Identification of type 2 diabetes subgroups through topological analysis of patient similarity

Unsupervised discovery of clinical disease signatures using probabilistic independence

OBJECTIVE

This study uses probabilistic independence to disentangle patient-specific sources of disease and their signatures in Electronic Health Record (EHR) data.

MATERIALS AND METHODS

We model a disease source as an unobserved root node in the causal graph of observed EHR variables (laboratory test results, medication exposures, billing codes, and demographics), and a signature as the set of downstream effects that a given source has on those observed variables. We used probabilistic independence to infer 2000 sources and their signatures from 9195 variables in 630,000 cross-sectional training instances sampled at random times from 269,099 longitudinal patient records. We evaluated the learned sources by using them to infer and explain the causes of benign vs. malignant pulmonary nodules in 13,252 records, comparing the inferred causes to an external reference list and other medical literature. We compared models trained by three different algorithms and used corresponding models trained directly from the observed variables as baselines.

RESULTS

The model recovered 92% of malignant and 30% of benign causes in the reference standard. Of the top 20 inferred causes of malignancy, 14 were not listed in the reference standard, but had supporting evidence in the literature, as did 11 of the top 20 inferred causes of benign nodules. The model decomposed listed malignant causes by an average factor of 5.5 and benign causes by 4.1, with most stratifying by disease course or treatment regimen. Predictive accuracy of causal predictive models trained on source expressions (Random Forest AUC 0.788) was similar to (p = 0.058) their associational baselines (0.738).

DISCUSSION

Most of the unrecovered causes were due to the rarity of the condition or lack of sufficient detail in the input data. Surprisingly, the causal model found many patients with apparently undiagnosed cancer as the source of the malignant nodules. Causal model AUC also suggests that some sources remained undiscovered in this cohort.

CONCLUSION

These promising results demonstrate the potential of using probabilistic independence to disentangle complex clinical signatures from noisy, asynchronous, and incomplete EHR data that represent the confluence of multiple simultaneous conditions, and to identify patient-specific causes that support precise treatment decisions.

Labour monitoring and decision support: a machine-learning-based paradigm

Introduction

A machine-learning-based paradigm, combining unsupervised and supervised components, is proposed for the problem of real-time monitoring and decision support during labour, addressing the limitations of current state-of-the-art approaches, such as the partograph or purely supervised models.

Methods

The proposed approach is illustrated with World Health Organisation's Better Outcomes in Labour Difficulty (BOLD) prospective cohort study data, including 9,995 women admitted for labour in 2014-2015 in thirteen major regional health care facilities across Nigeria and Uganda. Unsupervised dimensionality reduction is used to map complex labour data to a visually intuitive space. In this space, an ongoing labour trajectory can be compared to those of a historical cohort of women with similar characteristics and known outcomes-this information can be used to estimate personalised "healthy" trajectory references (and alert the healthcare provider to significant deviations), as well as draw attention to high incidences of different interventions/adverse outcomes among similar labours. To evaluate the proposed approach, the predictive value of simple risk scores quantifying deviation from normal progress and incidence of complications among similar labours is assessed in a caesarean section prediction context and compared to that of the partograph and state-of-the-art supervised machine-learning models.

Results

Considering all women, our predictors yielded sensitivity and specificity of ∼0.70. It was observed that this predictive performance could increase or decrease when looking at different subgroups.

Discussion

With a simple implementation, our approach outperforms the partograph and matches the performance of state-of-the-art supervised models, while offering superior flexibility and interpretability as a real-time monitoring and decision-support solution.

Generating realistic single-cell images from CellProfiler representations

High-throughput imaging techniques acquire large amounts of images efficiently. These images contain rich biological information including cellular processes. A common method to analyse them is to encode them into quantitative representation vectors. Generally, there are two ways to extract cell biological information into representations, hand-crafted and machine-learning. Although representations obtained from machine learning models often demonstrate commendable reconstruction performance, they lack biological interpretability. In contrast, hand-crafted representations have clear biological meanings, making them easily interpretable. However, the capability of hand-crafted representations to generate realistic images remains uncertain. In this work, we propose a CellProfiler to image (CP2Image) model capable of directly generating realistic cell images from CellProfiler representations. The proposed model is demonstrated to be robust to different architectures, including ResNet, InceptionNet and Transformer. We also show that the biological information is well preserved during the generation process. The changes in certain CellProfiler features will reflect the corresponding changes in the generated single-cell images. In addition, the CP2Image model can generate conditional phenotypes, which will ultimately help diagnostics and drug screening.

A novel method for subgroup discovery in precision medicine based on topological data analysis

BACKGROUND

The Mapper algorithm is a data mining topological tool that can help us to obtain higher level understanding of disease by visualising the structure of patient data as a similarity graph. It has been successfully applied for exploratory analysis of cancer data in the past, delivering several significant subgroup discoveries. Using the Mapper algorithm in practice requires setting up multiple parameters. The graph then needs to be manually analysed according to a research question at hand. It has been highlighted in the literature that Mapper's parameters have significant impact on the output graph shape and there is no established way to select their optimal values. Hence while using the Mapper algorithm, different parameter values and consequently different output graphs need to be studied. This prevents routine application of the Mapper algorithm in real world settings.

METHODS

We propose a new algorithm for subgroup discovery within the Mapper graph. We refer to the task as hotspot detection as it is designed to identify homogenous and geometrically compact subsets of patients, which are distinct with respect to their clinical or molecular profiles (e.g. survival). Furthermore, we propose to include the existence of a hotspot as a criterion while searching the parameter space, addressing one of the key limitations of the Mapper algorithm (i.e. parameter selection).

RESULTS

Two experiments were performed to demonstrate the efficacy of the algorithm, including an artificial hotspot in the Two Circles dataset and a real world case study of subgroup discovery in oestrogen receptor-positive breast cancer. Our hotspot detection algorithm successfully identified graphs containing homogenous communities of nodes within the Two Circles dataset. When applied to gene expression data of ER+ breast cancer patients, appropriate parameters were identified to generate a Mapper graph revealing a hotspot of ER+ patients with poor prognosis and characteristic patterns of gene expression. This was subsequently confirmed in an independent breast cancer dataset.

CONCLUSIONS

Our proposed method can be effectively applied for subgroup discovery with pathology data. It allows us to find optimal parameters of the Mapper algorithm, bridging the gap between its potential and the translational research.

Improving patient clustering by incorporating structured variable label relationships in similarity measures

BACKGROUND

Patient stratification is the cornerstone of numerous health investigations, serving to enhance the estimation of treatment efficacy and facilitating patient matching. To stratify patients, similarity measures between patients can be computed from clinical variables contained in medical health records. These variables have both values and labels structured in ontologies or other classification systems. The relevance of considering variable label relationships in the computation of patient similarity measures has been poorly studied.

OBJECTIVE

We adapt and evaluate several weighted versions of the Cosine similarity in order to consider structured label relationships to compute patient similarities from a medico-administrative database.

MATERIALS AND METHODS

As a use case, we clustered patients aged 60 years from their annual medicine reimbursements contained in the Échantillon Généraliste des Bénéficiaires, a random sample of a French medico-administrative database. We used four patient similarity measures: the standard Cosine similarity, a weighted Cosine similarity measure that includes variable frequencies and two weighted Cosine similarity measures that consider variable label relationships. We construct patient networks from each similarity measure and identify clusters of patients using the Markov Cluster algorithm. We evaluate the performance of the different similarity measures with enrichment tests based on patient diagnoses.

RESULTS

The weighted similarity measures that include structured variable label relationships perform better to identify similar patients. Indeed, using these weighted measures, we identify more clusters associated with different diagnose enrichment. Importantly, the enrichment tests provide clinically interpretable insights into these patient clusters.

CONCLUSION

Considering label relationships when computing patient similarities improves stratification of patients regarding their health status.

Distinct Roles of Common Genetic Variants and Their Contributions to Diabetes: MODY and Uncontrolled T2DM

Type 2 diabetes mellitus (T2DM) encompasses a range of clinical manifestations, with uncontrolled diabetes leading to progressive or irreversible damage to various organs. Numerous genes associated with monogenic diabetes, exhibiting classical patterns of inheritance (autosomal dominant or recessive), have been identified. Additionally, genes involved in complex diabetes, which interact with environmental factors to trigger the disease, have also been discovered. These genetic findings have raised hopes that genetic testing could enhance diagnostics, disease surveillance, treatment selection, and family counseling. However, the accurate interpretation of genetic data remains a significant challenge, as variants may not always be definitively classified as either benign or pathogenic. Research to date, however, indicates that periodic reevaluation of genetic variants in diabetes has led to more consistent findings, with biases being steadily eliminated. This has improved the interpretation of variants across diverse ethnicities. Clinical studies suggest that genetic risk information may motivate patients to adopt behaviors that promote the prevention or management of T2DM. Given that the clinical features of certain monogenic diabetes types overlap with T2DM, and considering the significant role of genetic variants in diabetes, healthcare providers caring for prediabetic patients should consider genetic testing as part of the diagnostic process. This review summarizes current knowledge of the most common genetic variants associated with T2DM, explores novel therapeutic targets, and discusses recent advancements in the pharmaceutical management of uncontrolled T2DM.

The research progress and future directions in the pathophysiological mechanisms of type 2 diabetes mellitus from the perspective of precision medicine

Type 2 diabetes mellitus (T2DM) is a complex metabolic disorder characterized by pathophysiological mechanisms such as insulin resistance and β-cell dysfunction. Recent advancements in T2DM research have unveiled intricate multi-level regulatory networks and contributing factors underlying this disease. The emergence of precision medicine has introduced new perspectives and methodologies for understanding T2DM pathophysiology. A recent study found that personalized treatment based on genetic, metabolic, and microbiome data can improve the management of T2DM by more than 30%. This perspective aims to summarize the progress in T2DM pathophysiological research from the past 5 years and to outline potential directions for future studies within the framework of precision medicine. T2DM develops through the interplay of factors such as gut microbiota, genetic and epigenetic modifications, metabolic processes, mitophagy, NK cell activity, and environmental influences. Future research should focus on understanding insulin resistance, β-cell dysfunction, interactions between gut microbiota and their metabolites, and the regulatory roles of miRNA and genes. By leveraging artificial intelligence and integrating data from genomics, epigenomics, metabolomics, and microbiomics, researchers can gain deeper insights into the pathophysiological mechanisms and heterogeneity of T2DM. Additionally, exploring the combined effects and interactions of these factors may pave the way for more effective prevention strategies and personalized treatments for T2DM.

Characterisation of phenotypic patterns in equine exercise-associated myopathies

BACKGROUND

Equine exercise-associated myopathies are prevalent, clinically heterogeneous, generally idiopathic disorders characterised by episodes of myofibre damage that occur in association with exercise. Episodes are intermittent and vary within and between affected horses and across breeds. The aetiopathogenesis is often unclear; there might be multiple causes. Poor phenotypic characterisation hinders genetic and other disease analyses.

OBJECTIVES

The aim of this study was to characterise phenotypic patterns across exercise-associated myopathies in horses.

STUDY DESIGN

Historical cross-sectional study, with subsequent masked case-control validation study.

METHODS

Historical clinical and histological features from muscle samples (n = 109) were used for k-means clustering and validated using principal components analysis and hierarchical clustering. For further validation, a blinded histological study (69 horses) was conducted comparing two phenotypic groups with selected controls and horses with histopathological features characterised by myofibrillar disruption.

RESULTS

We identified two distinct broad phenotypes: a non-classic exercise-associated myopathy syndrome (EAMS) subtype was associated with practitioner-described signs of apparent muscle pain (p < 0.001), reluctance to move (10.85, p = 0.001), abnormal gait (p < 0.001), ataxia (p = 0.001) and paresis (p = 0.001); while a non-specific classic RER subtype was not uniquely associated with any particular variables. No histological differences were identified between subtypes in the validation study, and no identifying histopathological features for other equine myopathies identified in either subtype.

MAIN LIMITATIONS

Lack of an independent validation population; small sample size of smaller identified subtypes; lack of positive control myofibrillar myopathy cases; case descriptions derived from multiple independent and unblinded practitioners.

CONCLUSIONS

This is the first study using computational clustering methods to identify phenotypic patterns in equine exercise-associated myopathies, and suggests that differences in patterns of presenting clinical signs support multiple disease subtypes, with EAMS a novel subtype not previously described. Routine muscle histopathology was not helpful in sub-categorising the phenotypes in our population.

The chronic heart failure evolutions: Different fates and routes

AIMS

Individual prognostic assessment and disease evolution pathways are undefined in chronic heart failure (HF). The application of unsupervised learning methodologies could help to identify patient phenotypes and the progression in each phenotype as well as to assess adverse event risk.

METHODS AND RESULTS

From a bulk of 7948 HF patients included in the MECKI registry, we selected patients with a minimum 2-year follow-up. We implemented a topological data analysis (TDA), based on 43 variables derived from clinical, biochemical, cardiac ultrasound, and exercise evaluations, to identify several patients' clusters. Thereafter, we used the trajectory analysis to describe the evolution of HF states, which is able to identify bifurcation points, characterized by different follow-up paths, as well as specific end-stages conditions of the disease. Finally, we conducted a 5-year survival analysis (composite of cardiovascular death, left ventricular assist device, or urgent heart transplant). Findings were validated on internal (n = 527) and external (n = 777) populations. We analyzed 4876 patients (age = 63 [53-71], male gender n = 3973 (81.5%), NYHA class I-II n = 3576 (73.3%), III-IV n = 1300 (26.7%), LVEF = 33 [25.5-39.9], atrial fibrillation n = 791 (16.2%), peak VO2% pred = 54.8 [43.8-67.2]), with a minimum 2-year follow-up. Nineteen patient clusters were identified by TDA. Trajectory analysis revealed a path characterized by 3 bifurcation and 4 end-stage points. Clusters survival rate varied from 44% to 100% at 2 years and from 20% to 100% at 5 years, respectively. The event frequency at 5-year follow-up for each study cohort cluster was successfully compared with those in the validation cohorts (R = 0.94 and R = 0.84, P < 0.001, for internal and external cohort, respectively). Finally, we conducted a 5-year survival analysis (composite of cardiovascular death, left ventricular assist device, or urgent heart transplant observed in 22% of cases).

CONCLUSIONS

Each HF phenotype has a specific disease progression and prognosis. These findings allow to individualize HF patient evolutions and to tailor assessment.

Characterizing Circulating microRNA Signatures of Type 2 Diabetes Subtypes

Type 2 diabetes (T2D) is a heterogeneous disease influenced by both genetic and environmental factors. Recent studies suggest that T2D subtypes may exhibit distinct gene expression profiles. In this study, we aimed to identify T2D cluster-specific miRNA expression signatures for the previously reported five clinical subtypes that characterize the underlying pathophysiology of long-standing T2D: severe insulin-resistant diabetes (SIRD), severe insulin-deficient diabetes (SIDD), mild age-related diabetes (MARD), mild obesity-related diabetes (MOD), and mild early-onset diabetes (MEOD). We analyzed the circulating microRNAs (miRNAs) in 45 subjects representing the five T2D clusters and 7 non-T2D healthy controls by single-end small RNA sequencing. Bioinformatic analyses identified a total of 430 known circulating miRNAs and 13 previously unreported novel miRNAs. Of these, 71 were upregulated and 37 were downregulated in either controls or individual clusters. Each T2D subtype was associated with a specific dysregulated miRNA profile, distinct from that of healthy controls. Specifically, 3 upregulated miRNAs were unique to SIRD, 1 to MARD, 9 to MOD, and 18 to MEOD. Among the downregulated miRNAs, 11 were specific to SIRD, 9 to SIDD, 2 to MARD, and 1 to MEOD. Our study confirms the heterogeneity of T2D, represented by distinguishable subtypes both clinically and epigenetically and highlights the potential of miRNAs as markers for distinguishing the pathophysiology of T2D subtypes.

Identifying subtypes of type 2 diabetes mellitus based on real-world electronic medical record data in China

AIMS

To replicate the European subtypes of type 2 diabetes mellitus (T2DM) in the Chinese diabetes population and investigate the risk of complications in different subtypes.

METHODS

A diabetes cohort using real-world patient data was constructed, and clustering was employed to subgroup the T2DM patients. Kaplan-Meier analysis and the Cox models were used to analyze the association between diabetes subtypes and the risk of complications.

RESULTS

A total of 2,652 T2DM patients with complete clustering data were extracted. Among them, 466 (17.57 %) were classified as severe insulin-deficient diabetes (SIDD), 502 (18.93 %) as severe insulin-resistant diabetes (SIRD), 672 (25.34 %) as mild obesity-related diabetes (MOD), and 1,012 (38.16 %) as mild age-related diabetes (MARD). The risk of chronic kidney disease (CKD) and diabetic retinopathy (DR) were different in the four subtypes. Compared with MARD, SIRD had a higher risk of CKD (HR 2.40 [1.16, 4.96]), and SIDD had a higher risk of DR (HR 2.16 [1.11, 4.20]). The risk of stroke and coronary events had no difference.

CONCLUSIONS

The European T2DM subtypes can be replicated in the Chinese diabetes population. The risk of CKD and DR varied among different subtypes, indicating that proper interventions can be taken to prevent specific complications in different subtypes.

Artificial intelligence driven definition of food preference endotypes in UK Biobank volunteers is associated with distinctive health outcomes and blood based metabolomic and proteomic profiles

BACKGROUND

Specific food preferences can determine an individual's dietary patterns and therefore, may be associated with certain health risks and benefits.

METHODS

Using food preference questionnaire (FPQ) data from a subset comprising over 180,000 UK Biobank participants, we employed Latent Profile Analysis (LPA) approach to identify the main patterns or profiles among participants. blood biochemistry across groups/profiles was compared using the non-parametric Kruskal-Wallis test. We applied the Limma algorithm for differential abundance analysis on 168 metabolites and 2923 proteins, and utilized the Database for Annotation, Visualization and Integrated Discovery (DAVID) to identify enriched biological processes and pathways. Relative risks (RR) were calculated for chronic diseases and mental conditions per group, adjusting for sociodemographic factors.

RESULTS

Based on their food preferences, three profiles were termed: the putative Health-conscious group (low preference for animal-based or sweet foods, and high preference for vegetables and fruits), the Omnivore group (high preference for all foods), and the putative Sweet-tooth group (high preference for sweet foods and sweetened beverages). The Health-conscious group exhibited lower risk of heart failure (RR = 0.86, 95%CI 0.79-0.93) and chronic kidney disease (RR = 0.69, 95%CI 0.65-0.74) compared to the two other groups. The Sweet-tooth group had greater risk of depression (RR = 1.27, 95%CI 1.21-1.34), diabetes (RR = 1.15, 95%CI 1.01-1.31), and stroke (RR = 1.22, 95%CI 1.15-1.31) compared to the other two groups. Cancer (overall) relative risk showed little difference across the Health-conscious, Omnivore, and Sweet-tooth groups with RR of 0.98 (95%CI 0.96-1.01), 1.00 (95%CI 0.98-1.03), and 1.01 (95%CI 0.98-1.04), respectively. The Health-conscious group was associated with lower levels of inflammatory biomarkers (e.g., C-reactive Protein) which are also known to be elevated in those with common metabolic diseases (e.g., cardiovascular disease). Other markers modulated in the Health-conscious group, ketone bodies, insulin-like growth factor-binding protein (IGFBP), and Growth Hormone 1 were more abundant, while leptin was less abundant. Further, the IGFBP pathway, which influences IGF1 activity, may be significantly enhanced by dietary choices.

CONCLUSIONS

These observations align with previous findings from studies focusing on weight loss interventions, which include a reduction in leptin levels. Overall, the Health-conscious group, with preference to healthier food options, has better health outcomes, compared to Sweet-tooth and Omnivore groups.

Language-model-based patient embedding using electronic health records facilitates phenotyping, disease forecasting, and progression analysis

Current studies regarding the secondary use of electronic health records (EHR) predominantly rely on domain expertise and existing medical knowledge. Though significant efforts have been devoted to investigating the application of machine learning algorithms in the EHR, efficient and powerful representation of patients is needed to unleash the potential of discovering new medical patterns underlying the EHR. Here, we present an unsupervised method for embedding high-dimensional EHR data at the patient level, aimed at characterizing patient heterogeneity in complex diseases and identifying new disease patterns associated with clinical outcome disparities. Inspired by the architecture of modern language models-specifically transformers with attention mechanisms, we use patient diagnosis and procedure codes as vocabularies and treat each patient as a sentence to perform the patient embedding. We applied this approach to 34,851 unique medical codes across 1,046,649 longitudinal patient events, including 102,739 patients from the electronic Medical Records and GEnomics (eMERGE) Network. The resulting patient vectors demonstrated excellent performance in predicting future disease events (median AUROC = 0.87 within one year) and bulk phenotyping (median AUROC = 0.84). We then illustrated the utility of these patient vectors in revealing heterogeneous comorbidity patterns, exemplified by disease subtypes in colorectal cancer and systemic lupus erythematosus, and capturing distinct longitudinal disease trajectories. External validation using EHR data from the University of Washington confirmed robust model performance, with median AUROCs of 0.83 and 0.84 for bulk phenotyping tasks and disease onset prediction, respectively. Importantly, the model reproduced the clustering results of disease subtypes identified in the eMERGE cohort and uncovered variations in overall mortality among these subtypes. Together, these results underscore the potential of representation learning in EHRs to enhance patient characterization and associated clinical outcomes, thereby advancing disease forecasting and facilitating personalized medicine.

Multi-Omic Graph Diagnosis (MOGDx): a data integration tool to perform classification tasks for heterogeneous diseases

MOTIVATION

Heterogeneity in human diseases presents challenges in diagnosis and treatments due to the broad range of manifestations and symptoms. With the rapid development of labelled multi-omic data, integrative machine learning methods have achieved breakthroughs in treatments by redefining these diseases at a more granular level. These approaches often have limitations in scalability, oversimplification, and handling of missing data.

RESULTS

In this study, we introduce Multi-Omic Graph Diagnosis (MOGDx), a flexible command line tool for the integration of multi-omic data to perform classification tasks for heterogeneous diseases. MOGDx has a network taxonomy. It fuses patient similarity networks, augments this integrated network with a reduced vector representation of genomic data and performs classification using a graph convolutional network. MOGDx was evaluated on three datasets from the cancer genome atlas for breast invasive carcinoma, kidney cancer, and low grade glioma. MOGDx demonstrated state-of-the-art performance and an ability to identify relevant multi-omic markers in each task. It integrated more genomic measures with greater patient coverage compared to other network integrative methods. Overall, MOGDx is a promising tool for integrating multi-omic data, classifying heterogeneous diseases, and aiding interpretation of genomic marker data.

AVAILABILITY AND IMPLEMENTATION

MOGDx source code is available from https://github.com/biomedicalinformaticsgroup/MOGDx.

Sex-stratified analyses of comorbidities associated with an inpatient delirium diagnosis using real world data

Delirium is a detrimental mental condition often seen in older, hospitalized patients and is currently hard to predict. In this study, we leverage electronic health records (EHR) to identify 7,492 UCSF patients and 19,417 UC health system patients with an inpatient delirium diagnosis and the same number of control patients without delirium. We found significant associations between comorbidities or laboratory values and an inpatient delirium diagnosis, including metabolic abnormalities and psychiatric diagnoses. Some associations were sex-specific, including dementia subtypes and infections. We further explored the associations with anemia and bipolar disorder by conducting longitudinal analyses from the time of first diagnosis to development of delirium, demonstrating a significant relationship across time. Finally, we show that an inpatient delirium diagnosis leads to increased risk of mortality. These results demonstrate the powerful application of the EHR to shed insights into prior diagnoses and laboratory values that could help predict development of inpatient delirium and the importance of sex when making these assessments.

Identification of Parkinson's disease PACE subtypes and repurposing treatments through integrative analyses of multimodal data

Parkinson's disease (PD) is a serious neurodegenerative disorder marked by significant clinical and progression heterogeneity. This study aimed at addressing heterogeneity of PD through integrative analysis of various data modalities. We analyzed clinical progression data (≥5 years) of individuals with de novo PD using machine learning and deep learning, to characterize individuals' phenotypic progression trajectories for PD subtyping. We discovered three pace subtypes of PD exhibiting distinct progression patterns: the Inching Pace subtype (PD-I) with mild baseline severity and mild progression speed; the Moderate Pace subtype (PD-M) with mild baseline severity but advancing at a moderate progression rate; and the Rapid Pace subtype (PD-R) with the most rapid symptom progression rate. We found cerebrospinal fluid P-tau/α-synuclein ratio and atrophy in certain brain regions as potential markers of these subtypes. Analyses of genetic and transcriptomic profiles with network-based approaches identified molecular modules associated with each subtype. For instance, the PD-R-specific module suggested STAT3, FYN, BECN1, APOA1, NEDD4, and GATA2 as potential driver genes of PD-R. It also suggested neuroinflammation, oxidative stress, metabolism, PI3K/AKT, and angiogenesis pathways as potential drivers for rapid PD progression (i.e., PD-R). Moreover, we identified repurposable drug candidates by targeting these subtype-specific molecular modules using network-based approach and cell line drug-gene signature data. We further estimated their treatment effects using two large-scale real-world patient databases; the real-world evidence we gained highlighted the potential of metformin in ameliorating PD progression. In conclusion, this work helps better understand clinical and pathophysiological complexity of PD progression and accelerate precision medicine.

Harnessing EHR data for health research

With the increasing availability of rich, longitudinal, real-world clinical data recorded in electronic health records (EHRs) for millions of patients, there is a growing interest in leveraging these records to improve the understanding of human health and disease and translate these insights into clinical applications. However, there is also a need to consider the limitations of these data due to various biases and to understand the impact of missing information. Recognizing and addressing these limitations can inform the design and interpretation of EHR-based informatics studies that avoid confusing or incorrect conclusions, particularly when applied to population or precision medicine. Here we discuss key considerations in the design, implementation and interpretation of EHR-based informatics studies, drawing from examples in the literature across hypothesis generation, hypothesis testing and machine learning applications. We outline the growing opportunities for EHR-based informatics studies, including association studies and predictive modeling, enabled by evolving AI capabilities-while addressing limitations and potential pitfalls to avoid.

Body mass index stratification optimizes polygenic prediction of type 2 diabetes in cross-biobank analyses

Type 2 diabetes (T2D) shows heterogeneous body mass index (BMI) sensitivity. Here, we performed stratification based on BMI to optimize predictions for BMI-related diseases. We obtained BMI-stratified datasets using data from more than 195,000 individuals (nT2D = 55,284) from BioBank Japan (BBJ) and UK Biobank. T2D heritability in the low-BMI group was greater than that in the high-BMI group. Polygenic predictions of T2D toward low-BMI targets had pseudo-R2 values that were more than 22% higher than BMI-unstratified targets. Polygenic risk scores (PRSs) from low-BMI discovery outperformed PRSs from high BMI, while PRSs from BMI-unstratified discovery performed best. Pathway-specific PRSs demonstrated the biological contributions of pathogenic pathways. Low-BMI T2D cases showed higher rates of neuropathy and retinopathy. Combining BMI stratification and a method integrating cross-population effects, T2D predictions showed greater than 37% improvements over unstratified-matched-population prediction. We replicated findings in the Tohoku Medical Megabank (n = 26,000) and the second BBJ cohort (n = 33,096). Our findings suggest that target stratification based on existing traits can improve the polygenic prediction of heterogeneous diseases.

Integrated Pleiotropic Gene Set Unveils Comorbidity Insights across Digestive Cancers and Other Diseases

Comorbidities are prevalent in digestive cancers, intensifying patient discomfort and complicating prognosis. Identifying potential comorbidities and investigating their genetic connections in a systemic manner prove to be instrumental in averting additional health challenges during digestive cancer management. Here, we investigated 150 diseases across 18 categories by collecting and integrating various factors related to disease comorbidity, such as disease-associated SNPs or genes from sources like MalaCards, GWAS Catalog and UK Biobank. Through this extensive analysis, we have established an integrated pleiotropic gene set comprising 548 genes in total. Particularly, there enclosed the genes encoding major histocompatibility complex or related to antigen presentation. Additionally, we have unveiled patterns in protein-protein interactions and key hub genes/proteins including TP53, KRAS, CTNNB1 and PIK3CA, which may elucidate the co-occurrence of digestive cancers with certain diseases. These findings provide valuable insights into the molecular origins of comorbidity, offering potential avenues for patient stratification and the development of targeted therapies in clinical trials.

Synergizing drug repurposing and target identification for neurodegenerative diseases

Despite dedicated research efforts, the absence of disease-curing remedies for neurodegenerative diseases (NDDs) continues to jeopardize human society and stands as a challenge. Drug repurposing is an attempt to find new functionality of existing drugs and take it as an opportunity to discourse the clinically unmet need to treat neurodegeneration. However, despite applying this approach to rediscover a drug, it can also be used to identify the target on which a drug could work. The primary objective of target identification is to unravel all the possibilities of detecting a new drug or repurposing an existing drug. Lately, scientists and researchers have been focusing on specific genes, a particular site in DNA, a protein, or a molecule that might be involved in the pathogenesis of the disease. However, the new era discusses directing the signaling mechanism involved in the disease progression, where receptors, ion channels, enzymes, and other carrier molecules play a huge role. This review aims to highlight how target identification can expedite the whole process of drug repurposing. Here, we first spot various target-identification methods and drug-repositioning studies, including drug-target and structure-based identification studies. Moreover, we emphasize various drug repurposing approaches in NDDs, namely, experimental-based, mechanism-based, and in silico approaches. Later, we draw attention to validation techniques and stress on drugs that are currently undergoing clinical trials in NDDs. Lastly, we underscore the future perspective of synergizing drug repurposing and target identification in NDDs and present an unresolved question to address the issue.

Development of phenotyping algorithms for hypertensive disorders of pregnancy (HDP) and their application in more than 22,000 pregnant women

Recently, many phenotyping algorithms for high-throughput cohort identification have been developed. Prospective genome cohort studies are critical resources for precision medicine, but there are many hurdles in the precise cohort identification. Consequently, it is important to develop phenotyping algorithms for cohort data collection. Hypertensive disorders of pregnancy (HDP) is a leading cause of maternal morbidity and mortality. In this study, we developed, applied, and validated rule-based phenotyping algorithms of HDP. Two phenotyping algorithms, algorithms 1 and 2, were developed according to American and Japanese guidelines, and applied into 22,452 pregnant women in the Birth and Three-Generation Cohort Study of the Tohoku Medical Megabank project. To precise cohort identification, we analyzed both structured data (e.g., laboratory and physiological tests) and unstructured clinical notes. The identified subtypes of HDP were validated against reference standards. Algorithms 1 and 2 identified 7.93% and 8.08% of the subjects as having HDP, respectively, along with their HDP subtypes. Our algorithms were high performing with high positive predictive values (0.96 and 0.90 for algorithms 1 and 2, respectively). Overcoming the hurdle of precise cohort identification from large-scale cohort data collection, we achieved both developed and implemented phenotyping algorithms, and precisely identified HDP patients and their subtypes from large-scale cohort data collection.

Emerging applications of machine learning in genomic medicine and healthcare

The integration of artificial intelligence technologies has propelled the progress of clinical and genomic medicine in recent years. The significant increase in computing power has facilitated the ability of artificial intelligence models to analyze and extract features from extensive medical data and images, thereby contributing to the advancement of intelligent diagnostic tools. Artificial intelligence (AI) models have been utilized in the field of personalized medicine to integrate clinical data and genomic information of patients. This integration allows for the identification of customized treatment recommendations, ultimately leading to enhanced patient outcomes. Notwithstanding the notable advancements, the application of artificial intelligence (AI) in the field of medicine is impeded by various obstacles such as the limited availability of clinical and genomic data, the diversity of datasets, ethical implications, and the inconclusive interpretation of AI models' results. In this review, a comprehensive evaluation of multiple machine learning algorithms utilized in the fields of clinical and genomic medicine is conducted. Furthermore, we present an overview of the implementation of artificial intelligence (AI) in the fields of clinical medicine, drug discovery, and genomic medicine. Finally, a number of constraints pertaining to the implementation of artificial intelligence within the healthcare industry are examined.

Non-stenotic fibro-calcific aortic valve as a predictor of myocardial infarction recurrence

BACKGROUND

Patients with acute myocardial infarction (AMI) are at increased risk of recurrent cardiovascular events. Non-stenotic aortic valve fibro-calcific remodeling (AVSc), reflecting systemic damage, may serve as a new marker of risk.

OBJECTIVES

To stratify subgroups of AMI patients with specific probabilities of recurrent AMI and to evaluate the importance of AVSc in this setting.

METHODS

Consecutive AMI patients (n = 2530) were admitted at Centro Cardiologico Monzino (2010-2019) and followed up for 5 years. Patients were divided into study (n = 1070) and test (n = 966) cohorts. Topological data analysis (TDA) was used to stratify patient subgroups, while Kaplan-Meier and Cox regressions analyses were used to evaluate the significance of baseline characteristics.

RESULTS

TDA identified 11 subgroups of AMI patients with specific baseline characteristics. Two subgroups showed the highest rate of reinfarction after 5 years from the indexed AMI with a combined hazard ratio (HR) of 3.8 (95%CI: 2.7-5.4) compared to the other subgroups. This was confirmed in the test cohort (HR = 3.1; 95%CI: 2.2-4.3). These two subgroups were mostly men, with hypertension and dyslipidemia, who exhibit higher prevalence of AVSc, higher levels of high-sensitive c-reactive protein and creatinine. In the year-by-year analysis, AVSc, adjusted for all confounders, showed an independent association with the increased risk of reinfarction (odds ratio of ∼2 at all time-points), in both the study and the test cohorts (all p < 0.01).

CONCLUSIONS

AVSc is a crucial variable for identifying AMI patients at high risk of recurrent AMI and its presence should be considered when assessing the management of AMI patients. The inclusion of AVSc in risk stratification models may improve the accuracy of predicting the likelihood of recurrent AMI, leading to more personalized treatment decisions.

Atopic dermatitis phenotypes based on cluster analysis of the Danish Skin Cohort

BACKGROUND

Despite previous attempts to classify atopic dermatitis (AD) into subtypes (e.g. extrinsic vs. intrinsic), there is a need to better understand specific phenotypes in adulthood.

OBJECTIVES

To identify, using machine learning (ML), adult AD phenotypes.

METHODS

We used unsupervised cluster analysis to identify AD phenotypes by analysing different responses to predetermined variables (age of disease onset, severity, itch and skin pain intensity, flare frequency, anatomical location, presence and/or severity of current comorbidities) in adults with AD from the Danish Skin Cohort.

RESULTS

The unsupervised cluster analysis resulted in five clusters where AD severity most clearly differed. We classified them as 'mild', 'mild-to-moderate', 'moderate', 'severe' and 'very severe'. The severity of multiple predetermined patient-reported outcomes was positively associated with AD, including an increased number of flare-ups and increased flare-up duration and disease severity. However, an increased severity of rhinitis and mental health burden was also found for the mild-to-moderate phenotype.

CONCLUSIONS

ML confirmed the use of disease severity for the categorization of phenotypes, and our cluster analysis provided novel detailed information about how flare patterns and duration are associated with AD disease severity.

A Patient Similarity Network (CHDmap) to Predict Outcomes After Congenital Heart Surgery: Development and Validation Study

Background

Although evidence-based medicine proposes personalized care that considers the best evidence, it still fails to address personal treatment in many real clinical scenarios where the complexity of the situation makes none of the available evidence applicable. "Medicine-based evidence" (MBE), in which big data and machine learning techniques are embraced to derive treatment responses from appropriately matched patients in real-world clinical practice, was proposed. However, many challenges remain in translating this conceptual framework into practice.

Objective

This study aimed to technically translate the MBE conceptual framework into practice and evaluate its performance in providing general decision support services for outcomes after congenital heart disease (CHD) surgery.

Methods

Data from 4774 CHD surgeries were collected. A total of 66 indicators and all diagnoses were extracted from each echocardiographic report using natural language processing technology. Combined with some basic clinical and surgical information, the distances between each patient were measured by a series of calculation formulas. Inspired by structure-mapping theory, the fusion of distances between different dimensions can be modulated by clinical experts. In addition to supporting direct analogical reasoning, a machine learning model can be constructed based on similar patients to provide personalized prediction. A user-operable patient similarity network (PSN) of CHD called CHDmap was proposed and developed to provide general decision support services based on the MBE approach.

Results

Using 256 CHD cases, CHDmap was evaluated on 2 different types of postoperative prognostic prediction tasks: a binary classification task to predict postoperative complications and a multiple classification task to predict mechanical ventilation duration. A simple poll of the k-most similar patients provided by the PSN can achieve better prediction results than the average performance of 3 clinicians. Constructing logistic regression models for prediction using similar patients obtained from the PSN can further improve the performance of the 2 tasks (best area under the receiver operating characteristic curve=0.810 and 0.926, respectively). With the support of CHDmap, clinicians substantially improved their predictive capabilities.

Conclusions

Without individual optimization, CHDmap demonstrates competitive performance compared to clinical experts. In addition, CHDmap has the advantage of enabling clinicians to use their superior cognitive abilities in conjunction with it to make decisions that are sometimes even superior to those made using artificial intelligence models. The MBE approach can be embraced in clinical practice, and its full potential can be realized.

Integrating DNA methylation and gene expression data in a single gene network using the iNETgrate package

Analyzing different omics data types independently is often too restrictive to allow for detection of subtle, but consistent, variations that are coherently supported based upon different assays. Integrating multi-omics data in one model can increase statistical power. However, designing such a model is challenging because different omics are measured at different levels. We developed the iNETgrate package ( https://bioconductor.org/packages/iNETgrate/ ) that efficiently integrates transcriptome and DNA methylation data in a single gene network. Applying iNETgrate on five independent datasets improved prognostication compared to common clinical gold standards and a patient similarity network approach.

Revolutionizing clinical trials: the role of AI in accelerating medical breakthroughs

Clinical trials are the essential assessment for safe, reliable, and effective drug development. Data-related limitations, extensive manual efforts, remote patient monitoring, and the complexity of traditional clinical trials on patients drive the application of Artificial Intelligence (AI) in medical and healthcare organisations. For expeditious and streamlined clinical trials, a personalised AI solution is the best utilisation. AI provides broad utility options through structured, standardised, and digitally driven elements in medical research. The clinical trials are a time-consuming process with patient recruitment, enrolment, frequent monitoring, and medical adherence and retention. With an AI-powered tool, the automated data can be generated and managed for the trial lifecycle with all the records of the medical history of the patient as patient-centric AI. AI can intelligently interpret the data, feed downstream systems, and automatically fill out the required analysis report. This article explains how AI has revolutionised innovative ways of collecting data, biosimulation, and early disease diagnosis for clinical trials and overcomes the challenges more precisely through cost and time reduction, improved efficiency, and improved drug development research with less need for rework. The future implications of AI to accelerate clinical trials are important in medical research because of its fast output and overall utility.

Characteristics of glucolipid metabolism and complications in novel cluster-based diabetes subgroups: a retrospective study

BACKGROUND

Glucolipid metabolism plays an important role in the occurrence and development of diabetes mellitus. However, there is limited research on the characteristics of glucolipid metabolism and complications in different subgroups of newly diagnosed diabetes. This study aimed to investigate the characteristics of glucolipid metabolism and complications in novel cluster-based diabetes subgroups and explore the contributions of different glucolipid metabolism indicators to the occurrence of complications and pancreatic function.

METHODS

This retrospective study included 547 newly diagnosed type 2 diabetes patients. Age, body mass index (BMI), glycated hemoglobin (HbA1C), homeostasis model assessment-2 beta-cell function (HOMA2-β), and homeostasis model assessment-2 insulin resistance (HOMA2-IR) were used as clustering variables. The participants were divided into 4 groups by k-means cluster analysis. The characteristics of glucolipid indicators and complications in each subgroup were analyzed. Regression analyses were used to evaluate the impact of glucolipid metabolism indicators on complications and pancreatic function.

RESULTS

Total cholesterol (TC), triglycerides (TG), triglyceride glucose index (TyG), HbA1C, fasting plasma glucose (FPG), and 2-h postprandial plasma glucose (2hPG) were higher in the severe insulin-resistant diabetes (SIRD) and severe insulin-deficient diabetes (SIDD) groups. Fasting insulin (FINS), fasting C-peptide (FCP), 2-h postprandial insulin (2hINS), 2-h postprandial C-peptide (2hCP), and the monocyte-to-high-density lipoprotein cholesterol ratio (MHR) were higher in mild obesity-related diabetes (MOD) and SIRD. 2hCP, FCP, and FINS were positively correlated with HOMA2-β, while FPG, TyG, HbA1C, and TG were negatively correlated with HOMA2-β. FINS, FPG, FCP, and HbA1C were positively correlated with HOMA2-IR, while high-density lipoprotein (HDL) was negatively correlated with HOMA2-IR. FINS (odds ratio (OR),1.043;95% confidence interval (CI) 1.006 ~ 1.081), FCP (OR,2.881;95%CI 2.041 ~ 4.066), and TyG (OR,1.649;95%CI 1.292 ~ 2.104) contributed to increase the risk of nonalcoholic fatty liver disease (NAFLD); 2hINS (OR,1.015;95%CI 1.008 ~ 1.022) contributed to increase the risk of atherosclerotic cardiovascular disease (ASCVD); FCP (OR,1.297;95%CI 1.027 ~ 1.637) significantly increased the risk of chronic kidney disease (CKD).

CONCLUSIONS

There were differences in the characteristics of glucolipid metabolism as well as complications among different subgroups of newly diagnosed type 2 diabetes. 2hCP, FCP, FINS, FPG, TyG, HbA1C, HDL and TG influenced the function of insulin. FINS, TyG, 2hINS, and FCP were associated with ASCVD, NAFLD, and CKD in newly diagnosed T2DM patients.

[Clinical features and complication rates in type 2 diabetes mellitus clusters on five variables: glycated hemoglobin, age at diagnosis, body mass index, HOMA-IR, HOMA-B]

BACKGROUND

Diabetes mellitus (T2DM) is a serious medical and social problem. Now they are studying the possibility of a new stratification of diabetes. The possibility of cluster analysis for different durations of diabetes, in different cohorts to identify phenotypic clusters of T2DM and validation by reproducing clusters is relevant.

AIM

Identify clusters of type 2 diabetes mellitus in patients with different disease duration based on five variables: HbA1c, age at diagnosis, BMI, HOMA-IR, HOMA-B and study the clinical features and complication rates in each cluster in the Novosibirsk region.

MATERIALS AND METHODS

Cluster analysis of K-means was performed in 2131 patients with T2DM, aged 44 to 70 years, with a duration of diabetes of 6.42±5.66 years, living in the Novosibirsk region based on 5 variables - HbA1c, age at -diagnosis, BMI, HOMA-IR, HOMA-B. All patients a complete clinical and laboratory examination. The insulin resistance index in the HOMA (HOMA-IR, u) and the β-cell function assessment index (HOMA-B) were calculated using the calculator -version 2.2.3 at www.dtu.ox.ac.uk.

RESULTS

Cluster analysis revealed: Cluster 1 included 455 patients with preserved β-cell function (HOMA-B 82.97±23.28%), moderate insulin resistance (HOMA-IR 5.57±4.72) and higher diastolic BP; Cluster 2 in 1658 patients with reduced function of β-cells (HOMA-B 21.71±12.51%), the lowest indices of insulin resistance (HOMA-IR 3.50±2.48) and was characterized by a longer duration of diabetes, high fasting glycemia , HbA1c, higher eGFR and MAU, men compared with women had a 31% higher risk of developing diabetic neuropathy and 28% more diabetic nephropathy; Cluster 3 in 18 patients with high function of β-cells (HOMA-B 228.53±63.32%), severe insulin resistance (HOMA-IR 6.92±4.77), features were high incidence of men, shorter duration of diabetes, lower fasting glycemia and HbA1c, lower diastolic BP and eGFR, high incidence of early development of diabetic retinopathy after 4.00±3.6 years.

CONCLUSION

Cluster analysis in patients with different durations of diabetes mellitus confirmed the possibility of using cluster analysis to identify T2DM phenotypes in the Russian population. The clusters differed in the clinical characteristics of patients, the frequency and risk of diabetic complications. These results have potential value for early stratification of therapy.

Vascular complications of diabetes: A narrative review

Diabetes mellitus is a complex chronic metabolic disease characterized by hyperglycemia and various complications. According to the different pathophysiological mechanisms, these complications can be classified as microvascular or macrovascular complications, which have long-term negative effects on vital organs such as the eyes, kidneys, heart, and brain, and lead to increased patient mortality. Diabetes mellitus is a major global health issue, and its incidence and prevalence have increased significantly in recent years. Moreover, the incidence is expected to continue to rise as more people adopt a Western lifestyle and diet. Thus, it is essential to understand the epidemiology, pathogenesis, risk factors, and treatment of vascular complications to aid patients in managing the disease effectively. This paper provides a comprehensive review of the literature to clarify the above content. Furthermore, this paper also delves into the correlation between novel risk factors, such as long noncoding RNAs, gut microbiota, and nonalcoholic fatty liver disease, with diabetic vascular complications.

Precision subclassification of type 2 diabetes: a systematic review

BACKGROUND

Heterogeneity in type 2 diabetes presentation and progression suggests that precision medicine interventions could improve clinical outcomes. We undertook a systematic review to determine whether strategies to subclassify type 2 diabetes were associated with high quality evidence, reproducible results and improved outcomes for patients.

METHODS

We searched PubMed and Embase for publications that used 'simple subclassification' approaches using simple categorisation of clinical characteristics, or 'complex subclassification' approaches which used machine learning or 'omics approaches in people with established type 2 diabetes. We excluded other diabetes subtypes and those predicting incident type 2 diabetes. We assessed quality, reproducibility and clinical relevance of extracted full-text articles and qualitatively synthesised a summary of subclassification approaches.

RESULTS

Here we show data from 51 studies that demonstrate many simple stratification approaches, but none have been replicated and many are not associated with meaningful clinical outcomes. Complex stratification was reviewed in 62 studies and produced reproducible subtypes of type 2 diabetes that are associated with outcomes. Both approaches require a higher grade of evidence but support the premise that type 2 diabetes can be subclassified into clinically meaningful subtypes.

CONCLUSION

Critical next steps toward clinical implementation are to test whether subtypes exist in more diverse ancestries and whether tailoring interventions to subtypes will improve outcomes.

ExpertNet: A Deep Learning Approach to Combined Risk Modeling and Subtyping in Intensive Care Units

Risk models play a crucial role in disease prevention, particularly in intensive care units (ICUs). Diseases often have complex manifestations with heterogeneous subpopulations, or subtypes, that exhibit distinct clinical characteristics. Risk models that explicitly model subtypes have high predictive accuracy and facilitate subtype-specific personalization. Such models combine clustering and classification methods but do not effectively utilize the inferred subtypes in risk modeling. Their limitations include tendency to obtain degenerate clusters and cluster-specific data scarcity leading to insufficient training data for the corresponding classifier. In this article, we develop a new deep learning model for simultaneous clustering and classification, ExpertNet, with novel loss terms and network training strategies that address these limitations. The performance of ExpertNet is evaluated on the tasks of predicting risk of (i) sepsis and (ii) acute respiratory distress syndrome (ARDS), using two large electronic medical records datasets from ICUs. Our extensive experiments show that, in comparison to state-of-the-art baselines for combined clustering and classification, ExpertNet achieves superior accuracy in risk prediction for both ARDS and sepsis; and comparable clustering performance. Visual analysis of the clusters further demonstrates that the clusters obtained are clinically meaningful and a knowledge-distilled model shows significant differences in risk factors across the subtypes. By addressing technical challenges in training neural networks for simultaneous clustering and classification, ExpertNet lays the algorithmic foundation for the future development of subtype-aware risk models.

MicroRNA-disease Network Analysis Repurposes Methotrexate for the Treatment of Abdominal Aortic Aneurysm in Mice

Abdominal aortic aneurysm (AAA) is a permanent dilatation of the abdominal aorta and is highly lethal. The main purpose of the current study is to search for noninvasive medical therapies for AAA, for which there is currently no effective drug therapy. Network medicine represents a cutting-edge technology, as analysis and modeling of disease networks can provide critical clues regarding the etiology of specific diseases and therapeutics that may be effective. Here, we proposed a novel algorithm to quantify disease relations based on a large accumulated microRNA-disease association dataset and then built a disease network covering 15 disease classes and 304 diseases. Analysis revealed some patterns for these diseases. For instance, diseases tended to be clustered and coherent in the network. Surprisingly, we found that AAA showed the strongest similarity with rheumatoid arthritis and systemic lupus erythematosus, both of which are autoimmune diseases, suggesting that AAA could be one type of autoimmune diseases in etiology. Based on this observation, we further hypothesized that drugs for autoimmune diseases could be repurposed for the prevention and therapy of AAA. Finally, animal experiments confirmed that methotrexate, a drug for autoimmune diseases, was able to alleviate the formation and development of AAA.

Deep learning on electronic medical records identifies distinct subphenotypes of diabetic kidney disease driven by genetic variations in the Rho pathway

Kidney disease affects 50% of all diabetic patients; however, prediction of disease progression has been challenging due to inherent disease heterogeneity. We use deep learning to identify novel genetic signatures prognostically associated with outcomes. Using autoencoders and unsupervised clustering of electronic health record data on 1,372 diabetic kidney disease patients, we establish two clusters with differential prevalence of end-stage kidney disease. Exome-wide associations identify a novel variant in ARHGEF18, a Rho guanine exchange factor specifically expressed in glomeruli. Overexpression of ARHGEF18 in human podocytes leads to impairments in focal adhesion architecture, cytoskeletal dynamics, cellular motility, and RhoA/Rac1 activation. Mutant GEF18 is resistant to ubiquitin mediated degradation leading to pathologically increased protein levels. Our findings uncover the first known disease-causing genetic variant that affects protein stability of a cytoskeletal regulator through impaired degradation, a potentially novel class of expression quantitative trait loci that can be therapeutically targeted.

Quantile regression for nonignorable missing data with its application of analyzing electronic medical records

Over the past decade, there has been growing enthusiasm for using electronic medical records (EMRs) for biomedical research. Quantile regression estimates distributional associations, providing unique insights into the intricacies and heterogeneity of the EMR data. However, the widespread nonignorable missing observations in EMR often obscure the true associations and challenge its potential for robust biomedical discoveries. We propose a novel method to estimate the covariate effects in the presence of nonignorable missing responses under quantile regression. This method imposes no parametric specifications on response distributions, which subtly uses implicit distributions induced by the corresponding quantile regression models. We show that the proposed estimator is consistent and asymptotically normal. We also provide an efficient algorithm to obtain the proposed estimate and a randomly weighted bootstrap approach for statistical inferences. Numerical studies, including an empirical analysis of real-world EMR data, are used to assess the proposed method's finite-sample performance compared to existing literature.

"iNETgrate": integrating DNA methylation and gene expression data in a single gene network

Integrating multi-omics data in one model can increase statistical power. However, designing such a model is challenging because different omics are measured at different levels. We developed the iNETgrate package (https://bioconductor.org/packages/iNETgrate/) that efficiently integrates transcriptome and DNA methylation data in a single gene network. Applying iNETgrate on five independent datasets improved prognostication compared to common clinical gold standards and a patient similarity network approach.

Machine learning in cardiology: Clinical application and basic research

Machine learning is a subfield of artificial intelligence. The quality and versatility of machine learning have been rapidly improving and playing a critical role in many aspects of social life. This trend is also observed in the medical field. Generally, there are three main types of machine learning: supervised, unsupervised, and reinforcement learning. Each type of learning is adequately selected for the purpose and type of data. In the field of medicine, various types of information are collected and used, and research using machine learning is becoming increasingly relevant. Many clinical studies are conducted using electronic health and medical records, including in the cardiovascular area. Machine learning has also been applied in basic research. Machine learning has been widely used for several types of data analysis, such as clustering of microarray analysis and RNA sequence analysis. Machine learning is essential for genome and multi-omics analyses. This review summarizes the recent advancements in the use of machine learning in clinical applications and basic cardiovascular research.

Topological data analysis for revealing dynamic brain reconfiguration in MEG data

In recent years, the focus of the functional connectivity community has shifted from stationary approaches to the ones that include temporal dynamics. Especially, non-invasive electrophysiological data (magnetoencephalography/electroencephalography (MEG/EEG)) with high temporal resolution and good spatial coverage have made it possible to measure the fast alterations in the neural activity in the brain during ongoing cognition. In this article, we analyze dynamic brain reconfiguration using MEG images collected from subjects during the rest and the cognitive tasks. Our proposed topological data analysis method, called Mapper, produces biomarkers that differentiate cognitive tasks without prior spatial and temporal collapse of the data. The suggested method provides an interactive visualization of the rapid fluctuations in electrophysiological data during motor and cognitive tasks; hence, it has the potential to extract clinically relevant information at an individual level without temporal and spatial collapse.

Stratification of diabetes in the context of comorbidities, using representation learning and topological data analysis

Diabetes is a heterogenous, multimorbid disorder with a large variation in manifestations, trajectories, and outcomes. The aim of this study is to validate a novel machine learning method for the phenotyping of diabetes in the context of comorbidities. Data from 9967 multimorbid patients with a new diagnosis of diabetes were extracted from Clinical Practice Research Datalink. First, using BEHRT (a transformer-based deep learning architecture), the embeddings corresponding to diabetes were learned. Next, topological data analysis (TDA) was carried out to test how different areas in high-dimensional manifold correspond to different risk profiles. The following endpoints were considered when profiling risk trajectories: major adverse cardiovascular events (MACE), coronary artery disease (CAD), stroke (CVA), heart failure (HF), renal failure (RF), diabetic neuropathy, peripheral arterial disease, reduced visual acuity and all-cause mortality. Kaplan Meier curves were plotted for each derived phenotype. Finally, we tested the performance of an established risk prediction model (QRISK) by adding TDA-derived features. We identified four subgroups of patients with diabetes and divergent comorbidity patterns differing in their risk of future cardiovascular, renal, and other microvascular outcomes. Phenotype 1 (young with chronic inflammatory conditions) and phenotype 2 (young with CAD) included relatively younger patients with diabetes compared to phenotypes 3 (older with hypertension and renal disease) and 4 (older with previous CVA), and those subgroups had a higher frequency of pre-existing cardio-renal diseases. Within ten years of follow-up, 2592 patients (26%) experienced MACE, 2515 patients (25%) died, and 2020 patients (20%) suffered RF. QRISK3 model's AUC was augmented from 67.26% (CI 67.25-67.28%) to 67.67% (CI 67.66-67.69%) by adding specific TDA-derived phenotype and the distances to both extremities of the TDA graph improving its performance in the prediction of CV outcomes. We confirmed the importance of accounting for multimorbidity when risk stratifying heterogenous cohort of patients with new diagnosis of diabetes. Our unsupervised machine learning method improved the prediction of clinical outcomes.

Identifying subgroups of patients with type 2 diabetes based on real-world traditional chinese medicine electronic medical records

Introduction: Type 2 diabetes (T2D) is a multifactorial complex chronic disease with a high prevalence worldwide, and Type 2 diabetes patients with different comorbidities often present multiple phenotypes in the clinic. Thus, there is a pressing need to improve understanding of the complexity of the clinical Type 2 diabetes population to help identify more accurate disease subtypes for personalized treatment. Methods: Here, utilizing the traditional Chinese medicine (TCM) clinical electronic medical records (EMRs) of 2137 Type 2 diabetes inpatients, we followed a heterogeneous medical record network (HEMnet) framework to construct heterogeneous medical record networks by integrating the clinical features from the electronic medical records, molecular interaction networks and domain knowledge. Results: Of the 2137 Type 2 diabetes patients, 1347 were male (63.03%), and 790 were female (36.97%). Using the HEMnet method, we obtained eight non-overlapping patient subgroups. For example, in H3, Poria, Astragali Radix, Glycyrrhizae Radix et Rhizoma, Cinnamomi Ramulus, and Liriopes Radix were identified as significant botanical drugs. Cardiovascular diseases (CVDs) were found to be significant comorbidities. Furthermore, enrichment analysis showed that there were six overlapping pathways and eight overlapping Gene Ontology terms among the herbs, comorbidities, and Type 2 diabetes in H3. Discussion: Our results demonstrate that identification of the Type 2 diabetes subgroup based on the HEMnet method can provide important guidance for the clinical use of herbal prescriptions and that this method can be used for other complex diseases.

Heterogeneity in Early Postpartum Metabolic Profiles Among Women with GDM Who Progressed to Type 2 Diabetes During 10-Year Follow-Up: The SWIFT Study

GDM is a strong risk factor for progression to T2D after pregnancy. Although both GDM and T2D exhibit heterogeneity, the link between the distinct heterogeneity of GDM and incident T2D has not been established. Herein, we evaluate early postpartum profiles of women with recent GDM who later developed incident T2D using a soft clustering method, followed by the integration of both clinical phenotypic variables and metabolomics to characterize these heterogeneous clusters/groups clinically and their molecular mechanisms. We identified three clusters based on two indices of glucose homeostasis at 6-9 weeks postpartum - HOMA-IR and HOMA-B among women who developed incident T2D during the 12-year follow-up. The clusters were classified as follows: pancreatic beta-cell dysfunction group (cluster-1), insulin resistant group (cluster-3), and a combination of both phenomena (cluster-2) comprising the majority of T2D. We also identified postnatal blood test parameters to distinguish the three clusters for clinical testing. Moreover, we compared these three clusters in their metabolomics profiles at the early stage of the disease to identify the mechanistic insights. A significantly higher concentration of a metabolite at the early stage of a T2D cluster than other clusters indicates its essentiality for the particular disease character. As such, the early-stage characters of T2D cluster-1 pathology include a higher concentration of sphingolipids, acyl-alkyl phosphatidylcholines, lysophosphatidylcholines, and glycine, indicating their essentiality for pancreatic beta-cell function. In contrast, the early-stage characteristics of T2D cluster-3 pathology include a higher concentration of diacyl phosphatidylcholines, acyl-carnitines, isoleucine, and glutamate, indicating their essentiality for insulin actions. Notably, all these biomolecules are found in the T2D cluster-2 with mediocre concentrations, indicating a true nature of a mixed group. In conclusion, we have deconstructed incident T2D heterogeneity and identified three clusters with their clinical testing procedures and molecular mechanisms. This information will aid in adopting proper interventions using a precision medicine approach.

Diabetes and climate change: current evidence and implications for people with diabetes, clinicians and policy stakeholders

Climate change will be a major challenge for the world's health systems in the coming decades. Elevated temperatures and increasing frequencies of heat waves, wildfires, heavy precipitation and other weather extremes can affect health in many ways, especially if chronic diseases are already present. Impaired responses to heat stress, including compromised vasodilation and sweating, diabetes-related comorbidities, insulin resistance and chronic low-grade inflammation make people with diabetes particularly vulnerable to environmental risk factors, such as extreme weather events and air pollution. Additionally, multiple pathogens show an increased rate of transmission under conditions of climate change and people with diabetes have an altered immune system, which increases the risk for a worse course of infectious diseases. In this review, we summarise recent studies on the impact of climate-change-associated risk for people with diabetes and discuss which individuals may be specifically prone to these risk conditions due to their clinical features. Knowledge of such high-risk groups will help to develop and implement tailored prevention and management strategies to mitigate the detrimental effect of climate change on the health of people with diabetes.

Artificial Intelligence Technologies in Cardiology

As the world produces exabytes of data, there is a growing need to find new methods that are more suitable for dealing with complex datasets. Artificial intelligence (AI) has significant potential to impact the healthcare industry, which is already on the road to change with the digital transformation of vast quantities of information. The implementation of AI has already achieved success in the domains of molecular chemistry and drug discoveries. The reduction in costs and in the time needed for experiments to predict the pharmacological activities of new molecules is a milestone in science. These successful applications of AI algorithms provide hope for a revolution in healthcare systems. A significant part of artificial intelligence is machine learning (ML), of which there are three main types-supervised learning, unsupervised learning, and reinforcement learning. In this review, the full scope of the AI workflow is presented, with explanations of the most-often-used ML algorithms and descriptions of performance metrics for both regression and classification. A brief introduction to explainable artificial intelligence (XAI) is provided, with examples of technologies that have developed for XAI. We review important AI implementations in cardiology for supervised, unsupervised, and reinforcement learning and natural language processing, emphasizing the used algorithm. Finally, we discuss the need to establish legal, ethical, and methodical requirements for the deployment of AI models in medicine.

The high-dimensional space of human diseases built from diagnosis records and mapped to genetic loci

Human diseases are traditionally studied as singular, independent entities, limiting researchers' capacity to view human illnesses as dependent states in a complex, homeostatic system. Here, using time-stamped clinical records of over 151 million unique Americans, we construct a disease representation as points in a continuous, high-dimensional space, where diseases with similar etiology and manifestations lie near one another. We use the UK Biobank cohort, with half a million participants, to perform a genome-wide association study of newly defined human quantitative traits reflecting individuals' health states, corresponding to patient positions in our disease space. We discover 116 genetic associations involving 108 genetic loci and then use ten disease constellations resulting from clustering analysis of diseases in the embedding space, as well as 30 common diseases, to demonstrate that these genetic associations can be used to robustly predict various morbidities.

Genomics data analysis via spectral shape and topology

Mapper, a topological algorithm, is frequently used as an exploratory tool to build a graphical representation of data. This representation can help to gain a better understanding of the intrinsic shape of high-dimensional genomic data and to retain information that may be lost using standard dimension-reduction algorithms. We propose a novel workflow to process and analyze RNA-seq data from tumor and healthy subjects integrating Mapper, differential gene expression, and spectral shape analysis. Precisely, we show that a Gaussian mixture approximation method can be used to produce graphical structures that successfully separate tumor and healthy subjects, and produce two subgroups of tumor subjects. A further analysis using DESeq2, a popular tool for the detection of differentially expressed genes, shows that these two subgroups of tumor cells bear two distinct gene regulations, suggesting two discrete paths for forming lung cancer, which could not be highlighted by other popular clustering methods, including t-distributed stochastic neighbor embedding (t-SNE). Although Mapper shows promise in analyzing high-dimensional data, tools to statistically analyze Mapper graphical structures are limited in the existing literature. In this paper, we develop a scoring method using heat kernel signatures that provides an empirical setting for statistical inferences such as hypothesis testing, sensitivity analysis, and correlation analysis.

A machine learning model identifies patients in need of autoimmune disease testing using electronic health records

Systemic autoimmune rheumatic diseases (SARDs) can lead to irreversible damage if left untreated, yet these patients often endure long diagnostic journeys before being diagnosed and treated. Machine learning may help overcome the challenges of diagnosing SARDs and inform clinical decision-making. Here, we developed and tested a machine learning model to identify patients who should receive rheumatological evaluation for SARDs using longitudinal electronic health records of 161,584 individuals from two institutions. The model demonstrated high performance for predicting cases of autoantibody-tested individuals in a validation set, an external test set, and an independent cohort with a broader case definition. This approach identified more individuals for autoantibody testing compared with current clinical standards and a greater proportion of autoantibody carriers among those tested. Diagnoses of SARDs and other autoimmune conditions increased with higher model probabilities. The model detected a need for autoantibody testing and rheumatology encounters up to five years before the test date and assessment date, respectively. Altogether, these findings illustrate that the clinical manifestations of a diverse array of autoimmune conditions are detectable in electronic health records using machine learning, which may help systematize and accelerate autoimmune testing.

Systematic review of precision subclassification of type 2 diabetes

Heterogeneity in type 2 diabetes presentation, progression and treatment has the potential for precision medicine interventions that can enhance care and outcomes for affected individuals. We undertook a systematic review to ascertain whether strategies to subclassify type 2 diabetes are associated with improved clinical outcomes, show reproducibility and have high quality evidence. We reviewed publications that deployed 'simple subclassification' using clinical features, biomarkers, imaging or other routinely available parameters or 'complex subclassification' approaches that used machine learning and/or genomic data. We found that simple stratification approaches, for example, stratification based on age, body mass index or lipid profiles, had been widely used, but no strategy had been replicated and many lacked association with meaningful outcomes. Complex stratification using clustering of simple clinical data with and without genetic data did show reproducible subtypes of diabetes that had been associated with outcomes such as cardiovascular disease and/or mortality. Both approaches require a higher grade of evidence but support the premise that type 2 diabetes can be subclassified into meaningful groups. More studies are needed to test these subclassifications in more diverse ancestries and prove that they are amenable to interventions.

Subtypes of type 2 diabetes and their association with outcomes in Korean adults - A cluster analysis of community-based prospective cohort

BACKGROUND

Little is known about the subtypes of type 2 diabetes (T2D) and their association with clinical outcomes in Asians.

METHODS

We performed data-driven cluster analysis in patients with newly diagnosed drug-naive T2D (n = 756) from the Korean Genome and Epidemiology Study. Clusters were based on five variables (age at diagnosis, BMI, HbA1c, and HOMA2 β-cell function, and insulin resistance).

RESULTS

We identified four clusters of patients with T2D according to k-means clustering: cluster 1 (22.4 %, severe insulin-resistant diabetes [SIRD]), cluster 2 (32.7 %, mild age-related diabetes [MARD]), cluster 3 (32.7 %, mild obesity-related diabetes [MOD]), and cluster 4 (12.3 %, severe insulin-deficient diabetes [SIDD]). During 14 years of follow-up, individuals in the SIDD cluster had the highest risk of initiation of glucose-lowering therapy compared to individuals in the other three clusters. Individuals in the MARD and SIDD clusters showed the highest risk of chronic kidney disease and cardiovascular disease, and individuals in the MOD clusters showed the lowest risk after adjusting for other risk factors (P < 0.05).

CONCLUSIONS

Patients with T2D can be categorized into four subgroups with different glycemic deterioration and risks of diabetes complications. Individualized management might be helpful for better clinical outcomes in Asian patients with different T2D subgroups.

A cardiologist's guide to machine learning in cardiovascular disease prognosis prediction

A modern-day physician is faced with a vast abundance of clinical and scientific data, by far surpassing the capabilities of the human mind. Until the last decade, advances in data availability have not been accompanied by analytical approaches. The advent of machine learning (ML) algorithms might improve the interpretation of complex data and should help to translate the near endless amount of data into clinical decision-making. ML has become part of our everyday practice and might even further change modern-day medicine. It is important to acknowledge the role of ML in prognosis prediction of cardiovascular disease. The present review aims on preparing the modern physician and researcher for the challenges that ML might bring, explaining basic concepts but also caveats that might arise when using these methods. Further, a brief overview of current established classical and emerging concepts of ML disease prediction in the fields of omics, imaging and basic science is presented.