Public Views on Medicaid Work Requirements and Mandatory Premiums in Kentucky.

Importance: Federal and state policymakers continue to pursue work requirements and premiums as conditions of Medicaid participation. Opinion polling should distinguish between general policy preferences and specific views on quotas, penalties, and other elements. Objective: To identify views of adults in Kentucky regarding the design of Medicaid work requirements and premiums. Design, Setting, and Participant: A cross-sectional survey was conducted via telephone and the internet from June 27 through July 11, 2019, of 1203 Kentucky residents 9 months before the state intended to implement Medicaid work requirements and mandatory premiums. Statistical analysis was performed from October 2019 to August 2023. Main Outcomes and Measures: Agreement, disagreement, or neutral views on policy components were the main outcomes. Recruitment for the survey used statewide random-digit dialing and an internet panel to recruit residents aged 18 years or older. Findings were weighted to reflect state demographics. Of 39 110 landlines called, 209 reached an eligible person (of whom 150 participated), 8654 were of unknown eligibility, and 30 247 were ineligible. Of 55 305 cell phone lines called, 617 reached an eligible person (of whom 451 participated), 29 951 were of unknown eligibility, and 24 737 were ineligible. Internet recruitment (602 participants) used a panel of adult Kentucky residents maintained by an external data collector. Results: Percentages were weighted to resemble the adult population of Kentucky residents. Of the participants in the study, 52% (95% CI, 48%-55%) were women, 80% (95% CI, 77%-82%) were younger than 65 years, 41% (95% CI, 38%-45%) were enrolled in Medicaid, 36% (95% CI, 32%-39%) were Republican voters, 32% (95% CI, 29%-36%) were Democratic voters, 14% (95% CI, 11%-16%) were members of racial and ethnic minority groups (including but not limited to American Indian or Alaska Native, Asian, Black, Hispanic or Latinx, and Native Hawaiian or Pacific Islander), and 48% (95% CI, 44%-52%) were employed. Most participants supported work requirements generally (69% [95% CI, 66%-72%]) but did not support terminating benefits due to noncompliance (43% [95% CI, 39%-46%]) or requiring quotas of 20 or more hours per week (34% [95% CI, 31%-38%]). Support for monthly premiums (34% [95% CI, 31%-38%]) and exclusion penalties for premium nonpayment (22% [95% CI, 19%-25%]) was limited. Medicaid enrollees were significantly less supportive of these policies than nonenrollees. For instance, regarding work requirements, agreement was lower (64% [95% CI, 59%-69%] vs 72% [95% CI, 68%-77%]) and disagreement higher (26% [95% CI, 21%-31%] vs 20% [95% CI, 16%-24%]) among current Medicaid enrollees compared with nonenrollees (P = .04). Among Medicaid enrollees, some beliefs about work requirements varied significantly by employment status but not by political affiliation. Among nonenrollees, beliefs about work requirements, premiums, and Medicaid varied significantly by political affiliation but not by employment. Conclusions and Relevance: This study suggests that even when public constituencies express general support for Medicaid work requirements or premiums, they may oppose central design features, such as quotas and termination of benefits. Program participants may also hold significantly different beliefs than nonparticipants, which should be understood before policies are changed.

Evaluating equity in performance of an electronic health record-based 6-month mortality risk model to trigger palliative care consultation: a retrospective model validation analysis.

OBJECTIVE: Evaluate predictive performance of an electronic health record (EHR)-based, inpatient 6-month mortality risk model developed to trigger palliative care consultation among patient groups stratified by age, race, ethnicity, insurance and socioeconomic status (SES), which may vary due to social forces (eg, racism) that shape health, healthcare and health data. DESIGN: Retrospective evaluation of prediction model. SETTING: Three urban hospitals within a single health system. PARTICIPANTS: All patients ≥18 years admitted between 1 January and 31 December 2017, excluding observation, obstetric, rehabilitation and hospice (n=58 464 encounters, 41 327 patients). MAIN OUTCOME MEASURES: General performance metrics (c-statistic, integrated calibration index (ICI), Brier Score) and additional measures relevant to health equity (accuracy, false positive rate (FPR), false negative rate (FNR)). RESULTS: For black versus non-Hispanic white patients, the model's accuracy was higher (0.051, 95% CI 0.044 to 0.059), FPR lower (-0.060, 95% CI -0.067 to -0.052) and FNR higher (0.049, 95% CI 0.023 to 0.078). A similar pattern was observed among patients who were Hispanic, younger, with Medicaid/missing insurance, or living in low SES zip codes. No consistent differences emerged in c-statistic, ICI or Brier Score. Younger age had the second-largest effect size in the mortality prediction model, and there were large standardised group differences in age (eg, 0.32 for non-Hispanic white versus black patients), suggesting age may contribute to systematic differences in the predicted probabilities between groups. CONCLUSIONS: An EHR-based mortality risk model was less likely to identify some marginalised patients as potentially benefiting from palliative care, with younger age pinpointed as a possible mechanism. Evaluating predictive performance is a critical preliminary step in addressing algorithmic inequities in healthcare, which must also include evaluating clinical impact, and governance and regulatory structures for oversight, monitoring and accountability.

Performance of Physician Groups and Hospitals Participating in Bundled Payments Among Medicare Beneficiaries.

Importance: Hospital participation in bundled payment initiatives has been associated with financial savings and stable quality of care. However, how physician group practices (PGPs) perform in bundled payments compared with hospitals remains unknown. Objectives: To evaluate the association of PGP participation in the Bundled Payments for Care Improvement (BPCI) initiative with episode outcomes and to compare these with outcomes for participating hospitals. Design, Settings, and Participants: This cohort study with a difference-in-differences analysis used 2011 to 2018 Medicare claims data to compare the association of BPCI participation with episode outcomes for PGPs vs hospitals providing medical and surgical care to Medicare beneficiaries. Data analyses were conducted from January 1, 2020, to May 31, 2022. Exposures: Hospitalization for any of the 10 highest-volume episodes (5 medical and 5 surgical) included in the BPCI initiative for Medicare patients of participating PGPs and hospitals. Main Outcomes and Measures: The primary outcome was 90-day total episode spending. Secondary outcomes were 90-day readmissions and mortality. Results: The total sample comprised data from 1 288 781 Medicare beneficiaries, of whom 696 710 (mean [SD] age, 76.2 [10.8] years; 432 429 [59.7%] women; 619 655 [85.5%] White individuals) received care through 379 BPCI-participating hospitals and 1441 propensity-matched non-BPCI-participating hospitals, and 592 071 (mean [SD] age, 75.4 [10.9] years; 527 574 [86.6%] women; 360 835 [59.3%] White individuals) received care from 6405 physicians in BPCI-participating PGPs and 24 758 propensity-matched physicians in non-BPCI-participating PGPs. For PGPs, BPCI participation was associated with greater reductions in episode spending for surgical (difference, -$1368; 95% CI, -$1648 to -$1088) but not for medical episodes (difference, -$101; 95% CI, -$410 to $206). Hospital participation in BPCI was associated with greater reductions in episode spending for both surgical (-$1010; 95% CI, -$1345 to -$675) and medical (-$763; 95% CI, -$1139 to -$386) episodes. Conclusions and Relevance: This cohort study and difference-in-differences analysis of PGPs and hospital participation in BPCI found that bundled payments were associated with cost savings for surgical episodes for PGPs, and savings for both surgical and medical episodes for hospitals. Policy makers should consider the comparative performance of participant types when designing and evaluating bundled payment models.

Equitable implementation of S.A.F.E. Firearm: A multi-method pilot study.

Attention to health equity is critical in the implementation of firearm safety efforts. We present our operationalization of equity-oriented recommendations in preparation for launch of a hybrid effectiveness-implementation trial focused on firearm safety promotion in pediatric primary care as a universal suicide prevention strategy. In Step 1 of our process, pre-trial engagement with clinican partners and literature review alerted us that delivery of a firearm safety program may vary by patients' medical complexity, race, and ethnicity. In Step 2, we selected the Health Equity Implementation Framework to inform our understanding of contextual determinants (i.e., barriers and facilitators). In Step 3, we leveraged an implementation pilot across 5 pediatric primary care clinics in 2 health system sites to study signals of inequities. Eligible well-child visits for 694 patients and 47 clinicians were included. Our results suggested that medical complexity was not associated with program delivery. We did see potential signals of inequities by race and ethnicity but must interpret with caution. Though we did not initially plan to examine differences by sex assigned at birth, we discovered that clinicians may be more likely to deliver the program to parents of male than female patients. Seven qualitative interviews with clinicians provided additional context. In Step 4, we interrogated equity considerations (e.g., why and how do these inequities exist). In Step 5, we will develop a plan to probe potential inequities related to race, ethnicity, and sex in the fully powered trial. Our process highlights that prospective, rigorous, exploratory work is vital for equity-informed implementation trials.

Oral health and oral health care use among able-bodied adults enrolled in Medicaid in Kentucky after Medicaid expansion: A mixed methods study.

BACKGROUND: Oral health care use remains low among adult Medicaid recipients, despite the Patient Protection and Affordable Care Act's expansion increasing access to care in many states. It remains unclear the extent to which low use reflects either low demand for care or barriers to accessing care. The authors aimed to examine factors associated with low oral health care use among adults enrolled in Medicaid. METHODS: The authors conducted a survey from May through September 2018 among able-bodied (n = 9,363) Medicaid recipients who were aged 19 through 65 years and nondisabled childless adults in Kentucky. The survey included questions on perceived oral health care use. Semistructured interviews were also conducted from May through November 2018 among a subset of participants (n = 127). RESULTS: More than one-third (37.8%) of respondents reported fair or poor oral health, compared with 26.2% who reported fair or poor physical health. Although 47.6% of respondents indicated needing oral health care in the past 6 months, only one-half of this group reported receiving all of the care they needed. Self-reported barriers included lack of coverage for needed services and lack of access to care (for example, low provider availability and transportation difficulties). CONCLUSIONS: Low rates of oral health care use can be attributed to a subset of the study population having low demand and another subset facing barriers to accessing care. Although Medicaid-covered services might be adequate for beneficiaries with good oral health, those with advanced dental diseases and a history of irregular care might benefit from coverage for more extensive restorative services. PRACTICAL IMPLICATIONS: These results can inform dentists and policy makers about how to design effective interventions and policies to improve oral health care use and oral health outcomes.

Spillover Effects of Medicare's Voluntary Bundled Payments for Joint Replacement Surgery to Patients Insured by Commercial Health Plans.

BACKGROUND: Under the Bundled Payments for Care Improvement (BPCI) program, bundled paymtents for lower-extremity joint replacement (LEJR) are associated with 2% to 4% cost savings with stable quality among Medicare fee-for-service beneficiaries. However, BPCI may prompt practice changes that benefit all patients, not just fee-for-service beneficiaries. OBJECTIVE: To examine the association between hospital participation in BPCI and LEJR outcomes for patients with commercial insurance or Medicare Advantage (MA). DESIGN: Quasi-experimental study using Health Care Cost Institute claims from 2011 to 2016. SETTING: LEJR at 281 BPCI hospitals and 562 non-BPCI hospitals. PATIENTS: 184 922 patients with MA or commercial insurance. MEASUREMENTS: Differential changes in LEJR outcomes at BPCI hospitals versus at non-BPCI hospitals matched on propensity score were evaluated using a difference-in-differences (DID) method. Secondary analyses evaluated associations by patient MA status and hospital characteristics. Primary outcomes were changes in 90-day total spending on LEJR episodes and 90-day readmissions; secondary outcomes were postacute spending and discharge to postacute care providers. RESULTS: Average episode spending decreased more at BPCI versus non-BPCI hospitals (change, -2.2% [95% CI, -3.6% to -0.71%]; P = 0.004), but differences in changes in 90-day readmissions were not significant (adjusted DID, -0.47 percentage point [CI, -1.0 to 0.06 percentage point]; P = 0.084). Participation in BPCI was also associated with differences in decreases in postacute spending and discharge to institutional postacute care providers. Decreases in episode spending were larger for hospitals with high baseline spending but did not vary by MA status. LIMITATION: Nonrandomized studies are subject to residual confounding and selection. CONCLUSION: Participation in BPCI was associated with modest spillovers in episode savings. Bundled payments may prompt hospitals to implement broad care redesign that produces benefits regardless of insurance coverage. PRIMARY FUNDING SOURCE: Leonard Davis Institute of Health Economics at the University of Pennsylvania.

Assessing The Effectiveness Of Peer Comparisons As A Way To Improve Health Care Quality.

Policy makers are increasingly using performance feedback that compares physicians to their peers as part of payment policy reforms. However, it is not known whether peer comparisons can improve broad outcomes, beyond changing specific individual behaviors such as reducing inappropriate prescribing of antibiotics. We conducted a cluster-randomized controlled trial with Blue Cross Blue Shield of Hawaii to examine the impact of providing peer comparisons feedback on the quality of care to primary care providers in the setting of a shift from fee-for-service to population-based payment. Over 74,000 patients and eighty-eight primary care providers across sixty-three sites were included over a period of nine months in 2016. Patients in the peer comparisons intervention group experienced a 3.1-percentage-point increase in quality scores compared to the control group-whose members received individual feedback only. This result underscores the effectiveness of peer comparisons as a way to improve health care quality, and it supports Medicare's decisions to provide comparative feedback as part of recently implemented primary care and specialty payment reform programs.

The design of a randomized controlled trial to evaluate multi-dimensional effects of a section 1115 Medicaid demonstration waiver with community engagement requirements.

Section 1115 demonstration waivers provide a mechanism for states to implement changes to their Medicaid programs. While such waivers are mandated to include evaluations of their impact, randomization - the gold standard for assessing causality - has not typically been a consideration. In a critical departure, the Commonwealth of Kentucky opted to pursue a two-arm randomized controlled trial (RCT) for their controversial 2018 Medicaid Demonstration waiver, which included work requirements as a condition for the subset of beneficiaries deemed able-bodied to maintain eligibility for benefits. Beneficiaries were randomized 9:1 to the new waiver program or a control group who would retain their current benefits as part of the existing Medicaid expansion program. To address potential bias from differential attrition from the Medicaid program that would accrue from solely analyzing administrative data, our team designed a rich, prospective, longitudinal survey to collect primary and secondary outcomes from six categories of interest to policymakers: insurance coverage, health care utilization and quality, health behaviors, socioeconomic measures, personal finances, and health outcomes. At baseline, a subset of survey participants was invited to participate in the collection of biometric samples via in-person follow-up visits, and a cross-section were also invited to participate in qualitative interviews. While the demonstration waiver was terminated before the program began, our study design illustrates that it is possible for other researchers and state agencies seeking to evaluate Medicaid demonstration waivers and other demonstration policies to work together to implement high quality randomized trials - even for controversial policies.

The Beneficial Effects Of Medicare Advantage Special Needs Plans For Patients With End-Stage Renal Disease.

Patients with end-stage renal disease (ESRD) are a vulnerable population with high rates of morbidity, mortality, and acute care use. Medicare Advantage Special Needs Plans (SNPs) are an alternative financing and delivery model designed to improve care and reduce costs for patients with ESRD, but little is known about their impact. We used detailed clinical, demographic, and claims data to identify fee-for-service Medicare beneficiaries who switched to ESRD SNPs offered by a single health plan (SNP enrollees) and similar beneficiaries who remained enrolled in fee-for-service Medicare plans (fee-for-service controls). We then compared three-year mortality and twelve-month utilization rates. Compared with fee-for-service controls, SNP enrollees had lower mortality and lower rates of utilization across the care continuum. These findings suggest that SNPs may be an effective alternative care financing and delivery model for patients with ESRD.

Changes in Outpatient Imaging Utilization and Spending Under a New Population-Based Primary Care Payment Model.

OBJECTIVE: To evaluate whether the implementation of a new population-based primary care payment system, Population-Based Payments for Primary Care (3PC), initiated by Hawaii Medical Service Association (HMSA; the Blue Cross Blue Shield of Hawaii), was associated with changes in spending and utilization for outpatient imaging in its first year. METHODS: In this observational study, we used claims data from January 1, 2012, to December 31, 2016. We used a propensity-weighted difference-in-differences design to compare 70,284 HMSA patients in Hawaii attributed to 107 primary care physicians (PCPs) and 4 physician organizations participating in 3PC in its first year of implementation (2016) and 195,902 patients attributed to 312 PCPs and 14 physician organizations that used a fee-for-service model during the study period. The primary outcome was total spending on outpatient imaging tests, and secondary outcomes included spending and utilization by modality. RESULTS: The study included 266,186 HMSA patients (mean age of 43.3 years; 51.7% women) and 419 PCPs (mean age of 54.9 years; 34.8% women). The 3PC system was not significantly associated with changes in total spending for outpatient imaging. Of 12 secondary outcomes, only 3 were statistically significant, including changes in nuclear medicine spending (adjusted differential change = -20.1% [95% confidence interval = -27.5% to -12.1%]; P < .001) and utilization (adjusted differential change = -18.1% [95% confidence interval = -23.8 to -11.9%]; P < .001). DISCUSSION: The HMSA 3PC system was not associated with significant changes in total spending for outpatient imaging, though spending and utilization on nuclear medicine tests decreased.

Assessment of Medicaid Beneficiaries Included in Community Engagement Requirements in Kentucky.

Importance: States are pursuing Section 1115 Medicaid demonstration waiver authority to apply community engagement (CE) requirements (eg, participation in work, volunteer activities, or training) to beneficiaries deemed able-bodied as a condition of coverage. Understanding the size and characteristics of the populations included in these requirements can help inform policy initiatives and anticipate effects. Objective: To estimate the number and characteristics of Kentucky Medicaid beneficiaries who would have to meet CE requirements. Design, Setting, and Participants: Cross-sectional study in which administrative records for the entire population of Medicaid beneficiaries in Kentucky as of February 2018 and original survey data, based on responses from 9396 Medicaid beneficiaries included in the waiver program, were analyzed. Exposures: Eligibility for Kentucky's Medicaid demonstration waiver as of the originally planned implementation date (July 2018). Main Outcomes and Measures: Number of beneficiaries included in CE requirements, including those already meeting vs not meeting hour quotas and those who may qualify for medical frailty exemptions. Results: Among the 9396 individuals included in the Section 1115 waiver program who participated in the survey, the mean weighted (SD) age was 36.1 (11.9) years; a weighted 47.2% of respondents were female, and most beneficiaries (weighted percentage, 78.2%) were non-Hispanic white participants. We estimated that 132 790 (95% CI, 129 132-136 449) beneficiaries would have been required to meet CE requirements in July 2018, amounting to 40.2% of Medicaid beneficiaries included in the demonstration waiver. Of this group, 25 422 (95% CI, 23 135-27 710) beneficiaries may have qualified for a medical frailty exemption either by self-attestation (after confirmation by their Medicaid insurer) or by being identified as eligible by physicians or their insurer. Another 58 943 (95% CI, 55 687-62 196) beneficiaries likely would have met CE hour requirements and been required to report compliance. Ultimately, 48 427 (95% CI, 45 281-51 574) individuals would have had to add new activities to meet CE requirements, amounting to 14.7% of those included in the demonstration waiver as a whole and 36.3% of those included in the CE component of the waiver. Beneficiaries in the potentially medically frail group reported worse socioeconomic status, poorer health outcomes, and higher rates of hospital admission and emergency department use than those meeting CE requirements. Similarly, the group currently not meeting and not exempt from CE hour requirements reported worse socioeconomic status than those meeting the CE requirements, although magnitudes of the differences were smaller. Conclusions and Relevance: Findings suggest that most beneficiaries who would be included in CE programs either already meet activity requirements, which they will be required to proactively report, or may qualify for a medical frailty exemption. Consequently, the outcomes of CE programs will depend on states' processes for addressing health-related, socioeconomic, and administrative barriers to participating in and reporting CE activities and identifying medical frailty.

Association Between the Implementation of a Population-Based Primary Care Payment System and Achievement on Quality Measures in Hawaii.

Importance: Hawaii Medical Service Association (HMSA), the Blue Cross Blue Shield of Hawaii, introduced Population-based Payments for Primary Care (3PC), a new capitation-based primary care payment system, in 2016. The effect of this system on quality measures has not been evaluated. Objective: To evaluate whether the 3PC system was associated with changes in quality, utilization, or spending in its first year. Design, Setting, and Participants: Observational study using HMSA claims and clinical registry data from January 1, 2012, to December 31, 2016, and a propensity-weighted difference-in-differences method to compare 77 225 HMSA members in Hawaii attributed to 107 primary care physicians (PCPs) and 4 physician organizations participating in the first wave of the 3PC and 222 233 members attributed to 312 PCPs and 14 physician organizations that continued in a fee-for-service model in 2016 but had 3PC start dates thereafter. Exposures: Participation in the 3PC system. Main Outcomes and Measures: The primary outcome was the change in a composite measure score reflecting the probability that a member achieved an eligible measure out of 13 pooled Healthcare Effectiveness Data and Information Set quality measures. Primary care visits and total cost of care were among 15 secondary outcomes. Results: In total, the study included 299 458 HMSA members (mean age, 42.1 years; 51.5% women) and 419 primary care physicians (mean age, 54.9 years; 34.8% women). The risk-standardized composite measure scores for 2012 to 2016 changed from 75.1% to 86.6% (+11.5 percentage points) in the 3PC group and 74.3% to 83.5% (+9.2 percentage points) in the non-3PC group (differential change, 2.3 percentage points [95% CI, 2.1 to 2.6 percentage points]; P < .001). Of 15 prespecified secondary end points for utilization and spending, 11 showed no significant difference. Compared with the non-3PC group, the 3PC system was associated with a significant reduction in the mean number of primary care visits (3.3 to 3.0 visits vs 3.3 to 3.1 visits; adjusted differential change, -3.9 percentage points [95% CI, -4.6 to -3.2 percentage points]; P < .001), but there was no significant difference in mean total cost of care ($3344 to $4087 vs $2977 to $3564; adjusted differential change, 1.0% [95% CI, -1.3% to 3.4%]; P = .39). Conclusions and Relevance: In its first year, the 3PC population-based primary care payment system in Hawaii was associated with small improvements in quality and a reduction in PCP visits but no significant difference in the total cost of care. Additional research is needed to assess longer-term outcomes as the program is more fully implemented and to determine whether results are generalizable to other health care markets.

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

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 forty-six 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.

Applying Machine Learning Algorithms to Segment High-Cost Patient Populations.

BACKGROUND: Efforts to improve the value of care for high-cost patients may benefit from care management strategies targeted at clinically distinct subgroups of patients. OBJECTIVE: To evaluate the performance of three different machine learning algorithms for identifying subgroups of high-cost patients. DESIGN: We applied three different clustering algorithms-connectivity-based clustering using agglomerative hierarchical clustering, centroid-based clustering with the k-medoids algorithm, and density-based clustering with the OPTICS algorithm-to a clinical and administrative dataset. We then examined the extent to which each algorithm identified subgroups of patients that were (1) clinically distinct and (2) associated with meaningful differences in relevant utilization metrics. PARTICIPANTS: Patients enrolled in a national Medicare Advantage plan, categorized in the top decile of spending (n = 6154). MAIN MEASURES: Post hoc discriminative models comparing the importance of variables for distinguishing observations in one cluster from the rest. Variance in utilization and spending measures. KEY RESULTS: Connectivity-based, centroid-based, and density-based clustering identified eight, five, and ten subgroups of high-cost patients, respectively. Post hoc discriminative models indicated that density-based clustering subgroups were the most clinically distinct. The variance of utilization and spending measures was the greatest among the subgroups identified through density-based clustering. CONCLUSIONS: Machine learning algorithms can be used to segment a high-cost patient population into subgroups of patients that are clinically distinct and associated with meaningful differences in utilization and spending measures. For these purposes, density-based clustering with the OPTICS algorithm outperformed connectivity-based and centroid-based clustering algorithms.