Artificial intelligence for dementia genetics and omics.

Biological processes are fundamentally driven by complex interactions between biomolecules. Integrated high-throughput omics studies enable multifaceted views of cells, organisms, or their communities. With the advent of new post-genomics technologies, omics studies are becoming increasingly prevalent; yet the full impact of these studies can only be realized through data harmonization, sharing, meta-analysis, and integrated research. These essential steps require consistent generation, capture, and distribution of metadata. To ensure transparency, facilitate data harmonization, and maximize reproducibility and usability of life sciences studies, we propose a simple common omics metadata checklist. The proposed checklist is built on the rich ontologies and standards already in use by the life sciences community. The checklist will serve as a common denominator to guide experimental design, capture important parameters, and be used as a standard format for stand-alone data publications. The omics metadata checklist and data publications will create efficient linkages between omics data and knowledge-based life sciences innovation and, importantly, allow for appropriate attribution to data generators and infrastructure science builders in the post-genomics era. We ask that the life sciences community test the proposed omics metadata checklist and data publications and provide feedback for their use and improvement.

Earth system models (ESMs) are our key tools for analyzing the planet's existing state and predicting its evolution in the next continuing human-caused events. However, the use of artificial intelligence (AI) approaches to augment or even replace conventional ESM functions has expanded in recent years, raising hopes that AI will be able to overcome some of the major difficulties in climate research. We address the advantages and disadvantages of neural ESM neurons, as well as the unsolved question of whether AI will eventually replace ESMs. Dynamic geophysical events are the foundation of Earth and environmental studies. Given the widespread acceptance of AI and the growing amount of Earth data, the geoscientific community may wish to seriously explore using artificial intelligence (AI) approaches at a much deeper level. Although it is a tall ambition to integrate hybrid physics and AI approaches from a fresh perspective, geology has yet to figure out how to make such methods feasible. This research is an important step towards realising the concept of combining physics and artificial intelligence to address problems with the Earth's system.

The primary objective of this study is to investigate various applications of artificial intelligence (AI) and statistical methodologies for analyzing and managing peritoneal metastases (PM) caused by gastrointestinal cancers. Relevant keywords and search criteria were comprehensively researched on PubMed and Google Scholar to identify articles and reviews related to the topic. The AI approaches considered were conventional machine learning (ML) and deep learning (DL) models, and the relevant statistical approaches included biostatistics and logistic models. The systematic literature review yielded nearly 30 articles meeting the predefined criteria. Analyses of these studies showed that AI methodologies consistently outperformed traditional statistical approaches. In the AI approaches, DL consistently produced the most precise results, while classical ML demonstrated varied performance but maintained high predictive accuracy. The sample size was the recurring factor that increased the accuracy of the predictions for models of the same type. AI and statistical approaches can detect PM developing among patients with gastrointestinal cancers. Therefore, if clinicians integrated these approaches into diagnostics and prognostics, they could better analyze and manage PM, enhancing clinical decision-making and patients' outcomes. Collaboration across multiple institutions would also help in standardizing methods for data collection and allowing consistent results.

New research and clinical criteria for Alzheimer's disease (AD) have recently been proposed, which include biomarker information on Alzheimer's plaque and tangle pathology, or AD-typical structural brain changes, as supporting or essential elements of an AD diagnosis.1, 2, 3 In a large group of patients with both genetic and cerebrospinal fluid (CSF) biomarker data, we here show that biomarker-assisted diagnosis-making almost doubles the effect size of the association between the ɛ4 variant of the apolipoprotein E (APOE) gene and AD. We included clinically diagnosed patients with either AD dementia (n=309) or mild cognitive impairment (MCI) due to AD (n=287), cognitively normal controls (n=251) and patients with MCI who remained stable over at least 2 years (n=399) or developed dementias other than AD (n=99) (Table 1, Supplementary Material). All had APOE ɛ2/ɛ3/ɛ4 genotypes and results on the CSF biomarkers total tau (T-tau), phosphorylated tau (P-tau) and the 42-amino-acid isoform of amyloid-β (Aβ42) determined. These CSF biomarkers reflect the core elements of Alzheimer's pathology4 and are strongly associated with AD in cross-sectional as well as longitudinal follow-up studies (Supplementary Material).5, 6 AD dementia and MCI-AD patients were first pooled into one clinical AD group (n=596) and compared with all remaining categories that were designated non-AD (n=749). A positive APOE ɛ4 carrier status (one or two ɛ4 alleles) was overrepresented in the AD group and yielded an odds ratio (OR) of 4.45 (95% confidence interval (CI) 3.52–5.62) for a clinical diagnosis of AD at inclusion or follow-up (Figure 1). This OR is similar to the AlzGene meta-analysis of APOE (3.68, 95% CI 3.30–4.11, www.alzgene.org/meta.asp?geneID=83, November 2012 freeze). Similarly, we tested the association of APOE ɛ4 with AD, comparing the 596 AD patients with the 251 cognitively normal controls, which resulted in an OR of 6.35 (95% CI 4.59–8.80). Figure 1 Odds ratios for a positive APOE ɛ4 carrier status based on (A) clinical diagnosis, comparing patients with clinical AD with dementia at inclusion or follow-up (n=596) versus all other diagnostic groups (n=749), (B) clinical diagnosis, comparing ... Disregarding the clinical diagnoses and subgrouping all subjects into amyloid-positive, defined as CSF Aβ42 <546 ng l−1 (n=779), and amyloid-negative, defined as CSF Aβ42 ⩾546 ng l−1 (n=563) (see Supplementary Material for details on cut-point determination), gave an OR for APOE ɛ4 as high as 6.27 (95% CI 4.93–7.98). Dichotomizing the material according to CSF T-tau or P-tau did not change the ORs as compared with clinical diagnosis only (Figure 1). Even though the OR for the ratio P-tau/Aβ42 (6.50 (95% CI 5.07–8.35)) was slightly higher than for Aβ42 alone, the difference was not statistically significant. We also compared patients, again disregarding the clinical diagnoses, who had a complete CSF biomarker signature indicative of AD, that is, low Aβ42 and both high T-tau and P-tau (n=438, see Supplementary Material for a detailed description of the signature), with subjects with a negative CSF biomarker pattern (n=414). The biomarker diagnosis strengthened the association to APOE ɛ4; the OR increased from 4.45 (95% CI 3.52–5.62) in pure clinical diagnosis to 7.66 (95% CI 5.65–10.39) in patients classified on the basis of biomarker data alone. Finally, ORs were calculated on subjects having both a clinical diagnosis and a concordant complete biomarker profile (n(AD)=324; n(control)=155). This approach resulted in an even stronger association of APOE ɛ4 with AD (OR 10.4, 95% CI 6.65–16.3). Similar effects were seen when comparing non-carriers with ɛ4 heterozygotes and homozygotes across the different diagnostic groups (Figure 1, Supplementary Material). These results have several important implications. First, APOE ɛ4 appears as strongly associated with amyloid pathology as clinical AD. Second, clinical criteria that incorporate biomarker information on Alzheimer's pathology give a stronger association with APOE ɛ4 than clinical diagnosis alone. This is compatible with the presumed higher diagnostic accuracy of the revised clinical approach,1, 2, 3 and has also been seen in a series of neuropathologically verified AD cases and controls.7 Third, the approach of combining clinical with biomarker data may increase the power of genetic association studies, as well as the potential to provide insights into the mechanistic pathways through which genetic risk factors may exert their effects.

Chronic Obstructive Pulmonary Disease (COPD) is the third leading cause of mortality in the United States; however, COPD has heterogeneous clinical phenotypes. This is the first large scale attempt which uses transcriptomics, proteomics, and metabolomics (multi-omics) to determine whether there are molecularly defined clusters with distinct clinical phenotypes that may underlie the clinical heterogeneity. Subjects included 3,278 subjects from the COPDGene cohort with at least one of the following profiles: whole blood transcriptomes (2,650 subjects); plasma proteomes (1,013 subjects); and plasma metabolomes (1,136 subjects). 489 subjects had all three contemporaneous -omics profiles. Autoencoder embeddings were performed individually for each -omics dataset. Embeddings underwent subspace clustering using MineClus, either individually by -omics or combined, followed by recursive feature selection based on Support Vector Machines. Clusters were tested for associations with clinical variables. Optimal single -omics clustering typically resulted in two clusters. Although there was overlap for individual -omics cluster membership, each -omics cluster tended to be defined by unique molecular pathways. For example, prominent molecular features of the metabolome-based clustering included sphingomyelin, while key molecular features of the transcriptome-based clusters were related to immune and bacterial responses. We also found that when we integrated the -omics data at a later stage, we identified subtypes that varied based on age, severity of disease, in addition to diffusing capacity of the lungs for carbon monoxide, and precent on atrial fibrillation. In contrast, when we integrated the -omics data at an earlier stage by treating all data sets equally, there were no clinical differences between subtypes. Similar to clinical clustering, which has revealed multiple heterogenous clinical phenotypes, we show that transcriptomics, proteomics, and metabolomics tend to define clusters of COPD patients with different clinical characteristics. Thus, integrating these different -omics data sets affords additional insight into the molecular nature of COPD and its heterogeneity.

The National Institute on Aging (NIA) is at the forefront of leveraging advances in artificial intelligence (AI) to better understanding of aging and the diagnosis and treatment of Alzheimer's Disease (AD) and Alzheimer's disease-related dementias (ADRD). Recent NIA-supported projects have highlighted the transformative potential of AI, digital health, and computational approaches in improving the modeling, detection, and monitoring of changes in healthy aging and AD/ADRD. This perspective is forward looking, emphasizing key areas and efforts in AI-driven precision measurement in cognition, behavior, and psychological function.

According to the latest revised National Institute of Neurological and Communicative Disorders and Stroke and the Alzheimer's Disease and Related Disorders Association (now known as the Alzheimer's Association) (NINCDS-ADRDA) diagnostic criteria for Alzheimer's disease dementia, the confidence in diagnosing mild cognitive impairment (MCI) due to Alzheimer's disease dementia is raised with the application of imaging biomarkers. These tests, added to core clinical criteria, might increase the sensitivity or specificity of a testing strategy. However, the accuracy of biomarkers in the diagnosis of Alzheimer's disease dementia and other dementias has not yet been systematically evaluated. A formal systematic evaluation of the sensitivity, specificity, and other properties of positron emission tomography (PET) imaging with the (11)C-labelled Pittsburgh Compound-B ((11)C-PIB) ligand was performed. To determine the diagnostic accuracy of the (11)C- PIB-PET scan for detecting participants with MCI at baseline who will clinically convert to Alzheimer's disease dementia or other forms of dementia over a period of time. The most recent search for this review was performed on 12 January 2013. We searched MEDLINE (OvidSP), EMBASE (OvidSP), BIOSIS Previews (ISI Web of Knowledge), Web of Science and Conference Proceedings (ISI Web of Knowledge), PsycINFO (OvidSP), and LILACS (BIREME). We also requested a search of the Cochrane Register of Diagnostic Test Accuracy Studies (managed by the Cochrane Renal Group).No language or date restrictions were applied to the electronic searches and methodological filters were not used so as to maximise sensitivity. We selected studies that had prospectively defined cohorts with any accepted definition of MCI with baseline (11)C-PIB-PET scan. In addition, we only selected studies that applied a reference standard for Alzheimer's dementia diagnosis for example NINCDS-ADRDA or Diagnostic and Statistical Manual of Mental Disorders-IV (DSM-IV) criteria. We screened all titles generated by electronic database searches. Two review authors independently assessed the abstracts of all potentially relevant studies. The identified full papers were assessed for eligibility and data were extracted to create two by two tables. Two independent assessors performed quality assessment using the QUADAS 2 tool. We used the hierarchical summary receiver operating characteristic (ROC) model to produce a summary ROC curve. Conversion from MCI to Alzheimer's disease dementia was evaluated in nine studies. The quality of the evidence was limited. Of the 274 participants included in the meta-analysis, 112 developed Alzheimer's dementia. Based on the nine included studies, the median proportion converting was 34%. The studies varied markedly in how the PIB scans were done and interpreted.The sensitivities were between 83% and 100% while the specificities were between 46% and 88%. Because of the variation in thresholds and measures of (11)C-PIB amyloid retention, we did not calculate summary sensitivity and specificity. Although subject to considerable uncertainty, to illustrate the potential strengths and weaknesses of (11)C-PIB-PET scans we estimated from the fitted summary ROC curve that the sensitivity was 96% (95% confidence interval (CI) 87 to 99) at the included study median specificity of 58%. This equated to a positive likelihood ratio of 2.3 and a negative likelihood ratio of 0.07. Assuming a typical conversion rate of MCI to Alzheimer's dementia of 34%, for every 100 PIB scans one person with a negative scan would progress and 28 with a positive scan would not actually progress to Alzheimer's dementia.There were limited data for formal investigation of heterogeneity. We performed two sensitivity analyses to assess the influence of type of reference standard and the use of a pre-specified threshold. There was no effect on our findings. Although the good sensitivity achieved in some included studies is promising for the value of (11)C-PIB-PET, given the heterogeneity in the conduct and interpretation of the test and the lack of defined thresholds for determination of test positivity, we cannot recommend its routine use in clinical practice.(11)C-PIB-PET biomarker is a high cost investigation, therefore it is important to clearly demonstrate its accuracy and standardise the process of the (11)C-PIB diagnostic modality prior to it being widely used.

Twenty Years of the Alzheimer’s Disease Amyloid Hypothesis: A Genetic Perspective

Dementia and stroke are major global causes of disability, with modifiable lifestyle factors playing a significant role in their development. The updated LIfestyle for BRAin health (LIBRA2) score integrates 15 modifiable risk and protective factors to quantify lifestyle-based dementia risk, but its relationship with stroke and dementia subtypes remains unexplored. We investigated LIBRA2's association with stroke and dementia subtypes while also assessing potential interactions with genetic susceptibility. Prospective data were used from the French multicenter Three-City (3C) Study, with participants aged 65 years and older followed for up to 17 years. Weighted LIBRA2 scores at baseline were constructed based on the presence of 15 modifiable risk and protective factors, with higher scores representing higher lifestyle-based dementia risk. Cox proportional hazards models were used to study the association of LIBRA2 with incident dementia (and subtypes) and stroke, adjudicated by expert neurologist panels. Genetic susceptibility to dementia and stroke was assessed using APOE ε4 carriership and disease-specific genetic risk scores. Analyses included 4,731 participants for stroke (mean age 73.8 years, 60.1% female) and 4,737 participants for dementia (mean age 73.8 years, 59.9% female). One-point increases in LIBRA2 scores (theoretical range -6.1 to +25.7) were associated with increased dementia risk (hazard ratio [HR] 1.08; 1.06-1.11), with a stronger association for vascular and mixed dementia (HR 1.13; 1.08-1.18) compared with Alzheimer disease (AD) dementia (HR 1.06; 1.03-1.09). LIBRA2 was not significantly associated with incident stroke risk (HR 1.03; 0.99-1.07). No significant interaction was found between LIBRA2 and APOE ε4 carriership or disease-specific genetic risk scores in relation to dementia subtypes or stroke. LIBRA2 serves as a valuable tool for assessing lifestyle-related dementia risk and its subtypes but showed no association with stroke, highlighting the potential for a stroke-specific risk reduction model. These associations were independent of genetic disease susceptibility, reinforcing the universal benefits of lifestyle modifications on dementia risk reduction. The stronger association between LIBRA2 (and some individual components) and vascular or mixed dementia, compared with AD dementia, highlights the pivotal role of vascular mechanisms in the relationship between lifestyle and brain health.

Many of the reports created at assembly lines, where all components of an aircraft are installed, frequently indicate that errors threaten safety. The proposed methodology in this study evaluates error prediction and risk mitigation to prevent failures and their consequences. The results linked to a typical electrical harness manufacture of a military aircraft estimated reductions of 93% in time and 90% in error during the creation of engineering manufacturing processes using AI techniques. However, traditional risk assessments methods struggle to identify and mitigate errors effectively. Thus, developing an advanced methodology to ensure systems safety is needed. This paper addresses how innovative AI technology solutions can overcome these challenges, mitigate error risks, and enhance safety in aerospace. Technologies, such as artificial intelligence, predictive algorithms, machine learning, and automation, can play a key role in enhancing safety. The aim of this study is to develop a model that considers the factors that can potentially contribute to error creation, through an artificial intelligence (AI) approach. The specific AI techniques used such as support vector machine, random forest, logistic regression, K-nearest neighbor, and XGBoost (Python 3.8.5) show good performance for use in error mitigation. We have compared the modeled values obtained in this study with the experimental ones. The results confirm that the best metrics are obtained by using support vector machine and logistic regression. The smallest deviation between the measured and modeled values for these AI methods do not exceed 5%. Furthermore, using advancements in machine learning methods can enhance error mitigation in aerospace. The use of AutoML can play a key role in automatically finding an appropriate model which provides the best performance metrics and therefore the most reliable forecast for data prediction and error mitigation.

Urban land use change is a complex and dynamic process. It is therefore important to understand the complexity involved with system dynamics and choose appropriate modelling approaches. For this purpose, this paper firstly reviews how artificial intelligence (AI) approaches provide solutions to aid urban land dynamics modelling. The three dimensions that are considered pivotal for the understanding of urban dynamic processes – urban land dynamics, planning support and AI infrastructure – are defined. Once these three dimensions are clarified, it is possible to propose the different solution spaces provided by AI approaches using a graphic representation of a cube and its associated mathematical formulation. It is therefore possible to understand and define the best data model to represent the complexity of different phenomena in urban systems.

Artificial Intelligence (AI) and Machine Learning (ML) are becoming common in our daily lives. The AI-driven processes significantly affect us as individuals and as a society, spanning across ethical dimensions like discrimination, misinformation, and fraud. Several of these AI & ML approaches rely on Knowledge Graph (KG) data. Due to the large volume and complexity of today's KG-driven approaches, enormous resources are spent to utilize the complex AI approaches. Efficient usage of the resources like hardware and power consumption is essential for sustainable KG-based ML technologies. This paper introduces the ethical and sustainability considerations, challenges, and optimizations in the context of KG-based ML. We have grouped the ethical and sustainability aspects according to the typical Research & Development (R&D) lifecycle: an initial investigation of the AI approach's responsibility dimensions; technical system setup; central KG data analytics and curating; model selection, training, and evaluation; and final technology deployment. We also describe significant trade-offs and alternative options for dedicated scenarios enriched through existing and reported ethical and sustainability issues in AI-driven approaches and research. These include, e.g., efficient hardware usage guidelines; or the trade-off between transparency and accessibility compared to the risk of manipulability and privacy-related data disclosure. In addition, we propose how biased data and barely explainable AI can result in discriminating ML predictions. This work supports researchers and developers in reflecting, evaluating, and optimizing dedicated KG-based ML approaches in the dimensions of ethics and sustainability.

This study introduces an improved artificial intelligence (AI) approach called intelligence optimized support vector regression (IO-SVR) for estimating the compressive strength of high-performance concrete (HPC). The nonlinear functional mapping between the HPC materials and compressive strength is conducted using the AI approach. A dataset with 1,030 HPC experimental tests is used to train and validate the prediction model. Depending on the results of the experiments, the forecast outcomes of the IO-SVR model are of a much higher quality compared to the outcomes of other AI approaches. Additionally, because of the high-quality learning capabilities, the IO-SVR is highly recommended for calculating HPC strength.

Alzheimer's disease (AD) is a disease of the brain that slowly destroys memory and thinking ability. It is one of the most common forms of dementia in people over the age of 65 worldwide. Early detection of Alzheimer's disease helps medical personnel diagnose this disease, which certainly reduces the risk of death. Therefore, early detection of Alzheimer's disease is an important healthcare issue. In order to achieve accurate and timely diagnosis, and for detection of AD in its early stages, many Artificial Intelligence (AI) and Machine learning approaches have been proposed using data from brain imaging. AI and ML are used for many medical and health purposes, such as disease detection. In this chapter, the main focus is on the diagnosis and detection of Alzheimer's disease using CNN model. A Convolutional Neural Network (CNN) is a deep learning model specialized in detecting and classifying patterns in visual data, commonly used for tasks like image recognition, object detection, and classification.

The purpose of this study was to identify common co-morbid conditions associated with dementia subtypes and to evaluate the association of hypertension, diabetes mellitus, atrial fibrillation, congestive heart failure, and anemia with dementia subtypes relative to controls. Hospital discharge data were used to identify 15,013 subjects from South Carolina with a diagnosis of dementia between 1998 and 1999. A control group of 15,013 persons without dementia was randomly sampled from hospital discharge records and matched to persons with dementia on the basis of age, race, and gender. Multiple hospitalizations for each patient were merged, and repeated diagnoses during separate hospitalizations were counted once. After adjusting for age, race, and gender, persons with Alzheimer's disease and dementia associated with medical conditions were less likely to be diagnosed with hypertension, diabetes, congestive heart failure, and atrial fibrillation than were controls. Patients with multi-infarct dementia were also less likely to have congestive heart failure, but were more likely to have diabetes. Anemia was not associated with any dementia subtype. There are distinct differences in comorbid conditions among dementia subtypes. Our research does not support previous studies that suggest a circulatory component to the development of Alzheimer's disease.