The Application of Unsupervised Clustering Methods to Alzheimer's Disease

Identification of clear cell renal cell carcinoma subtypes by integrating radiomics and transcriptomics

Objective

This study aimed to delineate the clear cell renal cell carcinoma (ccRCC) intrinsic subtypes through unsupervised clustering of radiomics and transcriptomics data and to evaluate their associations with clinicopathological features, prognosis, and molecular characteristics.

Methods

Using a retrospective dual-center approach, we gathered transcriptomic and clinical data from ccRCC patients registered in The Cancer Genome Atlas and contrast-enhanced computed tomography images from The Cancer Imaging Archive and local databases. Following the segmentation of images, radiomics feature extraction, and feature preprocessing, we performed unsupervised clustering based on the "CancerSubtypes" package to identify distinct radiotranscriptomic subtypes, which were then correlated with clinical-pathological, prognostic, immune, and molecular characteristics.

Results

Clustering identified three subtypes, C1, C2, and C3, each of which displayed unique clinicopathological, prognostic, immune, and molecular distinctions. Notably, subtypes C1 and C3 were associated with poorer survival outcomes than subtype C2. Pathway analysis highlighted immune pathway activation in C1 and metabolic pathway prominence in C2. Gene mutation analysis identified VHL and PBRM1 as the most commonly mutated genes, with more mutated genes observed in the C3 subtype. Despite similar tumor mutation burdens, microsatellite instability, and RNA interference across subtypes, C1 and C3 demonstrated greater tumor immune dysfunction and rejection. In the validation cohort, the various subtypes showed comparable results in terms of clinicopathological features and prognosis to those observed in the training cohort, thus confirming the efficacy of our algorithm.

Conclusion

Unsupervised clustering based on radiotranscriptomics can identify the intrinsic subtypes of ccRCC, and radiotranscriptomic subtypes can characterize the prognosis and molecular features of tumors, enabling noninvasive tumor risk stratification.

Medical calculators derived synthetic cohorts: a novel method for generating synthetic patient data

This study shows that we can use synthetic cohorts created from medical risk calculators to gain insights into how risk estimations, clinical reasoning, data-driven subgrouping, and the confidence in risk calculator scores are connected. When prediction variables aren't evenly distributed in these synthetic cohorts, they can be used to group similar cases together, revealing new insights about how cohorts behave. We also found that the confidence in predictions made by these calculators can vary depending on patient characteristics. This suggests that it might be beneficial to include a "normalized confidence" score in future versions of these calculators for healthcare professionals. We plan to explore this idea further in our upcoming research.

Predicting buoyant jet characteristics: a machine learning approach

We study positively buoyant miscible jets through high-speed imaging and planar laser-induced fluorescence methods, and we rely on supervised machine learning techniques to predict jet characteristics. These include, in particular, predictions to the laminar length and spread angle, over a wide range of Reynolds and Archimedes numbers. To make these predictions, we use linear regression, support vector regression, random forests, K-nearest neighbour, and artificial neural network algorithms. We evaluate the performance of the aforementioned models using various standard metrics, finding that the random forest algorithm is the best for predicting our jet characteristics. We also discover that this algorithm outperforms a recent empirical correlation, resulting in a significant increase in accuracy, especially for predicting the laminar length.

Identifying clusters of objective functional impairment in patients with degenerative lumbar spinal disease using unsupervised learning

OBJECTIVES

The five-repetition sit-to-stand (5R-STS) test was designed to capture objective functional impairment (OFI), and thus provides an adjunctive dimension in patient assessment. It is conceivable that there are different subsets of patients with OFI and degenerative lumbar disease. We aim to identify clusters of objectively functionally impaired individuals based on 5R-STS and unsupervised machine learning (ML).

METHODS

Data from two prospective cohort studies on patients with surgery for degenerative lumbar disease and 5R-STS times of ≥ 10.5 s-indicating presence of OFI. K-means clustering-an unsupervised ML algorithm-was applied to identify clusters of OFI. Cluster hallmarks were then identified using descriptive and inferential statistical analyses.

RESULTS

We included 173 patients (mean age [standard deviation]: 46.7 [12.7] years, 45% male) and identified three types of OFI. OFI Type 1 (57 pts., 32.9%), Type 2 (81 pts., 46.8%), and Type 3 (35 pts., 20.2%) exhibited mean 5R-STS test times of 14.0 (3.2), 14.5 (3.3), and 27.1 (4.4) seconds, respectively. The grades of OFI according to the validated baseline severity stratification of the 5R-STS increased significantly with each OFI type, as did extreme anxiety and depression symptoms, issues with mobility and daily activities. Types 1 and 2 are characterized by mild to moderate OFI-with female gender, lower body mass index, and less smokers as Type I hallmarks.

CONCLUSIONS

Unsupervised learning techniques identified three distinct clusters of patients with OFI that may represent a more holistic clinical classification of patients with OFI than test-time stratifications alone, by accounting for individual patient characteristics.

A health data led approach for assessing potential health benefits of green and blue spaces: Lessons from an Irish case study

Research producing evidence-based information on the health benefits of green and blue spaces often has within its design, the potential for inherent or implicit bias which can unconsciously orient the outcomes of such studies towards preconceived hypothesis. Many studies are situated in proximity to specific or generic green and blue spaces (hence, constituting a green or blue space led approach), others are conducted due to availability of green and blue space data (hence, applying a green or blue space data led approach), while other studies are shaped by particular interests in the association of particular health conditions with presence of, or engagements with green or blue spaces (hence, adopting a health or health status led approach). In order to tackle this bias and develop a more objective research design for studying associations between human health outcomes and green and blue spaces, this paper discussed the features of a methodological framework suitable for that purpose after an initial, year-long, exploratory Irish study. The innovative approach explored by this study (i.e., the health-data led approach) first identifies sample sites with good and poor health outcomes from available health data (using data clustering techniques) before examining the potential role of the presence of, or engagement with green and blue spaces in creating such health outcomes. By doing so, we argue that some of the bias associated with the other three listed methods can be reduced and even eliminated. Finally, we infer that the principles and paradigm adopted by the health data led approach can be applicable and effective in analyzing other sustainability problems beyond associations between human health outcomes and green and blue spaces (e.g., health, energy, food, income, environment and climate inequality and justice etc.). The possibility of this is also discussed within this paper.

ELMAS: a one-year dataset of hourly electrical load profiles from 424 French industrial and tertiary sectors

The combination of ongoing urban expansion and electrification of uses challenges the power grid. In such a context, information regarding customers' consumption is vital to assess the expected load at strategic nodes over time, and to guide power system planning strategies. Comprehensive household consumption databases are widely available today thanks to the roll-out of smart meters, while the consumption of tertiary premises is seldom shared mainly due to privacy concerns. To fill this gap, the French main distribution system operator, Enedis, commissioned Mines Paris to derive load profiles of industrial and tertiary sectors for its prospective tools. The ELMAS dataset is an open dataset of 18 electricity load profiles derived from hourly consumption time series collected continuously over one year from a total of 55,730 customers. These customers are divided into 424 fields of activity, and three levels of capacity subscription. A clustering approach is employed to gather activities sharing similar temporal patterns, before averaging the associated time series to ensure anonymity.

Improving clinical efficiency in screening for cognitive impairment due to Alzheimer's

INTRODUCTION

To reduce demands on expert time and improve clinical efficiency, we developed a framework to evaluate whether inexpensive, accessible data could accurately classify Alzheimer's disease (AD) clinical diagnosis and predict the likelihood of progression.

METHODS

We stratified relevant data into three tiers: obtainable at primary care (low-cost), mostly available at specialty visits (medium-cost), and research-only (high-cost). We trained several machine learning models, including a hierarchical model, an ensemble model, and a clustering model, to distinguish between diagnoses of cognitively unimpaired, mild cognitive impairment, and dementia due to AD.

RESULTS

All models showed viable classification, but the hierarchical and ensemble models outperformed the conventional model. Classifier "error" was predictive of progression rates, and cluster membership identified subgroups with high and low risk of progression within 1.5 to 3 years.

DISCUSSION

Accessible, inexpensive clinical data can be used to guide AD diagnosis and are predictive of current and future disease states.

HIGHLIGHTS

Classification performance using cost-effective features was accurate and robustHierarchical classification outperformed conventional multinomial classificationClassification labels indicated significant changes in conversion risk at follow-upA clustering-classification method identified subgroups at high risk of decline.

J-score: a robust measure of clustering accuracy

Background

Clustering analysis discovers hidden structures in a data set by partitioning them into disjoint clusters. Robust accuracy measures that evaluate the goodness of clustering results are critical for algorithm development and model diagnosis. Common problems of clustering accuracy measures include overlooking unmatched clusters, biases towards excessive clusters, unstable baselines, and difficulties of interpretation. In this study, we presented a novel accuracy measure, J-score, to address these issues.

Methods

Given a data set with known class labels, J-score quantifies how well the hypothetical clusters produced by clustering analysis recover the true classes. It starts with bidirectional set matching to identify the correspondence between true classes and hypothetical clusters based on Jaccard index. It then computes two weighted sums of Jaccard indices measuring the reconciliation from classes to clusters and vice versa. The final J-score is the harmonic mean of the two weighted sums.

Results

Through simulation studies and analyses of real data sets, we evaluated the performance of J-score and compared with existing measures. Our results show that J-score is effective in distinguishing partition structures that differ only by unmatched clusters, rewarding correct inference of class numbers, addressing biases towards excessive clusters, and having a relatively stable baseline. The simplicity of its calculation makes the interpretation straightforward. It is a valuable tool complementary to other accuracy measures. We released an R/jScore package implementing the algorithm.

Artificial Intelligence Can Define and Predict the "Optimal Observed Outcome" After Anterior Shoulder Instability Surgery: An Analysis of 200 Patients With 11-Year Mean Follow-Up

Purpose

The purpose of this study was to use unsupervised machine learning clustering to define the "optimal observed outcome" after surgery for anterior shoulder instability (ASI) and to identify predictors for achieving it.

Methods

Medical records, images, and operative reports were reviewed for patients <40 years old undergoing surgery for ASI. Four unsupervised machine learning clustering algorithms partitioned subjects into "optimal observed outcome" or "suboptimal outcome" based on combinations of actually observed outcomes. Demographic, clinical, and treatment variables were compared between groups using descriptive statistics and Kaplan-Meier survival curves. Variables were assessed for prognostic value through multivariate stepwise logistic regression.

Results

Two hundred patients with a mean follow-up of 11 years were included. Of these, 146 (64%) obtained the "optimal observed outcome," characterized by decreased: postoperative pain (23% vs 52%; P < 0.001), recurrent instability (12% vs 41%; P < 0.001), revision surgery (10% vs 24%; P = 0.015), osteoarthritis (OA) (5% vs 19%; P = 0.005), and restricted motion (161° vs 168°; P = 0.001). Forty-one percent of patients had a "perfect outcome," defined as ideal performance across all outcomes. Time from initial instability to presentation (odds ratio [OR] = 0.96; 95% confidence interval [CI], 0.92-0.98; P = 0.006) and habitual/voluntary instability (OR = 0.17; 95% CI, 0.04-0.77; P = 0.020) were negative predictors of achieving the "optimal observed outcome." A predilection toward subluxations rather than dislocations before surgery (OR = 1.30; 95% CI, 1.02-1.65; P = 0.030) was a positive predictor. Type of surgery performed was not a significant predictor.

Conclusion

After surgery for ASI, 64% of patients achieved the "optimal observed outcome" defined as minimal postoperative pain, no recurrent instability or OA, low revision surgery rates, and increased range of motion, of whom only 41% achieved a "perfect outcome." Positive predictors were shorter time to presentation and predilection toward preoperative subluxations over dislocations.

Level of Evidence

Retrospective cohort, level IV.

Voice acoustics allow classifying autism spectrum disorder with high accuracy

Early identification of children on the autism spectrum is crucial for early intervention with long-term positive effects on symptoms and skills. The need for improved objective autism detection tools is emphasized by the poor diagnostic power in current tools. Here, we aim to evaluate the classification performance of acoustic features of the voice in children with autism spectrum disorder (ASD) with respect to a heterogeneous control group (composed of neurotypical children, children with Developmental Language Disorder [DLD] and children with sensorineural hearing loss with Cochlear Implant [CI]). This retrospective diagnostic study was conducted at the Child Psychiatry Unit of Tours University Hospital (France). A total of 108 children, including 38 diagnosed with ASD (8.5 ± 0.25 years), 24 typically developing (TD; 8.2 ± 0.32 years) and 46 children with atypical development (DLD and CI; 7.9 ± 0.36 years) were enrolled in our studies. The acoustic properties of speech samples produced by children in the context of a nonword repetition task were measured. We used a Monte Carlo cross-validation with an ROC (Receiving Operator Characteristic) supervised k-Means clustering algorithm to develop a classification model that can differentially classify a child with an unknown disorder. We showed that voice acoustics classified autism diagnosis with an overall accuracy of 91% [CI95%, 90.40%-91.65%] against TD children, and of 85% [CI95%, 84.5%-86.6%] against an heterogenous group of non-autistic children. Accuracy reported here with multivariate analysis combined with Monte Carlo cross-validation is higher than in previous studies. Our findings demonstrate that easy-to-measure voice acoustic parameters could be used as a diagnostic aid tool, specific to ASD.

Multi-omic integration via similarity network fusion to detect molecular subtypes of ageing

Molecular subtyping of brain tissue provides insights into the heterogeneity of common neurodegenerative conditions, such as Alzheimer's disease. However, existing subtyping studies have mostly focused on single data modalities and only those individuals with severe cognitive impairment. To address these gaps, we applied similarity network fusion, a method capable of integrating multiple high-dimensional multi-omic data modalities simultaneously, to an elderly sample spanning the full spectrum of cognitive ageing trajectories. We analyzed human frontal cortex brain samples characterized by five omic modalities: bulk RNA sequencing (18 629 genes), DNA methylation (53 932 CpG sites), histone acetylation (26 384 peaks), proteomics (7737 proteins) and metabolomics (654 metabolites). Similarity network fusion followed by spectral clustering was used for subtype detection, and subtype numbers were determined by Eigen-gap and rotation cost statistics. Normalized mutual information determined the relative contribution of each modality to the fused network. Subtypes were characterized by associations with 13 age-related neuropathologies and cognitive decline. Fusion of all five data modalities (n = 111) yielded two subtypes (n S1 = 53, n S2 = 58), which were nominally associated with diffuse amyloid plaques; however, this effect was not significant after correction for multiple testing. Histone acetylation (normalized mutual information = 0.38), DNA methylation (normalized mutual information = 0.18) and RNA abundance (normalized mutual information = 0.15) contributed most strongly to this network. Secondary analysis integrating only these three modalities in a larger subsample (n = 513) indicated support for both three- and five-subtype solutions, which had significant overlap, but showed varying degrees of internal stability and external validity. One subtype showed marked cognitive decline, which remained significant even after correcting for tests across both three- and five-subtype solutions (p Bonf = 5.9 × 10-3). Comparison to single-modality subtypes demonstrated that the three-modal subtypes were able to uniquely capture cognitive variability. Comprehensive sensitivity analyses explored influences of sample size and cluster number parameters. We identified highly integrative molecular subtypes of ageing derived from multiple high dimensional, multi-omic data modalities simultaneously. Fusing RNA abundance, DNA methylation, and histone acetylation measures generated subtypes that were associated with cognitive decline. This work highlights the potential value and challenges of multi-omic integration in unsupervised subtyping of post-mortem brain.

K-medoids clustering of hospital admission characteristics to classify severity of influenza virus infection

Background

Patients are admitted to the hospital for respiratory illness at different stages of their disease course. It is important to appropriately analyse this heterogeneity in surveillance data to accurately measure disease severity among those hospitalized. The purpose of this study was to determine if unique baseline clusters of influenza patients exist and to examine the association between cluster membership and in-hospital outcomes.

Methods

Patients hospitalized with influenza at two hospitals in Southeast Michigan during the 2017/2018 (n = 242) and 2018/2019 (n = 115) influenza seasons were included. Physiologic and laboratory variables were collected for the first 24 h of the hospital stay. K-medoids clustering was used to determine groups of individuals based on these values. Multivariable linear regression or Firth's logistic regression were used to examine the association between cluster membership and clinical outcomes.

Results

Three clusters were selected for 2017/2018, mainly differentiated by blood glucose level. After adjustment, those in C₁₇1 had 5.6 times the odds of mechanical ventilator use than those in C₁₇2 (95% CI: 1.49, 21.1) and a significantly longer mean hospital length of stay than those in both C₁₇2 (mean 1.5 days longer, 95% CI: 0.2, 2.7) and C₁₇3 (mean 1.4 days longer, 95% CI: 0.3, 2.5). Similar results were seen between the two clusters selected for 2018/2019.

Conclusion

In this study of hospitalized influenza patients, we show that distinct clusters with higher disease acuity can be identified and could be targeted for evaluations of vaccine and influenza antiviral effectiveness against disease attenuation. The association of higher disease acuity with glucose level merits evaluation.

Associations between self-reported sleep patterns and health, cognition and amyloid measures: results from the Wisconsin Registry for Alzheimer's Prevention

Previous studies suggest associations between self-reported sleep problems and poorer health, cognition, Alzheimer's disease pathology and dementia-related outcomes. It is important to develop a deeper understanding of the relationship between these complications and sleep disturbance, a modifiable risk factor, in late midlife, a time when Alzheimer's disease pathology may be accruing. The objectives of this study included application of unsupervised machine learning procedures to identify distinct subgroups of persons with problematic sleep and the association of these subgroups with concurrent measures of mental and physical health, cognition and PET-identified amyloid. Dementia-free participants from the Wisconsin Registry for Alzheimer's Prevention (n = 619) completed sleep questionnaires including the Insomnia Severity Index, Epworth Sleepiness Scale and Medical Outcomes Study Sleep Scale. K-means clustering analysis identified discrete sleep problem groups who were then compared across concurrent health outcomes (e.g. depression, self-rated health and insulin resistance), cognitive composite indices including episodic memory and executive function and, in a subset, Pittsburgh Compound B PET imaging to assess amyloid burden. Significant omnibus tests (P < 0.05) were followed with pairwise comparisons. Mean (SD) sample baseline sleep assessment age was 62.6 (6.7). Cluster analysis identified three groups: healthy sleepers [n = 262 (42.3%)], intermediate sleepers [n = 229 (37.0%)] and poor sleepers [n = 128 (20.7%)]. All omnibus tests comparing demographics and health measures across sleep groups were significant except for age, sex and apolipoprotein E e4 carriers; the poor sleepers group was worse than one or both of the other groups on all other measures, including measures of depression, self-reported health and memory complaints. The poor sleepers group had higher average body mass index, waist-hip ratio and homeostatic model assessment of insulin resistance. After adjusting for covariates, the poor sleepers group also performed worse on all concurrent cognitive composites except working memory. There were no differences between sleep groups on PET-based measures of amyloid. Sensitivity analyses indicated that while different clustering approaches resulted in different group assignments for some (predominantly the intermediate group), between-group patterns in outcomes were consistent. In conclusion, distinct sleep characteristics groups were identified with a sizable minority (20.7%) exhibiting poor sleep characteristics, and this group also exhibited the poorest concurrent mental and physical health and cognition, indicating substantial multi-morbidity; sleep group was not associated with amyloid PET estimates. Precision-based management of sleep and related factors may provide an opportunity for early intervention that could serve to delay or prevent clinical impairment.

Design and Conceptual Proposal of an Intelligent Clinical Decision Support System for the Diagnosis of Suspicious Obstructive Sleep Apnea Patients from Health Profile

Obstructive Sleep Apnea (OSA) is a chronic sleep-related pathology characterized by recurrent episodes of total or partial obstruction of the upper airways during sleep. It entails a high impact on the health and quality of life of patients, affecting more than one thousand million people worldwide, which has resulted in an important public health concern in recent years. The usual diagnosis involves performing a sleep test, cardiorespiratory polygraphy, or polysomnography, which allows characterizing the pathology and assessing its severity. However, this procedure cannot be used on a massive scale in general screening studies of the population because of its execution and implementation costs; therefore, causing an increase in waiting lists which would negatively affect the health of the affected patients. Additionally, the symptoms shown by these patients are often unspecific, as well as appealing to the general population (excessive somnolence, snoring, etc.), causing many potential cases to be referred for a sleep study when in reality are not suffering from OSA. This paper proposes a novel intelligent clinical decision support system to be applied to the diagnosis of OSA that can be used in early outpatient stages, quickly, easily, and safely, when a suspicious OSA patient attends the consultation. Starting from information related to the patient's health profile (anthropometric data, habits, comorbidities, or medications taken), the system is capable of determining different alert levels of suffering from sleep apnea associated with different apnea-hypopnea index (AHI) levels to be studied. To that end, a series of automatic learning algorithms are deployed that, working concurrently, together with a corrective approach based on the use of an Adaptive Neuro-Based Fuzzy Inference System (ANFIS) and a specific heuristic algorithm, allow the calculation of a series of labels associated with the different levels of AHI previously indicated. For the initial software implementation, a data set with 4600 patients from the Álvaro Cunqueiro Hospital in Vigo was used. The results obtained after performing the proof tests determined ROC curves with AUC values in the range 0.8-0.9, and Matthews correlation coefficient values close to 0.6, with high success rates. This points to its potential use as a support tool for the diagnostic process, not only from the point of view of improving the quality of the services provided, but also from the best use of hospital resources and the consequent savings in terms of costs and time.

Membranoproliferative glomerulonephritis: no longer the same disease and may need very different treatment

Membranoproliferative glomerulonephritis (MPGN) is a pattern of glomerular injury that may be primary or secondary to infections, autoimmune diseases and haematological disorders. Primary C3G and IC-MPGN are rare and the prognosis is unfavourable. Based on immunofluorescence findings, MPGN has been classified into complement-mediated C3 glomerulopathy (C3G) and immune complex-mediated MPGN (IC-MPGN). However, this classification leaves a number of issues unresolved. The finding of genetic and acquired complement abnormalities in both C3G and IC-MPGN indicates that they represent a heterogeneous spectrum rather than distinct diseases. An unsupervised hierarchical clustering in a cohort of patients with primary C3G and IC-MPGN identified four distinct pathogenetic patterns, characterized by specific histologic and clinical features, and genetic and acquired complement abnormalities. These results provide the groundwork for a more accurate diagnosis and the development of targeted therapies. The drugs that are currently used, such as corticosteroids and immunosuppressants, are frequently ineffective in primary C3G and IC-MPGN. Eculizumab, an anti-C5 monoclonal antibody, has been used occasionally in single cases or small series. However, only a few patients have achieved remission. This heterogeneous response could be related to the extent of terminal complement activation, which may vary substantially from patient to patient. Several drugs that target the complement system at different levels are under investigation for C3G and IC-MPGN. However, clinical trials to test new therapeutics will be challenging and heavily influenced by the heterogeneity of these diseases. This creates the need to characterize each patient to match the specific complement abnormality with the type of intervention.

Clustering of prostate cancer healthcare pathways in the French National Healthcare database

BACKGROUND

Healthcare pathways of patients with prostate cancer are heterogeneous and complex to apprehend using traditional descriptive statistics. Clustering and visualization methods can enhance their characterization.

METHODS

Patients with prostate cancer in 2014 were identified in the French National Healthcare database (Système National des Données de Santé-SNDS) and their data were extracted with up to 5 years of history and 4 years of follow-up. Fifty-one-specific encounters constitutive of prostate cancer management were synthesized into four macro-variables using a clustering approach. Their values over patient follow-ups constituted healthcare pathways. Optimal matching was applied to calculate distances between pathways. Partitioning around medoids was then used to define consistent groups across four exclusive cohorts of incident prostate cancer patients: Hormone-sensitive (HSPC), metastatic hormone-sensitive (mHSPC), castration-resistant (CRPC), and metastatic castration-resistant (mCRPC). Index plots were used to represent pathways clusters.

RESULTS

The repartition of macro-variables values-surveillance, local treatment, androgenic deprivation, and advanced treatment-appeared to be consistent with prostate cancer status. Two to five clusters of healthcare pathways were observed in each of the different cohorts, corresponding for most of them to relevant clinical patterns, although some heterogeneity remained. For instance, clustering allowed to distinguish patients undergoing active surveillance, or treated according to cancer progression risk in HSPC, and patients receiving treatment for potentially curative or palliative purposes in mHSPC and mCRPC.

CONCLUSION

Visualization methods combined with a clustering approach enabled the identification of clinically relevant patterns of prostate cancer management. Characterization of these care pathways is an essential element for the comprehension and the robust assessment of healthcare technology effectiveness.

Exploring phenotypes of deep vein thrombosis in relation to clinical outcomes beyond recurrence

BACKGROUND

Deep vein thrombosis (DVT) is a multifactorial disease with several outcomes, but current classifications solely stratify it based on recurrence risk.

OBJECTIVES

We aimed to identify DVT phenotypes and assess their relation to recurrent venous thromboembolism (VTE), postthrombotic syndrome, arterial events, and cancer.

PATIENTS/METHODS

Hierarchical clustering was performed on a DVT cohort with a follow-up of up to 5 years using 23 baseline characteristics. Phenotypes were summarized by discriminative characteristics. Hazard ratios (HRs) were calculated using Cox regression; the recurrence risk was adjusted for the anticoagulant therapy duration. The study was carried out in accordance with the Declaration of Helsinki and approved by the medical ethics committee.

RESULTS

In total, 825 patients were clustered into 4 phenotypes: 1. women using estrogen therapy (n = 112); 2. patients with a cardiovascular risk profile (n = 268); 3. patients with previous VTE (n = 128); and 4. patients without discriminant characteristics (n = 317). Overall, the risks of recurrence, postthrombotic syndrome, arterial events, and cancer were low in phenotype 1 (reference), intermediate in phenotype 4 (HR: 4.6, 1.2, 2.2, 1.8), and high in phenotypes 2 (HR: 6.1, 1.6, 4.5, 2.9) and 3 (HR: 5.7, 2.5, 2.3, 3.7).

CONCLUSIONS

This study identified 4 distinct phenotypes among patients with DVT that are not only associated with the increasing recurrence risk but also with outcomes beyond recurrence. Our results thereby highlight the limitations of current risk stratifications that stratify based on the predictors of the recurrence risk only. Overall, risks were lowest in women using estrogen therapy and highest in patients with a cardiovascular risk profile. These findings might inform a more personalized approach to clinical management.

A Framework for Automatic Clustering of EHR Messages Using a Spatial Clustering Approach

Although Health Level Seven (HL 7) message standards (v2, v3, Clinical Document Architecture (CDA)) have been commonly adopted, there are still issues associated with them, especially the semantic interoperability issues and lack of support for smart devices (e.g., smartphones, fitness trackers, and smartwatches), etc. In addition, healthcare organizations in many countries are still using proprietary electronic health record (EHR) message formats, making it challenging to convert to other data formats-particularly the latest HL7 Fast Health Interoperability Resources (FHIR) data standard. The FHIR is based on modern web technologies such as HTTP, XML, and JSON and would be capable of overcoming the shortcomings of the previous standards and supporting modern smart devices. Therefore, the FHIR standard could help the healthcare industry to avail the latest technologies benefits and improve data interoperability. The data representation and mapping from the legacy data standards (i.e., HL7 v2 and EHR) to the FHIR is necessary for the healthcare sector. However, direct data mapping or conversion from the traditional data standards to the FHIR data standard is challenging because of the nature and formats of the data. Therefore, in this article, we propose a framework that aims to convert proprietary EHR messages into the HL7 v2 format and apply an unsupervised clustering approach using the DBSCAN (density-based spatial clustering of applications with noise) algorithm to automatically group a variety of these HL7 v2 messages regardless of their semantic origins. The proposed framework's implementation lays the groundwork to provide a generic mapping model with multi-point and multi-format data conversion input into the FHIR. Our experimental results show the proposed framework's ability to automatically cluster various HL7 v2 message formats and provide analytic insight behind them.

Clustering models for hospitals in Jakarta using fuzzy c-means and k-means

After facing the COVID-19 pandemic, national and local governments in Indonesia realized a gap in the distribution of health care and human health practitioners. This research proposes two unsupervised learning methods, K-Means and Fuzzy C-Means (FCM), for clustering a list of hospital data in Jakarta, Indonesia, which contains information about the number of its human health resources. The datasets used in this study were obtained from the website the Ministry of the Health Republic of Indonesia provided through the content scraping method. The result shows that implementing K-Means and FCM clustering results in the same number of clusters. Nevertheless, both results have different areas and proportions that can be observed by three distance metrics, such as Hamming, Euclidean, and Manhattan distance. By using the clustering result using the K-Means algorithm, the hospital list was separated into three clusters with a proportion of 84.82%, 14.66%, and 0.52% for clusters 0, 1, and 2, respectively. Meanwhile, using the FCM algorithm, the hospital list was separated into three clusters with a proportion of 17.80%, 73.82%, and 8.38% for clusters 0, 1, and 2, respectively. To the best of our knowledge, this is the first discussion of clustering healthcare facilities in Indonesia, especially hospitals, based on their health professionals.

Towards digital diagnosis of malaria: How far have we reached?

The need for precise and early diagnosis of malaria and its distinction from other febrile illnesses is no doubt a prerequisite, primarily when standard rapid diagnostic tests (RDTs) cannot be totally relied upon. At the time of disease outbreaks, the pressure on hospital staff remains high and the chances of human error increase. Therefore, in the era of digitalisation of medicine as well as diagnostic approaches, various technologies such as artificial intelligence (AI) and machine learning (ML) should be deployed to further aid the diagnosis, especially in endemic and epidemic situations. Computational techniques are now more at the forefront than ever, and the interest in developing such efficient technologies is continuously increasing. A comprehensive understanding of these digital technologies is needed to maintain the scientific rigour in these attempts. This would enhance the implementation of these novel technologies for malaria diagnosis. This review highlights the progression, strengths, and limitations of various computing techniques so far employed to diagnose malaria.

Kidney diseases

Dysregulation and accelerated activation of the alternative pathway (AP) of complement is known to cause or accentuate several pathologic conditions in which kidney injury leads to the appearance of hematuria and proteinuria and ultimately to the development of chronic renal failure. Multiple genetic and acquired defects involving plasma- and membrane-associated proteins are probably necessary to impair the protection of host tissues and to confer a significant predisposition to AP-mediated kidney diseases. This review aims to explore how our current understanding will make it possible to identify the mechanisms that underlie AP-mediated kidney diseases and to discuss the available clinical evidence that supports complement-directed therapies. Although the value of limiting uncontrolled complement activation has long been recognized, incorporating complement-targeted treatments into clinical use has proved challenging. Availability of anti-complement therapy has dramatically transformed the outcome of atypical hemolytic uremic syndrome, one of the most severe kidney diseases. Innovative drugs that directly counteract AP dysregulation have also opened new perspectives for the management of other kidney diseases in which complement activation is involved. However, gained experience indicates that the choice of drug should be tailored to each patient's characteristics, including clinical, histologic, genetic, and biochemical parameters. Successfully treating patients requires further research in the field and close collaboration between clinicians and researchers who have special expertise in the complement system.

Screen media and non-screen media habits among preschool children in Singapore, South Korea, Japan, and Finland: Insights from an unsupervised clustering approach

The main purpose of the research was to describe the daily screen media habits and non-screen media habits like indoor and outdoor play, and sleep of preschool children aged 2 to 6 years from Singapore, South Korea, Japan, and Finland using a content-validated online questionnaire (SMALLQ®) and unsupervised cluster analysis. Unsupervised cluster analysis on 5809 parent-reported weekday and weekend screen and non-screen media habits of preschool children from the four countries resulted in seven emergent clusters. Cluster 2 (n = 1288) or the Early-screen media, screen media-lite and moderate-to-vigorous physical activity-lite family made up 22.2% and Cluster 1 (n = 261) or the High-all-round activity and screen media-late family made up 4.5%, respectively represented the largest and smallest clusters among the seven clusters that were emergent from the pooled dataset. Finland was best represented by Cluster 2 and Japan was best represented by Cluster 3 (High-screen media-for-entertainment and low-engagement family). Parents from Finland and Japan displayed greater homogeneity in terms of the screen media and non-screen media habits of preschool children than the parents from South Korea and Singapore. South Korea was best represented by Clusters 6 (Screen media-physical activity-engagement hands-off family) and 7 (Screen media-lite, screen media-late and high-physical activity family). Singapore was best represented by Clusters 4, 5, 6 and 7, and these clusters ranged from Low all-round activity-high nap time family to Screen media-lite, screen media-late and high-physical activity family. Future research should explore in-depth reasons for the across-country and within-country cluster characteristics of screen media and non-screen media habits among preschool children to allow for more targeted interventions.

Alzheimer's disease classification using cluster-based labelling for graph neural network on heterogeneous data

Biomarkers for Alzheimer's disease (AD) diagnosis do not always correlate reliably with cognitive symptoms, making clinical diagnosis inconsistent. In this study, the performance of a graphical neural network (GNN) classifier based on data-driven diagnostic classes from unsupervised clustering on heterogeneous data is compared to the performance of a classifier using clinician diagnosis as an outcome. Unsupervised clustering on tau-positron emission tomography (PET) and cognitive and functional assessment data was performed. Five clusters embedded in a non-linear uniform manifold approximation and project (UMAP) space were identified. The individual clusters revealed specific feature characteristics with respect to clinical diagnosis of AD, gender, family history, age, and underlying neurological risk factors (NRFs). In particular, one cluster comprised mainly diagnosed AD cases. All cases within this cluster were re-labelled AD cases. The re-labelled cases are characterized by high cerebrospinal fluid amyloid beta (CSF Aβ) levels at a younger age, even though Aβ data was not used for clustering. A GNN model was trained using the re-labelled data with a multiclass area-under-the-curve (AUC) of 95.2%, higher than the AUC of a GNN trained on clinician diagnosis (91.7%; p = 0.02). Overall, our work suggests that more objective cluster-based diagnostic labels combined with GNN classification may have value in clinical risk stratification and diagnosis of AD.

Data-driven analysis and druggability assessment methods to accelerate the identification of novel cancer targets

Over the past few decades, drug discovery has greatly improved the outcomes for patients, but several challenges continue to hinder the rapid development of novel drugs. Addressing unmet clinical needs requires the pursuit of drug targets that have a higher likelihood to lead to the development of successful drugs. Here we describe a bioinformatic approach for identifying novel cancer drug targets by performing statistical analysis to ascertain quantitative changes in expression levels between protein-coding genes, as well as co-expression networks to classify these genes into groups. Subsequently, we provide an overview of druggability assessment methodologies to prioritize and select the best targets to pursue.

A diagnosis model of dementia via machine learning

As the aging population poses serious challenges to families and societies, the issue of dementia has also received increasing attention. Dementia detection often requires a series of complex tests and lengthy questionnaires, which are time-consuming. In order to solve this problem, this article aims at the diagnosis method of questionnaire survey, hoping to establish a diagnosis model to help doctors make a diagnosis through machine learning method, and use feature selection method to select important questions to reduce the number of questions in the questionnaire, so as to reduce medical and time costs. In this article, Clinical Dementia Rating (CDR) is used as the data source, and various methods are used for modeling and feature selection, so as to combine similar attributes in the data set, reduce the categories, and finally use the confusion matrix to judge the effect. The experimental results show that the model established by the bagging method has the best effect, and the accuracy rate can reach 80% of the true diagnosis rate; in terms of feature selection, the principal component analysis (PCA) has the best effect compared with other methods.

Oxygen debt repayment in the early phase of veno-arterial extracorporeal membrane oxygenation: a cluster analysis

Introduction

Early oxygen debt repayment is predictive of successful weaning from veno-arterial extracorporeal membrane oxygenation (V-A ECMO). However, studies are limited by the patient cohort’s heterogeneity. This study aimed to understand the early state of oxygen debt repayment and its association with end-organ failure and 30-day survival using cluster analysis.

Methods

A retrospective, single-center study was conducted on 153V-A ECMO patients. Patients were clustered using a two-step cluster analysis based on oxygen debt and its repayment during the first 24 h of ECMO. Primary outcomes were end-organ failure and 30-day survival.

Results

The overall mortality was 69.3%. For cluster analysis, 137 patients were included, due to an incomplete data set. The mortality rate in this subset was 67.9%. Three clusters were generated, representing increasing levels of total oxygen debt from cluster 1 to cluster 3. Thirty-day survival between clusters was significantly different (cluster 1: 46.9%, cluster 2: 23.4%, and cluster 3: 4.8%, p = 0.001). Patients in cluster 3 showed less decrement in liver enzymes, creatinine, and urea blood levels. There were significant differences in the baseline oxygen debt and the need for continuous veno-venous hemofiltration (CVVH) between survivors and non-survivors (p < 0.05). Forty-seven patients (34.3%) migrated between clusters within the first 24 h of support. Among these patients, 43.4% required CVVH. Notably, patients requiring CVVH and who migrated to a cluster with a higher oxygen debt repayment showed better survival rates compared to those who migrated to a cluster with a lower oxygen debt repayment.

Conclusions

Oxygen debt repayment during the first 24 h of V-A ECMO shows to correspond with survival, where the baseline oxygen debt value and the necessity for continuous kidney replacement therapy appear to be influential.

A New Clustering Method Based on the Inversion Formula

Data clustering is one area of data mining that falls into the data mining class of unsupervised learning. Cluster analysis divides data into different classes by discovering the internal structure of data set objects and their relationship. This paper presented a new density clustering method based on the modified inversion formula density estimation. This new method should allow one to improve the performance and robustness of the k-means, Gaussian mixture model, and other methods. The primary process of the proposed clustering algorithm consists of three main steps. Firstly, we initialized parameters and generated a T matrix. Secondly, we estimated the densities of each point and cluster. Third, we updated mean, sigma, and phi matrices. The new method based on the inversion formula works quite well with different datasets compared with K-means, Gaussian Mixture Model, and Bayesian Gaussian Mixture model. On the other hand, new methods have limitations because this one method in the current state cannot work with higher-dimensional data (d > 15). This will be solved in the future versions of the model, detailed further in future work. Additionally, based on the results, we can see that the MIDEv2 method works the best with generated data with outliers in all datasets (0.5%, 1%, 2%, 4% outliers). The interesting point is that a new method based on the inversion formula can cluster the data even if data do not have outliers; one of the most popular, for example, is the Iris dataset.

Cognitive Impairment Analysis of Myotonic Dystrophy via Weakly Supervised Classification of Neuropsychological Features

The myotonic dystrophies (DM1 and DM2) are dominantly inherited disorders that cause pathological changes throughout the body. Many individuals with DM experience cognitive, behavioral and other functional central nervous system effects that impact their quality of life. The extent of psychological impairment that will develop in each patient is variable and unpredictable. Hence, it is difficult to get strong supervision information like fully ground truth labels for all cognitive involvement patterns. This study is to assess cognitive involvement among healthy controls and patients with DM. The DM cognitive impairment pattern observation is modeled in a weakly supervised setting and supervision information is used to transform the input feature space to a more discriminative representation suitable for pattern observation. This study incorporated results from 59 adults with DM and 92 control subjects. The developed system categorized the neuropsychological testing data into five cognitive clusters. The quality of the obtained clustering solution was assessed using an internal validity metric. The experimental results show that the proposed algorithm can discover interesting patterns and useful information from neuropsychological data, which will be be crucial in planning clinical trials and monitoring clinical performance. The proposed system resulted in an average classification accuracy of 88%, which is very promising considering the unique challenges present in this population.

Towards a safe and efficient clinical implementation of machine learning in radiation oncology by exploring model interpretability, explainability and data-model dependency

The interest in machine learning (ML) has grown tremendously in recent years, partly due to the performance leap that occurred with new techniques of deep learning, convolutional neural networks for images, increased computational power, and wider availability of large datasets. Most fields of medicine follow that popular trend and, notably, radiation oncology is one of those that are at the forefront, with already a long tradition in using digital images and fully computerized workflows. ML models are driven by data, and in contrast with many statistical or physical models, they can be very large and complex, with countless generic parameters. This inevitably raises two questions, namely, the tight dependence between the models and the datasets that feed them, and the interpretability of the models, which scales with its complexity. Any problems in the data used to train the model will be later reflected in their performance. This, together with the low interpretability of ML models, makes their implementation into the clinical workflow particularly difficult. Building tools for risk assessment and quality assurance of ML models must involve then two main points: interpretability and data-model dependency. After a joint introduction of both radiation oncology and ML, this paper reviews the main risks and current solutions when applying the latter to workflows in the former. Risks associated with data and models, as well as their interaction, are detailed. Next, the core concepts of interpretability, explainability, and data-model dependency are formally defined and illustrated with examples. Afterwards, a broad discussion goes through key applications of ML in workflows of radiation oncology as well as vendors' perspectives for the clinical implementation of ML.

DivCom: A Tool for Systematic Partition of Groups of Microbial Profiles Into Intrinsic Subclusters and Distance-Based Subgroup Comparisons

When analyzing microbiome data, one of the main objectives is to effectively compare the microbial profiles of samples belonging to different groups. Beta diversity measures the level of similarity among samples, usually in the form of dissimilarity matrices. The use of suitable statistical tests in conjunction with those matrices typically provides us with all the necessary information to evaluate the overall similarity of groups of microbial communities. However, in some cases, this approach can lead us to deceptive conclusions, mainly due to the uneven dispersions of the groups and the existence of unique or unexpected substructures in the dataset. To address these issues, we developed divide and compare (DivCom), an automated tool for advanced beta diversity analysis. DivCom reveals the inner structure of groups by dividing their samples into the appropriate number of clusters and then compares the distances of every profile to the centers of these clusters. This information can be used for determining the existing interrelation of the groups. The proposed methodology and the developed tool were assessed by comparing the response of anemic patients with or without inflammatory bowel disease to different iron replacement therapies. DivCom generated results that revealed the inner structure of the dataset, evaluated the relationship among the clusters, and assessed the effect of the treatments. The DivCom tool is freely available at: https://github.com/Lagkouvardos/DivCom.

FCM Clustering Approach Optimization Using Parallel High-Speed Intel FPGA Technology

Fuzzy C-Means (FCM) is a widely used clustering algorithm that performs well in various scientific applications. Implementing FCM involves a massive number of computations, and many parallelization techniques based on GPUs and multicore systems have been suggested. In this study, we present a method for optimizing the FCM algorithm for high-speed field-programmable gate technology (FPGA) using a high-level C-like programming language called open computing language (OpenCL). The method was designed to enable the high-level compiler/synthesis tool to manipulate a task-parallelism model and create an efficient design. Our experimental results (based on several datasets) show that the proposed method makes the FCM execution time more than 186 times faster than the conventional design running on a single-core CPU platform. Also, its processing power reached 89 giga floating points operations per second (GFLOPs).

Longitudinal Study on Sustained Attention to Response Task (SART): Clustering Approach for Mobility and Cognitive Decline

The Sustained Attention to Response Task (SART) is a computer-based go/no-go task to measure neurocognitive function in older adults. However, simplified average features of this complex dataset lead to loss of primary information and fail to express associations between test performance and clinically meaningful outcomes. Here, we combine a novel method to visualise individual trial (raw) information obtained from the SART test in a large population-based study of ageing in Ireland and an automatic clustering technique. We employed a thresholding method, based on the individual trial number of mistakes, to identify poorer SART performances and a fuzzy clusters algorithm to partition the dataset into 3 subgroups, based on the evolution of SART performance after 4 years. Raw SART data were available for 3468 participants aged 50 years and over at baseline. The previously reported SART visualisation-derived feature ‘bad performance’, indicating the number of SART trials with at least 4 mistakes, and its evolution over time, combined with the fuzzy c-mean (FCM) algorithm, individuated 3 clusters corresponding to 3 degrees of physiological dysregulation. The biggest cluster (94% of the cohort) was constituted by healthy participants, a smaller cluster (5% of the cohort) by participants who showed improvement in cognitive and psychological status, and the smallest cluster (1% of the cohort) by participants whose mobility and cognitive functions dramatically declined after 4 years. We were able to identify in a cohort of relatively high-functioning community-dwelling adults a very small group of participants who showed clinically significant decline. The selected smallest subset manifested not only mobility deterioration, but also cognitive decline, the latter being usually hard to detect in population-based studies. The employed techniques could identify at-risk participants with more specificity than current methods, and help clinicians better identify and manage the small proportion of community-dwelling older adults who are at significant risk of functional decline and loss of independence.

Using bi-dimensional representations to understand patterns in COVID-19 blood exam data

Blood tests play an essential role in everyday medicine and are used by doctors in several diagnostic procedures. Moreover, this data is multivariate - and often some diseases, such as COVID-19, could have different symptom manifestations and outcomes. This study proposes a method of extracting useful information from blood tests using UMAP technique - Uniform Manifold Approximation and Projection for Dimension Reduction combined with DBSCAN clustering and statistical approaches. The analysis performed here indicates several clusters of infection prevalence varying between 2%-37%, showing that our procedure is indeed capable of finding different patterns. A possible explanation is that COVID-19 is not just a respiratory infection but a systemic disease with critical hematological implications, primarily on white-cell fractions, as indicated by relevant statistical test p -values in the range of 0.03-0.1. The novel analysis procedure proposed could be adopted in other data-sets of different illnesses to help researchers to discover new patterns of data that could be used in various diseases and contexts.

The penalty of stress - Epichaperomes negatively reshaping the brain in neurodegenerative disorders

Adaptation to acute and chronic stress and/or persistent stressors is a subject of wide interest in central nervous system disorders. In this context, stress is an effector of change in organismal homeostasis and the response is generated when the brain perceives a potential threat. Herein, we discuss a nuanced and granular view whereby a wide variety of genotoxic and environmental stressors, including aging, genetic risk factors, environmental exposures, and age- and lifestyle-related changes, act as direct insults to cellular, as opposed to organismal, homeostasis. These two concepts of how stressors impact the central nervous system are not mutually exclusive. We discuss how maladaptive stressor-induced changes in protein connectivity through epichaperomes, disease-associated pathologic scaffolds composed of tightly bound chaperones, co-chaperones, and other factors, impact intracellular protein functionality altering phenotypes, that in turn disrupt and remodel brain networks ranging from intercellular to brain connectome levels. We provide an evidence-based view on how these maladaptive changes ranging from stressor to phenotype provide unique precision medicine opportunities for diagnostic and therapeutic development, especially in the context of neurodegenerative disorders including Alzheimer's disease where treatment options are currently limited.

Trends in COVID-19 prevalence and mortality: A year in review

This paper introduces new methods to study the changing dynamics of COVID-19 cases and deaths among the 50 worst-affected countries throughout 2020. First, we analyse the trajectories and turning points of rolling mortality rates to understand at which times the disease was most lethal. We demonstrate five characteristic classes of mortality rate trajectories and determine structural similarity in mortality trends over time. Next, we introduce a class of virulence matrices to study the evolution of COVID-19 cases and deaths on a global scale. Finally, we introduce three-way inconsistency analysis to determine anomalous countries with respect to three attributes: countries' COVID-19 cases, deaths and human development indices. We demonstrate the most anomalous countries across these three measures are Pakistan, the United States and the United Arab Emirates.

A review on omics-based biomarkers discovery for Alzheimer's disease from the bioinformatics perspectives: Statistical approach vs machine learning approach

Alzheimer's Disease (AD) is a neurodegenerative disease that affects cognition and is the most common cause of dementia in the elderly. As the number of elderly individuals increases globally, the incidence and prevalence of AD are expected to increase. At present, AD is diagnosed clinically, according to accepted criteria. The essential elements in the diagnosis of AD include a patients history, a physical examination and neuropsychological testing, in addition to appropriate investigations such as neuroimaging. The omics-based approach is an emerging field of study that may not only aid in the diagnosis of AD but also facilitate the exploration of factors that influence the development of the disease. Omics techniques, including genomics, transcriptomics, proteomics and metabolomics, may reveal the pathways that lead to neuronal death and identify biomolecular markers associated with AD. This will further facilitate an understanding of AD neuropathology. In this review, omics-based approaches that were implemented in studies on AD were assessed from a bioinformatics perspective. Current state-of-the-art statistical and machine learning approaches used in the single omics analysis of AD were compared based on correlations of variants, differential expression, functional analysis and network analysis. This was followed by a review of the approaches used in the integration and analysis of multi-omics of AD. The strengths and limitations of multi-omics analysis methods were explored and the issues and challenges associated with omics studies of AD were highlighted. Lastly, future studies in this area of research were justified.

A single-cell tumor immune atlas for precision oncology

The tumor immune microenvironment is a main contributor to cancer progression and a promising therapeutic target for oncology. However, immune microenvironments vary profoundly between patients, and biomarkers for prognosis and treatment response lack precision. A comprehensive compendium of tumor immune cells is required to pinpoint predictive cellular states and their spatial localization. We generated a single-cell tumor immune atlas, jointly analyzing published data sets of >500,000 cells from 217 patients and 13 cancer types, providing the basis for a patient stratification based on immune cell compositions. Projecting immune cells from external tumors onto the atlas facilitated an automated cell annotation system. To enable in situ mapping of immune populations for digital pathology, we applied SPOTlight, combining single-cell and spatial transcriptomics data and identifying colocalization patterns of immune, stromal, and cancer cells in tumor sections. We expect the tumor immune cell atlas, together with our versatile toolbox for precision oncology, to advance currently applied stratification approaches for prognosis and immunotherapy.

Robust Discovery of Mild Cognitive Impairment Subtypes and Their Risk of Alzheimer's Disease Conversion Using Unsupervised Machine Learning and Gaussian Mixture Modeling

BACKGROUND

Alzheimer's Disease (AD) is an irreversible, progressive brain disorder that slowly destroys memory and thinking skills. The ability to correctly predict the diagnosis of Alzheimer's disease in its earliest stages can help physicians make more informed clinical decisions on therapy plans.

OBJECTIVE

This study aimed to determine whether the unsupervised discovering of latent classes of subjects with Mild Cognitive Impairment (MCI) may be useful in finding different prodromal AD stages and/or subjects with a low MCI to AD conversion risk.

METHODS

Total 18 features relevant to the MCI to AD conversion process led to the identification of 681 subjects with early MCI. Subjects were divided into training (70%) and validation (30%) sets. Subjects from the training set were analyzed using consensus clustering, and Gaussian Mixture Models (GMM) were used to describe the latent classes. The discovered GMM predicted the latent class of the validation set. Finally, descriptive statistics, rates of conversion, and Odds Ratios (OR) were computed for each discovered class.

RESULTS

Through consensus clustering, we discovered three different clusters among MCI subjects. The three clusters were associated with low-risk (OR = 0.12, 95%CI = 0.04 to 0.3|), medium-risk (OR = 1.33, 95%CI = 0.75 to 2.37), and high-risk (OR = 3.02, 95%CI = 1.64 to 5.57) of converting from MCI to AD, with the high-risk and low-risk groups highly contrasting. Hence, prodromal AD subjects were present in only two clusters.

CONCLUSION

We successfully discovered three different latent classes among MCI subjects with varied risks of MCI-to-AD conversion through consensus clustering. Two of the discovered classes may represent two different prodromal presentations of Alzheimer´s disease.

Cardiovascular phenotypes predict clinical outcomes in sickle cell disease: An echocardiography-based cluster analysis

This study sought to link cardiac phenotypes in homozygous Sickle Cell Disease (SCD) patients with clinical profiles and outcomes using cluster analysis. We analyzed data of 379 patients included in the French Etendard Cohort. A cluster analyses was performed based on echocardiographic variables, and the association between clusters, clinical profiles and outcomes was assessed. Three clusters were identified. Cluster 1 (n = 123) patients had the lowest cardiac output, mild left cardiac cavities remodeling, mild diastolic dysfunction, and higher tricuspid regurgitation velocity (TRV). They were predominantly female and displayed the most altered functional limitation. Cluster 2 (n = 102) patients had the highest cardiac output and the most remodeled cardiac cavities. Diastolic function and TRV were similar to cluster 1. These patients had a higher blood pressure and a severe hemolytic anemia. Cluster 3 (n = 154) patients had mild left cardiac cavities remodeling, normal diastolic function and lowest TRV values. They were younger with the highest hemoglobin value. Right heart catheterization was performed in 94 patients. Cluster 1 (n = 33) included the majority of pre-capillary PH whilst cluster 2 (n = 34) included post-capillary PH. No PH was found in cluster 3 (n = 27). After a follow-up of 11.4 ± 2 years, death occurred in 41 patients (11%). Cluster 2 patients had the worst prognosis with a 19% mortality rate versus 12% in cluster 1 and 5% in cluster 3 (p log-rank = 0.003). Cluster analysis of echocardiography variables identified three hemodynamic and clinical phenotypes among SCD patients, each predicting a different prognosis.

N6-methyladenosine (m6A) modification and its clinical relevance in cognitive dysfunctions

BACKGROUND

N6 adenosine methylation (m6A) is the most abundant internal RNA modification in eukaryotic cells. Dysregulation of m6A has been associated with the perturbations of cell proliferation and cell death in different diseases. However, the roles of m6A in the neurodegenerative process and cognitive dysfunction are unclear.

METHODS

We systematically investigated the molecular alterations of m6A regulators and their clinical relevance with cognitive dysfunctions using published datasets of Alzheimer's Disease (AD), vascular dementia, and mild cognitive impairment (MCI).

FINDINGS

The expressions of m6A regulators vary in different tissues and closely correlate with neurodegenerative pathways. We identified co-expressive m6A regulators SNRPG and SNRPD2 as potential biomarkers to predict transformation from MCI to AD. Moreover, we explored correlations between Apolipoprotein E4 and m6A methylations.

INTERPRETATION

Collectively, these findings suggest that m6A methylations as potential biomarkers and therapeutic targets for cognitive dysfunction.

FUNDING

This work was supported by the National Natural Science Foundation of China (81871040) and the Shanghai Health System Talent Training Program (2018BR29).

Spectral clustering based on structural magnetic resonance imaging and its relationship with major depressive disorder and cognitive ability

There is increasing interest in using data-driven unsupervised methods to identify structural underpinnings of common mental illnesses, including major depressive disorder (MDD) and associated traits such as cognition. However, studies are often limited to severe clinical cases with small sample sizes and most do not include replication. Here, we examine two relatively large samples with structural magnetic resonance imaging (MRI), measures of lifetime MDD and cognitive variables: Generation Scotland (GS subsample, N = 980) and UK Biobank (UKB, N = 8,900), for discovery and replication, using an exploratory approach. Regional measures of FreeSurfer derived cortical thickness (CT), cortical surface area (CSA), cortical volume (CV) and subcortical volume (subCV) were input into a clustering process, controlling for common covariates. The main analysis steps involved constructing participant K-nearest neighbour graphs and graph partitioning with Markov stability to determine optimal clustering of participants. Resultant clusters were (1) checked whether they were replicated in an independent cohort and (2) tested for associations with depression status and cognitive measures. Participants separated into two clusters based on structural brain measurements in GS subsample, with large Cohen's d effect sizes between clusters in higher order cortical regions, commonly associated with executive function and decision making. Clustering was replicated in the UKB sample, with high correlations of cluster effect sizes for CT, CSA, CV and subCV between cohorts across regions. The identified clusters were not significantly different with respect to MDD case-control status in either cohort (GS subsample: p_FDR  = .2239-.6585; UKB: p_FDR  = .2003-.7690). Significant differences in general cognitive ability were, however, found between the clusters for both datasets, for CSA, CV and subCV (GS subsample: d = 0.2529-.3490, p_FDR  < .005; UKB: d = 0.0868-0.1070, p_FDR  < .005). Our results suggest that there are replicable natural groupings of participants based on cortical and subcortical brain measures, which may be related to differences in cognitive performance, but not to the MDD case-control status.

Data mining in clinical big data: the frequently used databases, steps, and methodological models

Many high quality studies have emerged from public databases, such as Surveillance, Epidemiology, and End Results (SEER), National Health and Nutrition Examination Survey (NHANES), The Cancer Genome Atlas (TCGA), and Medical Information Mart for Intensive Care (MIMIC); however, these data are often characterized by a high degree of dimensional heterogeneity, timeliness, scarcity, irregularity, and other characteristics, resulting in the value of these data not being fully utilized. Data-mining technology has been a frontier field in medical research, as it demonstrates excellent performance in evaluating patient risks and assisting clinical decision-making in building disease-prediction models. Therefore, data mining has unique advantages in clinical big-data research, especially in large-scale medical public databases. This article introduced the main medical public database and described the steps, tasks, and models of data mining in simple language. Additionally, we described data-mining methods along with their practical applications. The goal of this work was to aid clinical researchers in gaining a clear and intuitive understanding of the application of data-mining technology on clinical big-data in order to promote the production of research results that are beneficial to doctors and patients.

Country transition index based on hierarchical clustering to predict next COVID-19 waves

COVID-19 has widely spread around the world, impacting the health systems of several countries in addition to the collateral damage that societies will face in the next years. Although the comparison between countries is essential for controlling this disease, the main challenge is the fact of countries are not simultaneously affected by the virus. Therefore, from the COVID-19 dataset by the Johns Hopkins University Center for Systems Science and Engineering, we present a temporal analysis on the number of new cases and deaths among countries using artificial intelligence. Our approach incrementally models the cases using a hierarchical clustering that emphasizes country transitions between infection groups over time. Then, one can compare the current situation of a country against others that have already faced previous waves. By using our approach, we designed a transition index to estimate the most probable countries' movements between infectious groups to predict next wave trends. We draw two important conclusions: (1) we show the historical infection path taken by specific countries and emphasize changing points that occur when countries move between clusters with small, medium, or large number of cases; (2) we estimate new waves for specific countries using the transition index.

Clustering of Unhealthy Behaviors: Protocol for a Multiple Behavior Analysis of Data From the Canadian Longitudinal Study on Aging

BACKGROUND

Health behaviors such as physical inactivity, unhealthy eating, smoking tobacco, and alcohol use are leading risk factors for noncommunicable chronic diseases and play a central role in limiting health and life satisfaction. To date, however, health behaviors tend to be considered separately from one another, resulting in guidelines and interventions for healthy aging siloed by specific behaviors and often focused only on a given health behavior without considering the co-occurrence of family, social, work, and other behaviors of everyday life.

OBJECTIVE

The aim of this study is to understand how behaviors cluster and how such clusters are associated with physical and mental health, life satisfaction, and health care utilization may provide opportunities to leverage this co-occurrence to develop and evaluate interventions to promote multiple health behavior changes.

METHODS

Using cross-sectional baseline data from the Canadian Longitudinal Study on Aging, we will perform a predefined set of exploratory and hypothesis-generating analyses to examine the co-occurrence of health and everyday life behaviors. We will use agglomerative hierarchical cluster analysis to cluster individuals based on their behavioral tendencies. Multinomial logistic regression will then be used to model the relationships between clusters and demographic indicators, health care utilization, and general health and life satisfaction, and assess whether sex and age moderate these relationships. In addition, we will conduct network community detection analysis using the clique percolation algorithm to detect overlapping communities of behaviors based on the strength of relationships between variables.

RESULTS

Baseline data for the Canadian Longitudinal Study on Aging were collected from 51,338 participants aged between 45 and 85 years. Data were collected between 2010 and 2015. Secondary data analysis for this project was approved by the Ottawa Health Science Network Research Ethics Board (protocol ID #20190506-01H).

CONCLUSIONS

This study will help to inform the development of interventions tailored to subpopulations of adults (eg, physically inactive smokers) defined by the multiple behaviors that describe their everyday life experiences.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

DERR1-10.2196/24887.

COVID-19 second wave mortality in Europe and the United States

This paper introduces new methods to analyze the changing progression of COVID-19 cases to deaths in different waves of the pandemic. First, an algorithmic approach partitions each country or state's COVID-19 time series into a first wave and subsequent period. Next, offsets between case and death time series are learned for each country via a normalized inner product. Combining these with additional calculations, we can determine which countries have most substantially reduced the mortality rate of COVID-19. Finally, our paper identifies similarities in the trajectories of cases and deaths for European countries and U.S. states. Our analysis refines the popular conception that the mortality rate has greatly decreased throughout Europe during its second wave of COVID-19; instead, we demonstrate substantial heterogeneity throughout Europe and the U.S. The Netherlands exhibited the largest reduction of mortality, a factor of 16, followed by Denmark, France, Belgium, and other Western European countries, greater than both Eastern European countries and U.S. states. Some structural similarity is observed between Europe and the United States, in which Northeastern states have been the most successful in the country. Such analysis may help European countries learn from each other's experiences and differing successes to develop the best policies to combat COVID-19 as a collective unit.

Association between COVID-19 cases and international equity indices

This paper analyzes the impact of COVID-19 on the populations and equity markets of 92 countries. We compare country-by-country equity market dynamics to cumulative COVID-19 case and death counts and new case trajectories. First, we examine the multivariate time series of cumulative cases and deaths, particularly regarding their changing structure over time. We reveal similarities between the case and death time series, and key dates that the structure of the time series changed. Next, we classify new case time series, demonstrate five characteristic classes of trajectories, and quantify discrepancy between them with respect to the behavior of waves of the disease. Finally, we show there is no relationship between countries' equity market performance and their success in managing COVID-19. Each country's equity index has been unresponsive to the domestic or global state of the pandemic. Instead, these indices have been highly uniform, with most movement in March.