Analysis of disease comorbidity patterns in a large-scale China population

Simplicity within biological complexity

Motivation

Heterogeneous, interconnected, systems-level, molecular (multi-omic) data have become increasingly available and key in precision medicine. We need to utilize them to better stratify patients into risk groups, discover new biomarkers and targets, repurpose known and discover new drugs to personalize medical treatment. Existing methodologies are limited and a paradigm shift is needed to achieve quantitative and qualitative breakthroughs.

Results

In this perspective paper, we survey the literature and argue for the development of a comprehensive, general framework for embedding of multi-scale molecular network data that would enable their explainable exploitation in precision medicine in linear time. Network embedding methods (also called graph representation learning) map nodes to points in low-dimensional space, so that proximity in the learned space reflects the network's topology-function relationships. They have recently achieved unprecedented performance on hard problems of utilizing few omic data in various biomedical applications. However, research thus far has been limited to special variants of the problems and data, with the performance depending on the underlying topology-function network biology hypotheses, the biomedical applications, and evaluation metrics. The availability of multi-omic data, modern graph embedding paradigms and compute power call for a creation and training of efficient, explainable and controllable models, having no potentially dangerous, unexpected behaviour, that make a qualitative breakthrough. We propose to develop a general, comprehensive embedding framework for multi-omic network data, from models to efficient and scalable software implementation, and to apply it to biomedical informatics, focusing on precision medicine and personalized drug discovery. It will lead to a paradigm shift in the computational and biomedical understanding of data and diseases that will open up ways to solve some of the major bottlenecks in precision medicine and other domains.

Disease Network-Based Approaches to Study Comorbidity in Heart Failure: Current State and Future Perspectives

PURPOSE OF REVIEW

Heart failure (HF) is often accompanied by a constellation of comorbidities, leading to diverse patient presentations and clinical trajectories. While traditional methods have provided valuable insights into our understanding of HF, network medicine approaches seek to leverage these complex relationships by analyzing disease at a systems level. This review introduces the concepts of network medicine and explores the use of comorbidity networks to study HF and heart disease.

RECENT FINDINGS

Comorbidity networks are used to understand disease trajectories, predict outcomes, and uncover potential molecular mechanisms through identification of genes and pathways relevant to comorbidity. These networks have shown the importance of non-cardiovascular comorbidities to the clinical journey of patients with HF. However, the community should be aware of important limitations in developing and implementing these methods. Network approaches hold promise for unraveling the impact of comorbidities in the complex presentation and genetics of HF. Methods that consider comorbidity presence and timing have the potential to help optimize management strategies and identify pathophysiological mechanisms.

The first comorbidity networks in companion dogs in the Dog Aging Project

Comorbidity and its association with age are of great interest in geroscience. However, there are few model organisms that are well-suited to study comorbidities that will have high relevance to humans. In this light, we turn our attention to the companion dog. The companion dog shares many morbidities with humans. Thus, a better understanding of canine comorbidity relationships could benefit both humans and dogs. We present an analysis of canine comorbidity networks from the Dog Aging Project, a large epidemiological cohort study of companion dogs in the United States. We included owner-reported health conditions that occurred in at least 60 dogs (n=166) and included only dogs that had at least one of those health conditions (n=26,523). We constructed an undirected comorbidity network using a Poisson binomial test, adjusting for age, sex, sterilization status, breed background (i.e., purebred vs. mixed-breed), and weight. The comorbidity network reveals well-documented comorbidities, such as diabetes with blindness and hypertension with chronic kidney disease. In addition, this network also supports less well-studied comorbidity relationships, such as proteinuria with anemia. A directed comorbidity network accounting for time of reported condition onset suggests that diabetes occurs before cataracts, which is consistent with the canine literature. Analysis of age-stratified networks reveals that global centrality measures increase with age and are the highest in the Senior group compared to the Young Adult and Mature Adult groups. Our results suggest that comorbidity network analysis is a promising method to enhance clinical knowledge and canine healthcare management.

"Using network analysis modularity to group health code systems and decrease dimensionality in machine learning models"

Background

Machine learning (ML) prediction models in healthcare and pharmacy-related research face challenges with encoding high-dimensional Healthcare Coding Systems (HCSs) such as ICD, ATC, and DRG codes, given the trade-off between reducing model dimensionality and minimizing information loss.

Objectives

To investigate using Network Analysis modularity as a method to group HCSs to improve encoding in ML models.

Methods

The MIMIC-III dataset was utilized to create a multimorbidity network in which ICD-9 codes are the nodes and the edges are the number of patients sharing the same ICD-9 code pairs. A modularity detection algorithm was applied using different resolution thresholds to generate 6 sets of modules. The impact of four grouping strategies on the performance of predicting 90-day Intensive Care Unit readmissions was assessed. The grouping strategies compared: 1) binary encoding of codes, 2) encoding codes grouped by network modules, 3) grouping codes to the highest level of ICD-9 hierarchy, and 4) grouping using the single-level Clinical Classification Software (CCS). The same methodology was also applied to encode DRG codes but limiting the comparison to a single modularity threshold to binary encoding.The performance was assessed using Logistic Regression, Support Vector Machine with a non-linear kernel, and Gradient Boosting Machines algorithms. Accuracy, Precision, Recall, AUC, and F1-score with 95% confidence intervals were reported.

Results

Models utilized modularity encoding outperformed ungrouped codes binary encoding models. The accuracy improved across all algorithms ranging from 0.736 to 0.78 for the modularity encoding, to 0.727 to 0.779 for binary encoding. AUC, recall, and precision also improved across almost all algorithms. In comparison with other grouping approaches, modularity encoding generally showed slightly higher performance in AUC, ranging from 0.813 to 0.837, and precision, ranging from 0.752 to 0.782.

Conclusions

Modularity encoding enhances the performance of ML models in pharmacy research by effectively reducing dimensionality and retaining necessary information. Across the three algorithms used, models utilizing modularity encoding showed superior or comparable performance to other encoding approaches. Modularity encoding introduces other advantages such as it can be used for both hierarchical and non-hierarchical HCSs, the approach is clinically relevant, and can enhance ML models' clinical interpretation. A Python package has been developed to facilitate the use of the approach for future research.

Applying precision medicine principles to the management of multimorbidity: the utility of comorbidity networks, graph machine learning, and knowledge graphs

The current management of patients with multimorbidity is suboptimal, with either a single-disease approach to care or treatment guideline adaptations that result in poor adherence due to their complexity. Although this has resulted in calls for more holistic and personalized approaches to prescribing, progress toward these goals has remained slow. With the rapid advancement of machine learning (ML) methods, promising approaches now also exist to accelerate the advance of precision medicine in multimorbidity. These include analyzing disease comorbidity networks, using knowledge graphs that integrate knowledge from different medical domains, and applying network analysis and graph ML. Multimorbidity disease networks have been used to improve disease diagnosis, treatment recommendations, and patient prognosis. Knowledge graphs that combine different medical entities connected by multiple relationship types integrate data from different sources, allowing for complex interactions and creating a continuous flow of information. Network analysis and graph ML can then extract the topology and structure of networks and reveal hidden properties, including disease phenotypes, network hubs, and pathways; predict drugs for repurposing; and determine safe and more holistic treatments. In this article, we describe the basic concepts of creating bipartite and unipartite disease and patient networks and review the use of knowledge graphs, graph algorithms, graph embedding methods, and graph ML within the context of multimorbidity. Specifically, we provide an overview of the application of graph theory for studying multimorbidity, the methods employed to extract knowledge from graphs, and examples of the application of disease networks for determining the structure and pathways of multimorbidity, identifying disease phenotypes, predicting health outcomes, and selecting safe and effective treatments. In today's modern data-hungry, ML-focused world, such network-based techniques are likely to be at the forefront of developing robust clinical decision support tools for safer and more holistic approaches to treating older patients with multimorbidity.

A scoping review finds a growing trend in studies validating multimorbidity patterns and identifies five broad types of validation methods

OBJECTIVES

Multimorbidity, the presence of two or more long-term conditions, is a growing public health concern. Many studies use analytical methods to discover multimorbidity patterns from data. We aimed to review approaches used in published literature to validate these patterns.

STUDY DESIGN AND SETTING

We systematically searched PubMed and Web of Science for studies published between July 2017 and July 2023 that used analytical methods to discover multimorbidity patterns.

RESULTS

Out of 31,617 studies returned by the searches, 172 were included. Of these, 111 studies (64%) conducted validation, the number of studies with validation increased from 53.13% (17 out of 32 studies) to 71.25% (57 out of 80 studies) in 2017-2019 to 2022-2023, respectively. Five types of validation were identified: assessing the association of multimorbidity patterns with clinical outcomes (n = 79), stability across subsamples (n = 26), clinical plausibility (n = 22), stability across methods (n = 7) and exploring common determinants (n = 2). Some studies used multiple types of validation.

CONCLUSION

The number of studies conducting a validation of multimorbidity patterns is clearly increasing. The most popular validation approach is assessing the association of multimorbidity patterns with clinical outcomes. Methodological guidance on the validation of multimorbidity patterns is needed.

Comorbidity Patterns in Patients Newly Diagnosed With Colorectal Cancer: Network-Based Study

BACKGROUND

Patients with colorectal cancer (CRC) often present with multiple comorbidities, and many of these can affect treatment and survival. However, previous comorbidity studies primarily focused on diseases in commonly used comorbidity indices. The comorbid status of CRC patients with respect to the entire spectrum of chronic diseases has not yet been investigated.

OBJECTIVE

This study aimed to systematically analyze all chronic diagnoses and diseases co-occurring, using a network-based approach and large-scale administrative health data, and provide a complete picture of the comorbidity pattern in patients newly diagnosed with CRC from southwest China.

METHODS

In this retrospective observational study, the hospital discharge records of 678 hospitals from 2015 to 2020 in Sichuan Province, China were used to identify new CRC cases in 2020 and their history of diseases. We examined all chronic diagnoses using ICD-10 (International Classification of Diseases, 10th Revision) codes at 3 digits and focused on chronic diseases with >1% prevalence in at least one subgroup (1-sided test, P<.025), which resulted in a total of 66 chronic diseases. Phenotypic comorbidity networks were constructed across all CRC patients and different subgroups by sex, age (18-59, 60-69, 70-79, and ≥80 years), area (urban and rural), and cancer site (colon and rectum), with comorbidity as a node and linkages representing significant correlations between multiple comorbidities.

RESULTS

A total of 29,610 new CRC cases occurred in Sichuan, China in 2020. The mean patient age at diagnosis was 65.6 (SD 12.9) years, and 75.5% (22,369/29,610) had at least one comorbidity. The most prevalent comorbidities were hypertension (8581/29,610, 29.0%; 95% CI 28.5%-29.5%), hyperplasia of the prostate (3816/17,426, 21.9%; 95% CI 21.3%-22.5%), and chronic obstructive pulmonary disease (COPD; 4199/29,610, 14.2%; 95% CI 13.8%-14.6%). The prevalence of single comorbidities was different in each subgroup in most cases. Comorbidities were closely associated, with disorders of lipoprotein metabolism and hyperplasia of the prostate mediating correlations between other comorbidities. Males and females shared 58.3% (141/242) of disease pairs, whereas male-female disparities occurred primarily in diseases coexisting with COPD, cerebrovascular diseases, atherosclerosis, heart failure, or renal failure among males and with osteoporosis or gonarthrosis among females. Urban patients generally had more comorbidities with higher prevalence and more complex disease coexistence relationships, whereas rural patients were more likely to have co-existing severe diseases, such as heart failure comorbid with the sequelae of cerebrovascular disease or COPD.

CONCLUSIONS

Male-female and urban-rural disparities in the prevalence of single comorbidities and their complex coexistence relationships in new CRC cases were not due to simple coincidence. The results reflect clinical practice in CRC patients and emphasize the importance of measuring comorbidity patterns in terms of individual and coexisting diseases in order to better understand comorbidity patterns.

Single-label machine learning classification revealed some hidden but inter-related causes of five psychotic disorder diseases

Psychotic disorder diseases (PDD) or mental illnesses are group of illnesses that affect the minds and impair the cognitive ability, retard emotional ability and obstruct the process of communication and relationship with others and are characterized by delusions, hallucinations and disoriented or disordered pattern of thinking. Prognosis of PDD is not sufficient because of the nature of the diseases and as such adequate form of diagnosis is required to detect, manage and treat the illness. This paper applied the single-label classification (SLC) machine learning approach in mining of electronic health records of people with PDD in Nigeria using eleven independent (demographic) variables and five PDD as target variables. The five PDDs are Insomnia, Schizophrenia, Minimal Brain dysfunction (MBD), which is also known as Attention-Deficit/Hyperactivity Disorder (ADHD), Vascular Dementia (VD) and Bipolar Disorder (BD). The aim of using SLC is that it would be easier to detect some PDDs that are related to each other without the loss of information, which is a plus over multi-label classification (MLC). ReliefF algorithm was used at each experiment to precipitate the order of importance of the independent variables and redundant variables were excluded from the analysis. The order of the variables in feature selection was matched with feature importance after the classifications and quantified using the Spearman rank correlation coefficient. The data was divided into: 70% for training and 30% for testing. Four new performance metrics adapted from the root mean square (RMSE) were proposed and used to measure the differences between the performance results of the 10 Machine learning models in terms of the training and testing and secondly, feature and without feature selection. The new metrics are close to zero which is an indication that the use of feature selection and cross validation may not greatly affects the accuracy of the SLC. When the PDDs are included as predictors for classifying others, there was a tremendous improvement as revealed by the four new metrics for classification accuracy (CA), precision and recall. Analysis of variance showed the four different metrics differs significantly for classification accuracy (CA) and precision. However, there were no significant difference between the CA and precision when the duo are compared together across the four evaluation metrics at p value less than 0.05.

A network medicine approach to study comorbidities in heart failure with preserved ejection fraction

BACKGROUND

Comorbidities are expected to impact the pathophysiology of heart failure (HF) with preserved ejection fraction (HFpEF). However, comorbidity profiles are usually reduced to a few comorbid disorders. Systems medicine approaches can model phenome-wide comorbidity profiles to improve our understanding of HFpEF and infer associated genetic profiles.

METHODS

We retrospectively explored 569 comorbidities in 29,047 HF patients, including 8062 HFpEF and 6585 HF with reduced ejection fraction (HFrEF) patients from a German university hospital. We assessed differences in comorbidity profiles between HF subtypes via multiple correspondence analysis. Then, we used machine learning classifiers to identify distinctive comorbidity profiles of HFpEF and HFrEF patients. Moreover, we built a comorbidity network (HFnet) to identify the main disease clusters that summarized the phenome-wide comorbidity. Lastly, we predicted novel gene candidates for HFpEF by linking the HFnet to a multilayer gene network, integrating multiple databases. To corroborate HFpEF candidate genes, we collected transcriptomic data in a murine HFpEF model. We compared predicted genes with the murine disease signature as well as with the literature.

RESULTS

We found a high degree of variance between the comorbidity profiles of HFpEF and HFrEF, while each was more similar to HFmrEF. The comorbidities present in HFpEF patients were more diverse than those in HFrEF and included neoplastic, osteologic and rheumatoid disorders. Disease communities in the HFnet captured important comorbidity concepts of HF patients which could be assigned to HF subtypes, age groups, and sex. Based on the HFpEF comorbidity profile, we predicted and recovered gene candidates, including genes involved in fibrosis (COL3A1, LOX, SMAD9, PTHL), hypertrophy (GATA5, MYH7), oxidative stress (NOS1, GSST1, XDH), and endoplasmic reticulum stress (ATF6). Finally, predicted genes were significantly overrepresented in the murine transcriptomic disease signature providing additional plausibility for their relevance.

CONCLUSIONS

We applied systems medicine concepts to analyze comorbidity profiles in a HF patient cohort. We were able to identify disease clusters that helped to characterize HF patients. We derived a distinct comorbidity profile for HFpEF, which was leveraged to suggest novel candidate genes via network propagation. The identification of distinctive comorbidity profiles and candidate genes from routine clinical data provides insights that may be leveraged to improve diagnosis and identify treatment targets for HFpEF patients.

A network medicine-based approach to explore the relationship between depression and inflammation

Background

Depression is widespread global problem that not only severely impacts individuals' physical and mental health but also imposes a heavy disease burden on nations and societies. The role of inflammation in the pathogenesis and pathophysiology of depression has received much attention, but the precise relationship between the two remains unclear. This study aims to investigate the correlation between depression and inflammation using a network medicine approach.

Methods

We utilized a degree-preserving approach to identify the large connected component (LCC) of all depression-related proteins in the human interactome. The LCC was deemed as the disease module for depression. To measure the association between depression and other diseases, we calculated the overlap between these disease protein modules using the Sab algorithm. A smaller Sab value indicates a stronger association between diseases. Building on the results of this analysis, we further explored the correlation between inflammation and depression by conducting enrichment and pathway analyses of critical targets. Finally, we used a network proximity approach to calculate drug-disease proximity to predict the efficacy of drugs for the treatment of depression. We calculated and ranked the distances between depression disease modules and 6,100 drugs. The top-ranked drugs were selected to explore their potential for treating depression based on the hypothesis that their antidepressant effects are related to reducing inflammation.

Results

In the human interactome, all depression-related proteins are clustered into a large connected component (LCC) consisting of 202 proteins and multiple small subgraphs. This indicates that depression-related proteins tend to form clusters within the same network. We used the 202 LCC proteins as the key disease module for depression. Next, we investigated the potential relationships between depression and 299 other diseases. Our analysis identified over 18 diseases that exhibited significant overlap with the depression module. Where S_AB = -0.075 for the vascular disease and depressive disorders module, S_AB = -0.070 for the gastrointestinal disease and depressive disorders module, and S_AB = -0.062 for the endocrine system disease and depressive disorders module. The distance between them S_AB < 0 implies that the pathogenesis of depression is likely to be related to the pathogenesis of its co-morbidities of depression and that potential therapeutic approaches may be derived from the disease treatment libraries of these co-morbidities. Further, considering that the inflammation is ubiquitous in some disease, we calculate the overlap between the collected inflammation module (236 proteins) and the depression module (202 proteins), finding that they are closely related (S_di = -0.358) in the human protein interaction network. After enrichment and pathway analysis of key genes, we identified the HIF-1 signaling pathway, PI3K-Akt signaling pathway, Th17 cell differentiation, hepatitis B, and inflammatory bowel disease as key to the inflammatory response in depression. Finally, we calculated the Z-score to determine the proximity of 6,100 drugs to the depression disease module. Among the top three drugs identified by drug-disease proximity analysis were Perphenazine, Clomipramine, and Amitriptyline, all of which had a greater number of targets in the network associated with the depression disease module. Notably, these drugs have been shown to exert both anti-inflammatory and antidepressant effects, suggesting that they may modulate depression through an anti-inflammatory mechanism. These findings demonstrate a correlation between depression and inflammation at the network medicine level, which has important implications for future elucidation of the etiology of depression and improved treatment outcomes.

Conclusion

Neuroimmune signaling pathways play an important role in the pathogenesis of depression, and many classes of antidepressants exhibiting anti-inflammatory properties. The pathogenesis of depression is closely related to inflammation.

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.

The impact of untreated hearing loss on depression, anxiety, stress, and loneliness in tonal language-speaking older adults in China

BACKGROUND

Age-related hearing loss, mental health conditions, and loneliness commonly affect older adults. This study aimed to determine whether untreated hearing loss is independently associated with depression, anxiety, stress, and loneliness in tonal language-speaking older adults in China.

STUDY DESIGN

Observational, cross-sectional study.

METHODS

293 older adults (111 males, M = 70.33 ± 4.90 years; 182 females, M = 69.02 ± 4.08 years) were recruited. All participants completed a pure tone audiometric hearing assessment, and provided information on living arrangements, marital status, leisure activities, tobacco and alcohol use, and medical history. The Mandarin version of the De Jong Gierveld Loneliness Scale was used to measure loneliness, and the Mandarin version of the 21-item Depression Anxiety Stress Scale (DASS-21) was used to assess a range of symptoms common to depression, stress, and anxiety of the participants. The analysis focused on determining the predictors of depression, anxiety, and stress, and the predictors of measures of loneliness.

RESULTS

Multiple stepwise regression analyses revealed that the emotional loneliness (β = 0.303, p < 0.001) and living status (β = 0.110, p = 0.048) significantly predicted DASS depression scores; emotional loneliness (β = 0.276, p < 0.001) and a history of vascular disease (β = 0.148, p = 0.009) were significantly related to DASS anxiety scores; emotional loneliness (β = 0.341, p < 0.001) and a history of vascular disease (β = 0.129, p = 0.019) significantly predicted DASS stress scores. Furthermore, multiple stepwise regression analyses showed that DASS stress scores (β = 0.333, p < 0.001), education years (β = -0.126, p = 0.020), marriage status (β = 0.122, p = 0.024), and a history of vascular disease (β = 0.111, p = 0.044) significantly predicted emotional loneliness; four-frequency average hearing loss (β = 0.149, p = 0.010) and DASS stress scores (β = 0.123, p = 0.034) significantly predicted social loneliness scale; and four-frequency average hearing loss (β = 0.167, p = 0.003) and DASS stress scores (β = 0.279, p < 0.001) also significantly predicted overall loneliness. There were no significant associations with high-frequency hearing loss.

CONCLUSION

This study revealed that loneliness has a significant relationship both with hearing loss and aspects of mental health in an older adult Mandarin-speaking population. However, mental health was not significantly associated with hearing loss in this population.

Exploring the genetic overlap between twelve psychiatric disorders

The widespread comorbidity among psychiatric disorders demonstrated in epidemiological studies1-5 is mirrored by non-zero, positive genetic correlations from large-scale genetic studies6-10. To identify shared biological processes underpinning this observed phenotypic and genetic covariance and enhance molecular characterization of general psychiatric disorder liability11-13, we used several strategies aimed at uncovering pleiotropic, that is, cross-trait-associated, single-nucleotide polymorphisms (SNPs), genes and biological pathways. We conducted cross-trait meta-analysis on 12 psychiatric disorders to identify pleiotropic SNPs. The meta-analytic signal was driven by schizophrenia, hampering interpretation and joint biological characterization of the cross-trait meta-analytic signal. Subsequent pairwise comparisons of psychiatric disorders identified substantial pleiotropic overlap, but mainly among pairs of psychiatric disorders, and mainly at less stringent P-value thresholds. Only annotations related to evolutionarily conserved genomic regions were significant for multiple (9 out of 12) psychiatric disorders. Overall, identification of shared biological mechanisms remains challenging due to variation in power and genetic architecture between psychiatric disorders.

LeMeDISCO is a computational method for large-scale prediction & molecular interpretation of disease comorbidity

To understand the origin of disease comorbidity and to identify the essential proteins and pathways underlying comorbid diseases, we developed LeMeDISCO (Large-Scale Molecular Interpretation of Disease Comorbidity), an algorithm that predicts disease comorbidities from shared mode of action proteins predicted by the artificial intelligence-based MEDICASCY algorithm. LeMeDISCO was applied to predict the occurrence of comorbid diseases for 3608 distinct diseases. Benchmarking shows that LeMeDISCO has much better comorbidity recall than the two molecular methods XD-score (44.5% vs. 6.4%) and the S_AB score (68.6% vs. 8.0%). Its performance is somewhat comparable to the phenotype method-based Symptom Similarity Score, 63.7% vs. 100%, but LeMeDISCO works for far more cases and its large comorbidity recall is attributed to shared proteins that can help provide an understanding of the molecular mechanism(s) underlying disease comorbidity. The LeMeDISCO web server is available for academic users at: http://sites.gatech.edu/cssb/LeMeDISCO .

Online in silico validation of disease and gene sets, clusterings or subnetworks with DIGEST

As the development of new drugs reaches its physical and financial limits, drug repurposing has become more important than ever. For mechanistically grounded drug repurposing, it is crucial to uncover the disease mechanisms and to detect clusters of mechanistically related diseases. Various methods for computing candidate disease mechanisms and disease clusters exist. However, in the absence of ground truth, in silico validation is challenging. This constitutes a major hurdle toward the adoption of in silico prediction tools by experimentalists who are often hesitant to carry out wet-lab validations for predicted candidate mechanisms without clearly quantified initial plausibility. To address this problem, we present DIGEST (in silico validation of disease and gene sets, clusterings or subnetworks), a Python-based validation tool available as a web interface (https://digest-validation.net), as a stand-alone package or over a REST API. DIGEST greatly facilitates in silico validation of gene and disease sets, clusterings or subnetworks via fully automated pipelines comprising disease and gene ID mapping, enrichment analysis, comparisons of shared genes and variants and background distribution estimation. Moreover, functionality is provided to automatically update the external databases used by the pipelines. DIGEST hence allows the user to assess the statistical significance of candidate mechanisms with regard to functional and genetic coherence and enables the computation of empirical $P$-values with just a few mouse clicks.

NETMAGE: A human disease phenotype map generator for the network-based visualization of phenome-wide association study results

BACKGROUND

Disease complications, the onset of secondary phenotypes given a primary condition, can exacerbate the long-term severity of outcomes. However, the exact cause of many of these cross-phenotype associations is still unknown. One potential reason is shared genetic etiology-common genetic drivers may lead to the onset of multiple phenotypes. Disease-disease networks (DDNs), where nodes represent diseases and edges represent associations between diseases, can provide an intuitive way of understanding the relationships between phenotypes. Using summary statistics from a phenome-wide association study (PheWAS), we can generate a corresponding DDN where edges represent shared genetic variants between diseases. Such a network can help us analyze genetic associations across the diseasome, the landscape of all human diseases, and identify potential genetic influences for disease complications.

RESULTS

To improve the ease of network-based analysis of shared genetic components across phenotypes, we developed the humaN disEase phenoType MAp GEnerator (NETMAGE), a web-based tool that produces interactive DDN visualizations from PheWAS summary statistics. Users can search the map by various attributes and select nodes to view related phenotypes, associated variants, and various network statistics. As a test case, we used NETMAGE to construct a network from UK BioBank (UKBB) PheWAS summary statistic data. Our map correctly displayed previously identified disease comorbidities from the UKBB and identified concentrations of hub diseases in the endocrine/metabolic and circulatory disease categories. By examining the associations between phenotypes in our map, we can identify potential genetic explanations for the relationships between diseases and better understand the underlying architecture of the human diseasome. Our tool thus provides researchers with a means to identify prospective genetic targets for drug design, using network medicine to contribute to the exploration of personalized medicine.

An explainable artificial intelligence approach for predicting cardiovascular outcomes using electronic health records

Understanding the conditionally-dependent clinical variables that drive cardiovascular health outcomes is a major challenge for precision medicine. Here, we deploy a recently developed massively scalable comorbidity discovery method called Poisson Binomial based Comorbidity discovery (PBC), to analyze Electronic Health Records (EHRs) from the University of Utah and Primary Children's Hospital (over 1.6 million patients and 77 million visits) for comorbid diagnoses, procedures, and medications. Using explainable Artificial Intelligence (AI) methodologies, we then tease apart the intertwined, conditionally-dependent impacts of comorbid conditions and demography upon cardiovascular health, focusing on the key areas of heart transplant, sinoatrial node dysfunction and various forms of congenital heart disease. The resulting multimorbidity networks make possible wide-ranging explorations of the comorbid and demographic landscapes surrounding these cardiovascular outcomes, and can be distributed as web-based tools for further community-based outcomes research. The ability to transform enormous collections of EHRs into compact, portable tools devoid of Protected Health Information solves many of the legal, technological, and data-scientific challenges associated with large-scale EHR analyses.

Using the Symptom Patient Similarity Network to Explore the Difference between the Chinese and Western Medicine Pathways of Ischemic Stroke and its Comorbidities

Methods

Individualized treatment of traditional Chinese medicine (TCM) provides a theoretical basis for the study of the personalized classification of complex diseases. Utilizing the TCM clinical electronic medical records (EMRs) of 7170 in patients with IS, a patient similarity network (PSN) with shared symptoms was constructed. Next, patient subgroups were identified using community detection methods and enrichment analyses were performed. Finally, genetic data of symptoms, herbs, and drugs were used for pathway and GO analysis to explore the characteristics of pathways of subgroups and to compare the similarities and differences in genetic pathways of herbs and drugs from the perspective of molecular pathways of symptoms.

Results

We identified 34 patient modules from the PSN, of which 7 modules include 98.48% of the whole cases. The 7 patient subgroups have their own characteristics of risk factors, complications, and comorbidities and the underlying genetic pathways of symptoms, drugs, and herbs. Each subgroup has the largest number of herb pathways. For specific symptom pathways, the number of herb pathways is more than that of drugs.

Conclusion

The research of disease classification based on community detection of symptom-shared patient networks is practical; the common molecular pathway of symptoms and herbs reflects the rationality of TCM herbs on symptoms and the wide range of therapeutic targets.

A weighted patient network-based framework for predicting chronic diseases using graph neural networks

Chronic disease prediction is a critical task in healthcare. Existing studies fulfil this requirement by employing machine learning techniques based on patient features, but they suffer from high dimensional data problems and a high level of bias. We propose a framework for predicting chronic disease based on Graph Neural Networks (GNNs) to address these issues. We begin by projecting a patient-disease bipartite graph to create a weighted patient network (WPN) that extracts the latent relationship among patients. We then use GNN-based techniques to build prediction models. These models use features extracted from WPN to create robust patient representations for chronic disease prediction. We compare the output of GNN-based models to machine learning methods by using cardiovascular disease and chronic pulmonary disease. The results show that our framework enhances the accuracy of chronic disease prediction. The model with attention mechanisms achieves an accuracy of 93.49% for cardiovascular disease prediction and 89.15% for chronic pulmonary disease prediction. Furthermore, the visualisation of the last hidden layers of GNN-based models shows the pattern for the two cohorts, demonstrating the discriminative strength of the framework. The proposed framework can help stakeholders improve health management systems for patients at risk of developing chronic diseases and conditions.

A Visual Phenotype-Based Differential Diagnosis Process for Rare Diseases

PURPOSE

Phenotype-based rapid diagnosis can make up for the time-consuming genetic sequencing diagnosis of rare diseases. However, the collected phenotypes of patients can sometimes be inaccurate or incomplete, which limits the accuracy of diagnostic results. To solve this problem, we try to design a phenotype-based differential diagnosis process for rare diseases to achieve rapid and accurate diagnosis of rare diseases.

METHODS

The core of the differential diagnosis of rare diseases is to optimize the phenotype information of a specific patient and the visualized comparative analysis of diseases. To recommend additional phenotypes, replace the fuzzy phenotypes and filter the unexplained phenotypes for patients, we constructed a phenotype hierarchical network and a disease-phenotype differential network and calculated the phenotype co-occurrence relationship. In addition, we designed a visual comparative analysis method to explore the correlation and difference of disease phenotypes.

RESULTS

The evaluation based on the published 10 rare disease cases demonstrated that after the optimization of patient phenotype information through our differential diagnosis, the target disease often got a better ranking and recommendation score than before. We have deployed this scheme on the RDmap project ( http://rdmap.nbscn.org ).

CONCLUSION

Compared to genetic and molecular analysis, phenotype-based diagnosis is faster, cheaper, and easier. The differential diagnosis process we designed can optimize the phenotype information of patients and better locate the target disease. It can also help to make screening decisions before genetic testing.

Deep learning in systems medicine

Systems medicine (SM) has emerged as a powerful tool for studying the human body at the systems level with the aim of improving our understanding, prevention and treatment of complex diseases. Being able to automatically extract relevant features needed for a given task from high-dimensional, heterogeneous data, deep learning (DL) holds great promise in this endeavour. This review paper addresses the main developments of DL algorithms and a set of general topics where DL is decisive, namely, within the SM landscape. It discusses how DL can be applied to SM with an emphasis on the applications to predictive, preventive and precision medicine. Several key challenges have been highlighted including delivering clinical impact and improving interpretability. We used some prototypical examples to highlight the relevance and significance of the adoption of DL in SM, one of them is involving the creation of a model for personalized Parkinson's disease. The review offers valuable insights and informs the research in DL and SM.

Comorbidity Networks in Cardiovascular Diseases

Background: Cardiovascular diseases are the leading causes of mortality worldwide. One reason behind this lethality lies in the fact that often cardiovascular illnesses develop into systemic failure due to the multiple connections to organismal metabolism. This in turn is associated with co-morbidities and multimorbidity. The prevalence of coexisting diseases and the relationship between the molecular origins adds to the complexity of the management of cardiovascular diseases and thus requires a profound knowledge of the genetic interaction of diseases. Objective: In order to develop a deeper understanding of this phenomenon, we examined the patterns of comorbidity as well as their genetic interaction of the diseases (or the lack of evidence of it) in a large set of cases diagnosed with cardiovascular conditions at the national reference hospital for cardiovascular diseases in Mexico. Methods: We performed a cross-sectional study of the National Institute of Cardiology. Socioeconomic information, principal diagnosis that led to the hospitalization and other conditions identified by an ICD-10 code were obtained for 34,099 discharged cases. With this information a cardiovascular comorbidity networks were built both for the full database and for ten 10-years age brackets. The associated cardiovascular comorbidities modules were found. Data mining was performed in the comprehensive ClinVar database with the disease names (as extracted from ICD-10 codes) to establish (when possible) connections between the genetic associations of the genetic interaction of diseases. The rationale is that some comorbidities may have a stronger genetic origin, whereas for others, the environment and other factors may be stronger. Results: We found that comorbidity networks are highly centralized in prevalent diseases, such as cardiac arrhythmias, heart failure, chronic kidney disease, hypertension, and ischemic diseases. Said comorbidity networks are actually modular on their connectivity. Modules recapitulate physiopathological commonalities, e.g., ischemic diseases clustering together. This is also the case of chronic systemic diseases, of congenital malformations and others. The genetic and environmental commonalities behind some of the relations in these modules were also found by resorting to clinical genetics databases and functional pathway enrichment studies. Conclusions: This methodology, hence may allow the clinician to look up for non-evident comorbidities whose knowledge will lead to improve therapeutically designs. By continued and consistent analysis of these types of patterns, we envisaged that it may be possible to acquire, strong clinical and basic insights that may further our advance toward a better understanding of cardiovascular diseases as a whole. Hopefully these may in turn lead to further development of better, integrated therapeutic strategies.

Patterns of Comorbidity in Hepatocellular Carcinoma: A Network Perspective

Hepatocellular carcinoma (HCC) is a common and fatal cancer. People with HCC report higher odds of comorbidity compared with people without HCC. To explore the association between HCC and medical comorbidity, we used routinely collected clinical data and applied a network perspective. In the network perspective, we used correlation analysis and community detection tests that described direct relationships among comorbidities. We collected 14,891 patients with HCC living in Jilin Province, China, between 2016 and 2018. Cirrhosis was the most common comorbidity of HCC. Hypertension and renal cysts were more common in male patients, while chronic viral hepatitis C, hypersplenism, hypoproteinemia, anemia and coronary heart disease were more common in female patients. The proportion of chronic diseases in comorbidities increased with age. The main comorbidity patterns of HCC were: HCC, cirrhosis, chronic viral hepatitis B, portal hypertension, ascites and other common complications of cirrhosis; HCC, hypertension, diabetes mellitus, coronary heart disease and cerebral infarction; and HCC, hypoproteinemia, electrolyte disorders, gastrointestinal hemorrhage and hemorrhagic anemia. Our findings provide comprehensive information on comorbidity patterns of HCC, which may be used for the prevention and management of liver cancer.

Symptom Distribution Regularity of Insomnia: Network and Spectral Clustering Analysis

Background

Recent research in machine-learning techniques has led to significant progress in various research fields. In particular, knowledge discovery using this method has become a hot topic in traditional Chinese medicine. As the key clinical manifestations of patients, symptoms play a significant role in clinical diagnosis and treatment, which evidently have their underlying traditional Chinese medicine mechanisms.

Objective

We aimed to explore the core symptoms and potential regularity of symptoms for diagnosing insomnia to reveal the key symptoms, hidden relationships underlying the symptoms, and their corresponding syndromes.

Methods

An insomnia dataset with 807 samples was extracted from real-world electronic medical records. After cleaning and selecting the theme data referring to the syndromes and symptoms, the symptom network analysis model was constructed using complex network theory. We used four evaluation metrics of node centrality to discover the core symptom nodes from multiple aspects. To explore the hidden relationships among symptoms, we trained each symptom node in the network to obtain the symptom embedding representation using the Skip-Gram model and node embedding theory. After acquiring the symptom vocabulary in a digital vector format, we calculated the similarities between any two symptom embeddings, and clustered these symptom embeddings into five communities using the spectral clustering algorithm.

Results

The top five core symptoms of insomnia diagnosis, including difficulty falling asleep, easy to wake up at night, dysphoria and irascibility, forgetful, and spiritlessness and weakness, were identified using evaluation metrics of node centrality. The symptom embeddings with hidden relationships were constructed, which can be considered as the basic dataset for future insomnia research. The symptom network was divided into five communities, and these symptoms were accurately categorized into their corresponding syndromes.

Conclusions

These results highlight that network and clustering analyses can objectively and effectively find the key symptoms and relationships among symptoms. Identification of the symptom distribution and symptom clusters of insomnia further provide valuable guidance for clinical diagnosis and treatment.