Applying a data-driven population segmentation approach in German claims data

BACKGROUND

Segmenting the population into homogenous groups according to their healthcare needs may help to understand the population's demand for healthcare services and thus support health systems to properly allocate healthcare resources and plan interventions. It may also help to reduce the fragmented provision of healthcare services. The aim of this study was to apply a data-driven utilisation-based cluster analysis to segment a defined population in the south of Germany.

METHODS

Based on claims data of one big German health insurance a two-stage clustering approach was applied to group the population into segments. A hierarchical method (Ward's linkage) was performed to determine the optimal number of clusters, followed by a k-means cluster analysis using age and healthcare utilisation data in 2019. The resulting segments were described in terms of their morbidity, costs and demographic characteristics.

RESULTS

The 126,046 patients were divided into six distinct population segments. Healthcare utilisation, morbidity and demographic characteristics differed significantly across the segments. The segment "High overall care use" comprised the smallest share of patients (2.03%) but accounted for 24.04% of total cost. The overall utilisation of services was higher than the population average. In contrast, the segment "Low overall care use" included 42.89% of the study population, accounting for 9.94% of total cost. Utilisation of services by patients in this segment was lower than population average.

CONCLUSION

Population segmentation offers the opportunity to identify patient groups with similar healthcare utilisation patterns, patient demographics and morbidity. Thereby, healthcare services could be tailored for groups of patients with similar healthcare needs.

Population segmentation of type 2 diabetes mellitus patients and its clinical applications - a scoping review

Background

Population segmentation permits the division of a heterogeneous population into relatively homogenous subgroups. This scoping review aims to summarize the clinical applications of data driven and expert driven population segmentation among Type 2 diabetes mellitus (T2DM) patients.

Methods

The literature search was conducted in Medline®, Embase®, Scopus® and PsycInfo®. Articles which utilized expert-based or data-driven population segmentation methodologies for evaluation of outcomes among T2DM patients were included. Population segmentation variables were grouped into five domains (socio-demographic, diabetes related, non-diabetes medical related, psychiatric / psychological and health system related variables). A framework for PopulAtion Segmentation Study design for T2DM patients (PASS-T2DM) was proposed.

Results

Of 155,124 articles screened, 148 articles were included. Expert driven population segmentation approach was most commonly used, of which judgemental splitting was the main strategy employed (n = 111, 75.0%). Cluster based analyses (n = 37, 25.0%) was the main data driven population segmentation strategies utilized. Socio-demographic (n = 66, 44.6%), diabetes related (n = 54, 36.5%) and non-diabetes medical related (n = 18, 12.2%) were the most used domains. Specifically, patients’ race, age, Hba1c related parameters and depression / anxiety related variables were most frequently used. Health grouping/profiling (n = 71, 48%), assessment of diabetes related complications (n = 57, 38.5%) and non-diabetes metabolic derangements (n = 42, 28.4%) were the most frequent population segmentation objectives of the studies.

Conclusions

Population segmentation has a wide range of clinical applications for evaluating clinical outcomes among T2DM patients. More studies are required to identify the optimal set of population segmentation framework for T2DM patients.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12874-021-01209-w.

Population segments as a tool for health care performance reporting: an exploratory study in the Canadian province of British Columbia

Background

Primary care serves all age groups and individuals with health states ranging from those with no chronic conditions to those who are medically complex, or frail and approaching the end of life. For information to be actionable and guide planning, there must be some population disaggregation based on differences in expected needs for care. Promising approaches to segmentation in primary care reflect both the breadth and severity of health states, the types and amounts of health care utilization that are expected, and the roles of the primary care provider. The purpose of this study was to assess population segmentation as a tool to create distinct patient groups for use in primary care performance reporting.

Methods

This cross-sectional study used administrative data (patient characteristics, physician and hospital billings, prescription medicines data, emergency department visits) to classify the population of British Columbia (BC), Canada into one of four population segments: low need, multiple morbidities, medically complex, and frail. Each segment was further classified using socioeconomic status (SES) as a proxy for patient vulnerability. Regression analyses were used to examine predictors of health care use, costs and selected measures of primary care attributes (access, continuity, coordination) by segment.

Results

Average annual health care costs increased from the low need ($ 1460) to frail segment ($10,798). Differences in primary care cost by segment only emerged when attributes of primary care were included in regression models: accessing primary care outside business hours and discontinuous primary care (≥5 different GP’s in a given year) were associated with higher health care costs across all segments and higher continuity of care was associated with lower costs in the frail segment (cost ratio = 0.61). Additionally, low SES was associated with higher costs across all segments, but the difference was largest in the medically complex group (cost ratio = 1.11).

Conclusions

Population segments based on expected need for care can support primary care measurement and reporting by identifying nuances which may be lost when all patients are grouped together. Our findings demonstrate that variables such as SES and use of regression analyses can further enhance the usefulness of segments for performance measurement and reporting.

Can cluster analyses of linked healthcare data identify unique population segments in a general practice-registered population?

BACKGROUND

Population segmentation is useful for understanding the health needs of populations. Expert-driven segmentation is a traditional approach which involves subjective decisions on how to segment data, with no agreed best practice. The limitations of this approach are theoretically overcome by more data-driven approaches such as utilisation-based cluster analysis. Previous explorations of using utilisation-based cluster analysis for segmentation have demonstrated feasibility but were limited in potential usefulness for local service planning. This study explores the potential for practical application of using utilisation-based cluster analyses to segment a local General Practice-registered population in the South Wales Valleys.

METHODS

Primary and secondary care datasets were linked to create a database of 79,607 patients including socio-demographic variables, morbidities, care utilisation, cost and risk factor information. We undertook utilisation-based cluster analysis, using k-means methodology to group the population into segments with distinct healthcare utilisation patterns based on seven utilisation variables: elective inpatient admissions, non-elective inpatient admissions, outpatient first & follow-up attendances, Emergency Department visits, GP practice visits and prescriptions. We analysed segments post-hoc to understand their morbidity, risk and demographic profiles.

RESULTS

Ten population segments were identified which had distinct profiles of healthcare use, morbidity, demographic characteristics and risk attributes. Although half of the study population were in segments characterised as 'low need' populations, there was heterogeneity in this group with respect to variables relevant to service planning - e.g. settings in which care was mostly consumed. Significant and complex healthcare need was a feature across age groups and was driven more by deprivation and behavioural risk factors than by age and functional limitation.

CONCLUSIONS

This analysis shows that utilisation-based cluster analysis of linked primary and secondary healthcare use data for a local GP-registered population can segment the population into distinct groups with unique health and care needs, providing useful intelligence to inform local population health service planning and care delivery. This segmentation approach can offer a detailed understanding of the health and care priorities of population groups, potentially supporting the integration of health and care, reducing fragmentation of healthcare and reducing healthcare costs in the population.

Do healthcare needs-based population segments predict outcomes among the elderly? Findings from a prospective cohort study in an urbanized low-income community

Background

A rapidly ageing population with increasing prevalence of chronic disease presents policymakers the urgent task of tailoring healthcare services to optimally meet changing needs. While healthcare needs-based segmentation is a promising approach to efficiently assessing and responding to healthcare needs at the population level, it is not clear how available schemes perform in the context of community-based surveys administered by non-medically trained personnel. The aim of this prospective cohort, community setting study is to evaluate 4 segmentation schemes in terms of practicality and predictive validity for future health outcomes and service utilization.

Methods

A cohort was identified from a cross-sectional health and social characteristics survey of Singapore public rental housing residents aged 60 years and above. Baseline survey data was used to assign individuals into segments as defined by 4 predefined population segmentation schemes developed in Singapore, Delaware, Lombardy and North-West London. From electronic data records, mortality, hospital admissions, emergency department visits, and specialist outpatient clinic visits were assessed for 180 days after baseline segment assignment and compared to segment membership for each segmentation scheme.

Results

Of 1324 residents contacted, 928 agreed to participate in the survey (70% response). All subjects could be assigned an exclusive segment for each segmentation scheme. Individuals in more severe segments tended to have lower quality of life as assessed by the EQ-5D Index for health utility. All population segmentation schemes were observed to exhibit an ability to differentiate different levels of mortality and healthcare utilization.

Conclusions

It is practical to assign individuals to healthcare needs-based population segments through community surveys by non-medically trained personnel. The resulting segments for all 4 schemes evaluated in this way have an ability to predict health outcomes and utilization over the medium term (180 days), with significant overlap for some segments. Healthcare needs-based segmentation schemes which are designed to guide action hold particular promise for promoting efficient allocation of services to meet the needs of salient population groups. Further evaluation is needed to determine if these schemes also predict responsiveness to interventions to meet needs implied by segment membership.

Identifying optimal indicators and purposes of population segmentation through engagement of key stakeholders: a qualitative study

BACKGROUND

Various population segmentation tools have been developed to inform the design of interventions that improve population health. However, there has been little consensus on the core indicators and purposes of population segmentation. The existing frameworks were further limited by their applicability in different practice settings involving stakeholders at all levels. The aim of this study was to generate a comprehensive set of indicators and purposes of population segmentation based on the experience and perspectives of key stakeholders involved in population health.

METHODS

We conducted in-depth semi-structured interviews using purposive sampling with key stakeholders (e.g. government officials, healthcare professionals, social service providers, researchers) involved in population health at three distinct levels (micro, meso, macro) in Singapore. The interviews were audio-recorded and transcribed verbatim. Thematic content analysis was undertaken using NVivo 12.

RESULTS

A total of 25 interviews were conducted. Eight core indicators (demographic characteristics, economic characteristics, behavioural characteristics, disease state, functional status, organisation of care, psychosocial factors and service needs of patients) and 21 sub-indicators were identified. Age and financial status were commonly stated as important indicators that could potentially be used for population segmentation across three levels of participants. Six intended purposes for population segmentation included improving health outcomes, planning for resource allocation, optimising healthcare utilisation, enhancing psychosocial and behavioural outcomes, strengthening preventive efforts and driving policy changes. There was consensus that planning for resource allocation and improving health outcomes were considered two of the most important purposes for population segmentation.

CONCLUSIONS

Our findings shed light on the need for a more person-centric population segmentation framework that incorporates upstream and holistic indicators to be able to measure population health outcomes and to plan for appropriate resource allocation. Core elements of the framework may apply to other healthcare settings and systems responsible for improving population health.

TRIAL REGISTRATION

The study was approved by the SingHealth Institutional Review Board (CIRB Reference number: 2017/2597).

Population segmentation based on healthcare needs: a systematic review

BACKGROUND

Healthcare needs-based population segmentation is a promising approach for enabling the development and evaluation of integrated healthcare service models that meet healthcare needs. However, healthcare policymakers interested in understanding adult population healthcare needs may not be aware of suitable population segmentation tools available for use in the literature and barring better-known alternatives, may reinvent the wheel by creating and validating their own tools rather than adapting available tools in the literature. Therefore, we undertook a systematic review to identify all available tools which operationalize healthcare need-based population segmentation, to help inform policymakers developing population-level health service programmes.

METHODS

Using search terms reflecting concepts of population, healthcare need and segmentation, we systematically reviewed and included articles containing healthcare need-based adult population segmentation tools in PubMed, CINAHL and Web of Science databases. We included tools comprising mutually exclusive segments with prognostic value for clinically relevant outcomes. An updated secondary search on the PubMed database was also conducted as the last search was conducted 2 years ago. All identified tools were characterized in terms of segment formulation, segmentation base, whether they received peer-reviewed validation, requirement for comprehensive electronic medical records, proprietary status and number of segments.

RESULTS

A total of 16 unique tools were identified from systematically reviewing 9970 articles. Peer-reviewed validation studies were found for 9 of these tools.

DISCUSSION AND CONCLUSIONS

The underlying segmentation basis of most identified tools was found to be conceptually comparable to each other which suggests a broad recognition of archetypical patient overall healthcare need profiles. While many tools operate based on administrative record data, it is noted that healthcare systems without comprehensive electronic medical records would benefit from tools which segment populations through primary data collection. Future work could therefore include development and validation of such primary data collection-based tools. While this study is limited by exclusion of non-English literature, the identified and characterized tools will nonetheless facilitate efforts by policymakers to improve patient-centred care through development and evaluation of services tailored for specific populations segmented by these tools.

Predictive ability of an expert-defined population segmentation framework for healthcare utilization and mortality - a retrospective cohort study

Background

Population segmentation of patients into parsimonious and relatively homogenous subgroups or segments based on healthcare requirements can aid healthcare resource planning and the development of targeted intervention programs. In this study, we evaluated the predictive ability of a previously described expert-defined segmentation approach on 3-year hospital utilization and mortality.

Methods

We segmented all adult patients who had a healthcare encounter with Singapore Health Services (SingHealth) in 2012 using the SingHealth Electronic Health Records (SingHealth EHRs). Patients were divided into non-overlapping segments defined as Mostly Healthy, Stable Chronic, Serious Acute, Complex Chronic without Frequent Hospital Admissions, Complex Chronic with Frequent Hospital Admissions, and End of Life, using a previously described expert-defined segmentation approach. Hospital admissions, emergency department attendances (ED), specialist outpatient clinic attendances (SOC) and mortality in different patient subgroups were analyzed from 2013 to 2015.

Results

819,993 patients were included in this study. Patients in Complex Chronic with Frequent Hospital Admissions segment were most likely to have a hospital admission (IRR 22.7; p < 0.001) and ED visit (IRR 14.5; p < 0.001) in the follow-on 3 years compared to other segments. Patients in the End of Life and Complex Chronic with Frequent Hospital Admissions segments had the lowest three-year survival rates of 58.2 and 62.6% respectively whereas other segments had survival rates of above 90% after 3 years.

Conclusion

In this study, we demonstrated the predictive ability of an expert-driven segmentation framework on longitudinal healthcare utilization and mortality.

Electronic supplementary material

The online version of this article (10.1186/s12913-019-4251-6) contains supplementary material, which is available to authorized users.

Identifying heterogeneous health profiles of primary care utilizers and their differential healthcare utilization and mortality - a retrospective cohort study

BACKGROUND

Heterogeneity of population health needs and the resultant difficulty in health care resources planning are challenges faced by primary care systems globally. To address this challenge in population health management, it is critical to have a better understanding of primary care utilizers' heterogeneous health profiles. We aimed to segment a population of primary care utilizers into classes with unique disease patterns, and to report the 1 year follow up healthcare utilizations and all-cause mortality across the classes.

METHODS

Using de-identified administrative data, we included all adult Singapore citizens or permanent residents who utilized Singapore Health Services (SingHealth) primary care services in 2012. Latent class analysis was used to identify patient subgroups having unique disease patterns in the population. The models were assessed by Bayesian Information Criterion and clinical interpretability. We compared healthcare utilizations in 2013 and one-year all-cause mortality across classes and performed regression analysis to assess predictive ability of class membership on healthcare utilizations and mortality.

RESULTS

We included 100,747 patients in total. The best model (k = 6) revealed the following classes of patients: Class 1 "Relatively healthy" (n = 58,213), Class 2 "Stable metabolic disease" (n = 26,309), Class 3 "Metabolic disease with vascular complications" (n = 2964), Class 4 "High respiratory disease burden" (n = 1104), Class 5 "High metabolic disease without complication" (n = 11,122), and Class 6 "Metabolic disease with multi-organ complication" (n = 1035). The six derived classes had different disease patterns in 2012 and 1 year follow up healthcare utilizations and mortality in 2013. "Metabolic disease with multiple organ complications" class had the highest healthcare utilization (e.g. incidence rate ratio = 19.68 for hospital admissions) and highest one-year all-cause mortality (hazard ratio = 27.97).

CONCLUSIONS

Primary care utilizers are heterogeneous and can be segmented by latent class analysis into classes with unique disease patterns, healthcare utilizations and all-cause mortality. This information is critical to population level health resource planning and population health policy formulation.

A systematic review of the clinical application of data-driven population segmentation analysis

BACKGROUND

Data-driven population segmentation analysis utilizes data analytics to divide a heterogeneous population into parsimonious and relatively homogenous groups with similar healthcare characteristics. It is a promising patient-centric analysis that enables effective integrated healthcare interventions specific for each segment. Although widely applied, there is no systematic review on the clinical application of data-driven population segmentation analysis.

METHODS

We carried out a systematic literature search using PubMed, Embase and Web of Science following PRISMA criteria. We included English peer-reviewed articles that applied data-driven population segmentation analysis on empirical health data. We summarized the clinical settings in which segmentation analysis was applied, compared and contrasted strengths, limitations, and practical considerations of different segmentation methods, and assessed the segmentation outcome of all included studies. The studies were assessed by two independent reviewers.

RESULTS

We retrieved 14,514 articles and included 216 articles. Data-driven population segmentation analysis was widely used in different clinical contexts. 163 studies examined the general population while 53 focused on specific population with certain diseases or conditions, including psychological, oncological, respiratory, cardiovascular, and gastrointestinal conditions. Variables used for segmentation in the studies are heterogeneous. Most studies (n = 170) utilized secondary data in community settings (n = 185). The most common segmentation method was latent class/profile/transition/growth analysis (n = 96) followed by K-means cluster analysis (n = 60) and hierarchical analysis (n = 50), each having its advantages, disadvantages, and practical considerations. We also identified key criteria to evaluate a segmentation framework: internal validity, external validity, identifiability/interpretability, substantiality, stability, actionability/accessibility, and parsimony.

CONCLUSIONS

Data-driven population segmentation has been widely applied and holds great potential in managing population health. The evaluations of segmentation outcome require the interplay of data analytics and subject matter expertise. The optimal framework for segmentation requires further research.

Evaluation of a practical expert defined approach to patient population segmentation: a case study in Singapore

Background

Segmenting the population into groups that are relatively homogeneous in healthcare characteristics or needs is crucial to facilitate integrated care and resource planning. We aimed to evaluate the feasibility of segmenting the population into discrete, non-overlapping groups using a practical expert and literature driven approach. We hypothesized that this approach is feasible utilizing the electronic health record (EHR) in SingHealth.

Methods

In addition to well-defined segments of “Mostly healthy”, “Serious acute illness but curable” and “End of life” segments that are also present in the Ministry of Health Singapore framework, patients with chronic diseases were segmented into “Stable chronic disease”, “Complex chronic diseases without frequent hospital admissions”, and “Complex chronic diseases with frequent hospital admissions”. Using the electronic health record (EHR), we applied this framework to all adult patients who had a healthcare encounter in the Singapore Health Services Regional Health System in 2012. ICD-9, 10 and polyclinic codes were used to define chronic diseases with a comprehensive look-back period of 5 years. Outcomes (hospital admissions, emergency attendances, specialist outpatient clinic attendances and mortality) were analyzed for years 2012 to 2015.

Results

Eight hundred twenty five thousand eight hundred seventy four patients were included in this study with the majority being healthy without chronic diseases. The most common chronic disease was hypertension. Patients with “complex chronic disease” with frequent hospital admissions segment represented 0.6% of the eligible population, but accounted for the highest hospital admissions (4.33 ± 2.12 admissions; p < 0.001) and emergency attendances (ED) (3.21 ± 3.16 ED visits; p < 0.001) per patient, and a high mortality rate (16%). Patients with metastatic disease accounted for the highest specialist outpatient clinic attendances (27.48 ± 23.68 visits; p < 0.001) per patient despite their relatively shorter course of illness and high one-year mortality rate (33%).

Conclusion

This practical segmentation framework can potentially distinguish among groups of patients, and highlighted the high disease burden of patients with chronic diseases. Further research to validate this approach of population segmentation is needed.

Electronic supplementary material

The online version of this article (doi: 10.1186/s12913-017-2736-8) contains supplementary material, which is available to authorized users.

Who does not reduce their sodium intake despite being advised to do so? A population segmentation analysis

Excessive sodium intake is linked to an increased risk for hypertension and cardiovascular disease. Although health care providers and other health professionals frequently provide counseling on healthful levels of sodium consumption, many people who consume sodium in excess of recommend levels still do not watch or reduce their sodium intake. In this study, we used a population segmentation approach to identify profiles of adults who are not watching or reducing their sodium intake despite been advised to do so. We analyzed sodium intake data in 125,764 respondents sampled in 15 states, the District of Columbia and Puerto Rico through the Behavioral Risk Factor Surveillance System to identify and segment adults into subgroups according to differences in sodium intake behaviors. We found that about 16% of adults did not watch or reduce their sodium intake despite been told to do so by a health professional. This proportion varied substantially across the 25 different population subgroups identified. For example, about 44% of adults 18 to 44years of age who live in West Virginia were not reducing their sodium intake whereas only about 7.2% of black adults 65years of age and older with diabetes were not reducing their sodium intake. Population segmentation identifies subpopulations most likely to benefit from targeted and intensive public health and clinical interventions. In the case of sodium consumption, population segmentation can guide public health practitioners and policymakers to design programs and interventions that change sodium intake in people who are resistant to behavior change.

A quantitative evidence base for population health: applying utilization-based cluster analysis to segment a patient population

BACKGROUND

To improve population health it is crucial to understand the different care needs within a population. Traditional population groups are often based on characteristics such as age or morbidities. However, this does not take into account specific care needs across care settings and tends to focus on high-needs patients only. This paper explores the potential of using utilization-based cluster analysis to segment a general patient population into homogenous groups.

METHODS

Administrative datasets covering primary and secondary care were used to construct a database of 300,000 patients, which included socio-demographic variables, morbidities, care utilization, and cost. A k-means cluster analysis grouped the patients into segments with distinct care utilization, based on six utilization variables: non-elective inpatient admissions, elective inpatient admissions, outpatient visits, GP practice visits, GP home visits, and prescriptions. These segments were analyzed post-hoc to understand their morbidity and demographic profile.

RESULTS

Eight population segments were identified, and utilization of each care setting was significantly different across all segments. Each segment also presented with different morbidity patterns and demographic characteristics, creating eight distinct care user types. Comparing these segments to traditional patient groups shows the heterogeneity of these approaches, especially for lower-needs patients.

CONCLUSIONS

This analysis shows that utilization-based cluster analysis segments a patient population into distinct groups with unique care priorities, providing a quantitative evidence base to improve population health. Contrary to traditional methods, this approach also segments lower-needs populations, which can be used to inform preventive interventions. In addition, the identification of different care user types provides insight into needs across the care continuum.

Patterns of care for clinically distinct segments of high cost Medicare beneficiaries

BACKGROUND

Efforts to improve the efficiency of care for the Medicare population commonly target high cost beneficiaries. We describe and evaluate a novel management approach, population segmentation, for identifying and managing high cost beneficiaries.

METHODS

A retrospective cross-sectional analysis of 6,919,439 Medicare fee-for-service beneficiaries in 2012. We defined and characterized eight distinct clinical population segments, and assessed heterogeneity in managing practitioners.

RESULTS

The eight segments comprised 9.8% of the population and 47.6% of annual Medicare payments. The eight segments included 61% and 69% of the population in the top decile and top 5% of annual Medicare payments. The positive-predictive values within each segment for meeting thresholds of Medicare payments ranged from 72% to 100%, 30% to 83%, and 14% to 56% for the upper quartile, upper decile, and upper 5% of Medicare payments respectively. Sensitivity and positive-predictive values were substantially improved over predictive algorithms based on historical utilization patterns and comorbidities. The mean [95% confidence interval] number of unique practitioners and practices delivering E&M services ranged from 1.82 [1.79-1.84] to 6.94 [6.91-6.98] and 1.48 [1.46-1.50] to 4.98 [4.95-5.00] respectively. The percentage of cognitive services delivered by primary care practitioners ranged from 23.8% to 67.9% across segments, with significant variability among specialty types.

CONCLUSIONS

Most high cost Medicare beneficiaries can be identified based on a single clinical reason and are managed by different practitioners.

IMPLICATIONS

Population segmentation holds potential to improve efficiency in the Medicare population by identifying opportunities to improve care for specific populations and managing clinicians, and forecasting and evaluating the impact of specific interventions.