Phenotypic Disease Network Analysis to Identify Comorbidity Patterns in Hospitalized Patients with Ischemic Heart Disease Using Large-Scale Administrative Data

Analyzing Comorbidity Patterns in Patients With Thyroid Disease Using Large-Scale Electronic Medical Records: Network-Based Retrospective Observational Study

BACKGROUND

Thyroid disease (TD) is a prominent endocrine disorder that raises global health concerns; however, its comorbidity patterns remain unclear.

OBJECTIVE

This study aims to apply a network-based method to comprehensively analyze the comorbidity patterns of TD using large-scale real-world health data.

METHODS

In this retrospective observational study, we extracted the comorbidities of adult patients with TD from both private and public data sets. All comorbidities were identified using ICD-10 (International Classification of Diseases, 10th Revision) codes at the 3-digit level, and those with a prevalence greater than 2% were analyzed. Patients were categorized into several subgroups based on sex, age, and disease type. A phenotypic comorbidity network (PCN) was constructed, where comorbidities served as nodes and their significant correlations were represented as edges, encompassing all patients with TD and various subgroups. The associations and differences in comorbidities within the PCN of each subgroup were analyzed and compared. The PageRank algorithm was used to identify key comorbidities.

RESULTS

The final cohorts included 18,311 and 50,242 patients with TD in the private and public data sets, respectively. Patients with TD demonstrated complex comorbidity patterns, with coexistence relationships differing by sex, age, and type of TD. The number of comorbidities increased with age. The most prevalent TDs were nontoxic goiter, hypothyroidism, hyperthyroidism, and thyroid cancer, while hypertension, diabetes, and lipoprotein metabolism disorders had the highest prevalence and PageRank values among comorbidities. Males and patients with benign TD exhibited a greater number of comorbidities, increased disease diversity, and stronger comorbidity associations compared with females and patients with thyroid cancer.

CONCLUSIONS

Patients with TD exhibited complex comorbidity patterns, particularly with cardiocerebrovascular diseases and diabetes. The associations among comorbidities varied across different TD subgroups. This study aims to enhance the understanding of comorbidity patterns in patients with TD and improve the integrated management of these individuals.

"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.

SAGL: A self-attention-based graph learning framework for predicting survival of colorectal cancer patients

BACKGROUND AND OBJECTIVE

Colorectal cancer (CRC) is one of the most commonly diagnosed cancers worldwide. The accurate survival prediction for CRC patients plays a significant role in the formulation of treatment strategies. Recently, machine learning and deep learning approaches have been increasingly applied in cancer survival prediction. However, most existing methods inadequately represent and leverage the dependencies among features and fail to sufficiently mine and utilize the comorbidity patterns of CRC. To address these issues, we propose a self-attention-based graph learning (SAGL) framework to improve the postoperative cancer-specific survival prediction for CRC patients.

METHODS

We present a novel method for constructing dependency graph (DG) to reflect two types of dependencies including comorbidity-comorbidity dependencies and the dependencies between features related to patient characteristics and cancer treatments. This graph is subsequently refined by a disease comorbidity network, which offers a holistic view of comorbidity patterns of CRC. A DG-guided self-attention mechanism is proposed to unearth novel dependencies beyond what DG offers, thus augmenting CRC survival prediction. Finally, each patient will be represented, and these representations will be used for survival prediction.

RESULTS

The experimental results show that SAGL outperforms state-of-the-art methods on a real-world dataset, with the receiver operating characteristic curve for 3- and 5-year survival prediction achieving 0.849±0.002 and 0.895±0.005, respectively. In addition, the comparison results with different graph neural network-based variants demonstrate the advantages of our DG-guided self-attention graph learning framework.

CONCLUSIONS

Our study reveals that the potential of the DG-guided self-attention in optimizing feature graph learning which can improve the performance of CRC survival prediction.

The regional disparities in liver disease comorbidity among elderly Chinese based on a health ecological model: the China Health and Retirement Longitudinal Study

PURPOSE

This study aimed to investigate the risk factors for liver disease comorbidity among older adults in eastern, central, and western China, and explored binary, ternary and quaternary co-morbid co-causal patterns of liver disease within a health ecological model.

METHOD

Basic information from 9,763 older adults was analyzed using data from the China Health and Retirement Longitudinal Study (CHARLS). LASSO regression was employed to identify significant predictors in eastern, central, and western China. Patterns of liver disease comorbidity were studied using association rules, and spatial distribution was analyzed using a geographic information system. Furthermore, binary, ternary, and quaternary network diagrams were constructed to illustrate the relationships between liver disease comorbidity and co-causes.

RESULTS

Among the 9,763 elderly adults studied, 536 were found to have liver disease comorbidity, with binary or ternary comorbidity being the most prevalent. Provinces with a high prevalence of liver disease comorbidity were primarily concentrated in Inner Mongolia, Sichuan, and Henan. The most common comorbidity patterns identified were "liver-heart-metabolic", "liver-kidney", "liver-lung", and "liver-stomach-arthritic". In the eastern region, important combination patterns included "liver disease-metabolic disease", "liver disease-stomach disease", and "liver disease-arthritis", with the main influencing factors being sleep duration of less than 6 h, frequent drinking, female, and daily activity capability. In the central region, common combination patterns included "liver disease-heart disease", "liver disease-metabolic disease", and "liver disease-kidney disease", with the main influencing factors being an education level of primary school or below, marriage, having medical insurance, exercise, and no disabilities. In the western region, the main comorbidity patterns were "liver disease-chronic lung disease", "liver disease-stomach disease", "liver disease-heart disease", and "liver disease-arthritis", with the main influencing factors being general or poor health satisfaction, general or poor health condition, severe pain, and no disabilities.

CONCLUSION

The comorbidities associated with liver disease exhibit specific clustering patterns at both the overall and local levels. By analyzing the comorbidity patterns of liver diseases in different regions and establishing co-morbid co-causal patterns, this study offers a new perspective and scientific basis for the prevention and treatment of liver diseases.

A Laplacian regularized graph neural network for predictive modeling of multiple chronic conditions

BACKGROUND AND GOALS

One of the biggest difficulties facing healthcare systems today is the prevalence of multiple chronic diseases (MCC). Mortality and the development of new chronic illnesses are more likely in those with MCC. Pre-existing diseases and risk factors specific to the patient have an impact on the complex stochastic process that guides the evolution of MCC. This study's goal is to use a brand-new Graph Neural Network (GNN) model to examine the connections between specific chronic illnesses, patient-level risk factors, and pre-existing conditions.

METHODS

We propose a graph neural network model to analyze the relationship between five chronic conditions (diabetes, obesity, cognitive impairment, hyperlipidemia, and hypertension). The proposed model adds a graph Laplacian regularization term to the loss function, which aims to improve the parameter learning process and accuracy of the GNN based on the graph structure. For validation, we used historical data from the Cameron County Hispanic Cohort (CCHC).

RESULTS

Evaluating the Laplacian regularized GNN on data from 600 patients, we expanded our analysis from two chronic conditions to five chronic conditions. The proposed model consistently surpassed a baseline GNN model, achieving an average accuracy of ≥89% across all combinations. In contrast, the performance of the standard model declined more markedly with the addition of more chronic conditions. The Laplacian regularization provided consistent predictions for adjacent nodes, beneficial in cases with shared attributes among nodes.

CONCLUSIONS

The incorporation of Laplacian regularization in our GNN model is essential, resulting in enhanced node categorization and better predictive performance by harnessing the graph structure. This study underscores the significance of considering graph structure when designing neural networks for graph data. Future research might further explore and refine this regularization method for various tasks using graph-structured data.

A network-based approach to explore comorbidity patterns among community-dwelling older adults living alone

The detailed comorbidity patterns of community-dwelling older adults have not yet been explored. This study employed a network-based approach to investigate the comorbidity patterns of community-dwelling older adults living alone. The sample comprised a cross-sectional cohort of adults 65 or older living alone in a Korean city (n = 1041; mean age = 77.7 years, 77.6% women). A comorbidity network analysis that estimates networks aggregated from measures of significant co-occurrence between pairs of diseases was employed to investigate comorbid associations between 31 chronic conditions. A cluster detection algorithm was employed to identify specific clusters of comorbidities. The association strength was expressed as the observed-to-expected ratio (OER). As a result, fifteen diseases were interconnected within the network (OER > 1, p-value < .05). While hypertension had a high prevalence, osteoporosis was the most central disease, co-occurring with numerous other diseases. The strongest associations among comorbidities were found between thyroid disease and urinary incontinence, chronic otitis media and osteoporosis, gastric duodenal ulcer/gastritis and anemia, and depression and gastric duodenal ulcer/gastritis (OER > 1.85). Three distinct clusters were identified as follows: (a) cataracts, osteoporosis, chronic otitis media, osteoarthritis/rheumatism, low back pain/sciatica, urinary incontinence, post-accident sequelae, and thyroid diseases; (b) hyperlipidemia, diabetes mellitus, and hypertension; and (c) depression, skin disease, gastric duodenal ulcer/gastritis, and anemia. The results may prove valuable in guiding the early diagnosis, management, and treatment of comorbidities in older adults living alone.

Comorbidity increases the risk of pulmonary tuberculosis: a nested case-control study using multi-source big data

BACKGROUND

Some medical conditions may increase the risk of developing pulmonary tuberculosis (PTB); however, no systematic study on PTB-associated comorbidities and comorbidity clusters has been undertaken.

METHODS

A nested case-control study was conducted from 2013 to 2017 using multi-source big data. We defined cases as patients with incident PTB, and we matched each case with four event-free controls using propensity score matching (PSM). Comorbidities diagnosed prior to PTB were defined with the International Classification of Diseases-10 (ICD-10). The longitudinal relationships between multimorbidity burden and PTB were analyzed using a generalized estimating equation. The associations between PTB and 30 comorbidities were examined using conditional logistic regression, and the comorbidity clusters were identified using network analysis.

RESULTS

A total of 4265 cases and 17,060 controls were enrolled during the study period. A total of 849 (19.91%) cases and 1141 (6.69%) controls were multimorbid before the index date. Having 1, 2, and ≥ 3 comorbidities was associated with an increased risk of PTB (aOR 2.85-5.16). Fourteen out of thirty comorbidities were significantly associated with PTB (aOR 1.28-7.27), and the associations differed by sex and age. Network analysis identified three major clusters, mainly in the respiratory, circulatory, and endocrine/metabolic systems, in PTB cases.

CONCLUSIONS

Certain comorbidities involving multiple systems may significantly increase the risk of PTB. Enhanced awareness and surveillance of comorbidity are warranted to ensure early prevention and timely control of PTB.

Comorbidity Patterns in Older Patients Undergoing Hip Fracture Surgery: A Comorbidity Network Analysis Study

Comorbidity network analysis (CNA) is a technique in which mathematical graphs encode correlations (edges) among diseases (nodes) inferred from the disease co-occurrence data of a patient group. The present study applied this network-based approach to identifying comorbidity patterns in older patients undergoing hip fracture surgery. This was a retrospective observational cohort study using electronic health records (EHR). EHR data were extracted from the one University Health System in the southeast United States. The cohort included patients aged 65 and above who had a first-time low-energy traumatic hip fracture treated surgically between October 1, 2015 and December 31, 2018 (n = 1,171). Comorbidity includes 17 diagnoses classified by the Charlson Comorbidity Index. The CNA investigated the comorbid associations among 17 diagnoses. The association strength was quantified using the observed-to-expected ratio (OER). Several network centrality measures were used to examine the importance of nodes, namely degree, strength, closeness, and betweenness centrality. A cluster detection algorithm was employed to determine specific clusters of comorbidities. Twelve diseases were significantly interconnected in the network (OER > 1, p-value < .05). The most robust associations were between metastatic carcinoma and mild liver disease, myocardial infarction and congestive heart failure, and hemi/paraplegia and cerebrovascular disease (OER > 2.5). Cerebrovascular disease, congestive heart failure, and myocardial infarction were identified as the central diseases that co-occurred with numerous other diseases. Two distinct clusters were noted, and the largest cluster comprised 10 diseases, primarily encompassing cardiometabolic and cognitive disorders. The results highlight specific patient comorbidities that could be used to guide clinical assessment, management, and targeted interventions that improve hip fracture outcomes in this patient group.

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.

Understanding human aging and the fundamental cell signaling link in age-related diseases: the middle-aging hypovascularity hypoxia hypothesis

Aging-related hypoxia, oxidative stress, and inflammation pathophysiology are closely associated with human age-related carcinogenesis and chronic diseases. However, the connection between hypoxia and hormonal cell signaling pathways is unclear, but such human age-related comorbid diseases do coincide with the middle-aging period of declining sex hormonal signaling. This scoping review evaluates the relevant interdisciplinary evidence to assess the systems biology of function, regulation, and homeostasis in order to discern and decipher the etiology of the connection between hypoxia and hormonal signaling in human age-related comorbid diseases. The hypothesis charts the accumulating evidence to support the development of a hypoxic milieu and oxidative stress-inflammation pathophysiology in middle-aged individuals, as well as the induction of amyloidosis, autophagy, and epithelial-to-mesenchymal transition in aging-related degeneration. Taken together, this new approach and strategy can provide the clarity of concepts and patterns to determine the causes of declining vascularity hemodynamics (blood flow) and physiological oxygenation perfusion (oxygen bioavailability) in relation to oxygen homeostasis and vascularity that cause hypoxia (hypovascularity hypoxia). The middle-aging hypovascularity hypoxia hypothesis could provide the mechanistic interface connecting the endocrine, nitric oxide, and oxygen homeostasis signaling that is closely linked to the progressive conditions of degenerative hypertrophy, atrophy, fibrosis, and neoplasm. An in-depth understanding of these intrinsic biological processes of the developing middle-aged hypoxia could provide potential new strategies for time-dependent therapies in maintaining healthspan for healthy lifestyle aging, medical cost savings, and health system sustainability.

Risk prediction of heart failure in patients with ischemic heart disease using network analytics and stacking ensemble learning

BACKGROUND

Heart failure (HF) is a major complication following ischemic heart disease (IHD) and it adversely affects the outcome. Early prediction of HF risk in patients with IHD is beneficial for timely intervention and for reducing disease burden.

METHODS

Two cohorts, cases for patients first diagnosed with IHD and then with HF (N = 11,862) and control IHD patients without HF (N = 25,652), were established from the hospital discharge records in Sichuan, China during 2015-2019. Directed personal disease network (PDN) was constructed for each patient, and then these PDNs were merged to generate the baseline disease network (BDN) for the two cohorts, respectively, which identifies the health trajectories of patients and the complex progression patterns. The differences between the BDNs of the two cohort was represented as disease-specific network (DSN). Three novel network features were exacted from PDN and DSN to represent the similarity of disease patterns and specificity trends from IHD to HF. A stacking-based ensemble model DXLR was proposed to predict HF risk in IHD patients using the novel network features and basic demographic features (i.e., age and sex). The Shapley Addictive exPlanations method was applied to analyze the feature importance of the DXLR model.

RESULTS

Compared with the six traditional machine learning models, our DXLR model exhibited the highest AUC (0.934 ± 0.004), accuracy (0.857 ± 0.007), precision (0.723 ± 0.014), recall (0.892 ± 0.012) and F₁ score (0.798 ± 0.010). The feature importance showed that the novel network features ranked as the top three features, playing a notable role in predicting HF risk of IHD patient. The feature comparison experiment also indicated that our novel network features were superior to those proposed by the state-of-the-art study in improving the performance of the prediction model, with an increase in AUC by 19.9%, in accuracy by 18.7%, in precision by 30.7%, in recall by 37.4%, and in F₁ score by 33.7%.

CONCLUSIONS

Our proposed approach that combines network analytics and ensemble learning effectively predicts HF risk in patients with IHD. This highlights the potential value of network-based machine learning in disease risk prediction field using administrative data.

Phenotypic Disease Network-Based Multimorbidity Analysis in Idiopathic Cardiomyopathy Patients with Hospital Discharge Records

BACKGROUND

Idiopathic cardiomyopathy (ICM) is a rare disease affecting numerous physiological and biomolecular systems with multimorbidity. However, due to the small sample size of uncommon diseases, the whole spectrum of chronic disease co-occurrence, especially in developing nations, has not yet been investigated. To grasp the multimorbidity pattern, we aimed to present a multidimensional model for ICM and differences among age groups.

METHODS

Hospital discharge records were collected from a rare disease centre of ICM inpatients (n = 1036) over 10 years (2012 to 2021) for this retrospective analysis. One-to-one matched controls were also included. First, by looking at the first three digits of the ICD-10 code, we concentrated on chronic illnesses with a prevalence of more than 1%. The ICM and control inpatients had a total of 71 and 69 chronic illnesses, respectively. Second, to evaluate the multimorbidity pattern in both groups, we built age-specific cosine-index-based multimorbidity networks. Third, the associated rule mining (ARM) assessed the comorbidities with heart failure for ICM, specifically.

RESULTS

The comorbidity burden of ICM was 78% larger than that of the controls. All ages were affected by the burden, although those over 50 years old had more intense interactions. Moreover, in terms of disease connectivity, central, hub, and authority diseases were concentrated in the metabolic, musculoskeletal and connective tissue, genitourinary, eye and adnexa, respiratory, and digestive systems. According to the age-specific connection, the impaired coagulation function was required for raising attention (e.g., autoimmune-attacked digestive and musculoskeletal system disorders) in young adult groups (ICM patients aged 20-49 years). For the middle-aged (50-60 years) and older (≥70 years) groups, malignant neoplasm and circulatory issues were the main confrontable problems. Finally, according to the result of ARM, the comorbidities and comorbidity patterns of heart failure include diabetes mellitus and metabolic disorder, sleeping disorder, renal failure, liver, and circulatory diseases.

CONCLUSIONS

The main cause of the comorbid load is aging. The ICM comorbidities were concentrated in the circulatory, metabolic, musculoskeletal and connective tissue, genitourinary, eye and adnexa, respiratory, and digestive systems. The network-based approach optimizes the integrated care of patients with ICM and advances our understanding of multimorbidity associated with the disease.

Network-Based Methods for Approaching Human Pathologies from a Phenotypic Point of View

Network and systemic approaches to studying human pathologies are helping us to gain insight into the molecular mechanisms of and potential therapeutic interventions for human diseases, especially for complex diseases where large numbers of genes are involved. The complex human pathological landscape is traditionally partitioned into discrete “diseases”; however, that partition is sometimes problematic, as diseases are highly heterogeneous and can differ greatly from one patient to another. Moreover, for many pathological states, the set of symptoms (phenotypes) manifested by the patient is not enough to diagnose a particular disease. On the contrary, phenotypes, by definition, are directly observable and can be closer to the molecular basis of the pathology. These clinical phenotypes are also important for personalised medicine, as they can help stratify patients and design personalised interventions. For these reasons, network and systemic approaches to pathologies are gradually incorporating phenotypic information. This review covers the current landscape of phenotype-centred network approaches to study different aspects of human diseases.