structure for automatic region segmentation. The proposed image compensation improved the illumination problems from the use of laryngoscope lens. Fisher linear discriminant was used to find out features and classification performance while support vector machine was used as the classifier for judging LPR. Evaluation results were 97.16% accuracy, 98.11% sensitivity, and 3.77% false positive rate. To evaluate the severity, quantized data of the laryngeal variation was used. LPR images were combined with reflux symptom index score chart, and severity was graded using a neural network. The results indicated 96.08% accuracy. The experiment indicated that laryngeal variation induced by LPR could be quantized by using image processing techniques to assist in diagnosing and treating LPR.

Detection of medications associated with Alzheimer's disease using ensemble methods and cooperative game theory

OBJECTIVE

To study the feasibility of evaluating feature importance with Shapley Values and ensemble methods in the context of pharmacoepidemiology and medication safety.

METHODS

We detected medications associated with Alzheimer's disease (AD) by examining the additive feature attribution with combined approach of Gradient Boosting and Shapley Values in the Medication use and Alzheimer's disease (MEDALZ) study, a nested case-control study of 70,719 verified AD cases in Finland. Our methodological approach is to do binary classification using Gradient boosting (an ensemble of weak classifiers) in a supervised learning manner. Then we apply Shapley Values (from cooperative game theory) to analyze how feature combinations affect the classification result. Medication use with a five to one year time-window before AD diagnosis was ascertained from Prescription register.

RESULTS

Antipsychotics with low or medium dose, antidepressants with medium to high dose, and cardiovascular medications with medium to high dose were identified as the contributing features for separating cases with AD from controls. Medium to high amount of irregularity in the purchase pattern were an indicating feature for separating AD cases from controls. The similarity of medication purchases between AD cases and controls made the feature evaluation challenging.

CONCLUSIONS

The combined approach of Gradient Boosting and feature evaluation with Shapley Values identified features that were consistent with findings from previous hypothesis-driven studies. Additionally, the results from the additive feature attribution identified new candidates for future studies on AD risk factors. Our approach also shows promise for studies based on observational studies, where feature identification and interactions in populations are of interest; and the applicability of using Shapley Values for evaluating feature relevance in pattern recognition tasks.

Multivariate Pattern Analysis Techniques for Electroencephalography Data to Study Flanker Interference Effects

A central challenge in cognitive neuroscience is to understand the neural mechanisms that underlie the capacity to control our behavior according to internal goals. Flanker tasks, which require responding to stimuli surrounded by distracters that trigger incompatible action tendencies, are frequently used to measure this conflict. Even though the interference generated in these situations has been broadly studied, multivariate analysis techniques can shed new light into the underlying neural mechanisms. The current study is an initial approximation to adapt an interference Flanker paradigm embedded in a Demand-Selection Task (DST) to a format that allows measuring concurrent high-density electroencephalography (EEG). We used multivariate pattern analysis (MVPA) to decode conflict-related electrophysiological markers associated with congruent or incongruent target events in a time-frequency resolved way. Our results replicate findings obtained with other analysis approaches and offer new information regarding the dynamics of the underlying mechanisms, which show signs of reinstantiation. Our findings, some of which could not have been obtained with classic analytical strategies, open novel avenues of research.

Autosomal Dominantly Inherited Alzheimer Disease: Analysis of genetic subgroups by Machine Learning

Despite subjects with Dominantly-Inherited Alzheimer's Disease (DIAD) represent less than 1% of all Alzheimer's Disease (AD) cases, the Dominantly Inherited Alzheimer Network (DIAN) initiative constitutes a strong impact in the understanding of AD disease course with special emphasis on the presyptomatic disease phase. Until now, the 3 genes involved in DIAD pathogenesis (PSEN1, PSEN2 and APP) have been commonly merged into one group (Mutation Carriers, MC) and studied using conventional statistical analysis. Comparisons between groups using null-hypothesis testing or longitudinal regression procedures, such as the linear-mixed-effects models, have been assessed in the extant literature. Within this context, the work presented here performs a comparison between different groups of subjects by considering the 3 genes, either jointly or separately, and using tools based on Machine Learning (ML). This involves a feature selection step which makes use of ANOVA followed by Principal Component Analysis (PCA) to determine which features would be realiable for further comparison purposes. Then, the selected predictors are classified using a Support-Vector-Machine (SVM) in a nested k-Fold cross-validation resulting in maximum classification rates of 72-74% using PiB PET features, specially when comparing asymptomatic Non-Carriers (NC) subjects with asymptomatic PSEN1 Mutation-Carriers (PSEN1-MC). Results obtained from these experiments led to the idea that PSEN1-MC might be considered as a mixture of two different subgroups including: a first group whose patterns were very close to NC subjects, and a second group much more different in terms of imaging patterns. Thus, using a k-Means clustering algorithm it was determined both subgroups and a new classification scenario was conducted to validate this process. The comparison between each subgroup vs. NC subjects resulted in classification rates around 80% underscoring the importance of considering DIAN as an heterogeneous entity.

Identification of Optimum Panel of Blood-based Biomarkers for Alzheimer's Disease Diagnosis Using Machine Learning

With the increasing number of people living with Alzheimer's disease (AD), there is a need for low-cost and easy to use methods to detect AD early to facilitate access to appropriate care pathways. Neuroimaging biomarkers (such as those based on PET and MRI) and biochemical biomarkers (such as those based on CSF) are recommended by international guidelines to facilitate diagnosis. However, neuroimaging is expensive and may not be widely available and CSF testing is invasive. Bloodbased biomarkers offer the potential for the development of a low-cost and more time efficient tool to detect AD to complement CSF and neuroimaging as blood is much easier to obtain. Although no single blood biomarker is yet able to detect AD, combinations of biomarkers (also called panels) have shown good results. However, a large number of biomarkers are often needed to achieve a satisfactory detection performance. In addition, it is difficult to reproduce reported results within and across different study cohorts because of data overfitting and lack of access to the datasets used in the studies. In this study, our focus is to identify an optimum panel (in terms of the least number of blood biomarkers to meet the specified diagnostic performance of 80% sensitivity and specificity) based on a widely accessible data set, and to demonstrate a testing methodology that reinforces reproducibility of results. Realizing a panel with reduced number of markers will have significant impact on the complexity and cost of diagnosis and potential development of cost-effective point of care devices.

A practical computerized decision support system for predicting the severity of Alzheimer's disease of an individual

Computerized clinical decision support systems can help to provide objective, standardized, and timely dementia diagnosis. However, current computerized systems are mainly based on group analysis, discrete classification of disease stages, or expensive and not readily accessible biomarkers, while current clinical practice relies relatively heavily on cognitive and functional assessments (CFA). In this study, we developed a computational framework using a suite of machine learning tools for identifying key markers in predicting the severity of Alzheimer's disease (AD) from a large set of biological and clinical measures. Six machine learning approaches, namely Kernel Ridge Regression (KRR), Support Vector Regression, and k-Nearest Neighbor for regression and Support Vector Machine (SVM), Random Forest, and k-Nearest Neighbor for classification, were used for the development of predictive models. We demonstrated high predictive power of CFA. Predictive performance of models incorporating CFA was shown to consistently have higher accuracy than those based solely on biomarker modalities. We found that KRR and SVM were the best performing regression and classification methods respectively. The optimal SVM performance was observed for a set of four CFA test scores (FAQ, ADAS13, MoCA, MMSE) with multi-class classification accuracy of 83.0%, 95%CI = (72.1%, 93.8%) while the best performance of the KRR model was reported with combined CFA and MRI neuroimaging data, i.e., R ² = 0.874, 95%CI = (0.827, 0.922). Given the high predictive power of CFA and their widespread use in clinical practice, we then designed a data-driven and self-adaptive computerized clinical decision support system (CDSS) prototype for evaluating the severity of AD of an individual on a continuous spectrum. The system implemented an automated computational approach for data pre-processing, modelling, and validation and used exclusively the scores of selected cognitive measures as data entries. Taken together, we have developed an objective and practical CDSS to aid AD diagnosis.

Leveraging network analysis to support experts in their analyses of subjects with MCI and AD

In this paper, we propose a network analysis-based approach to help experts in their analyses of subjects with mild cognitive impairment (hereafter, MCI) and Alzheimer's disease (hereafter, AD) and to investigate the evolution of these subjects over time. The inputs of our approach are the electroencephalograms (hereafter, EEGs) of the patients to analyze, performed at a certain time and, again, 3 months later. Given an EEG of a subject, our approach constructs a network with nodes that represent the electrodes and edges that denote connections between electrodes. Then, it applies several network-based techniques allowing the investigation of subjects with MCI and AD and the analysis of their evolution over time. (i) A connection coefficient, supporting experts to distinguish patients with MCI from patients with AD; (ii) A conversion coefficient, supporting experts to verify if a subject with MCI is converting to AD; (iii) Some network motifs, i.e., network patterns very frequent in one kind of patient and absent, or very rare, in the other. Patients with AD, just by the very nature of their condition, cannot be forced to stay motionless while undergoing examinations for a long time. EEG is a non-invasive examination that can be easily done on them. Since AD and MCI, if prodromal to AD, are associated with a loss of cortical connections, the adoption of network analysis appears suitable to investigate the effects of the progression of the disease on EEG. This paper confirms the suitability of this idea Graphical Abstract Ability of our proposed model to distinguish a control subject from a patient with MCI and a patient with AD. Blue edges represent strong connections among the corresponding brain areas; red edges denote middle connections, whereas green edges indicate weak connections. In the control subject (at the top), most connections are blue. In the patient with MCI (at the middle), most connections are red and green. In the patient with AD (at the bottom), most connections are either absent or green. .

Neuroimaging and Machine Learning for Dementia Diagnosis: Recent Advancements and Future Prospects

Dementia, a chronic and progressive cognitive declination of brain function caused by disease or impairment, is becoming more prevalent due to the aging population. A major challenge in dementia is achieving accurate and timely diagnosis. In recent years, neuroimaging with computer-aided algorithms have made remarkable advances in addressing this challenge. The success of these approaches is mostly attributed to the application of machine learning techniques for neuroimaging. In this review paper, we present a comprehensive survey of automated diagnostic approaches for dementia using medical image analysis and machine learning algorithms published in the recent years. Based on the rigorous review of the existing works, we have found that, while most of the studies focused on Alzheimer's disease, recent research has demonstrated reasonable performance in the identification of other types of dementia remains a major challenge. Multimodal imaging analysis deep learning approaches have shown promising results in the diagnosis of these other types of dementia. The main contributions of this review paper are as follows. 1) Based on the detailed analysis of the existing literature, this paper discusses neuroimaging procedures for dementia diagnosis. 2) It systematically explains the most recent machine learning techniques and, in particular, deep learning approaches for early detection of dementia.

Decision Supporting Model for One-year Conversion Probability from MCI to AD using CNN and SVM

Prediction of Alzheimer's disease (AD) from Mild Cognitive Impairment (MCI) has become popular in recent years. Especially, deep learning technique has been used to extract high-quality features and for classification in this topic. Whether the patient would converse from MCI into AD is a particular evaluation criteria in clinics. However, there is no such a conversion prediction model in literature. Therefore, the purpose of this study is to propose a decision supporting model based on deep learning and machine learning to predict the conversion probability from MCI into AD within one year. We analyzed 165 samples with MRI scans from Alzheimer's Disease Neuroimaging Initiative (ADNI) database, in which all MCI patients were converted into AD in different time span for conversion. In this model, we first extracted image features based on convolutional neural network (CNN) method, and then we used support vector machine (SVM) classifier to classify these features. The results showed that the classification accuracy using linear, polynomial and RBF kernel could achieve 91.0%, 90.0% and 92.3%. As a result, this study indicated that the decision supporting model is potential to be applied into predicting the conversion probability from MCI into AD within one year.

Machine-learning based identification of undiagnosed dementia in primary care: a feasibility study

Background

Up to half of patients with dementia may not receive a formal diagnosis, limiting access to appropriate services. It is hypothesised that it may be possible to identify undiagnosed dementia from a profile of symptoms recorded in routine clinical practice.

Aim

The aim of this study is to develop a machine learning-based model that could be used in general practice to detect dementia from routinely collected NHS data. The model would be a useful tool for identifying people who may be living with dementia but have not been formally diagnosed.

Design & setting

The study involved a case-control design and analysis of primary care data routinely collected over a 2-year period. Dementia diagnosed during the study period was compared to no diagnosis of dementia during the same period using pseudonymised routinely collected primary care clinical data.

Method

Routinely collected Read-encoded data were obtained from 18 consenting GP surgeries across Devon, for 26 483 patients aged >65 years. The authors determined Read codes assigned to patients that may contribute to dementia risk. These codes were used as features to train a machine-learning classification model to identify patients that may have underlying dementia.

Results

The model obtained sensitivity and specificity values of 84.47% and 86.67%, respectively.

Conclusion

The results show that routinely collected primary care data may be used to identify undiagnosed dementia. The methodology is promising and, if successfully developed and deployed, may help to increase dementia diagnosis in primary care.

Ensemble of random forests One vs. Rest classifiers for MCI and AD prediction using ANOVA cortical and subcortical feature selection and partial least squares

BACKGROUND

Alzheimer's disease (AD) is the most common cause of dementia in the elderly and affects approximately 30 million individuals worldwide. Mild cognitive impairment (MCI) is very frequently a prodromal phase of AD, and existing studies have suggested that people with MCI tend to progress to AD at a rate of about 10-15% per year. However, the ability of clinicians and machine learning systems to predict AD based on MRI biomarkers at an early stage is still a challenging problem that can have a great impact in improving treatments.

METHOD

The proposed system, developed by the SiPBA-UGR team for this challenge, is based on feature standardization, ANOVA feature selection, partial least squares feature dimension reduction and an ensemble of One vs. Rest random forest classifiers. With the aim of improving its performance when discriminating healthy controls (HC) from MCI, a second binary classification level was introduced that reconsiders the HC and MCI predictions of the first level.

RESULTS

The system was trained and evaluated on an ADNI datasets that consist of T1-weighted MRI morphological measurements from HC, stable MCI, converter MCI and AD subjects. The proposed system yields a 56.25% classification score on the test subset which consists of 160 real subjects.

COMPARISON WITH EXISTING METHOD(S)

The classifier yielded the best performance when compared to: (i) One vs. One (OvO), One vs. Rest (OvR) and error correcting output codes (ECOC) as strategies for reducing the multiclass classification task to multiple binary classification problems, (ii) support vector machines, gradient boosting classifier and random forest as base binary classifiers, and (iii) bagging ensemble learning.

CONCLUSIONS

A robust method has been proposed for the international challenge on MCI prediction based on MRI data. The system yielded the second best performance during the competition with an accuracy rate of 56.25% when evaluated on the real subjects of the test set.

Improved Diagnostic Accuracy of Alzheimer's Disease by Combining Regional Cortical Thickness and Default Mode Network Functional Connectivity: Validated in the Alzheimer's Disease Neuroimaging Initiative Set

OBJECTIVE

To identify potential imaging biomarkers of Alzheimer's disease by combining brain cortical thickness (CThk) and functional connectivity and to validate this model's diagnostic accuracy in a validation set.

MATERIALS AND METHODS

Data from 98 subjects was retrospectively reviewed, including a study set (n = 63) and a validation set from the Alzheimer's Disease Neuroimaging Initiative (n = 35). From each subject, data for CThk and functional connectivity of the default mode network was extracted from structural T1-weighted and resting-state functional magnetic resonance imaging. Cortical regions with significant differences between patients and healthy controls in the correlation of CThk and functional connectivity were identified in the study set. The diagnostic accuracy of functional connectivity measures combined with CThk in the identified regions was evaluated against that in the medial temporal lobes using the validation set and application of a support vector machine.

RESULTS

Group-wise differences in the correlation of CThk and default mode network functional connectivity were identified in the superior temporal (p < 0.001) and supramarginal gyrus (p = 0.007) of the left cerebral hemisphere. Default mode network functional connectivity combined with the CThk of those two regions were more accurate than that combined with the CThk of both medial temporal lobes (91.7% vs. 75%).

CONCLUSION

Combining functional information with CThk of the superior temporal and supramarginal gyri in the left cerebral hemisphere improves diagnostic accuracy, making it a potential imaging biomarker for Alzheimer's disease.

11C-PIB PET image analysis for Alzheimer's diagnosis using weighted voting ensembles

Alzheimer's Disease (AD) is one of the leading causes of death and dementia worldwide. Early diagnosis confers many benefits, including improved care and access to effective treatment. However, it is still a medical challenge due to the lack of an efficient and inexpensive way to assess cognitive function [1]. Although research on data from Neuroimaging and Brain Initiative and the advancement in data analytics has greatly enhanced our understanding of the underlying disease process, there is still a lack of complete knowledge regarding the indicative biomarkers of Alzheimer's Disease. Recently, computer aided diagnosis of mild cognitive impairment and AD with functional brain images using machine learning methods has become popular. However, the prediction accuracy remains unoptimistic, with prediction accuracy ranging from 60% to 88% [2,3,6]. Among them, support vector machine is the most popular classifier. However, because of the relatively small sample size and the amount of noise in functional brain imaging data, a single classifier cannot achieve high classification performance. Instead of using a global classifier, in this work, we aim to improve AD prediction accuracy by combining three different classifiers using weighted and unweighted schemes. We rank image-derived features according to their importance to the classification performance and show that the top ranked features are localized in the brain areas which have been found to associate with the progression of AD. We test the proposed approach on 11C-PIB PET scans from The Alzheimer's Disease Neuroimaging Initiative (ADNI) database and demonstrated that the weighted ensemble models outperformed individual models of K-Nearest Neighbors, Random Forests, Neural Nets with overall cross validation accuracy of 86.1% ± 8.34%, specificity of 90.6% ± 12.9% and test accuracy of 80.9% and specificity 85.76% in classification of AD, mild cognitive impairment and healthy elder adults.

Quad-phased data mining modeling for dementia diagnosis

BACKGROUND

The number of people with dementia is increasing along with people's ageing trend worldwide. Therefore, there are various researches to improve a dementia diagnosis process in the field of computer-aided diagnosis (CAD) technology. The most significant issue is that the evaluation processes by physician which is based on medical information for patients and questionnaire from their guardians are time consuming, subjective and prone to error. This problem can be solved by an overall data mining modeling, which subsidizes an intuitive decision of clinicians.

METHODS

Therefore, in this paper we propose a quad-phased data mining modeling consisting of 4 modules. In Proposer Module, significant diagnostic criteria are selected that are effective for diagnostics. Then in Predictor Module, a model is constructed to predict and diagnose dementia based on a machine learning algorism. To help clinical physicians understand results of the predictive model better, in Descriptor Module, we interpret causes of diagnostics by profiling patient groups. Lastly, in Visualization Module, we provide visualization to effectively explore characteristics of patient groups.

RESULTS

The proposed model is applied for CREDOS study which contains clinical data collected from 37 university-affiliated hospitals in republic of Korea from year 2005 to 2013.

CONCLUSIONS

This research is an intelligent system enabling intuitive collaboration between CAD system and physicians. And also, improved evaluation process is able to effectively reduce time and cost consuming for clinicians and patients.

Applying a computer-aided scheme to detect a new radiographic image marker for prediction of chemotherapy outcome

Background

To investigate the feasibility of automated segmentation of visceral and subcutaneous fat areas from computed tomography (CT) images of ovarian cancer patients and applying the computed adiposity-related image features to predict chemotherapy outcome.

Methods

A computerized image processing scheme was developed to segment visceral and subcutaneous fat areas, and compute adiposity-related image features. Then, logistic regression models were applied to analyze association between the scheme-generated assessment scores and progression-free survival (PFS) of patients using a leave-one-case-out cross-validation method and a dataset involving 32 patients.

Results

The correlation coefficients between automated and radiologist’s manual segmentation of visceral and subcutaneous fat areas were 0.76 and 0.89, respectively. The scheme-generated prediction scores using adiposity-related radiographic image features significantly associated with patients’ PFS (p < 0.01).

Conclusion

Using a computerized scheme enables to more efficiently and robustly segment visceral and subcutaneous fat areas. The computed adiposity-related image features also have potential to improve accuracy in predicting chemotherapy outcome.

On the early diagnosis of Alzheimer's Disease from multimodal signals: A survey

INTRODUCTION

The number of Alzheimer's Disease (AD) patients is increasing with increased life expectancy and 115.4 million people are expected to be affected in 2050. Unfortunately, AD is commonly diagnosed too late, when irreversible damages have been caused in the patient.

OBJECTIVE

An automatic, continuous and unobtrusive early AD detection method would be required to improve patients' life quality and avoid big healthcare costs. Thus, the objective of this survey is to review the multimodal signals that could be used in the development of such a system, emphasizing on the accuracy that they have shown up to date for AD detection. Some useful tools and specific issues towards this goal will also have to be reviewed.

METHODS

An extensive literature review was performed following a specific search strategy, inclusion criteria, data extraction and quality assessment in the Inspec, Compendex and PubMed databases.

RESULTS

This work reviews the extensive list of psychological, physiological, behavioural and cognitive measurements that could be used for AD detection. The most promising measurements seem to be magnetic resonance imaging (MRI) for AD vs control (CTL) discrimination with an 98.95% accuracy, while electroencephalogram (EEG) shows the best results for mild cognitive impairment (MCI) vs CTL (97.88%) and MCI vs AD distinction (94.05%). Available physiological and behavioural AD datasets are listed, as well as medical imaging analysis steps and neuroimaging processing toolboxes. Some issues such as "label noise" and multi-site data are discussed.

CONCLUSIONS

The development of an unobtrusive and transparent AD detection system should be based on a multimodal system in order to take full advantage of all kinds of symptoms, detect even the smallest changes and combine them, so as to detect AD as early as possible. Such a multimodal system might probably be based on physiological monitoring of MRI or EEG, as well as behavioural measurements like the ones proposed along the article. The mentioned AD datasets and image processing toolboxes are available for their use towards this goal. Issues like "label noise" and multi-site neuroimaging incompatibilities may also have to be overcome, but methods for this purpose are already available.

Discriminative Learning for Alzheimer's Disease Diagnosis via Canonical Correlation Analysis and Multimodal Fusion

To address the challenging task of diagnosing neurodegenerative brain disease, such as Alzheimer's disease (AD) and mild cognitive impairment (MCI), we propose a novel method using discriminative feature learning and canonical correlation analysis (CCA) in this paper. Specifically, multimodal features and their CCA projections are concatenated together to represent each subject, and hence both individual and shared information of AD disease are captured. A discriminative learning with multilayer feature hierarchy is designed to further improve performance. Also, hybrid representation is proposed to maximally explore data from multiple modalities. A novel normalization method is devised to tackle the intra- and inter-subject variations from the multimodal data. Based on our extensive experiments, our method achieves an accuracy of 96.93% [AD vs. normal control (NC)], 86.57 % (MCI vs. NC), and 82.75% [MCI converter (MCI-C) vs. MCI non-converter (MCI-NC)], respectively, which outperforms the state-of-the-art methods in the literature.

Intraoperative optical mapping of epileptogenic cortices during non-ictal periods in pediatric patients

Complete removal of epileptogenic cortex while preserving eloquent areas is crucial in patients undergoing epilepsy surgery. In this manuscript, the feasibility was explored of developing a new methodology based on dynamic intrinsic optical signal imaging (DIOSI) to intraoperatively detect and differentiate epileptogenic from eloquent cortices in pediatric patients with focal epilepsy. From 11 pediatric patients undergoing epilepsy surgery, negatively-correlated hemodynamic low-frequency oscillations (LFOs, ~ 0.02-0.1 Hz) were observed from the exposed epileptogenic and eloquent cortical areas, as defined by electrocorticography (ECoG), using a DIOSI system. These LFOs were classified into multiple groups in accordance with their unique temporal profiles. Causal relationships within these groups were investigated using the Granger causality method, and 83% of the ECoG-defined epileptogenic cortical areas were found to have a directed influence on one or more cortical areas showing LFOs within the field of view of the imaging system. To understand the physiological origins of LFOs, blood vessel density was compared between epileptogenic and normal cortical areas and a statistically-significant difference (p < 0.05) was detected. The differences in blood-volume and blood-oxygenation dynamics between eloquent and epileptogenic cortices were also uncovered using a stochastic modeling approach. This, in turn, yielded a means by which to separate epileptogenic from eloquent cortex using hemodynamic LFOs. The proposed methodology detects epileptogenic cortices by exploiting the effective connectivity that exists within cortical regions displaying LFOs and the biophysical features contributed by the altered vessel networks within the epileptogenic cortex. It could be used in conjunction with existing technologies for epileptogenic/eloquent cortex localization and thereby facilitate clinical decision-making.

Risk Factors for Emergency Department Short Time Readmission in Stratified Population

Background. Emergency department (ED) readmissions are considered an indicator of healthcare quality that is particularly relevant in older adults. The primary objective of this study was to identify key factors for predicting patients returning to the ED within 30 days of being discharged. Methods. We analysed patients who attended our ED in June 2014, stratified into four groups based on the Kaiser pyramid. We collected data on more than 100 variables per case including demographic and clinical characteristics and drug treatments. We identified the variables with the highest discriminating power to predict ED readmission and constructed classifiers using machine learning methods to provide predictions. Results. Classifier performance distinguishing between patients who were and were not readmitted (within 30 days), in terms of average accuracy (AC). The variables with the greatest discriminating power were age, comorbidity, reasons for consultation, social factors, and drug treatments. Conclusions. It is possible to predict readmissions in stratified groups with high accuracy and to identify the most important factors influencing the event. Therefore, it will be possible to develop interventions to improve the quality of care provided to ED patients.

A computational framework for cancer response assessment based on oncological PET-CT scans

In this work we present a comprehensive computational framework to help in the clinical assessment of cancer response from a pair of time consecutive oncological PET-CT scans. In this scenario, the design and implementation of a supervised machine learning system to predict and quantify cancer progression or response conditions by introducing a novel feature set that models the underlying clinical context is described. Performance results in 100 clinical cases (corresponding to 200 whole body PET-CT scans) in comparing expert-based visual analysis and classifier decision making show up to 70% accuracy within a completely automatic pipeline and 90% accuracy when providing the system with expert-guided PET tumor segmentation masks.

Parametrization of textural patterns in 123I-ioflupane imaging for the automatic detection of Parkinsonism

PURPOSE

A novel approach to a computer aided diagnosis system for the Parkinson's disease is proposed. This tool is intended as a supporting tool for physicians, based on fully automated methods that lead to the classification of (123)I-ioflupane SPECT images.

METHODS

(123)I-ioflupane images from three different databases are used to train the system. The images are intensity and spatially normalized, then subimages are extracted and a 3D gray-level co-occurrence matrix is computed over these subimages, allowing the characterization of the texture using Haralick texture features. Finally, different discrimination estimation methods are used to select a feature vector that can be used to train and test the classifier.

RESULTS

Using the leave-one-out cross-validation technique over these three databases, the system achieves results up to a 97.4% of accuracy, and 99.1% of sensitivity, with positive likelihood ratios over 27.

CONCLUSIONS

The system presents a robust feature extraction method that helps physicians in the diagnosis task by providing objective, operator-independent textural information about (123)I-ioflupane images, commonly used in the diagnosis of the Parkinson's disease. Textural features computation has been optimized by using a subimage selection algorithm, and the discrimination estimation methods used here makes the system feature-independent, allowing us to extend it to other databases and diseases.

PSO-based support vector machine with cuckoo search technique for clinical disease diagnoses

Disease diagnosis is conducted with a machine learning method. We have proposed a novel machine learning method that hybridizes support vector machine (SVM), particle swarm optimization (PSO), and cuckoo search (CS). The new method consists of two stages: firstly, a CS based approach for parameter optimization of SVM is developed to find the better initial parameters of kernel function, and then PSO is applied to continue SVM training and find the best parameters of SVM. Experimental results indicate that the proposed CS-PSO-SVM model achieves better classification accuracy and F-measure than PSO-SVM and GA-SVM. Therefore, we can conclude that our proposed method is very efficient compared to the previously reported algorithms.