Machine Learning for Dementia Prediction: A Systematic Review and Future Research Directions

Prediction of cognitive impairment among Medicare beneficiaries using a machine learning approach

OBJECTIVE

Developing machine learning (ML) models to predict cognitive impairment among Medicare beneficiaries in the United States.

METHODS

This retrospective study used the 2016-2019 Medicare Current Beneficiary Survey Cost and Use and Survey Public Use Files. Medicare beneficiaries aged 65 and older (n=4,965) with at least two consecutive years' data were included. Cognitive impairment was categorized into three stages: severe, moderate, and none based on self-reported data. Baseline year's demographic, socioeconomic factors, self-reported functional limitations, health status and comorbidities, number of concurrent medications, level of social engagement, behavioral variables, and satisfaction of medical care's quality were features assessed in ML algorithms to predict next years' cognitive function. ML models in six major categories were developed, tested, and compared (accuracy, AUC, and F1 score) using Python version 3.11. The importance of features was evaluated using the total reduction of the Gini. A subgroup analysis was conducted among beneficiaries who were 80 years and older.

RESULTS

Approximately 11.1% of beneficiaries aged ≥ 65 had moderate or severe cognitive function impairment. Baseline cognitive function was the most significant predictor for next year's cognitive function impairment, followed by baseline IADL, level of social activities, ADL, general health status, income, age, education, region of residence, and body mass index. Beneficiaries 80 years and older had satisfaction of medical care's quality among the top 10 most significant predictors.

CONCLUSIONS

Older adults' baseline cognitive function and IADL were top two predictors of cognitive function impairment. Clinicians should regularly screen and monitor older adults' cognitive and daily function.

Beyond group classification: Probabilistic differential diagnosis of frontotemporal dementia and Alzheimer's disease with MRI and CSF biomarkers

Neuroimaging and fluid biomarkers are used to differentiate frontotemporal dementia (FTD) from Alzheimer's disease (AD). We implemented a machine learning algorithm that provides individual probabilistic scores based on magnetic resonance imaging (MRI) and cerebrospinal fluid (CSF) data. We investigated whether combining MRI and CSF levels could improve the diagnosis confidence. 215 AD patients, 103 FTD patients, and 173 healthy controls (CTR) were studied. With MRI data, we obtained an accuracy of 82 % for AD vs. FTD. A total of 74 % of FTD and 73 % of AD participants have a high probability of accurate diagnosis. Adding CSF-NfL and 14-3-3 levels improved the accuracy and the number of patients in the confidence group for differentiating FTD from AD. We obtain individual diagnostic probabilities with high precision to address the problem of confidence in the diagnosis. We suggest when MRI, CSF, or the combination are necessary to improve the FTD and AD diagnosis. This algorithm holds promise towards clinical applications as support to clinical findings or in settings with limited access to expert diagnoses.

Predicting the onset of Alzheimer's disease and related dementia using electronic health records: findings from the cache county study on memory in aging (1995-2008)

INTRODUCTION

Clinical notes, biomarkers, and neuroimaging have proven valuable in dementia prediction models. Whether commonly available structured clinical data can predict dementia is an emerging area of research. We aimed to predict gold-standard, research-based diagnoses of dementia including Alzheimer's disease (AD) and/or Alzheimer's disease related dementias (ADRD), in addition to ICD-based AD and/or ADRD diagnoses, in a well-phenotyped, population-based cohort using a machine learning approach.

METHODS

Administrative healthcare data (k = 163 diagnostic features), in addition to census/vital record sociodemographic data (k = 6 features), were linked to the Cache County Study (CCS, 1995-2008).

RESULTS

Among successfully linked UPDB-CCS participants (n = 4206), 522 (12.4%) had incident dementia (AD alone, AD comorbid with ADRD, or ADRD alone) as per the CCS "gold standard" assessments. Random Forest models, with a 1-year prediction window, achieved the best performance with an Area Under the Curve (AUC) of 0.67. Accuracy declined for dementia subtypes: AD/ADRD (AUC = 0.65); ADRD (AUC = 0.49). Accuracy improved when using ICD-based dementia diagnoses (AUC = 0.77).

DISCUSSION

Commonly available structured clinical data (without labs, notes, or prescription information) demonstrate modest ability to predict "gold-standard" research-based AD/ADRD diagnoses, corroborated by prior research. Using ICD diagnostic codes to identify dementia as done in the majority of machine learning dementia prediction models, as compared to "gold-standard" dementia diagnoses, can result in higher accuracy, but whether these models are predicting true dementia warrants further research.

An intelligent learning system based on electronic health records for unbiased stroke prediction

Stroke has a negative impact on people's lives and is one of the leading causes of death and disability worldwide. Early detection of symptoms can significantly help predict stroke and promote a healthy lifestyle. Researchers have developed several methods to predict strokes using machine learning (ML) techniques. However, the proposed systems have suffered from the following two main problems. The first problem is that the machine learning models are biased due to the uneven distribution of classes in the dataset. Recent research has not adequately addressed this problem, and no preventive measures have been taken. Synthetic Minority Oversampling (SMOTE) has been used to remove bias and balance the training of the proposed ML model. The second problem is to solve the problem of lower classification accuracy of machine learning models. We proposed a learning system that combines an autoencoder with a linear discriminant analysis (LDA) model to increase the accuracy of the proposed ML model for stroke prediction. Relevant features are extracted from the feature space using the autoencoder, and the extracted subset is then fed into the LDA model for stroke classification. The hyperparameters of the LDA model are found using a grid search strategy. However, the conventional accuracy metric does not truly reflect the performance of ML models. Therefore, we employed several evaluation metrics to validate the efficiency of the proposed model. Consequently, we evaluated the proposed model's accuracy, sensitivity, specificity, area under the curve (AUC), and receiver operator characteristic (ROC). The experimental results show that the proposed model achieves a sensitivity and specificity of 98.51% and 97.56%, respectively, with an accuracy of 99.24% and a balanced accuracy of 98.00%.

Predicting Alzheimer's disease from cognitive footprints in mid and late life: How much can register data and machine learning help?

BACKGROUND

Real-world data with decades-long medical records are increasingly available alongside the growing adoption of machine learning in healthcare research. We evaluated the performance of machine learning models in predicting the risk of Alzheimer's disease (AD) using data from the Finnish national registers.

METHODS

We conducted a case-control study using data from the Finnish MEDALZ (Medication use and Alzheimer's disease) study. Altogether 56,741 individuals with incident AD diagnosis (age ≥ 65 years at diagnosis and born after 1922) and their 1:1 age-, sex-, and region of residence-matched controls were included. The association of risk factors, evaluated at different age periods (45-54, 55-64, 65+), and AD were assessed with logistic regression. Predictive accuracies of logistic regressions were compared with seven machine learning models (L1-regularized logistic regression, Naive bayes, Decision tree, Random Forest, Multilayer perceptron, XGBoost, and LightGBM).

FINDINGS

63.5 % of cases and controls were females and the mean age was 79.1 (SD = 5.1). The strongest associations with AD were observed for head injuries at age 55-64 (OR, 95 % CI 1.33, 1.19-1.48) and 65+ (1.31, 1.23-1.40), followed by antidepressant use (1.30, 1.22-1.38) at 55-64 and antipsychotic use (1.27, 1.19-1.35) at 65+. The predictive accuracies of all models were low, with the best performance (AUC 0.603) observed in Random Forest for predicting AD onset at age 65-69.

INTERPRETATION

Although significant associations were identified between many risk factors and AD, the low predictive accuracies suggest that specialised healthcare diagnosis data is not sufficient for predicting AD and linkage with other data sources is needed.

Incremental Value of Multidomain Risk Factors for Dementia Prediction: A Machine Learning Approach

OBJECTIVE

The current evidence regarding how different predictor domains contributes to predicting incident dementia remains unclear. This study aims to assess the incremental value of five predictor domains when added to a simple dementia risk prediction model (DRPM) for predicting incident dementia in older adults.

DESIGN

Population-based, prospective cohort study.

SETTING

UK Biobank study.

PARTICIPANTS

Individuals aged 60 or older without dementia.

MEASUREMENTS

Fifty-five dementia-related predictors were gathered and categorized into clinical and medical history, questionnaire, cognition, polygenetic risk, and neuroimaging domains. Incident dementia (all-cause) and the subtypes, Alzheimer's disease (AD) and vascular dementia (VaD), were determined through hospital and death registries. Ensemble machine learning (ML) DRPMs were employed for prediction. The incremental values of risk predictors were assessed using the percent change in Area Under the Curve (∆AUC%) and the net reclassification index (NRI).

RESULTS

The simple DRPM which included age, body mass index, sex, education, diabetes, hyperlipidaemia, hypertension, depression, smoking, and alcohol consumption yielded an AUC of 0.711 (± 0.008 SD). The five predictor domains exhibited varying levels of incremental value over the basic model when predicting all-cause dementia and the two subtypes. Neuroimaging markers provided the highest incremental value in predicting all-cause dementia (∆AUC% +9.6%) and AD (∆AUC% +16.5%) while clinical and medical history data performed the best at predicting VaD (∆AUC% +12.2%). Combining clinical and medical history, and questionnaire data synergistically enhanced ML DRPM performance.

CONCLUSION

Combining predictors from different domains generally results in better predictive performance. Selecting predictors involves trade-offs, and while neuroimaging markers can significantly enhance predictive accuracy, they may pose challenges in terms of cost or accessibility.

Machine and deep learning algorithms for classifying different types of dementia: A literature review

The cognitive impairment known as dementia affects millions of individuals throughout the globe. The use of machine learning (ML) and deep learning (DL) algorithms has shown great promise as a means of early identification and treatment of dementia. Dementias such as Alzheimer's Dementia, frontotemporal dementia, Lewy body dementia, and vascular dementia are all discussed in this article, along with a literature review on using ML algorithms in their diagnosis. Different ML algorithms, such as support vector machines, artificial neural networks, decision trees, and random forests, are compared and contrasted, along with their benefits and drawbacks. As discussed in this article, accurate ML models may be achieved by carefully considering feature selection and data preparation. We also discuss how ML algorithms can predict disease progression and patient responses to therapy. However, overreliance on ML and DL technologies should be avoided without further proof. It's important to note that these technologies are meant to assist in diagnosis but should not be used as the sole criteria for a final diagnosis. The research implies that ML algorithms may help increase the precision with which dementia is diagnosed, especially in its early stages. The efficacy of ML and DL algorithms in clinical contexts must be verified, and ethical issues around the use of personal data must be addressed, but this requires more study.

Predicting the onset of Alzheimer's disease and related dementia using Electronic Health Records: Findings from the Cache County Study on Memory in Aging (1995-2008)

Introduction

Clinical notes, biomarkers, and neuroimaging have been proven valuable in dementia prediction models. Whether commonly available structured clinical data can predict dementia is an emerging area of research. We aimed to predict Alzheimer's disease (AD) and Alzheimer's disease related dementias (ADRD) in a well-phenotyped, population-based cohort using a machine learning approach.

Methods

Administrative healthcare data (k=163 diagnostic features), in addition to Census/vital record sociodemographic data (k = 6 features), were linked to the Cache County Study (CCS, 1995-2008).

Results

Among successfully linked UPDB-CCS participants (n=4206), 522 (12.4%) had incident AD/ADRD as per the CCS "gold standard" assessments. Random Forest models, with a 1-year prediction window, achieved the best performance with an Area Under the Curve (AUC) of 0.67. Accuracy declined for dementia subtypes: AD/ADRD (AUC = 0.65); ADRD (AUC = 0.49).

DISCUSSION

Commonly available structured clinical data (without labs, notes, or prescription information) demonstrate modest ability to predict AD/ADRD, corroborated by prior research.

Machine Learning Accelerates De Novo Design of Antimicrobial Peptides

Efficient and precise design of antimicrobial peptides (AMPs) is of great importance in the field of AMP development. Computing provides opportunities for peptide de novo design. In the present investigation, a new machine learning-based AMP prediction model, AP_Sin, was trained using 1160 AMP sequences and 1160 non-AMP sequences. The results showed that AP_Sin correctly classified 94.61% of AMPs on a comprehensive dataset, outperforming the mainstream and open-source models (Antimicrobial Peptide Scanner vr.2, iAMPpred and AMPlify) and being effective in identifying AMPs. In addition, a peptide sequence generator, AP_Gen, was devised based on the concept of recombining dominant amino acids and dipeptide compositions. After inputting the parameters of the 71 tridecapeptides from antimicrobial peptides database (APD3) into AP_Gen, a tridecapeptide bank consisting of de novo designed 17,496 tridecapeptide sequences were randomly generated, from which 2675 candidate AMP sequences were identified by AP_Sin. Chemical synthesis was performed on 180 randomly selected candidate AMP sequences, of which 18 showed high antimicrobial activities against a wide range of the tested pathogenic microorganisms, and 16 of which had a minimal inhibitory concentration of less than 10 μg/mL against at least one of the tested pathogenic microorganisms. The method established in this research accelerates the discovery of valuable candidate AMPs and provides a novel approach for de novo design of antimicrobial peptides.

Deep learning approaches for seizure video analysis: A review

Seizure events can manifest as transient disruptions in the control of movements which may be organized in distinct behavioral sequences, accompanied or not by other observable features such as altered facial expressions. The analysis of these clinical signs, referred to as semiology, is subject to observer variations when specialists evaluate video-recorded events in the clinical setting. To enhance the accuracy and consistency of evaluations, computer-aided video analysis of seizures has emerged as a natural avenue. In the field of medical applications, deep learning and computer vision approaches have driven substantial advancements. Historically, these approaches have been used for disease detection, classification, and prediction using diagnostic data; however, there has been limited exploration of their application in evaluating video-based motion detection in the clinical epileptology setting. While vision-based technologies do not aim to replace clinical expertise, they can significantly contribute to medical decision-making and patient care by providing quantitative evidence and decision support. Behavior monitoring tools offer several advantages such as providing objective information, detecting challenging-to-observe events, reducing documentation efforts, and extending assessment capabilities to areas with limited expertise. The main applications of these could be (1) improved seizure detection methods; (2) refined semiology analysis for predicting seizure type and cerebral localization. In this paper, we detail the foundation technologies used in vision-based systems in the analysis of seizure videos, highlighting their success in semiology detection and analysis, focusing on work published in the last 7 years. We systematically present these methods and indicate how the adoption of deep learning for the analysis of video recordings of seizures could be approached. Additionally, we illustrate how existing technologies can be interconnected through an integrated system for video-based semiology analysis. Each module can be customized and improved by adapting more accurate and robust deep learning approaches as these evolve. Finally, we discuss challenges and research directions for future studies.

Deep learning applications in vascular dementia using neuroimaging

PURPOSE OF REVIEW

Vascular dementia (VaD) is the second common cause of dementia after Alzheimer's disease, and deep learning has emerged as a critical tool in dementia research. The aim of this article is to highlight the current deep learning applications in VaD-related imaging biomarkers and diagnosis.

RECENT FINDINGS

The main deep learning technology applied in VaD using neuroimaging data is convolutional neural networks (CNN). CNN models have been widely used for lesion detection and segmentation, such as white matter hyperintensities (WMH), cerebral microbleeds (CMBs), perivascular spaces (PVS), lacunes, cortical superficial siderosis, and brain atrophy. Applications in VaD subtypes classification also showed excellent results. CNN-based deep learning models have potential for further diagnosis and prognosis of VaD.

SUMMARY

Deep learning neural networks with neuroimaging data in VaD research represent significant promise for advancing early diagnosis and treatment strategies. Ongoing research and collaboration between clinicians, data scientists, and neuroimaging experts are essential to address challenges and unlock the full potential of deep learning in VaD diagnosis and management.

Comparative study of machine learning methods for modeling associations between risk factors and future dementia cases

A substantial portion of dementia risk can be attributed to modifiable risk factors that can be affected by lifestyle changes. Identifying the contributors to dementia risk could prove valuable. Recently, machine learning methods have been increasingly applied to healthcare data. Several studies have attempted to predict dementia progression by using such techniques. This study aimed to compare the performance of different machine-learning methods in modeling associations between known cognitive risk factors and future dementia cases. A subset of the AGES-Reykjavik Study dataset was analyzed using three machine-learning methods: logistic regression, random forest, and neural networks. Data were collected twice, approximately five years apart. The dataset included information from 1,491 older adults who underwent a cognitive screening process and were considered to have healthy cognition at baseline. Cognitive risk factors included in the models were based on demographics, MRI data, and other health-related data. At follow-up, participants were re-evaluated for dementia using the same cognitive screening process. Various performance metrics for all three machine learning algorithms were assessed. The study results indicate that a random forest algorithm performed better than neural networks and logistic regression in predicting the association between cognitive risk factors and dementia. Compared to more traditional statistical analyses, machine-learning methods have the potential to provide more accurate predictions about which individuals are more likely to develop dementia than others.

Breaking barriers: a statistical and machine learning-based hybrid system for predicting dementia

Introduction: Dementia is a condition (a collection of related signs and symptoms) that causes a continuing deterioration in cognitive function, and millions of people are impacted by dementia every year as the world population continues to rise. Conventional approaches for determining dementia rely primarily on clinical examinations, analyzing medical records, and administering cognitive and neuropsychological testing. However, these methods are time-consuming and costly in terms of treatment. Therefore, this study aims to present a noninvasive method for the early prediction of dementia so that preventive steps should be taken to avoid dementia. Methods: We developed a hybrid diagnostic system based on statistical and machine learning (ML) methods that used patient electronic health records to predict dementia. The dataset used for this study was obtained from the Swedish National Study on Aging and Care (SNAC), with a sample size of 43040 and 75 features. The newly constructed diagnostic extracts a subset of useful features from the dataset through a statistical method (F-score). For the classification, we developed an ensemble voting classifier based on five different ML models: decision tree (DT), naive Bayes (NB), logistic regression (LR), support vector machines (SVM), and random forest (RF). To address the problem of ML model overfitting, we used a cross-validation approach to evaluate the performance of the proposed diagnostic system. Various assessment measures, such as accuracy, sensitivity, specificity, receiver operating characteristic (ROC) curve, and Matthew's correlation coefficient (MCC), were used to thoroughly validate the devised diagnostic system's efficiency. Results: According to the experimental results, the proposed diagnostic method achieved the best accuracy of 98.25%, as well as sensitivity of 97.44%, specificity of 95.744%, and MCC of 0.7535. Discussion: The effectiveness of the proposed diagnostic approach is compared to various cutting-edge feature selection techniques and baseline ML models. From experimental results, it is evident that the proposed diagnostic system outperformed the prior feature selection strategies and baseline ML models regarding accuracy.

Comparison of multiple linear regression and machine learning methods in predicting cognitive function in older Chinese type 2 diabetes patients

INTRODUCTION

The prevalence of type 2 diabetes (T2D) has increased dramatically in recent decades, and there are increasing indications that dementia is related to T2D. Previous attempts to analyze such relationships principally relied on traditional multiple linear regression (MLR). However, recently developed machine learning methods (Mach-L) outperform MLR in capturing non-linear relationships. The present study applied four different Mach-L methods to analyze the relationships between risk factors and cognitive function in older T2D patients, seeking to compare the accuracy between MLR and Mach-L in predicting cognitive function and to rank the importance of risks factors for impaired cognitive function in T2D.

METHODS

We recruited older T2D between 60-95 years old without other major comorbidities. Demographic factors and biochemistry data were used as independent variables and cognitive function assessment (CFA) was conducted using the Montreal Cognitive Assessment as an independent variable. In addition to traditional MLR, we applied random forest (RF), stochastic gradient boosting (SGB), Naïve Byer's classifier (NB) and eXtreme gradient boosting (XGBoost).

RESULTS

Totally, the test cohort consisted of 197 T2D (98 men and 99 women). Results showed that all ML methods outperformed MLR, with symmetric mean absolute percentage errors for MLR, RF, SGB, NB and XGBoost respectively of 0.61, 0.599, 0.606, 0.599 and 0.2139. Education level, age, frailty score, fasting plasma glucose and body mass index were identified as key factors in descending order of importance.

CONCLUSION

In conclusion, our study demonstrated that RF, SGB, NB and XGBoost are more accurate than MLR for predicting CFA score, and identify education level, age, frailty score, fasting plasma glucose, body fat and body mass index as important risk factors in an older Chinese T2D cohort.

Rethinking Dementia Risk Prediction: A Critical Evaluation of a Multimodal Machine Learning Predictive Model

A recent study by Ding et al. explores the integration of artificial intelligence (AI) in predicting dementia risk over a 10-year period using a multimodal approach. While revealing the potential of machine learning models in identifying high-risk individuals through neuropsychological testing, MRI imaging, and clinical risk factors, the imperative of dynamic frailty assessment emerges for accurate late-life dementia prediction. The commentary highlights challenges associated with AI models, including dimensionality and data standardization, emphasizing the critical need for a dynamic, comprehensive approach to reflect the evolving nature of dementia and improve predictive accuracy.

Brain Disorder Detection and Diagnosis using Machine Learning and Deep Learning - A Bibliometric Analysis

BACKGROUND AND OBJECTIVE

Brain disorders are one of the major global mortality issues, and their early detection is crucial for healing. Machine learning, specifically deep learning, is a technology that is increasingly being used to detect and diagnose brain disorders. Our objective is to provide a quantitative bibliometric analysis of the field to inform researchers about trends that can inform their Research directions in the future.

METHODS

We carried out a bibliometric analysis to create an overview of brain disorder detection and diagnosis using machine learning and deep learning. Our bibliometric analysis includes 1550 articles gathered from the Scopus database on automated brain disorder detection and diagnosis using machine learning and deep learning published from 2015 to May 2023. A thorough bibliometric análisis is carried out with the help of Biblioshiny and the VOSviewer platform. Citation analysis and various measures of collaboration are analyzed in the study.

RESULTS

According to a study, maximum research is reported in 2022, with a consistent rise from preceding years. The majority of the authors referenced have concentrated on multiclass classification and innovative convolutional neural network models that are effective in this field. A keyword analysis revealed that among the several brain disorder types, Alzheimer's, autism, and Parkinson's disease had received the greatest attention. In terms of both authors and institutes, the USA, China, and India are among the most collaborating countries. We built a future research agenda based on our findings to help progress research on machine learning and deep learning for brain disorder detection and diagnosis.

CONCLUSION

In summary, our quantitative bibliometric analysis provides useful insights about trends in the field and points them to potential directions in applying machine learning and deep learning for brain disorder detection and diagnosis.

.

New Horizons in artificial intelligence in the healthcare of older people

Artificial intelligence (AI) in healthcare describes algorithm-based computational techniques which manage and analyse large datasets to make inferences and predictions. There are many potential applications of AI in the care of older people, from clinical decision support systems that can support identification of delirium from clinical records to wearable devices that can predict the risk of a fall. We held four meetings of older people, clinicians and AI researchers. Three priority areas were identified for AI application in the care of older people. These included: monitoring and early diagnosis of disease, stratified care and care coordination between healthcare providers. However, the meetings also highlighted concerns that AI may exacerbate health inequity for older people through bias within AI models, lack of external validation amongst older people, infringements on privacy and autonomy, insufficient transparency of AI models and lack of safeguarding for errors. Creating effective interventions for older people requires a person-centred approach to account for the needs of older people, as well as sufficient clinical and technological governance to meet standards of generalisability, transparency and effectiveness. Education of clinicians and patients is also needed to ensure appropriate use of AI technologies, with investment in technological infrastructure required to ensure equity of access.

Artificial intelligence for dementia research methods optimization

Artificial intelligence (AI) and machine learning (ML) approaches are increasingly being used in dementia research. However, several methodological challenges exist that may limit the insights we can obtain from high-dimensional data and our ability to translate these findings into improved patient outcomes. To improve reproducibility and replicability, researchers should make their well-documented code and modeling pipelines openly available. Data should also be shared where appropriate. To enhance the acceptability of models and AI-enabled systems to users, researchers should prioritize interpretable methods that provide insights into how decisions are generated. Models should be developed using multiple, diverse datasets to improve robustness, generalizability, and reduce potentially harmful bias. To improve clarity and reproducibility, researchers should adhere to reporting guidelines that are co-produced with multiple stakeholders. If these methodological challenges are overcome, AI and ML hold enormous promise for changing the landscape of dementia research and care. HIGHLIGHTS: Machine learning (ML) can improve diagnosis, prevention, and management of dementia. Inadequate reporting of ML procedures affects reproduction/replication of results. ML models built on unrepresentative datasets do not generalize to new datasets. Obligatory metrics for certain model structures and use cases have not been defined. Interpretability and trust in ML predictions are barriers to clinical translation.

Dementia prediction in the general population using clinically accessible variables: a proof-of-concept study using machine learning. The AGES-Reykjavik study

BACKGROUND

Early identification of dementia is crucial for prompt intervention for high-risk individuals in the general population. External validation studies on prognostic models for dementia have highlighted the need for updated models. The use of machine learning in dementia prediction is in its infancy and may improve predictive performance. The current study aimed to explore the difference in performance of machine learning algorithms compared to traditional statistical techniques, such as logistic and Cox regression, for prediction of all-cause dementia. Our secondary aim was to assess the feasibility of only using clinically accessible predictors rather than MRI predictors.

METHODS

Data are from 4,793 participants in the population-based AGES-Reykjavik Study without dementia or mild cognitive impairment at baseline (mean age: 76 years, % female: 59%). Cognitive, biometric, and MRI assessments (total: 59 variables) were collected at baseline, with follow-up of incident dementia diagnoses for a maximum of 12 years. Machine learning algorithms included elastic net regression, random forest, support vector machine, and elastic net Cox regression. Traditional statistical methods for comparison were logistic and Cox regression. Model 1 was fit using all variables and model 2 was after feature selection using the Boruta package. A third model explored performance when leaving out neuroimaging markers (clinically accessible model). Ten-fold cross-validation, repeated ten times, was implemented during training. Upsampling was used to account for imbalanced data. Tuning parameters were optimized for recalibration automatically using the caret package in R.

RESULTS

19% of participants developed all-cause dementia. Machine learning algorithms were comparable in performance to logistic regression in all three models. However, a slight added performance was observed in the elastic net Cox regression in the third model (c = 0.78, 95% CI: 0.78-0.78) compared to the traditional Cox regression (c = 0.75, 95% CI: 0.74-0.77).

CONCLUSIONS

Supervised machine learning only showed added benefit when using survival techniques. Removing MRI markers did not significantly worsen our model's performance. Further, we presented the use of a nomogram using machine learning methods, showing transportability for the use of machine learning models in clinical practice. External validation is needed to assess the use of this model in other populations. Identifying high-risk individuals will amplify prevention efforts and selection for clinical trials.

Sooty Tern Optimization Algorithm-Based Deep Learning Model for Diagnosing NSCLC Tumours

Lung cancer is one of the most common causes of cancer deaths in the modern world. Screening of lung nodules is essential for early recognition to facilitate treatment that improves the rate of patient rehabilitation. An increase in accuracy during lung cancer detection is vital for sustaining the rate of patient persistence, even though several research works have been conducted in this research domain. Moreover, the classical system fails to segment cancer cells of different sizes accurately and with excellent reliability. This paper proposes a sooty tern optimization algorithm-based deep learning (DL) model for diagnosing non-small cell lung cancer (NSCLC) tumours with increased accuracy. We discuss various algorithms for diagnosing models that adopt the Otsu segmentation method to perfectly isolate the lung nodules. Then, the sooty tern optimization algorithm (SHOA) is adopted for partitioning the cancer nodules by defining the best characteristics, which aids in improving diagnostic accuracy. It further utilizes a local binary pattern (LBP) for determining appropriate feature retrieval from the lung nodules. In addition, it adopts CNN and GRU-based classifiers for identifying whether the lung nodules are malignant or non-malignant depending on the features retrieved during the diagnosing process. The experimental results of this SHOA-optimized DNN model achieved an accuracy of 98.32%, better than the baseline schemes used for comparison.

Early Prediction of Dementia Using Feature Extraction Battery (FEB) and Optimized Support Vector Machine (SVM) for Classification

Dementia is a cognitive disorder that mainly targets older adults. At present, dementia has no cure or prevention available. Scientists found that dementia symptoms might emerge as early as ten years before the onset of real disease. As a result, machine learning (ML) scientists developed various techniques for the early prediction of dementia using dementia symptoms. However, these methods have fundamental limitations, such as low accuracy and bias in machine learning (ML) models. To resolve the issue of bias in the proposed ML model, we deployed the adaptive synthetic sampling (ADASYN) technique, and to improve accuracy, we have proposed novel feature extraction techniques, namely, feature extraction battery (FEB) and optimized support vector machine (SVM) using radical basis function (rbf) for the classification of the disease. The hyperparameters of SVM are calibrated by employing the grid search approach. It is evident from the experimental results that the newly pr oposed model (FEB-SVM) improves the dementia prediction accuracy of the conventional SVM by 6%. The proposed model (FEB-SVM) obtained 98.28% accuracy on training data and a testing accuracy of 93.92%. Along with accuracy, the proposed model obtained a precision of 91.80%, recall of 86.59, F1-score of 89.12%, and Matthew's correlation coefficient (MCC) of 0.4987. Moreover, the newly proposed model (FEB-SVM) outperforms the 12 state-of-the-art ML models that the researchers have recently presented for dementia prediction.

Predicting Progression to Clinical Alzheimer's Disease Dementia Using the Random Survival Forest

BACKGROUND

Assessing the risk of developing clinical Alzheimer's disease (AD) dementia, by machine learning survival analysis approaches, among participants registered in Alzheimer's Disease Centers is important for AD dementia management.

OBJECTIVE

To construct a prediction model for the onset time of clinical AD dementia using the National Alzheimer Coordinating Center (NACC) and the Alzheimer's Disease Neuroimaging Initiative (ADNI) registered cohorts.

METHODS

A model was constructed using the Random Survival Forest (RSF) approach and internally and externally validated on the NACC cohort and the ADNI cohort. An R package and a Shiny app were provided for accessing the model.

RESULTS

We built a predictive model having the six predictors: delayed logical memory score (story recall), CDR® Dementia Staging Instrument - Sum of Boxes, general orientation in CDR®, ability to remember dates and ability to pay bills in the Functional Activities Questionnaire, and patient age. The C indices of the model were 90.82% (SE = 0.71%) and 86.51% (SE = 0.75%) in NACC and ADNI respectively. The time-dependent AUC and accuracy at 48 months were 92.48% (SE = 1.12%) and 88.66% (SE = 1.00%) respectively in NACC, and 90.16% (SE = 1.12%) and 85.00% (SE = 1.14%) respectively in ADNI.

CONCLUSION

The model showed good prediction performance and the six predictors were easy to obtain, cost-effective, and non-invasive. The model could be used to inform clinicians and patients on the probability of developing clinical AD dementia in 4 years with high accuracy.