Employing Informatics Strategies in Alzheimer's Disease Research: A Review from Genetics, Multiomics, and Biomarkers to Clinical Outcomes.

Alzheimer's disease (AD) is a critical national concern, affecting 5.8 million people and costing more than 250 billion annually. However, there is no available cure. Thus, effective strategies are in urgent need to discover AD biomarkers for disease early detection and drug development. In this review, we study AD from a biomedical data scientist perspective to discuss the four fundamental components in AD research: genetics (G), molecular multiomics (M), multimodal imaging biomarkers (B), and clinical outcomes (O) (collectively referred to as the GMBO framework). We provide a comprehensive review of common statistical and informatics methodologies for each component within the GMBO framework, accompanied by the major findings from landmark AD studies. Our review highlights the potential of multimodal biobank data in addressing key challenges in AD, such as early diagnosis, disease heterogeneity, and therapeutic development. We identify major hurdles in AD research, including data scarcity and complexity, and advocate for enhanced collaboration, data harmonization, and advanced modeling techniques. This review aims to be an essential guide for understanding current biomedical data science strategies in AD research, emphasizing the need for integrated, multidisciplinary approaches to advance our understanding and management of AD.

Multiplexed serum biomarkers to discriminate nonviable and ectopic pregnancy.

OBJECTIVE: To evaluate combinations of candidate biomarkers to develop a multiplexed prediction model for identifying the viability and location of an early pregnancy. In this study, we assessed 24 biomarkers with multiple machine learning-based methodologies to assess if multiplexed biomarkers may improve the diagnosis of normal and abnormal early pregnancies. DESIGN: A nested case-control design evaluated the predictive ability and discrimination of biomarkers in patients at risk of early pregnancy failure in the first trimester to classify viability and location. SETTING: Three university hospitals. PATIENTS: A total of 218 individuals with pain and/or bleeding in early pregnancy: 75 had an ongoing intrauterine gestation; 68 had ectopic pregnancies (EPs); and 75 had miscarriages. INTERVENTIONS: Serum levels of 24 biomarkers were assessed in the same patients. Multiple machine learning-based methodologies to evaluate combinations of these top candidates to develop a multiplexed prediction model for the identification of a nonviable pregnancy (ongoing intrauterine pregnancy vs. miscarriage or EP) and an EP (EP vs. ongoing intrauterine pregnancy or miscarriage). MAIN OUTCOME MEASURES: The predicted classification using each model was compared with the actual diagnosis, and sensitivity, specificity, positive predictive value, negative predictive value, conclusive classification, and accuracy were calculated. RESULTS: Models using classification regression tree analysis using 3 (pregnancy-specific beta-1-glycoprotein 3 [PSG3], chorionic gonadotropin-alpha subunit, and pregnancy-associated plasma protein-A) biomarkers were able to predict a maximum sensitivity of 93.3% and a maximum specificity of 98.6%. The model with the highest accuracy was 97.4% (with 70.2% receiving classification). Models using an overlapping group of 3 (soluble fms-like tyrosine kinase-1, PSG3, and tissue factor pathway inhibitor 2) biomarkers achieved a maximum sensitivity of 98.5% and a maximum specificity of 95.3%. The model with the highest accuracy was 94.4% (with 65.6% receiving classification). When the models were used simultaneously, the conclusive classification increased to 72.7% with an accuracy of 95.9%. The predictive ability of the biomarkers in the random forest produced similar test characteristics when using 11 predictive biomarkers. CONCLUSION: We have demonstrated a pool of biomarkers from divergent biological pathways that can be used to classify individuals with potential early pregnancy loss. The biomarkers choriogonadotropin alpha, pregnancy-associated plasma protein-A, and PSG3 can be used to predict viability, and soluble fms-like tyrosine kinase-1, tissue factor pathway inhibitor 2, and PSG3 can be used to predict pregnancy location.

Normal Values of Central, Peripheral, and Root Motor Conduction Times in a Healthy Korean Population.

PURPOSE: Central, peripheral, and root motor conduction times (CMCTs, PMCTs, and RMCTs, respectively) are valuable diagnostic tools for spinal cord and motor nerve root lesions. We investigated the normal values and the effects of age and height on each motor conduction time. METHODS: This study included 190 healthy Korean subjects who underwent magnetic stimulation of the cortex and spinous processes at the C7 and L1 levels. Recording muscles were abductor pollicis brevis and abductor digiti minimi in the unilateral upper limb and extensor digitorum brevis and abductor hallucis in the contralateral lower limb. F-wave and compound motor nerve action potentials were also recorded. Central motor conduction time was evaluated as the difference between cortical motor evoked potential onset latency and PMCT using calculation and spinal stimulation methods. Root motor conduction time was computed as the difference between spinal stimulated and calculated CMCTs. RESULTS: The average age and height of the participants were 41.21 ± 14.39 years and 164.64 ± 8.27 cm, respectively; 39.5% (75/190) patients were men. In the linear regression analyses, upper limb CMCTs showed a significant and weak positive relationship with height. Lower limb CMCTs demonstrated a significant and weak positive relationship with age and height. Peripheral motor conduction times were significantly and positively correlated with age and height. Root motor conduction times showed no significant relationship with age and height, except for abductor pollicis brevis-RMCT, which had a weak negative correlation with height. CONCLUSIONS: This study provides normal values of CMCTs, PMCTs, and RCMTs, which have potential clinical applications. When interpreting CMCTs, age and height should be considered.

Clinical effects of novel susceptibility genes for beta-amyloid: a gene-based association study in the Korean population.

Amyloid-beta (Aß) is a pathological hallmark of Alzheimer's disease (AD). We aimed to identify genes related to Aß uptake in the Korean population and investigate the effects of these novel genes on clinical outcomes, including neurodegeneration and cognitive impairments. We recruited a total of 759 Korean participants who underwent neuropsychological tests, brain magnetic resonance imaging, 18F-flutemetamol positron emission tomography, and microarray genotyping data. We performed gene-based association analysis, and also performed expression quantitative trait loci and network analysis. In genome-wide association studies, no single nucleotide polymorphism (SNP) passed the genome-wide significance threshold. In gene-based association analysis, six genes (LCMT1, SCRN2, LRRC46, MRPL10, SP6, and OSBPL7) were significantly associated with Aß standardised uptake value ratio in the brain. The three most significant SNPs (rs4787307, rs9903904, and rs11079797) on these genes are associated with the regulation of the LCMT1, OSBPL7, and SCRN2 genes, respectively. These SNPs are involved in decreasing hippocampal volume and cognitive scores by mediating Aß uptake. The 19 enriched gene sets identified by pathway analysis included axon and chemokine activity. Our findings suggest novel susceptibility genes associated with the uptake of Aß, which in turn leads to worse clinical outcomes. Our findings might lead to the discovery of new AD treatment targets.

Early-stage chronic venous disorder as a cause of leg pain overlooked for lumbar spinal disease.

Leg pain can be caused by both lumbar spinal disease and chronic venous disorder (CVD) of leg veins, but their clinical differences have not been thoroughly investigated. This study aimed to determine the incidence of CVD among patients visiting a spine center for leg pain. A total of 196 cases underwent ultrasound examination with a diagnosis rate were 85.7% (168 cases). CVD-diagnosed cases were divided into two groups based on the severity of lumbar spinal disease. The Clinical grades, symptom areas, and symptom types were compared. The differences in symptom improvements with vasoactive medication were also assessed. The most common symptom area was calf then the foot in CVD, while calf then thigh in lumbar spinal disease. Tingling-paresthesia was the most common symptom type for both, with pain and cramping similarly common in CVD and pain more common than cramping in lumbar spinal disease. Considering that the majority of CVD cases (78.6%) had minor cutaneous changes and almost half of cases (41.7%) had refluxes only in tributaries, significant differences in symptom improvement in CVD-dominant group suggested that early-stage venous reflux is a symptomatic disease and a possible cause of leg pain and other symptoms.

Characteristics of diabetic and non-diabetic carpal tunnel syndrome in terms of clinical, electrophysiological, and Sonographic features: a cross-sectional study.

BACKGROUND: Although diabetes is considered a major risk factor for carpal tunnel syndrome (CTS), the characteristics of diabetic CTS have not been fully understood. OBJECTIVE: This study is aimed at evaluation of the clinical, electrophysiological, and ultrasonographic findings of non-diabetic and diabetic CTS. METHODS: This retrospective, cross-sectional study included patients diagnosed with CTS. Patient age, sex, involved side, body mass index, clinical and electrophysiological findings, and median nerve cross-sectional area (CSA) were identified. Diabetes was identified through patient or guardian interviews, medical records, and medication history. Linear and binary logistic regression models were established to confirm the associations between the electrophysiological findings, median nerve CSA, and clinical outcomes. Covariates, such as age, sex, body mass index, diabetes, symptom duration, and thenar muscle weakness were adjusted. RESULTS: Out of the 920 hands, 126 and 794 belonged to the diabetic and non-diabetic CTS groups, respectively. The patients were significantly older in the diabetic CTS group (P < 0.001). The rate of thenar weakness in the diabetic CTS group was also significantly higher than that in the non-diabetic CTS group (P = 0.009). The diabetic CTS group had a more severe electrodiagnostic grade (P = 0.001). The prolonged onset latency of the compound motor nerve action potential (CMAP) and median nerve CSA were well associated with the degree of clinical symptoms. Increased median nerve CSA was significantly associated with prolonged CMAP onset latency (ß = 0.64; P = 0.012), prolonged transcarpal latency (ß = 0.95; P = 0.044), and decreased CMAP amplitude (ß = -0.17; P = 0.002) in the non-diabetic CTS group. CONCLUSION: Diabetic CTS had more profound electrophysiological abnormalities. Distal motor latency and median nerve CSA were not only associated with each other, but also with clinical symptoms. Further studies are needed to investigate the pathophysiological mechanisms underlying diabetic CTS.

Extra-Basal Ganglia Brain Structures Are Related to Motor Reserve in Parkinson's Disease.

BACKGROUND: The "motor reserve" is an emerging concept based on the discrepancy between the severity of parkinsonism and dopaminergic degeneration; however, the related brain structures have not yet been elucidated. OBJECTIVE: We investigated brain structures relevant to the motor reserve in Parkinson's disease (PD) in this study. METHODS: Patients with drug-naïve, early PD were enrolled, who then underwent dopamine transporter (DAT) scan and diffusion tensor imaging (DTI). The severity of motor symptoms was evaluated with the Unified Parkinson's Disease Rating Scale score of bradykinesia and rigidity on the more affected side and dopaminergic degeneration of DAT uptake of the more affected putamen. Individual motor reserve estimate (MRE) was evaluated based on the discrepancy between the severity of motor symptoms and dopaminergic degeneration. Using DTI and the Brainnetome atlas, brain structures correlated with MRE were identified. RESULTS: We enrolled 193 patients with drug-naïve PD (mean disease duration of 15.6±13.2 months), and the MRE successfully predicted the increase of levodopa equivalent dose after two years. In the DTI analysis, fractional anisotropy values of medial, inferior frontal, and temporal lobes, limbic structures, nucleus accumbens, and thalamus were positively correlated with the MRE, while no brain structures were correlated with mean diffusivity. Additionally, degree centrality derived from the structural connectivity of the frontal and temporal lobes and limbic structures was positively correlated with the MRE. CONCLUSION: Our results show empirical evidence for MR in PD and brain structures relevant to MR, particularly, the extra-basal ganglia system including the limbic and frontal structures.

Detection of C8/T1 radiculopathy by measuring the root motor conduction time.

BACKGROUND: Root motor conduction time (RMCT) can noninvasively evaluate the status of the proximal root segment. However, its clinical application remains limited, and wider studies regarding its use are scarce. We aimed to investigate the association between C8/T1 level radiculopathy and RMCT. METHODS: This was a retrospective cross-sectional study. Subjects were extracted from a general hospital's spine clinic database. A total of 48 C8/T1 root lesions from 37 patients were included, and 48 C8/T1 root levels from control subjects were matched for age, sex, and height. RMCT was measured in the abductor pollicis brevis muscle and the assessment of any delays owing to C8/T1 radiculopathy. RESULTS: The RMCT of the C8/T1 radiculopathy group was 1.7 ± 0.6 ms, which was significantly longer than that in the control group (1.2 ± 0.8 ms; p = 0.001). The delayed RMCT was independently associated with radiculopathy (adjusted odds ratio, 1.15; 95% confidence interval, 1.06-1.27; p = 0.011) after adjusting for the peripheral motor conduction time, amplitude of median compound motor nerve action potential, and shortest F-wave latency. The area under the Receiver Operating Characteristic curve for diagnosing C8/T1 radiculopathy using RMCT was 0.72 (0.61-0.82). The RMCT was significantly correlated with symptom duration (coefficient = 0.58; p < 0.001) but was not associated with the degree of arm pain. CONCLUSION: Our findings illustrate the clinical applicability of the RMCT by demonstrating its utility in diagnosing radiculopathy at certain spinal levels.

Deep multiview learning to identify imaging-driven subtypes in mild cognitive impairment.

BACKGROUND: In Alzheimer's Diseases (AD) research, multimodal imaging analysis can unveil complementary information from multiple imaging modalities and further our understanding of the disease. One application is to discover disease subtypes using unsupervised clustering. However, existing clustering methods are often applied to input features directly, and could suffer from the curse of dimensionality with high-dimensional multimodal data. The purpose of our study is to identify multimodal imaging-driven subtypes in Mild Cognitive Impairment (MCI) participants using a multiview learning framework based on Deep Generalized Canonical Correlation Analysis (DGCCA), to learn shared latent representation with low dimensions from 3 neuroimaging modalities. RESULTS: DGCCA applies non-linear transformation to input views using neural networks and is able to learn correlated embeddings with low dimensions that capture more variance than its linear counterpart, generalized CCA (GCCA). We designed experiments to compare DGCCA embeddings with single modality features and GCCA embeddings by generating 2 subtypes from each feature set using unsupervised clustering. In our validation studies, we found that amyloid PET imaging has the most discriminative features compared with structural MRI and FDG PET which DGCCA learns from but not GCCA. DGCCA subtypes show differential measures in 5 cognitive assessments, 6 brain volume measures, and conversion to AD patterns. In addition, DGCCA MCI subtypes confirmed AD genetic markers with strong signals that existing late MCI group did not identify. CONCLUSION: Overall, DGCCA is able to learn effective low dimensional embeddings from multimodal data by learning non-linear projections. MCI subtypes generated from DGCCA embeddings are different from existing early and late MCI groups and show most similarity with those identified by amyloid PET features. In our validation studies, DGCCA subtypes show distinct patterns in cognitive measures, brain volumes, and are able to identify AD genetic markers. These findings indicate the promise of the imaging-driven subtypes and their power in revealing disease structures beyond early and late stage MCI.

Classification of expert-level therapeutic decisions for degenerative cervical myelopathy using ensemble machine learning algorithms.

Background: Therapeutic decisions for degenerative cervical myelopathy (DCM) are complex and should consider various factors. We aimed to develop machine learning (ML) models for classifying expert-level therapeutic decisions in patients with DCM. Methods: This retrospective cross-sectional study included patients diagnosed with DCM, and the diagnosis of DCM was confirmed clinically and radiologically. The target outcomes were defined as conservative treatment, anterior surgical approaches (ASA), and posterior surgical approaches (PSA). We performed the following classifications using ML algorithms: multiclass, one-versus-rest, and one-versus-one. Two ensemble ML algorithms were used: random forest (RF) and extreme gradient boosting (XGB). The area under the receiver operating characteristic curve (AUC-ROC) was the primary metric. We also identified the variable importance for each classification. Results: In total, 304 patients were included (109 conservative, 66 ASA, 125 PSA, and 4 combined surgeries). For multiclass classification, the AUC-ROC of RF and XGB models were 0.91 and 0.92, respectively. In addition, ML models showed AUC-ROC values of >0.9 for all types of binary classifications. Variable importance analysis revealed that the modified Japanese Orthopaedic Association score and central motor conduction time were the two most important variables for distinguishing between conservative and surgical treatments. When classifying ASA and PSA, the number of involved levels, age, and body mass index were important contributing factors. Conclusion: ML-based classification of DCM therapeutic options is valid and feasible. This study can be a basis for establishing generalizable ML-based surgical decision models for DCM. Further studies are needed with a large multicenter database.

Mining High-Level Imaging Genetic Associations via Clustering AD Candidate Variants with Similar Brain Association Patterns.

Brain imaging genetics examines associations between imaging quantitative traits (QTs) and genetic factors such as single nucleotide polymorphisms (SNPs) to provide important insights into the pathogenesis of Alzheimer's disease (AD). The individual level SNP-QT signals are high dimensional and typically have small effect sizes, making them hard to be detected and replicated. To overcome this limitation, this work proposes a new approach that identifies high-level imaging genetic associations through applying multigraph clustering to the SNP-QT association maps. Given an SNP set and a brain QT set, the association between each SNP and each QT is evaluated using a linear regression model. Based on the resulting SNP-QT association map, five SNP-SNP similarity networks (or graphs) are created using five different scoring functions, respectively. Multigraph clustering is applied to these networks to identify SNP clusters with similar association patterns with all the brain QTs. After that, functional annotation is performed for each identified SNP cluster and its corresponding brain association pattern. We applied this pipeline to an AD imaging genetic study, which yielded promising results. For example, in an association study between 54 AD SNPs and 116 amyloid QTs, we identified two SNP clusters with one responsible for amyloid beta clearances and the other regulating amyloid beta formation. These high-level findings have the potential to provide valuable insights into relevant genetic pathways and brain circuits, which can help form new hypotheses for more detailed imaging and genetics studies in independent cohorts.

Identifying genetic markers enriched by brain imaging endophenotypes in Alzheimer's disease.

BACKGROUND: Alzheimer's disease (AD) is a complex neurodegenerative disorder and the most common type of dementia. AD is characterized by a decline of cognitive function and brain atrophy, and is highly heritable with estimated heritability ranging from 60 to 80[Formula: see text]. The most straightforward and widely used strategy to identify AD genetic basis is to perform genome-wide association study (GWAS) of the case-control diagnostic status. These GWAS studies have identified over 50 AD related susceptibility loci. Recently, imaging genetics has emerged as a new field where brain imaging measures are studied as quantitative traits to detect genetic factors. Given that many imaging genetics studies did not involve the diagnostic outcome in the analysis, the identified imaging or genetic markers may not be related or specific to the disease outcome. RESULTS: We propose a novel method to identify disease-related genetic variants enriched by imaging endophenotypes, which are the imaging traits associated with both genetic factors and disease status. Our analysis consists of three steps: (1) map the effects of a genetic variant (e.g., single nucleotide polymorphism or SNP) onto imaging traits across the brain using a linear regression model, (2) map the effects of a diagnosis phenotype onto imaging traits across the brain using a linear regression model, and (3) detect SNP-diagnosis association via correlating the SNP effects with the diagnostic effects on the brain-wide imaging traits. We demonstrate the promise of our approach by applying it to the Alzheimer's Disease Neuroimaging Initiative database. Among 54 AD related susceptibility loci reported in prior large-scale AD GWAS, our approach identifies 41 of those from a much smaller study cohort while the standard association approaches identify only two of those. Clearly, the proposed imaging endophenotype enriched approach can reveal promising AD genetic variants undetectable using the traditional method. CONCLUSION: We have proposed a novel method to identify AD genetic variants enriched by brain-wide imaging endophenotypes. This approach can not only boost detection power, but also reveal interesting biological pathways from genetic determinants to intermediate brain traits and to phenotypic AD outcomes.

Pallidal Structural Changes Related to Levodopa-induced Dyskinesia in Parkinson's Disease.

Background: Despite the clinical impact of levodopa-induced dyskinesia (LID) in Parkinson's disease (PD), the mechanism, especially the role of basal ganglia (BG), is not fully elucidated yet. We investigated the BG structural changes related to LID in PD using a surface-based shape analysis technique. Methods: We recruited patients with PD who developed LID within 3 years (LID group, 28 patients) and who did not develop it after 7 years (non-LID group, 35 patients) from levodopa treatment for the extreme case-control study. BG structure volumes were measured using volumetry analysis and the surface-based morphometry feature (i.e., Jacobian) from the subcortical surface vertices. We compared the volume and Jacobian of meshes in the regions between the two groups. We also performed a correlation analysis between local atrophy and the severity of LID. Additionally, we evaluated structural connectivity profiles from globus pallidus interna and externa (GPi and GPe) to other brain structures based on the group comparison. Results: The demographic and clinical data showed no significant difference except for disease duration, treatment duration, parkinsonism severity, and levodopa equivalent dose. The LID group had more local atrophies of vertices in the right GPi than the non-LID group, despite no difference in volumes. Furthermore, the LID group demonstrated significantly reduced structural connectivity between left GPi and thalamus. Conclusion: This is the first demonstration of distinct shape alterations of basal ganglia structures, especially GPi, related to LID in PD. Considering both direct and indirect BG pathways share the connection between GPi and thalamus, the BG pathway plays a crucial role in the development of LID.

Identifying Alzheimer's genes via brain transcriptome mapping.

BACKGROUND: Alzheimer's disease (AD) is one of the most common neurodegenerative disorders characterized by progressive decline in cognitive function. Targeted genetic analyses, genome-wide association studies, and imaging genetic analyses have been performed to detect AD risk and protective genes and have successfully identified dozens of AD susceptibility loci. Recently, brain imaging transcriptomics analyses have also been conducted to investigate the relationship between neuroimaging traits and gene expression measures to identify interesting gene-traits associations. These imaging transcriptomic studies typically do not involve the disease outcome in the analysis, and thus the identified brain or transcriptomic markers may not be related or specific to the disease outcome. RESULTS: We propose an innovative two-stage approach to identify genes whose expression profiles are related to diagnosis phenotype via brain transcriptome mapping. Specifically, we first map the effects of a diagnosis phenotype onto imaging traits across the brain using a linear regression model. Then, the gene-diagnosis association is assessed by spatially correlating the brain transcriptome map with the diagnostic effect map on the brain-wide imaging traits. To demonstrate the promise of our approach, we apply it to the integrative analysis of the brain transcriptome data from the Allen Human Brain Atlas (AHBA) and the amyloid imaging data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort. Our method identifies 12 genes whose brain-wide transcriptome patterns are highly correlated with six different diagnostic effect maps on the amyloid imaging traits. These 12 genes include four confirmatory findings (i.e., AD genes reported in DisGeNET) and eight novel genes that have not be associated with AD in DisGeNET. CONCLUSION: We have proposed a novel disease-related brain transcriptomic mapping method to identify genes whose expression profiles spatially correlated with regional diagnostic effects on a studied brain trait. Our empirical study on the AHBA and ADNI data shows the promise of the approach, and the resulting AD gene discoveries provide valuable information for better understanding biological pathways from transcriptomic signatures to intermediate brain traits and to phenotypic disease outcomes.

Behavioral and Disease-Related Characteristics of Patients with Acute Stroke during the Coronavirus Disease Pandemic.

This study aimed to evaluate the behavioral and disease-related characteristics of patients with acute stroke during the Coronavirus disease (COVID-19) pandemic. This retrospective study was conducted using the Korean Stroke Registry database from a single cerebrovascular specialty hospital. We categorized the COVID-19 pandemic (February 2020 to June 2021) into three waves according to the number of COVID-19 cases recorded and the subjective fear index of the general population and matched them with the corresponding pre-COVID-19 (January 2019 to January 2020) periods. The total number of acute stroke hospitalizations during the pre-COVID-19 and COVID-19 periods was 402 and 379, respectively. The number of acute stroke hospitalizations recorded during the regional outbreak of COVID-19 was higher than that recorded during the corresponding pre-COVID-19 period (97 vs. 80). Length of hospital stay was significantly longer during the COVID-19 pandemic than during the pre-COVID-19 period (11.1 and 8.5 days, respectively; p = 0.003). There were no significant differences in the time from onset to hospital arrival, rate of acute intravenous/intra-arterial (IV/IA) treatments, and door-to-IV/IA times between the pre-COVID-19 and COVID-19 periods. This study suggests that specialty hospitals can effectively maintain the quality of healthcare through the management of acute time-dependent diseases, even during pandemics.

Multi-task learning based structured sparse canonical correlation analysis for brain imaging genetics.

The advances in technologies for acquiring brain imaging and high-throughput genetic data allow the researcher to access a large amount of multi-modal data. Although the sparse canonical correlation analysis is a powerful bi-multivariate association analysis technique for feature selection, we are still facing major challenges in integrating multi-modal imaging genetic data and yielding biologically meaningful interpretation of imaging genetic findings. In this study, we propose a novel multi-task learning based structured sparse canonical correlation analysis (MTS2CCA) to deliver interpretable results and improve integration in imaging genetics studies. We perform comparative studies with state-of-the-art competing methods on both simulation and real imaging genetic data. On the simulation data, our proposed model has achieved the best performance in terms of canonical correlation coefficients, estimation accuracy, and feature selection accuracy. On the real imaging genetic data, our proposed model has revealed promising features of single-nucleotide polymorphisms and brain regions related to sleep. The identified features can be used to improve clinical score prediction using promising imaging genetic biomarkers. An interesting future direction is to apply our model to additional neurological or psychiatric cohorts such as patients with Alzheimer's or Parkinson's disease to demonstrate the generalizability of our method.

Genomics transformer for diagnosing Parkinson's disease.

Parkinson's disease (PD) is the second most common neurodegenerative disease and presents a complex etiology with genomic and environmental factors and no recognized cures. Genotype data, such as single nucleotide polymorphisms (SNPs), could be used as a prodromal factor for early detection of PD. However, the polygenic nature of PD presents a challenge as the complex relationships between SNPs towards disease development are difficult to model. Traditional assessment methods such as polygenic risk scores and machine learning approaches struggle to capture the complex interactions present in the genotype data, thus limiting their discriminative capabilities in diagnosis. On the other hand, deep learning models are better suited for this task. Nevertheless, they encounter difficulties of their own such as a lack of interpretability. To overcome these limitations, in this work, a novel transformer encoder-based model is introduced to classify PD patients from healthy controls based on their genotype. This method is designed to effectively model complex global feature interactions and enable increased interpretability through the learned attention scores. The proposed framework outperformed traditional machine learning models and multilayer perceptron (MLP) baseline models. Moreover, visualization of the learned SNP-SNP associations provides not only interpretability to the model but also valuable insights into the biochemical pathways underlying PD development, which are corroborated by pathway enrichment analysis. Our results suggest novel SNP interactions to be further studied in wet lab and clinical settings.

Identifying imaging genetic associations via regional morphometricity estimation.

Brain imaging genetics is an emerging research field aiming to reveal the genetic basis of brain traits captured by imaging data. Inspired by heritability analysis, the concept of morphometricity was recently introduced to assess trait association with whole brain morphology. In this study, we extend the concept of morphometricity from its original definition at the whole brain level to a more focal level based on a region of interest (ROI). We propose a novel framework to identify the SNP-ROI association via regional morphometricity estimation of each studied single nucleotide polymorphism (SNP). We perform an empirical study on the structural MRI and genotyping data from a landmark Alzheimer's disease (AD) biobank; and yield promising results. Our findings indicate that the AD-related SNPs have higher overall regional morphometricity estimates than the SNPs not yet related to AD. This observation suggests that the variance of AD SNPs can be explained more by regional morphometric features than non-AD SNPs, supporting the value of imaging traits as targets in studying AD genetics. Also, we identified 11 ROIs, where the AD/non-AD SNPs and significant/insignificant morphometricity estimation of the corresponding SNPs in these ROIs show strong dependency. Supplementary motor area (SMA) and dorsolateral prefrontal cortex (DPC) are enriched by these ROIs. Our results also demonstrate that using all the detailed voxel-level measures within the ROI to incorporate morphometric information outperforms using only a single average ROI measure, and thus provides improved power to detect imaging genetic associations.

Identifying highly heritable brain amyloid phenotypes through mining Alzheimer's imaging and sequencing biobank data.

Brain imaging genetics, an emerging and rapidly growing research field, studies the relationship between genetic variations and brain imaging quantitative traits (QTs) to gain new insights into the phenotypic characteristics and genetic mechanisms of the brain. Heritability is an important measurement to quantify the proportion of the observed variance in an imaging QT that is explained by genetic factors, and can often be used to prioritize brain QTs for subsequent imaging genetic association studies. Most existing studies define regional imaging QTs using predefined brain parcellation schemes such as the automated anatomical labeling (AAL) atlas. However, the power to dissect genetic underpinnings under QTs defined in such an unsupervised fashion could be negatively affected by heterogeneity within the regions in the partition. To bridge this gap, we propose a novel method to define highly heritable brain regions. Based on voxelwise heritability estimates, we extract brain regions containing spatially connected voxels with high heritability. We perform an empirical study on the amyloid imaging and whole genome sequencing data from a landmark Alzheimer's disease biobank; and demonstrate the regions defined by our method have much higher estimated heritabilities than the regions defined by the AAL atlas. Our proposed method refines the imaging endophenotype constructions in light of their genetic dissection, and yields more powerful imaging QTs for subsequent detection of genetic risk factors along with better interpretability.

Application of digital infrared thermography for carpal tunnel syndrome evaluation.

We investigated the thermographic findings of carpal tunnel syndrome (CTS). We enrolled 304 hands with electrodiagnostically identified CTS and 88 control hands. CTS hands were assigned to duration groups (D1, < 3 months; D2, 3‒6 months; D3, 6‒12 months; D4, ≥ 12 months) and severity groups (S1, very mild; S2, mild; S3, moderate; S4, severe). The temperature difference between the median and ulnar nerve territories (ΔM-U territories) decreased as CTS duration and severity increased. Significant differences in ΔM-U territories between the D1 and D3, D1 and D4, D2 and D4, and S1 and S4 groups (P = 0.003, 0.001, 0.001, and < 0.001, respectively) were observed. Thermal anisometry increased as CTS duration and severity increased. Significant differences in thermal anisometry between the D1 and D4 as well as the D2 and D4 groups (P = 0.005 and 0.04, respectively) were noted. Thermal anisometry was higher in the S4 group than in the S1, S2, and S3 groups (P = 0.009, < 0.001, and 0.003, respectively). As CTS progresses, skin temperature tends to decrease and thermal variation tends to increase in the median nerve-innervated area. Thermographic findings reflect the physiological changes of the entrapped median nerve.