Dataset Information

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

ABSTRACT: 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 split-sample 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, particularly because numerous health care organizations are increasingly using these routinely collected data.

SUBMITTER: Lauffenburger JC

PROVIDER: S-EPMC7573679 | biostudies-literature | 2020 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Lauffenburger Julie C JC Mahesri Mufaddal M Choudhry Niteesh K NK

JAMA network open 20201001 10

<h4>Importance</h4>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.<h4>Objective</h4>To classify patients by their long-term, dynamic health care spending patterns using a data-driven approac ...[more]

PMID: 33074324

Similar Datasets

Project description:Background and objectivesDespite representing 1% of the population, beneficiaries on long-term dialysis account for over 7% of Medicare's fee-for-service spending. Because of their focus on care coordination, Accountable Care Organizations may be an effective model to reduce spending inefficiencies for this population. We analyzed Medicare data to examine time trends in long-term dialysis beneficiary alignment to Accountable Care Organizations and differences in spending for those who were Accountable Care Organization aligned versus nonaligned.Design, setting, participants, & measurementsIn this retrospective cohort study, beneficiaries on long-term dialysis between 2009 and 2016 were identified using a 20% random sample of Medicare beneficiaries. Trends in alignment to an Accountable Care Organization were compared with alignment of the general Medicare population from 2012 to 2016. Using an interrupted time series approach, we examined the association between Accountable Care Organization alignment and the primary outcome of total spending for long-term dialysis beneficiaries from prior to Accountable Care Organization implementation (2009-2011) through implementation of the Comprehensive ESRD Care model in October 2015. We fit linear regression models with generalized estimating equations to adjust for patient characteristics.ResultsDuring the study period, 135,152 beneficiaries on long-term dialysis were identified. The percentage of long-term dialysis beneficiaries aligned to an Accountable Care Organization increased from 6% to 23% from 2012 to 2016. In the time series analysis, spending on Accountable Care Organization-aligned beneficiaries was $143 (95% confidence interval, $5 to $282) less per beneficiary-quarter than spending for nonaligned beneficiaries. In analyses stratified by whether beneficiaries received care from a primary care physician, savings by Accountable Care Organization-aligned beneficiaries were limited to those with care by a primary care physician ($235; 95% confidence interval, $73 to $397).ConclusionsThere was a substantial increase in the percentage of long-term dialysis beneficiaries aligned to an Accountable Care Organization from 2012 to 2016. Moreover, in adjusted models, Accountable Care Organization alignment was associated with modest cost savings among long-term dialysis beneficiaries with care by a primary care physician.

Project description:Importance:Despite a growing recognition of the increased mortality risk among sepsis survivors, little is known about the patterns of end-of-life care among this population. Objective:To describe patterns of end-of-life care among a national sample of sepsis survivors and identify factors associated with long-term mortality risk and hospice use. Design, Setting, and Participants:This cohort study assessed sepsis survivors who were Medicare fee-for-service beneficiaries discharged to home health care using national Medicare administrative, claims, and home health assessment data from 2013 to 2014. The initial and final primary analyses were conducted in July 2017 and from July to August 2019, respectively. Exposures:Sepsis hospital discharge and 1 or more home health assessments within 1 week. Main Outcomes and Measures:Outcomes were 1-year mortality among all sepsis survivors and hospitalization in the last 30 days of life, death in an acute care hospital, and hospice use among decedents. Multivariate logistic regression was used to identify factors associated with 1-year mortality and hospice use. Results:Among 87 581 sepsis survivors who were Medicare fee-for-service beneficiaries discharged to home health care, 49 323 (56.3%) were aged 75 years or older, 69 499 (79.4%) were non-Hispanic white, and 48 472 (55.3%) were female. Among the total survivors, 24 423 (27.9%) people died within 1 year of discharge, with a median (interquartile range) survival time of 119 (51-220) days. Among these decedents, 16 684 (68.2%) were hospitalized in the last 30 days of life, 6560 (26.8%) died in an acute care hospital, and 12 573 (51.4%) were enrolled in hospice, with 5729 (45.6%) using hospice for 7 or fewer days. Several factors were associated with 1-year mortality, including a cancer diagnosis (odds ratio [OR], 3.66; 95% CI, 3.50-3.83; P?<?.001), multiple dependencies of activities of daily living or instrumental activities of daily living (OR, 2.80; 95% CI, 2.57-3.05; P?<?.001), and an overall poor health status (OR, 2.21; 95% CI, 2.01-2.44; P?<?.001) documented on home health assessment. Among the decedents, cancer was associated with hospice use (OR, 2.25; 95% CI, 2.11-2.41; P?<?.001), patients aged 85 years or older (OR, 1.49; 95% CI, 1.37-1.61; P?<?.001), and living in an assisted living setting (OR, 1.93; 95% CI, 1.69-2.19; P?<?.001). Conclusions and Relevance:The findings of this study suggest that death within 1 year after sepsis discharge may be common among Medicare beneficiaries discharged to home health care. Although 1 in 2 decedents used hospice, aggressive care near the end of life and late hospice referral were common. Readily identifiable risk factors suggest opportunities to target efforts to improve palliative and end-of-life care among high-risk sepsis survivors.

Project description:The Medicare accountable care organization (ACO) programs rely on delivery system integration and health care provider risk sharing to lower spending while improving quality of care.To compare spending and quality between larger and smaller provider groups and examine how size-related differences vary by 2 factors considered central to ACO performance: group primary care orientation and financial risk sharing by health care providers.Using 2009 Medicare claims and linked American Medical Association Group Practice data, we assigned 4.29 million beneficiaries to health care provider groups based on primary care use. We categorized group size according to eligibility thresholds for the Shared Savings (?5000 assigned beneficiaries) and Pioneer (?15,000) ACO programs and distinguished hospital-based from independent groups. We assessed the primary care orientation of larger groups' specialty mix and used health maintenance organization market penetration and data from the Community Tracking Study to measure the extent of financial risk accepted by different types of provider groups in different areas for managed care patients. We estimated linear regression models comparing spending and quality between larger and smaller health care provider groups, allowing size-related differences to vary by measures of group primary care orientation and risk sharing. Spending and quality measures included total medical spending, spending by type of service, 5 process measures of quality, and 30-day readmissions, all adjusted for sociodemographic and clinical characteristics.Compared with smaller groups, larger hospital-based groups had higher total per-beneficiary spending in 2009 (mean difference, +$849), higher 30-day readmission rates (+1.3 percentage points), and similar performance on 4 of 5 process measures of quality. In contrast, larger independent physician groups performed better than smaller groups on all process measures and exhibited significantly lower per-beneficiary spending in counties where risk sharing by these groups was more common (-$426). Among all groups sufficiently large to participate in ACO programs, a strong primary care orientation was associated with lower spending, fewer readmissions, and better quality of diabetes care.Spending was lower and quality of care better for Medicare beneficiaries served by larger independent physician groups with strong primary care orientations in environments where health care providers accepted greater risk.

Project description:ImportanceThe benefits of public payment policy may extend to private populations through "spillover" effects. If cost-saving efforts in Medicare also reduce costs among commercially insured patients, Medicare payment systems could be a versatile policy tool in future reform efforts.ObjectivesTo determine whether physicians who participated in a Medicare Accountable Care Organization (ACO) reduced spending among their commercial patients.DesignThis was a retrospective, longitudinal study which was conducted using Blue Cross Blue Shield of Michigan (BCBSM) claims data from 2010 to 2015. We compared patients seen by physicians who participated in a Medicare ACO to patients whose physicians were not part of an ACO. We used a difference-in-differences (DIDs) design to test whether physician participation in an ACO was associated with reduced spending among their commercially insured patients. We also tested for heterogeneous effects: we assessed whether spillovers were larger among patients with clinical conditions (acute myocardial infarction, pneumonia, congestive heart failure) that have previously been targeted by Medicare payment programs.SettingThis was a population-based study of commercially insured patients in Michigan.ParticipantsPatients who experienced a significant clinical episode (eg, labor and delivery, acute myocardial infarction) between 2010 and 2015.ExposureOur patient-level exposure is treatment by a Medicare ACO-affiliated physician.Main outcomes and measuresMedical spending of 0-90 days and 91-365 days after a clinical episode.ResultsPatients in the exposure group (n=54,750) and in the control group (n=137,883) were similar in demographic characteristics of age, sex, and type of clinical episodes. Adjusted mean 90-day spending in the preexposure period was $21,292 among the exposure group and $21,157 among the comparison group; these means declined to $21,250 and $20,995 in the postperiod, yielding a DIDs estimate of $119 [95% confidence interval (CI), -$170 to $408]. Adjusted means for 91-365 days spending in the preperiod were $4258 among the exposure group and $4251 among the comparison group; these means rose to $4338 and $4421 in the postperiod, yielding a DIDs estimate of -$90 (95% CI, -$312 to $132). We also separately examined patients with conditions that have been targeted by other Medicare payment programs. Among these patients, 90-day spending did not differ between exposure and comparison groups (DIDs, -$223; 95% CI, -$2037 to $1591), although 91-365 days spending decreased among the exposure group with marginal statistical significance (DIDs, -$1160; 95% CI, -$2459 to $140).Conclusions and relevancePhysicians who participated in Medicare ACOs did not reduce spending among most of their commercially insured patients. Medicare policy is unlikely to confer significant spillover benefits to the commercially insured population.

Project description:BackgroundLong-term opioid therapy was prescribed with increasing frequency over the past decade. However, factors surrounding long-term use of opioids in older adults remains poorly understood, probably because older people are not at the center stage of the national opioid crisis.ObjectivesTo estimate the annual utilization and trends in long-term opioid use among older adults in the United States.Study designRetrospective cohort study.SettingData from Medicare-enrolled older adults.MethodsThis study utilized a nationally representative sample of Medicare administrative claims data from the years 2012 to 2016 containing records of health care services for more than 2.3 million Medicare beneficiaries each year. Medicare beneficiaries who were 65 years of age or older and who were enrolled in Medicare Parts A, B, and D, but not Part C, for at least 10 months in a year were included in the study. We measured annual utilization and trends in new long-term opioid use episodes over 4 years (2013-2016). We examined claims records for the demographic characteristics of the eligible individuals and for the presence of chronic non-cancer pain (CNCP), cancer, and other comorbidities.ResultsFrom 2013 to 2016, administrative claims of approximately 2.3 million elderly Medicare beneficiaries were analyzed in each year with a majority of them being women (~56%) and white (~82%) with a mean age of approximately 75 years. The proportion of all eligible beneficiaries with at least one new opioid prescription increased from 6.64% in 2013, peaked at 10.32% in 2015, and then decreased to 8.14% in 2016. The proportion of individuals with long-term opioid use among those with a new opioid prescription was 12.40% in 2013 and 10.20% in 2016. Among new long-term opioid users, the proportion of beneficiaries with a cancer diagnosis during the study years increased from 13.30% in 2013 to 15.67% in 2016, and the proportion with CNCP decreased from 30.25% in 2013 to 27.36% in 2016. Across all years, long-term opioid use was consistently high in the Southern states followed by the Midwest region.LimitationsThis study used Medicare fee-for-service administrative claims data to capture prescription fill patterns, which do not allow for the capture of individuals enrolled in Medicare Advantage plans, cash prescriptions, or for the evaluation of appropriateness of prescribing, or the actual use of medication. This study only examined long-term use episodes among patients who were defined as opioid-naive. Finally, estimates captured for 2016 could only utilize data from 9 months of the year to capture 90-day long-term-use episodes.ConclusionsUsing a national sample of elderly Medicare beneficiaries, we observed that from 2013 to 2016 the use of new prescription opioids increased from 2013 to 2014 and peaked in 2015. The use of new long-term prescription opioids peaked in 2014 and started to decrease from 2015 and 2016. Future research needs to evaluate the impact of the changes in new and long-term prescription opioid use on population health outcomes.

Dataset Information

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

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets