Applying Machine Learning Algorithms to Segment High-Cost Patient Populations

Yan, Jiali; Linn, Kristin A.; Powers, Brian; Zhu, Jingsan; Jain, Sachin H.; Kowalski, Jennifer; Navathe, Amol S.

doi:10.1007/s11606-018-4760-8

Cited by 26 publications

(30 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different clustering algorithms are likely to produce different results. However, as discussed in an accompanying article, 23 we believe OPTICS is the optimal algorithm for clustering high-cost patient populations.…”

Section: Discussionmentioning

confidence: 98%

“…Additional detail regarding dimension reduction is provided in Appendix 3 and an accompanying article. 23 Finally, we applied a density-based clustering algorithm-Ordering Points To Identify the Clustering Structure (OPTICS) 26,27 -to the low-dimension dataset. We restricted the minimum number of patients per subgroup to be at least 62 (or 1% of the high-cost population) in order to ensure that the subgroups were operationally meaningful.…”

Section: Identifying Subgroupsmentioning

confidence: 99%

“…Our rationale for choosing the OPTICS algorithm and information on tuning parameters is described in an accompanying article. 23…”

Section: Identifying Subgroupsmentioning

confidence: 99%

See 2 more Smart Citations

Subgroups of High-Cost Medicare Advantage Patients: an Observational Study

et al. 2018

Self Cite

View full text Add to dashboard Cite

BACKGROUND: There is a growing focus on improving the quality and value of health care delivery for high-cost patients. Compared to fee-for-service Medicare, less is known about the clinical composition of high-cost Medicare Advantage populations. OBJECTIVE: To describe a high-cost Medicare Advantage population and identify clinically and operationally significant subgroups of patients. DESIGN: We used a density-based clustering algorithm to group high-cost patients (top 10% of spending) according to 161 distinct demographic, clinical, and claims-based variables. We then examined rates of utilization, spending, and mortality among subgroups. PARTICIPANTS: Sixty-one thousand five hundred fortysix Medicare Advantage beneficiaries. MAIN MEASURES: Spending, utilization, and mortality. KEY RESULTS: High-cost patients (n = 6154) accounted for 55% of total spending. High-cost patients were more likely to be younger, male, and have higher rates of comorbid illnesses. We identified ten subgroups of high-cost patients: acute exacerbations of chronic disease (mixed); end-stage renal disease (ESRD); recurrent gastrointestinal bleed (GIB); orthopedic trauma (trauma); vascular disease (vascular); surgical infections and other complications (complications); cirrhosis with hepatitis C (liver); ESRD with increased medical and behavioral comorbidity (ESRD+); cancer with high-cost imaging and radiation therapy (oncology); and neurologic disorders (neurologic). The average number of inpatient days ranged from 3.25 (oncology) to 26.09 (trauma). Preventable spending (as a percentage of total spending) ranged from 0.8% (oncology) to 9.5% (complications) and the percentage of spending attributable to prescription medications ranged from 7.9% (trauma and oncology) to 77.0% (liver). The percentage of patients who were persistently high-cost ranged from 11.8% (trauma) to 100.0% (ESRD+). One-year mortality ranged from 0.0% (liver) to 25.8% (ESRD+). CONCLUSIONS:We identified clinically distinct subgroups of patients within a heterogeneous high-cost Medicare Advantage population using cluster analysis. These subgroups, defined by condition-specific profiles and illness trajectories, had markedly different patterns of utilization, spending, and mortality, holding important implications for clinical strategy.KEY WORDS: high-cost patients; care management; medicare advantage.

show abstract

Section: Discussionmentioning

confidence: 98%

Section: Identifying Subgroupsmentioning

confidence: 99%

See 1 more Smart Citation

Subgroups of High-Cost Medicare Advantage Patients: an Observational Study

et al. 2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…2,5,36,37 Two recently published approaches offer other cluster-based solutions to elucidate subgroups of high-cost patients with some notable successes. 38,39 However, these were not applied to evaluate changes in spending, outcomes over more than 1 year, or to elucidate patients with rising Downloaded From: https://jamanetwork.com/ on 11/01/2020 costs. 38,39 They also focused on Medicare Advantage populations, which can differ from fee-forservice beneficiaries.…”

Section: Discussionmentioning

confidence: 99%

Use of Data-Driven Methods to Predict Long-term Patterns of Health Care Spending for Medicare Patients

2020

View full text Add to dashboard Cite

IMPORTANCE Current approaches to predicting health care costs generally rely on a single composite value of spending and focus on short time horizons. By contrast, examining patients' spending patterns using dynamic measures applied over longer periods may better identify patients with different spending and help target interventions to those with the greatest need. OBJECTIVE To classify patients by their long-term, dynamic health care spending patterns using a data-driven approach and assess the ability to predict spending patterns, particularly using characteristics that are potentially modifiable through intervention. DESIGN, SETTING, AND PARTICIPANTS This cohort study used a retrospective cohort design from a random nationwide sample of Medicare fee-for-service administrative claims data to identify beneficiaries aged 65 years or older with continuous eligibility from 2011 to 2013. Statistical analysis was performed from August 2018 to December 2019. MAIN OUTCOMES AND MEASURES Group-based trajectory modeling was applied to the claims data to classify the Medicare beneficiaries by their total health care spending patterns over a 2-year period. The ability to predict membership in each trajectory spending group was assessed using generalized boosted regression, a data mining approach to model building and prediction, with splitsample validation. Models were estimated using (1) prior-year predictors and (2) prior-year predictors potentially modifiable through intervention measured in the claims data. These models were evaluated using validated C-statistics. The relative influence of individual predictors in the models was evaluated. RESULTS Among the 329 476 beneficiaries, the mean (SD) age was 76.0 (7.2) years and 190 346 (57.8%) were female. This final 5-group model included a minimal-user group (group 1, 37 572 individuals [11.4%]), a low-cost group (group 2, 48 575 individuals [14.7%]), a rising-cost group (group 3, 24 736 individuals [7.5%]), a moderate-cost group (group 4, 83 338 individuals [25.3%]), and a high-cost group (group 5, 135 255 individuals [41.2%]). Potentially modifiable characteristics strongly predicted these patterns (C-statistics range: 0.68-0.94). For groups with progressively increasing spending in particular, the most influential factors were number of medications (relative influence: 29.2), number of office visits (relative influence: 30.3), and mean medication adherence (relative influence: 33.6). CONCLUSIONS AND RELEVANCE Using a data-driven approach, distinct spending patterns were identified with high accuracy. The potentially modifiable predictors of membership in the rising-cost group represent important levers for early interventions that may prevent later spending increases. This approach could be adapted by organizations to target quality improvement interventions, (continued) Key Points Question What are the long-term spending patterns by Medicare beneficiaries, and do baseline patient factors that are potentially modifiable predict these patterns? Findings In this cohort st...

show abstract

“…Previous population health approaches in primary and specialty care have demonstrated only modest, if any, reductions in inpatient utilization and expenses for patient populations requiring multispecialty care. 27 , 47 – 55 Limitations of previous programs include (1) leadership residing within siloed specialties that limit system-wide implementation, (2) patients not completing specialty clinic visits, 18 , 26 , 27 , 56 (3) local data constraints that limit responsiveness to patient needs, 21 , 50 , 55 – 60 (4) unclear identification of patients most likely to benefit from interventions, 61 (5) nebulous primary and specialty care clinical alignment, 18 , 26 , 53 , 62 – 65 and (6) narrowly resourced ambulatory care services. 66 …”

Section: Discussionmentioning

confidence: 99%

A System-Wide Population Health Value Approach to Reduce Hospitalization Among Chronic Kidney Disease Patients: an Observational Study

Gupta¹,

Skootsky²,

Kahn³

et al. 2020

J GEN INTERN MED

View full text Add to dashboard Cite

Background Chronic kidney disease (CKD) is a leading cause of healthcare morbidity, utilization, and expenditures nationally, and caring for late-stage CKD populations is complex. Improving health system efficiency could mitigate these outcomes and, in the COVID-19 era, reduce risks of viral exposure. Objective As part of a system-wide transformation to improve healthcare value among populations with high healthcare utilization and morbidity, UCLA Health evaluated a new patient-centered approach that we hypothesized would reduce inpatient utilization for CKD patients. Design For 18 months in 2015–2016 and 12 months in 2017, we conducted an interrupted time series regression analysis to evaluate the intervention’s impact on inpatient utilization. We used internal electronic health records and claims data across six payers. Participants A total of 1442 stage 4–5 CKD patients at a large academic medical center. Intervention Between October and December 2016, the organization implemented a Population Health Value CKD intervention for the CKD stages 4–5 population. A multispecialty leadership team risk stratified the population and identified improvement opportunities, redesigned multispecialty care coordination pathways across settings, and developed greater ambulatory infrastructure to support care needs. Main Measures Outcomes included utilization of hospitalizations, emergency department (ED) visits, inpatient bed days, and 30-day all-cause readmissions. Key Results During the 12 months following intervention implementation, the monthly estimated rate of decline for hospitalizations was 5.4% (95% CI: 3.4–7.4%), which was 3.4 percentage points faster than the 18-month pre-intervention decline of 2.0% (95% CI: 1.0–2.2%) per month ( p = 0.004). Medicare CKD patients’ monthly ED visit rate of decline was 3.0% (95% CI: 1.2–4.8%) after intervention, which was 2.6 percentage points faster than the pre-intervention decline of 0.4% (95% CI: − 0.8 to 1.6%) per month ( p = 0.02). Conclusions By creating care pathways that link primary and specialty care teams across settings with increased ambulatory infrastructure, healthcare systems have potential to reduce inpatient healthcare utilization. Electronic supplementary material The online version of this article (10.1007/s11606-020-06272-5) contains supplementary material, which is available to authorized users.

show abstract

Applying Machine Learning Algorithms to Segment High-Cost Patient Populations

Cited by 26 publications

References 27 publications

Subgroups of High-Cost Medicare Advantage Patients: an Observational Study

Subgroups of High-Cost Medicare Advantage Patients: an Observational Study

Use of Data-Driven Methods to Predict Long-term Patterns of Health Care Spending for Medicare Patients

A System-Wide Population Health Value Approach to Reduce Hospitalization Among Chronic Kidney Disease Patients: an Observational Study

Contact Info

Product

Resources

About