A cluster-based approach for integrating clinical management of Medicare beneficiaries with multiple chronic conditions

General Principles, Etiologies, Evaluation, and Management in Older Adults

Hypertension impacts most older adults as one of many multiple chronic conditions. A thorough evaluation is required to assess overall health, cardiovascular status, and comorbid conditions that impact treatment targets. In the absence of severe frailty or dementia, intensive treatment prevents more cardiovascular events than standard treatment and may slow cognitive decline. "Start low and go slow" is not the best strategy for many older adults as fewer cardiovascular events occur when hypertension is controlled within the first 3 to 6 months of treatment.

Managing Hypertension in Older Adults

PURPOSE OF REVIEW

The population of older adults 60-79 years globally is projected to double from 800 million to 1.6 billion between 2015 and 2050, while adults ≥ 80 years were forecast to more than triple from 125 to 430 million. The risk for cardiovascular events doubles with each decade of aging and each 20 mmHg increase of systolic blood pressure. Thus, successful management of hypertension in older adults is critical in mitigating the projected global health and economic burden of cardiovascular disease.

RECENT FINDINGS

Women live longer than men, yet with aging systolic blood pressure and prevalent hypertension increase more, and hypertension control decreases more than in men, i.e., hypertension in older adults is disproportionately a women's health issue. Among older adults who are healthy to mildly frail, the absolute benefit of hypertension control, including more intensive control, on cardiovascular events is greater in adults ≥ 80 than 60-79 years old. The absolute rate of serious adverse events during antihypertensive therapy is greater in adults ≥ 80 years older than 60-79 years, yet the excess adverse event rate with intensive versus standard care is only moderately increased. Among adults ≥ 80 years, benefits of more intensive therapy appear non-existent to reversed with moderate to marked frailty and when cognitive function is less than roughly the twenty-fifth percentile. Accordingly, assessment of functional and cognitive status is important in setting blood pressure targets in older adults. Given substantial absolute cardiovascular benefits of more intensive antihypertensive therapy in independent-living older adults, this group merits shared-decision making for hypertension targets.

Epidemiology, mortality, and health service use of local-level multimorbidity patterns in South Spain

Multimorbidity -understood as the occurrence of chronic diseases together- represents a major challenge for healthcare systems due to its impact on disability, quality of life, increased use of services and mortality. However, despite the global need to address this health problem, evidence is still needed to advance our understanding of its clinical and social implications. Our study aims to characterise multimorbidity patterns in a dataset of 1,375,068 patients residing in southern Spain. Combining LCA techniques and geographic information, together with service use, mortality, and socioeconomic data, 25 chronicity profiles were identified and subsequently characterised by sex and age. The present study has led us to several findings that take a step forward in this field of knowledge. Specifically, we contribute to the identification of an extensive range of at-risk groups. Moreover, our study reveals that the complexity of multimorbidity patterns escalates at a faster rate and is associated with a poorer prognosis in local areas characterised by lower socioeconomic status. These results emphasize the persistence of social inequalities in multimorbidity, highlighting the need for targeted interventions to mitigate the impact on patients' quality of life, healthcare utilisation, and mortality rates.

Risk factors, outcomes and healthcare utilisation in individuals with multimorbidity including heart failure, chronic kidney disease and type 2 diabetes mellitus: a national electronic health record study

BACKGROUND

Heart failure (HF), type 2 diabetes (T2D) and chronic kidney disease (CKD) commonly coexist. We studied characteristics, prognosis and healthcare utilisation of individuals with two of these conditions.

METHODS

We performed a retrospective, population-based linked electronic health records study from 1998 to 2020 in England to identify individuals diagnosed with two of: HF, T2D or CKD. We described cohort characteristics at time of second diagnosis and estimated risk of developing the third condition and mortality using Kaplan-Meier and Cox regression models. We also estimated rates of healthcare utilisation in primary care and hospital settings in follow-up.

FINDINGS

We identified cohorts of 64 226 with CKD and HF, 82 431 with CKD and T2D, and 13 872 with HF and T2D. Compared with CKD and T2D, those with CKD and HF and HF and T2D had more severe risk factor profile. At 5 years, incidence of the third condition and all-cause mortality occurred in 37% (95% CI: 35.9%, 38.1%%) and 31.3% (30.4%, 32.3%) in HF+T2D, 8.7% (8.4%, 9.0%) and 51.6% (51.1%, 52.1%) in HF+CKD, and 6.8% (6.6%, 7.0%) and 17.9% (17.6%, 18.2%) in CKD+T2D, respectively. In each of the three multimorbid groups, the order of the first two diagnoses was also associated with prognosis. In multivariable analyses, we identified risk factors for developing the third condition and mortality, such as age, sex, medical history and the order of disease diagnosis. Inpatient and outpatient healthcare utilisation rates were highest in CKD and HF, and lowest in CKD and T2D.

INTERPRETATION

HF, CKD and T2D carry significant mortality and healthcare burden in combination. Compared with other disease pairs, individuals with CKD and HF had the most severe risk factor profile, prognosis and healthcare utilisation. Service planning, policy and prevention must take into account and monitor data across conditions.

Social determinants of multimorbidity patterns: A systematic review

Social determinants of multimorbidity are poorly understood in clinical practice. This review aims to characterize the different multimorbidity patterns described in the literature while identifying the social and behavioral determinants that may affect their emergence and subsequent evolution. We searched PubMed, Embase, Scopus, Web of Science, Ovid MEDLINE, CINAHL Complete, PsycINFO and Google Scholar. In total, 97 studies were chosen from the 48,044 identified. Cardiometabolic, musculoskeletal, mental, and respiratory patterns were the most prevalent. Cardiometabolic multimorbidity profiles were common among men with low socioeconomic status, while musculoskeletal, mental and complex patterns were found to be more prevalent among women. Alcohol consumption and smoking increased the risk of multimorbidity, especially in men. While the association of multimorbidity with lower socioeconomic status is evident, patterns of mild multimorbidity, mental and respiratory related to middle and high socioeconomic status are also observed. The findings of the present review point to the need for further studies addressing the impact of multimorbidity and its social determinants in population groups where this problem remains invisible (e.g., women, children, adolescents and young adults, ethnic groups, disabled population, older people living alone and/or with few social relations), as well as further work with more heterogeneous samples (i.e., not only focusing on older people) and using more robust methodologies for better classification and subsequent understanding of multimorbidity patterns. Besides, more studies focusing on the social determinants of multimorbidity and its inequalities are urgently needed in low- and middle-income countries, where this problem is currently understudied.

Changing the research paradigm for digital transformation in healthcare delivery

The growing focus on healthcare transformation (i.e., new healthcare delivery models) raises interesting issues related to research design, methodology, and funding. More than 20 years have passed since the Institute of Medicine first called for the transition to digital health with a focus on system-wide change. Yet progress in healthcare delivery system change has been painfully slow. A knowledge gap exists; research has been inadequate and critical information is lacking. Despite calls by the National Academies of Science, Engineering, and Medicine for convergent, team-based transdisciplinary research with societal impact, the preponderance of healthcare research and funding continues to support more traditional siloed discipline research approaches. The lack of impact on healthcare delivery suggests that it is time to step back and consider differences between traditional science research methods and the realities of research in the domain of transformational change. The proposed new concepts in research design, methodologies, and funding are a needed step to advance the science. The Introduction looks at the growing gap in expectations for transdisciplinary convergent research and prevalent practices in research design, methodologies, and funding. The second section summarizes current expectations and drivers related to digital health transformation and the complex system problem of healthcare fragmentation. The third section then discusses strengths and weaknesses of current research and practice with the goal of identifying gaps. The fourth section introduces the emerging science of healthcare delivery and associated research methodologies with a focus on closing the gaps between research and translation at the frontlines. The final section concludes by proposing new transformational science research methodologies and offers evidence that suggests how and why they better align with the aims of digital transformation in healthcare delivery and could significantly accelerate progress in achieving them. It includes a discussion of challenges related to grant funding for non-traditional research design and methods. The findings have implications broadly beyond healthcare to any research that seeks to achieve high societal impact.

Remote Patient Management May Reduce All-Cause Mortality in Patients With Heart-Failure and Renal Impairment

Background

Remote patient management (RPM) in heart failure (HF) patients has been investigated in several prospective randomized trials. The Telemedical Interventional Management in Heart Failure II (TIM-HF2)-trial showed reduced all-cause mortality and hospitalizations in heart failure (HF) patients using remote patient management (RPM) vs. usual care (UC). We report the trial's results for prespecified eGFR-subgroups.

Methods

TIM-HF2 was a prospective, randomized, controlled, parallel-group, unmasked (with randomization concealment), multicenter trial. A total of 1,538 patients with stable HF were enrolled in Germany from 2013 to 2017 and randomized to RPM (+UC) or UC. Using CKD-EPI-formula at baseline, prespecified subgroups were defined. In RPM, patients transmitted their vital parameters daily. The telemedical center reviewed and co-operated with the patient's General Practitioner (GP) and cardiologist. In UC, patients were treated by their GPs or cardiologist applying the current guidelines for HF management and treatment. The primary endpoint was the percentage of days lost due to unplanned cardiovascular hospitalizations or death, secondary outcomes included hospitalizations, all-cause, and cardiovascular mortality.

Results

Our sub analysis showed no difference between RPM and UC in both eGFR-subgroups for the primary endpoint (<60 ml/min/1.73 m2: 40.9% vs. 43.6%, p = 0.1, ≥60 ml/min/1.73 m2 26.5 vs. 29.3%, p = 0.36). In patients with eGFR < 60 ml/min/1.73 m2, 1-year-survival was higher in RPM than UC (89.4 vs. 84.6%, p = 0.02) with an incident rate ratio (IRR) 0.67 (p = 0.03). In the recurrent event analysis, HF hospitalizations and all-cause death were lower in RPM than UC in both eGFR-subgroups (<60 ml/min/1.73 m2: IRR 0.70, p = 0.02; ≥60 ml/min/1.73 m2: IRR 0.64, p = 0.04). In a cox regression analysis, age, NT-pro BNP, eGFR, and BMI were associated with all-cause mortality.

Conclusion

RPM may reduce all-cause mortality and HF hospitalizations in patients with HF and eGFR < 60 ml/min/1.73 m2. HF hospitalizations and all-cause death were lower in RPM in both eGFR-subgroups in the recurrent event analysis. Further studies are needed to investigate and confirm this finding.

Exploring patient multimorbidity and complexity using health insurance claims data: a cluster analysis approach (Preprint)

Background

Although the trend of progressing morbidity is widely recognized, there are numerous challenges when studying multimorbidity and patient complexity. For multimorbid or complex patients, prone to fragmented care and high health care use, novel estimation approaches need to be developed.

Objective

This study aims to investigate the patient multimorbidity and complexity of Swiss residents aged ≥50 years using clustering methodology in claims data.

Methods

We adopted a clustering methodology based on random forests and used 34 pharmacy-based cost groups as the only input feature for the procedure. To detect clusters, we applied hierarchical density-based spatial clustering of applications with noise. The reasonable hyperparameters were chosen based on various metrics embedded in the algorithms (out-of-bag misclassification error, normalized stress, and cluster persistence) and the clinical relevance of the obtained clusters.

Results

Based on cluster analysis output for 18,732 individuals, we identified an outlier group and 7 clusters: individuals without diseases, patients with only hypertension-related diseases, patients with only mental diseases, complex high-cost high-need patients, slightly complex patients with inexpensive low-severity pharmacy-based cost groups, patients with 1 costly disease, and older high-risk patients.

Conclusions

Our study demonstrated that cluster analysis based on pharmacy-based cost group information from claims-based data is feasible and highlights clinically relevant clusters. Such an approach allows expanding the understanding of multimorbidity beyond simple disease counts and can identify the population profiles with increased health care use and costs. This study may foster the development of integrated and coordinated care, which is high on the agenda in policy making, care planning, and delivery.

Abandonment at the Transition from Hospital to Home: Family Caregivers' Experiences

Background

People with concurrent chronic conditions face different situations that lead to frequent transferring between the hospital and home. Despite the use of different strategies for improving transitional care, these transferring is associated with different challenges. This article aims to explore family caregivers' experiences of transitional care in diabetes with concurrent chronic conditions.

Methods

This descriptive explorative study was done at university hospitals in two big cities (Isfahan and Tehran) of Iran. The data collection was conducted from November 2018 to February 2020 using deep, semi-structured, and face-to-face interviews which are focused on family caregivers' experiences of transitional care. The researchers continued the sampling until the data saturation. Finally, 15 family caregivers were selected through purposive sampling. Data collection and data analysis were performed concurrently. Data were analyzed through the conventional content analysis method.

Results

Two main themes were identified: unsafe transition (unplanned discharge, inappropriate communication, lack of patient center care, and unavailable healthcare team) and erosive effort (financial burden, psychological stress, physical exhaustion, and lack of supportive sources).

Conclusion

The findings point to the importance of designing a discharge plan and preparing family caregivers before being discharged by healthcare providers. It appears to be essential for health managers and policymakers to pay attention to safe transitional care planning. The establishment of transitional care centers will help to ensure continuity of care. Future research focusing on the design and implementation of an appropriate transitional care model is recommended.

Simulation-derived best practices for clustering clinical data

INTRODUCTION

Clustering analyses in clinical contexts hold promise to improve the understanding of patient phenotype and disease course in chronic and acute clinical medicine. However, work remains to ensure that solutions are rigorous, valid, and reproducible. In this paper, we evaluate best practices for dissimilarity matrix calculation and clustering on mixed-type, clinical data.

METHODS

We simulate clinical data to represent problems in clinical trials, cohort studies, and EHR data, including single-type datasets (binary, continuous, categorical) and 4 data mixtures. We test 5 single distance metrics (Jaccard, Hamming, Gower, Manhattan, Euclidean) and 3 mixed distance metrics (DAISY, Supersom, and Mercator) with 3 clustering algorithms (hierarchical (HC), k-medoids, self-organizing maps (SOM)). We quantitatively and visually validate by Adjusted Rand Index (ARI) and silhouette width (SW). We applied our best methods to two real-world data sets: (1) 21 features collected on 247 patients with chronic lymphocytic leukemia, and (2) 40 features collected on 6000 patients admitted to an intensive care unit.

RESULTS

HC outperformed k-medoids and SOM by ARI across data types. DAISY produced the highest mean ARI for mixed data types for all mixtures except unbalanced mixtures dominated by continuous data. Compared to other methods, DAISY with HC uncovered superior, separable clusters in both real-world data sets.

DISCUSSION

Selecting an appropriate mixed-type metric allows the investigator to obtain optimal separation of patient clusters and get maximum use of their data. Superior metrics for mixed-type data handle multiple data types using multiple, type-focused distances. Better subclassification of disease opens avenues for targeted treatments, precision medicine, clinical decision support, and improved patient outcomes.

Umpire 2.0: Simulating realistic, mixed-type, clinical data for machine learning

The Umpire 2.0 R-package offers a streamlined, user-friendly workflow to simulate complex, heterogeneous, mixed-type data with known subgroup identities, dichotomous outcomes, and time-to-event data, while providing ample opportunities for fine-tuning and flexibility. Here, we describe how we have expanded the core Umpire 1.0 R-package, developed to simulate gene expression data, to generate clinically realistic, mixed-type data for use in evaluating unsupervised and supervised machine learning (ML) methods. As the availability of large-scale clinical data for ML has increased, clinical data has posed unique challenges, including widely variable size, individual biological heterogeneity, data collection and measurement noise, and mixed data types. Developing and validating ML methods for clinical data requires data sets with known ground truth, generated from simulation. Umpire 2.0 addresses challenges to simulating realistic clinical data by providing the user a series of modules to generate survival parameters and subgroups, apply meaningful additive noise, and discretize to single or mixed data types. Umpire 2.0 provides broad functionality across sample sizes, feature spaces, and data types, allowing the user to simulate correlated, heterogeneous, binary, continuous, categorical, or mixed type data from the scale of a small clinical trial to data on thousands of patients drawn from electronic health records. The user may generate elaborate simulations by varying parameters in order to compare algorithms or interrogate operating characteristics of an algorithm in both supervised and unsupervised ML.

Use of Latent Class Analysis and k-Means Clustering to Identify Complex Patient Profiles

IMPORTANCE

Medically complex patients are a heterogeneous group that contribute to a substantial proportion of health care costs. Coordinated efforts to improve care and reduce costs for this patient population have had limited success to date.

OBJECTIVE

To define distinct patient clinical profiles among the most medically complex patients through clinical interpretation of analytically derived patient clusters.

DESIGN, SETTING, AND PARTICIPANTS

This cohort study analyzed the most medically complex patients within Kaiser Permanente Northern California, a large integrated health care delivery system, based on comorbidity score, prior emergency department admissions, and predicted likelihood of hospitalization, from July 18, 2018, to July 15, 2019. From a starting point of over 5000 clinical variables, we used both clinical judgment and analytic methods to reduce to the 97 most informative covariates. Patients were then grouped using 2 methods (latent class analysis, generalized low-rank models, with k-means clustering). Results were interpreted by a panel of clinical stakeholders to define clinically meaningful patient profiles.

MAIN OUTCOMES AND MEASURES

Complex patient profiles, 1-year health care utilization, and mortality outcomes by profile.

RESULTS

The analysis included 104 869 individuals representing 3.3% of the adult population (mean [SD] age, 70.7 [14.5] years; 52.4% women; 39% non-White race/ethnicity). Latent class analysis resulted in a 7-class solution. Stakeholders defined the following complex patient profiles (prevalence): high acuity (9.4%), older patients with cardiovascular complications (15.9%), frail elderly (12.5%), pain management (12.3%), psychiatric illness (12.0%), cancer treatment (7.6%), and less engaged (27%). Patients in these groups had significantly different 1-year mortality rates (ranging from 3.0% for psychiatric illness profile to 23.4% for frail elderly profile; risk ratio, 7.9 [95% CI, 7.1-8.8], P < .001). Repeating the analysis using k-means clustering resulted in qualitatively similar groupings. Each clinical profile suggested a distinct collaborative care strategy to optimize management.

CONCLUSIONS AND RELEVANCE

The findings suggest that highly medically complex patient populations may be categorized into distinct patient profiles that are amenable to varying strategies for resource allocation and coordinated care interventions.

Unsupervised machine learning and prognostic factors of survival in chronic lymphocytic leukemia

OBJECTIVE

Unsupervised machine learning approaches hold promise for large-scale clinical data. However, the heterogeneity of clinical data raises new methodological challenges in feature selection, choosing a distance metric that captures biological meaning, and visualization. We hypothesized that clustering could discover prognostic groups from patients with chronic lymphocytic leukemia, a disease that provides biological validation through well-understood outcomes.

METHODS

To address this challenge, we applied k-medoids clustering with 10 distance metrics to 2 experiments ("A" and "B") with mixed clinical features collapsed to binary vectors and visualized with both multidimensional scaling and t-stochastic neighbor embedding. To assess prognostic utility, we performed survival analysis using a Cox proportional hazard model, log-rank test, and Kaplan-Meier curves.

RESULTS

In both experiments, survival analysis revealed a statistically significant association between clusters and survival outcomes (A: overall survival, P = .0164; B: time from diagnosis to treatment, P = .0039). Multidimensional scaling separated clusters along a gradient mirroring the order of overall survival. Longer survival was associated with mutated immunoglobulin heavy-chain variable region gene (IGHV) status, absent Zap 70 expression, female sex, and younger age.

CONCLUSIONS

This approach to mixed-type data handling and selection of distance metric captured well-understood, binary, prognostic markers in chronic lymphocytic leukemia (sex, IGHV mutation status, ZAP70 expression status) with high fidelity.