Comorbidity Scoring with Causal Disease Networks

Phenome-wide comorbidity network analysis reveals clinical risk patterns in enthesopathy and enthesitis

Background

Enthesopathy and enthesitis, including rotator cuff disease and other tendon disorders, represent a heterogeneous group of musculoskeletal conditions with complex etiologies. Understanding how systemic health profiles influence their onset remains a critical challenge in musculoskeletal medicine.

Methods

We conducted a large-scale, phenome-wide comorbidity analysis using longitudinal electronic health records (EHR) from 432,757 UK Biobank participants. Incident cases of peripheral enthesopathies were compared to controls across 434 baseline disease phenotypes. A directed ego network was constructed to link significantly associated comorbidities to the target condition using odds ratio-based associations. Unsupervised clustering via UMAP and DBSCAN identified data-driven comorbidity clusters, which were consolidated into unified endotypes-interpreted as distinct systemic profiles contributing to disease risk. Additionally, metapath-based trajectory analysis was applied to uncover temporally structured multimorbidity chains leading to disease onset.

Results

We identified 183 baseline conditions significantly associated with the future development of enthesopathy (FDR < 0.05). Network clustering revealed eight comorbidity clusters, which were consolidated into four unified endotypes: Metabolic-Psychosomatic, Inflammatory-Multisystem, Mechanical-Injury-driven, and Aging-Intervention-related. Metapath analysis uncovered common three-step disease trajectories, such as metabolic-infectious-musculoskeletal and inflammatory skin-to-joint progressions, highlighting potential mechanistic pathways. These endotypes showed diverse clinical features but shared biological coherence, suggesting that different systemic health profiles can converge to drive tendon-related disease.

Conclusions

This study introduces a scalable framework for identifying systemic multimorbidity patterns underlying enthesopathy and enthesitis using phenome-wide comorbidity networks. By integrating network clustering and metapath analysis, we uncover interpretable, data-driven endotypes that may inform individualized risk assessment and targeted care strategies. These findings contribute to the growing field of biobank-scale disease modeling and offer a foundation for precision approaches in musculoskeletal medicine.

Genetically and semantically aware homogeneous network for prediction and scoring of comorbidities

OBJECTIVE

Patients with comorbidities are highly prone to mortality risk than those suffering from a single disease. Therefore, quantification and prediction of disease comorbidities is necessary to stratify the mortality risk of the patients, predict the probability of their occurrence, design treatment strategies, and to prevent the progression of diseases. Enriching comorbidity disease relationships with rich semantics established by genetic components play a vital role in effectively quantifying and predicting comorbidities. However, the existing studies have not extensively explored the semantic richness conveyed by different types of genetic links connecting the comorbidity pairs.

METHODS

To solve this, a novel genetic-semantic aware weighted homogeneous network-based method, GSWHomoNet is proposed which first constructs the gene enriched comorbidity heterogeneous network, CoGHetNet with encoded genetic semantic aware weighted meta-path instance disease pair embedding to obtain an enhanced disease node embedding of the network. For enhanced comorbidity prediction and scoring, both direct and indirect semantically enriched comorbidity relationships of the disease nodes is preserved while transforming heterogeneous to homogeneous comorbidity network GSWHomoNet. The proposed GSWHomoNet not only helps discover comorbidity links transductively between known-known disease pairs but also improves the inductive link prediction between known-unknown disease pairs by supplying unknown disease nodes with semantically enriched heterogeneous structural knowledge.

RESULTS

The effectiveness of the proposed components is proved by AUC scores of 0.895 and 0.860, as well as AUPR scores of 0.903 and 0.873 for transductive and inductive link prediction respectively. In comorbidity scoring, GSWHomoNet outperformed other methods with a correlation result of 0.848. The effect of the improved association prediction ability of the genetic semantic aware weighted meta-path instance embedding based node embedding is proved on disease-microbe and bibliographic heterogeneous network datasets. For biological significance of GSWHomoNet-based comorbidity scoring, we compared it with gene, pathway, and protein-protein interaction (PPI) perspectives, revealing a stronger correlation with the PPI aspect. We identified a substantial number of predicted comorbidity disease pairs, with 77,456 and 48,972 pairs supported by literature evidence for transductive and inductive predictions, respectively. Additionally, we highlighted shared pathways and PPIs for these pairs, demonstrating the robustness of comorbidity predictions.

Machine learning applications in preventive healthcare: A systematic literature review on predictive analytics of disease comorbidity from multiple perspectives

Artificial intelligence is constantly revolutionizing biomedical research and healthcare management. Disease comorbidity is a major threat to the quality of life for susceptible groups, especially middle-aged and elderly patients. The presence of multiple chronic diseases makes precision diagnosis challenging to realize and imposes a heavy burden on the healthcare system and economy. Given an enormous amount of accumulated health data, machine learning techniques show their capability in handling this puzzle. The present study conducts a review to uncover current research efforts in applying these methods to understanding comorbidity mechanisms and making clinical predictions considering these complex patterns. A descriptive metadata analysis of 791 unique publications aims to capture the overall research progression between January 2012 and June 2023. To delve into comorbidity-focused research, 61 of these scientific papers are systematically assessed. Four predictive analytics of tasks are detected: disease comorbidity data extraction, clustering, network, and risk prediction. It is observed that some machine learning-driven applications address inherent data deficiencies in healthcare datasets and provide a model interpretation that identifies significant risk factors of comorbidity development. Based on insights, both technical and practical, gained from relevant literature, this study intends to guide future interests in comorbidity research and draw conclusions about chronic disease prevention and diagnosis with managerial implications.

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.

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

Ischemic heart disease (IHD) exhibits elevated comorbidity. However, few studies have systematically analyzed the comorbid status of IHD patients with respect to the entire spectrum of chronic diseases. This study applied network analysis to provide a complete picture of physical and mental comorbidities in hospitalized patients with IHD using large-scale administrative data. Hospital discharge records from a provincial healthcare database of IHD inpatients (n = 1,035,338) and one-to-one matched controls were included in this retrospective analysis. We constructed the phenotypic disease networks in IHD and control patients and further assessed differences in comorbidity patterns. The community detection method was applied to cluster diagnoses within the comorbidity network. Age- and sex-specific patterns of IHD comorbidities were also analyzed. IHD inpatients showed 50% larger comorbid burden when compared to controls. The IHD comorbidity network consisted of 1941 significant associations between 71 chronic conditions. Notably, the more densely connected comorbidities in IHD patients were not within the highly prevalent ones but the rarely prevalent ones. Two highly interlinked communities were detected in the IHD comorbidity network, where one included hypertension with heart and multi-organ failures, and another included cerebrovascular diseases, cerebrovascular risk factors and anxiety. Males exhibited higher comorbid burden than females, and thus more complex comorbidity relationships were found in males. Sex-specific disease pairs were detected, e.g., 106 and 30 disease pairs separately dominated in males and females. Aging accounts for the majority of comorbid burden, and the complexity of the comorbidity network increased with age. The network-based approach improves our understanding of IHD-related comorbidities and enhances the integrated management of patients with IHD.

SUBCLINICAL INFLAMMATION IN NON/ALCOHOLIC FATTY LIVER DISEASE AT THE REMOTE PERIOD AFTER THE CHORNOBYL ACCIDENT

OBJECTIVE

to evaluate the parameters of inflammatory reaction and oxidative stress in patients with non-alcoholicfatty liver disease (NAFLD) in the remote period after the influence of the Chornobyl accident factors.

MATERIALS AND METHODS

Eighty two patients with NAFLD who had been exposed to ionizing radiation as a result ofthe Chornobyl accident and have concomitant cardiovascular pathology were examined. Hematological parametersand the level of highly sensitive C-reactive protein (hsCRP) were determined, and the content of products of oxida-tive modification of lipids and proteins was evaluated.

RESULTS

Activation of the processes of oxidative modification of lipids and proteins was observed in most patientswith NAFLD. According to the level of hsCRP, the presence of subclinical inflammation and the risk of developingcomplicated cardiovascular pathology was found in 58 % of patients with NAFLD. The neutrophil / lymphocyte ratiocorrelates positively with hsCRP and can be used as an available routine clinical marker for selection among patientswith NAFLD persons with increased risk of cardiovascular complications.

CONCLUSIONS

HsCRP, oxidative modification products of lipids and proteins, ESR, and leukograms should be used toassess the degree of systemic inflammation in people affected by the Chornobyl accident, suffering NAFLD with con-comitant cardiovascular disease.

Reduced risk of COVID-19 hospitalization in asthmatic and COPD patients: a benefit of inhaled corticosteroids?

Background: The comorbidities and clinical signs of coronavirus disease 2019 (COVID-19) patients have been reported mainly as descriptive statistics, rather than quantitative analysis even in very large investigations. The aim of this study was to identify specific patients’ characteristics that may modulate COVID-19 hospitalization risk.

Research design and methods: A pooled analysis was performed on high-quality epidemiological studies to quantify the prevalence (%) of comorbidities and clinical signs in hospitalized COVID-19 patients. Pooled data were used to calculate the relative risk (RR) of specific comorbidities by matching the frequency of comorbidities in hospitalized COVID-19 patients with those of general population.

Results: The most frequent comorbidities were hypertension, diabetes mellitus, and cardiovascular and/or cerebrovascular diseases. The RR of COVID-19 hospitalization was significantly (P < 0.05) reduced in patients with asthma (0.86, 0.77–0.97) or chronic obstructive pulmonary disease (COPD) (0.46, 0.40–0.52). The most frequent clinical signs were fever and cough.

Conclusion: The clinical signs of hospitalized COVID-19 patients are similar to those of other infective diseases. Patients with asthma or COPD were at lower hospitalization risk. This paradoxical evidence could be related with the protective effect of inhaled corticosteroids that are administered worldwide to most asthmatic and COPD patients.