Comorbidity progression analysis: patient stratification and comorbidity prediction using temporal comorbidity network.

Objective: The study aims to identify distinct population-specific comorbidity progression patterns, timely detect potential comorbidities, and gain better understanding of the progression of comorbid conditions among patients. Methods: This work presents a comorbidity progression analysis framework that utilizes temporal comorbidity networks (TCN) for patient stratification and comorbidity prediction. We propose a TCN construction approach that utilizes longitudinal, temporal diagnosis data of patients to construct their TCN. Subsequently, we employ the TCN for patient stratification by conducting preliminary analysis, and typical prescription analysis to uncover potential comorbidity progression patterns in different patient groups. Finally, we propose an innovative comorbidity prediction method by utilizing the distance-matched temporal comorbidity network (TCN-DM). This method identifies similar patients with disease prevalence and disease transition patterns and combines their diagnosis information with that of the current patient to predict potential comorbidity at the patient's next visit. Results: This study validated the capability of the framework using a real-world dataset MIMIC-III, with heart failure (HF) as interested disease to investigate comorbidity progression in HF patients. With TCN, this study can identify four significant distinctive HF subgroups, revealing the progression of comorbidities in patients. Furthermore, compared to other methods, TCN-DM demonstrated better predictive performance with F1-Score values ranging from 0.454 to 0.612, showcasing its superiority. Conclusions: This study can identify comorbidity patterns for individuals and population, and offer promising prediction for future comorbidity developments in patients.

Understanding Comorbidity Between Non-Suicidal Self-Injury and Depressive Symptoms in a Clinical Sample of Adolescents: A Network Analysis.

Background: Non-suicidal self-injury (NSSI) and depression often co-occur among adolescents with more severe clinical symptoms. This study examined the network structures of NSSI and depressive symptoms in adolescents. Methods: Participants were recruited in the psychiatric outpatient clinics of three tertiary hospitals between April 10 and July 10, 2023. All participants been already found with self-injury behaviors in outpatient when enrolled. NSSI diagnostic criteria and Patient Health Questionnaire-9 (PHQ-9) were utilized to collect NSSI and depressive symptoms separately. We performed a network analysis to visualize the correlation between each symptom and to identify core and bridging symptoms in comorbidities. Results: A total of 248 patients were enrolled in the study, with a mean age of 15.48 (SD = 1.62). Based on the PHQ-9 scores and grades, our results showed that the incidence of depression in adolescents with non-suicidal self-injury behavior was relatively high (N=235, 94.76%), with the majority having severe depression. The network analysis revealed that nodes D-6 "feeling bad, failing or letting yourself or your family down", D-1 "little interest or pleasure" and D-4 "feeling tired" were the most vital and most central symptoms. The most crucial bridging symptom is the node NSSI-8 "frequent thinking about self-injury", which connects the NSSI to the depression comorbid network. Conclusion: This study offers a significant symptom-level conceptualization of the association between NSSI and depressive symptoms in a clinical sample of adolescents, which not only enhances our understanding of the comorbid but also identifies potential treatment targets to prevent and treat comorbidity between adolescent NSSI and depression.

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 network analysis using graphical models for electronic health records.

Importance: The comorbidity network represents multiple diseases and their relationships in a graph. Understanding comorbidity networks among critical care unit (CCU) patients can help doctors diagnose patients faster, minimize missed diagnoses, and potentially decrease morbidity and mortality. Objective: The main objective of this study was to identify the comorbidity network among CCU patients using a novel application of a machine learning method (graphical modeling method). The second objective was to compare the machine learning method with a traditional pairwise method in simulation. Method: This cross-sectional study used CCU patients' data from Medical Information Mart for the Intensive Care-3 (MIMIC-3) dataset, an electronic health record (EHR) of patients with CCU hospitalizations within Beth Israel Deaconess Hospital from 2001 to 2012. A machine learning method (graphical modeling method) was applied to identify the comorbidity network of 654 diagnosis categories among 46,511 patients. Results: Out of the 654 diagnosis categories, the graphical modeling method identified a comorbidity network of 2,806 associations in 510 diagnosis categories. Two medical professionals reviewed the comorbidity network and confirmed that the associations were consistent with current medical understanding. Moreover, the strongest association in our network was between "poisoning by psychotropic agents" and "accidental poisoning by tranquilizers" (logOR 8.16), and the most connected diagnosis was "disorders of fluid, electrolyte, and acid-base balance" (63 associated diagnosis categories). Our method outperformed traditional pairwise comorbidity network methods in simulation studies. Some strongest associations between diagnosis categories were also identified, for example, "diagnoses of mitral and aortic valve" and "other rheumatic heart disease" (logOR: 5.15). Furthermore, our method identified diagnosis categories that were connected with most other diagnosis categories, for example, "disorders of fluid, electrolyte, and acid-base balance" was associated with 63 other diagnosis categories. Additionally, using a data-driven approach, our method partitioned the diagnosis categories into 14 modularity classes. Conclusion and relevance: Our graphical modeling method inferred a logical comorbidity network whose associations were consistent with current medical understanding and outperformed traditional network methods in simulation. Our comorbidity network method can potentially assist CCU doctors in diagnosing patients faster and minimizing missed diagnoses.

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.

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.

Adverse health consequences of undiagnosed hearing loss at middle age: A prospective cohort study with the UK Biobank.

OBJECTIVES: Hearing impairment is common in the middle-aged population but remains largely undiagnosed and untreated. The knowledge about to what extent and how hearing impairment matters for health is currently lacking. Thus, we aimed to comprehensively examine the adverse health consequences as well as the comorbidity patterns of undiagnosed hearing loss. STUDY DESIGN: Based on the prospective cohort of the UK Biobank, we included 14,620 individuals (median age 61 years) with audiometry-determined (i.e., speech-in-noise test) objective hearing loss and 38,479 individuals with subjective hearing loss (i.e., tested negative but with self-reported hearing problems; median age 58 years) at recruitment (2006-2010), together with 29,240 and 38,479 matched unexposed individuals respectively. MAIN OUTCOME MEASURES: Cox regression was used to determine the associations of both hearing-loss exposures with the risk of 499 medical conditions and 14 cause-specific deaths, adjusting for ethnicity, annual household income, smoking and alcohol intake, exposure to working noise, and BMI. Comorbidity patterns following both exposures were visualized by comorbidity modules (i.e., sets of connected diseases) identified in the comorbidity network analyses. RESULTS: During a median follow-up of 9 years, 28 medical conditions and mortality related to nervous system disease showed significant associations with prior objective hearing loss. Subsequently, the comorbidity network identified four comorbidity modules (i.e., neurodegenerative, respiratory, psychiatric, and cardiometabolic diseases), with the most pronounced association noted for the module related to neurodegenerative diseases (meta-hazard ratio [HR] = 2.00, 95%confidence interval [CI] 1.67-2.39). For subjective hearing loss, we found 57 associated medical conditions, which were partitioned into four modules (i.e., diseases related to the digestive, psychiatric, inflammatory, and cardiometabolic systems), with meta-HRs varying from 1.17 to 1.25. CONCLUSIONS: Undiagnosed hearing loss captured by screening could identify individuals with at greater risk of multiple adverse health consequences, highlighting the importance of screening for speech-in-noise hearing impairment in the middle-aged population, for potential early diagnosis and intervention.

Health consequences of early-onset compared with late-onset type 2 diabetes mellitus.

Background: Although cumulating evidence has suggested that early-onset type 2 diabetes mellitus (T2DM) conferred on patients a broader tendency for complications beyond vascular ones, a comprehensive analysis of patterns of complications across all relevant systems is currently lacking. Method: We prospectively studied 1 777 early-onset (age at diagnosis ≤ 45 years) and 35 889 late-onset (>45 years) T2DM patients with matched unexposed individuals from the UK Biobank. Diabetes-specific and -related complications were examined using phenome-wide association analysis, with patterns identified by comorbidity network analysis. We also evaluated the effect of lifestyle modifications and glycemic control on complication development. Results: The median follow-up times for early-onset and late-onset T2DM patients were 17.83 and 9.39 years, respectively. Compared to late-onset T2DM patients, patients with early-onset T2DM faced a significantly higher relative risk of developing subsequent complications that primarily affected sense organs [hazard ratio (HR) 3.46 vs. 1.72], the endocrine/metabolic system (HR 3.08 vs. 2.01), and the neurological system (HR 2.70 vs. 1.81). Despite large similarities in comorbidity patterns, a more complex and well-connected network was observed for early-onset T2DM. Furthermore, while patients with early-onset T2DM got fewer benefits (12.67% reduction in pooled HR for all studied complications) through fair glycemic control (median HbA1c ≤ 53 mmol/mol) compared to late-onset T2DM patients (18.01% reduction), they seemed to benefit more from favorable lifestyles, including weight control, healthy diet, and adequate physical activity. Conclusions: Our analyses reveal that early-onset T2DM is an aggressive disease resulting in more complex complication networks than late-onset T2DM. Aggressive glucose-lowering intervention, complemented by lifestyle modifications, are feasible strategies for controlling early-onset T2DM-related complications.

Nature and Extent of Physical Comorbidities Among Korean Patients With Mental Illnesses: Pairwise and Network Analysis Based on Health Insurance Claims Data.

OBJECTIVE: The nature of physical comorbidities in patients with mental illness may differ according to diagnosis and personal characteristics. We investigated this complexity by conventional logistic regression and network analysis. METHODS: A health insurance claims data in Korea was analyzed. For every combination of psychiatric and physical diagnoses, odds ratios were calculated adjusting age and sex. From the patient-diagnosis data, a network of diagnoses was constructed using Jaccard coefficient as the index of comorbidity. RESULTS: In 1,017,024 individuals, 77,447 (7.6%) were diagnosed with mental illnesses. The number of physical diagnoses among them was 11.2, which was 1.6 times higher than non-psychiatric groups. The most noticeable associations were 1) neurotic illnesses with gastrointestinal/pain disorders and 2) dementia with fracture, Parkinson's disease, and cerebrovascular accidents. Unexpectedly, the diagnosis of metabolic syndrome was only scarcely found in patients with severe mental illnesses (SMIs). However, implicit associations between metabolic syndrome and SMIs were suggested in comorbidity networks. CONCLUSION: Physical comorbidities in patients with mental illnesses were more extensive than those with other disease categories. However, the result raised questions as to whether the medical resources were being diverted to less serious conditions than more urgent conditions in patients with SMIs.

VIRdb 2.0: Interactive analysis of comorbidity conditions associated with vitiligo pathogenesis using co-expression network-based approach.

Vitiligo is a disease of mysterious origins in the context of its occurrence and pathogenesis. The autoinflammatory theory is perhaps the most widely accepted theory that discusses the occurrence of Vitiligo. The theory elaborates the clinical association of vitiligo with autoimmune disorders such as Psoriasis, Multiple Sclerosis and Rheumatoid Arthritis and Diabetes. In the present work, we discuss the comprehensive set of differentially co-expressed genes involved in the crosstalk events between Vitiligo and associated autoimmune disorders (Psoriasis, Multiple Sclerosis and Rheumatoid Arthritis). We progress our previous tool, Vitiligo Information Resource (VIRdb), and incorporate into it a compendium of Vitiligo-related multi-omics datasets and present it as VIRdb 2.0. It is available as a web-resource consisting of statistically sound and manually curated information. VIRdb 2.0 is an integrative database as its datasets are connected to KEGG, STRING, GeneCards, SwissProt, NPASS. Through the present study, we communicate the major updates and expansions in the VIRdb and deliver the new version as VIRdb 2.0. VIRdb 2.0 offers the maximum user interactivity along with ease of navigation. We envision that VIRdb 2.0 will be pertinent for the researchers and clinicians engaged in drug development for vitiligo.

The Alzheimer's comorbidity phenome: mining from a large patient database and phenome-driven genetics prediction.

OBJECTIVE: Alzheimer's disease (AD) is a severe neurodegenerative disorder and has become a global public health problem. Intensive research has been conducted for AD. But the pathophysiology of AD is still not elucidated. Disease comorbidity often associates diseases with overlapping patterns of genetic markers. This may inform a common etiology and suggest essential protein targets. US Food and Drug Administration (FDA) Adverse Event Reporting System (FAERS) collects large-scale postmarketing surveillance data that provide a unique opportunity to investigate disease co-occurrence pattern. We aim to construct a heterogeneous network that integrates disease comorbidity network (DCN) from FAERS with protein-protein interaction (PPI) to prioritize the AD risk genes using network-based ranking algorithm. MATERIALS AND METHODS: We built a DCN based on indication data from FAERS using association rule mining. DCN was further integrated with PPI network. We used random walk with restart ranking algorithm to prioritize AD risk genes. RESULTS: We evaluated the performance of our approach using AD risk genes curated from genetic association studies. Our approach achieved an area under a receiver operating characteristic curve of 0.770. Top 500 ranked genes achieved 5.53-fold enrichment for known AD risk genes as compared to random expectation. Pathway enrichment analysis using top-ranked genes revealed that two novel pathways, ERBB and coagulation pathways, might be involved in AD pathogenesis. CONCLUSION: We innovatively leveraged FAERS, a comprehensive data resource for FDA postmarket drug safety surveillance, for large-scale AD comorbidity mining. This exploratory study demonstrated the potential of disease-comorbidities mining from FAERS in AD genetics discovery.

Large-scale mining disease comorbidity relationships from post-market drug adverse events surveillance data.

BACKGROUND: Systems approaches in studying disease relationship have wide applications in biomedical discovery, such as disease mechanism understanding and drug discovery. The FDA Adverse Event Reporting System (FAERS) contains rich information about patient diseases, medications, drug adverse events and demographics of 17 million case reports. Here, we explored this data resource to mine disease comorbidity relationships using association rule mining algorithm and constructed a disease comorbidity network. RESULTS: We constructed a disease comorbidity network with 1059 disease nodes and 12,608 edges using association rule mining of FAERS (14,157 rules). We evaluated the performance of comorbidity mining from FAERS using known disease comorbidities of multiple sclerosis (MS), psoriasis and obesity that represent rare, moderate and common disease respectively. Comorbidities of MS, obesity and psoriasis obtained from our network achieved precisions of 58.6%, 73.7%, 56.2% and recalls 87.5%, 69.2% and 72.7% separately. We performed comparative analysis of the disease comorbidity network with disease semantic network, disease genetic network and disease treatment network. We showed that (1) disease comorbidity clusters exhibit significantly higher semantic similarity than random network (0.18 vs 0.10); (2) disease comorbidity clusters share significantly more genes (0.46 vs 0.06); and (3) disease comorbidity clusters share significantly more drugs (0.64 vs 0.17). Finally, we demonstrated that the disease comorbidity network has potential in uncovering novel disease relationships using asthma as a case study. CONCLUSIONS: Our study presented the first comprehensive attempt to build a disease comorbidity network from FDA Adverse Event Reporting System. This network shows well correlated with disease semantic similarity, disease genetics and disease treatment, which has great potential in disease genetics prediction and drug discovery.

A new approach to disentangle genetic and epigenetic components on disease comorbidities: studying correlation between genotypic and phenotypic disease networks.

Disease comorbidity is a result of complex epigenetic interplay. A disease is rarely a consequence of an abnormality in a single gene; complex pathways to disease patterns emerge from gene-gene interactions and gene-environment interactions. Understanding these mechanisms of disease and comorbidity development, breaking down them into clusters and disentangling the epigenetic - actionable - components, is of utter importance from a public health perspective. With the increase in the average life expectancy, healthy aging becomes a primary objective, from both an individual (i.e. quality of life) and a societal (i.e. healthcare costs) standpoint. Many studies have analyzed disease networks based on common altered genes, on protein-protein interactions, or on shared disease comorbidites, i.e. phenotypic disease networks. In this work we aim at studying the relations between genotypic and phenotypic disease networks, using a large statewide cohort of individuals (100, 000+ from California, USA) with linked clinical and genotypic information, the Genetic Epidemiology Research on Adult Health and Aging (GERA). By comparing their phenotypic and genotypic networks, we try to disentangle the epigenetic component of disease comorbidity.

Disease Comorbidity Network Guides the Detection of Molecular Evidence for the Link Between Colorectal Cancer and Obesity.

Epidemiological studies suggested that obesity increases the risk of colorectal cancer (CRC). The genetic connection between CRC and obesity is multifactorial and inconclusive. In this study, we hypothesize that the study of shared comorbid diseases between CRC and obesity can offer unique insights into common genetic basis of these two diseases. We constructed a comorbidity network based on mining health data for millions of patients. We developed a novel approach and extracted the diseases that play critical roles in connecting obesity and CRC in the comorbidity network. Our approach was able to prioritize metabolic syndrome and diabetes, which are known to be associated with obesity and CRC through insulin resistance pathways. Interestingly, we found that osteoporosis was highly associated with the connection between obesity and CRC. Through gene expression meta-analysis, we identified novel genes shared among CRC, obesity and osteoporosis. Literature evidences support that these genes may contribute in explaining the genetic overlaps between obesity and CRC.