How High-Risk Comorbidities Co-Occur in Readmitted Patients With Hip Fracture: Big Data Visual Analytical Approach

Abstract

Background When older adult patients with hip fracture (HFx) have unplanned hospital readmissions within 30 days of discharge, it doubles their 1-year mortality, resulting in substantial personal and financial burdens. Although such unplanned readmissions are predominantly caused by reasons not related to HFx surgery, few studies have focused on how pre-existing high-risk comorbidities co-occur within and across subgroups of patients with HFx. Objective This study aims to use a combination of supervised and unsupervised visual analytical methods to (1) obtain an integrated understanding of comorbidity risk, comorbidity co-occurrence, and patient subgroups, and (2) enable a team of clinical and methodological stakeholders to infer the processes that precipitate unplanned hospital readmission, with the goal of designing targeted interventions. Methods We extracted a training data set consisting of 16,886 patients (8443 readmitted patients with HFx and 8443 matched controls) and a replication data set consisting of 16,222 patients (8111 readmitted patients with HFx and 8111 matched controls) from the 2010 and 2009 Medicare database, respectively. The analyses consisted of a supervised combinatorial analysis to identify and replicate combinations of comorbidities that conferred significant risk for readmission, an unsupervised bipartite network analysis to identify and replicate how high-risk comorbidity combinations co-occur across readmitted patients with HFx, and an integrated visualization and analysis of comorbidity risk, comorbidity co-occurrence, and patient subgroups to enable clinician stakeholders to infer the processes that precipitate readmission in patient subgroups and to propose targeted interventions. Results The analyses helped to identify (1) 11 comorbidity combinations that conferred significantly higher risk (ranging from P<.001 to P=.01) for a 30-day readmission, (2) 7 biclusters of patients and comorbidities with a significant bicluster modularity (P<.001; Medicare=0.440; random mean 0.383 [0.002]), indicating strong heterogeneity in the comorbidity profiles of readmitted patients, and (3) inter- and intracluster risk associations, which enabled clinician stakeholders to infer the processes involved in the exacerbation of specific combinations of comorbidities leading to readmission in patient subgroups. Conclusions The integrated analysis of risk, co-occurrence, and patient subgroups enabled the inference of processes that precipitate readmission, leading to a comorbidity exacerbation risk model for readmission after HFx. These results have direct implications for (1) the management of comorbidities targeted at high-risk subgroups of patients with the goal of pre-emptively reducing their risk of readmission and (2) the development of more accurate risk prediction models that incorporate information about patient subgroups.

Age- and Sex-Specific Differences in Multimorbidity Patterns and Temporal Trends on Assessing Hospital Discharge Records in Southwest China: Network-Based Study

“…For example, we identified some disease pairs that occurred throughout life (eg, heart failure co-occurring with complications of heart disease and lipoprotein metabolism disorders co-occurring with diabetes mellitus) and some pairs with a stronger comorbid strength but only occurrence among a typical age group (eg, congenital malformation co-existence in children <7 years old). Intuitively, chronic diseases would be expected to co-occur in an individual if their resilience or vulnerability was altered or if they shared a common pattern of influence [48][49][50]. Thus, as in previous studies assessing the disease trajectory in patients with depression [51] and type 2 diabetes [52], and the general population [24], regional databases collecting HDRs spanning a sufficient time period (generally 10+ years as in the above mentioned studies) will support further studies to explore the potential causal directions among complex correlations.…”

Modeling and Interpreting Patient Subgroups in Hospital Readmission: Visual Analytical Approach

“…In contrast, Figure 1B shows a bipartite network where nodes are of two types, and edges exist only between different types such as between patients (circles) and comorbidities (triangles). This approach uses bipartite modularity maximization [20,[24][25][26], a graph-theoretic approach to (a) quantitatively output the number, size, and statistical significance [18,27] of biclusters (consisting of a patient subgroup and its most frequently co-occurring comorbidities), and (b) visualize those biclusters using layout algorithms [28,29] to enable their clinical interpretation [11,12,[30][31][32][33][34][35][36]. As shown in Fig.…”

“…1C, a bipartite visualization could enable clinicians to inspect the bicluster associations, infer potential mechanisms in each patient subgroup, and design targeted interventions. Our prior use of bipartite networks have enabled three types of discoveries related to subgroups: (1) novel subtypes (e.g., in asthma [33]); (2) frequency of known subtypes in a new condition (e.g., in COVID-19 [11]), and (3) risk of subtypes for adverse outcomes (e.g., in hip fracture hospital readmission [12]). Furthermore, the above subgroups could be used to train classifiers for classifying a new patient into a subgroup, and to build predictive models that leverage such patient subgroups to predict an outcome in a new patient.…”

“…None of the CMS models used information related to patient subgroups. Therefore, while such models provide the risk of readmission for an individual patient, they do not leverage the existence of patient subgroups known to be present among patients with hospital readmission [12]. Such patient subgroups could be used in hierarchical regression models to potentially achieve higher predictive accuracy.…”

“…Furthermore, multiple comorbidities often do not act independently, but rather interact with each other, resulting in processes that can precipitate readmission [45]. For example, due to the systemic nature of renal disease, a hip fracture patient with congestive heart failure and renal failure is at a higher risk of renal failure exacerbation, precipitating a hospital readmission, compared to one who only had renal failure [12]. To enable a head-to-head comparison with the CMS predictive models, we used the same independent variables for our predictive models.…”