Dataset Information

Novel Machine Learning Approach to Identify Preoperative Risk Factors Associated With Super-Utilization of Medicare Expenditure Following Surgery.

ABSTRACT:

Importance

Typically defined as the top 5% of health care users, super-utilizers are responsible for an estimated 40% to 55% of all health care costs. Little is known about which factors may be associated with increased risk of long-term postoperative super-utilization.

Objective

To identify clusters of patients with distinct constellations of clinical and comorbid patterns who may be associated with an elevated risk of super-utilization in the year following elective surgery.

Design, setting, and participants

A retrospective longitudinal cohort study of 1 049 160 patients who underwent abdominal aortic aneurysm repair, coronary artery bypass graft, colectomy, total hip arthroplasty, total knee arthroplasty, or lung resection were identified from the 100% Medicare inpatient and outpatient Standard Analytic Files at all inpatient facilities performing 1 or more of the evaluated surgical procedures from 2013 to 2015. Data from 2012 to 2016 were used to evaluate expenditures in the year preceding and following surgery. Using a machine learning approach known as Logic Forest, comorbidities and interactions of comorbidities that put patients at an increased chance of becoming a super-utilizer were identified. All comorbidities, as defined by the Charlson (range, 0-24) and Elixhauser (range, 0-29) comorbidity indices, were used in the analysis. Higher scores indicated higher comorbidity burden. Data analysis was completed on November 16, 2018.

Main outcome and measures

Super-utilization of health care in the year following surgery.

Results

In total, 1 049 160 patients met inclusion criteria and were included in the analytic cohort. Their median (interquartile range) age was 73 (69-78) years, and approximately 40% were male. Super-utilizers comprised 4.8% of the overall cohort (n = 79 746) yet incurred 31.7% of the expenditures. Although the difference in overall expenditures per person between super-utilizers ($4049) and low users ($2148) was relatively modest prior to surgery, the difference in expenditures between super-utilizers ($79 698) vs low users ($2977) was marked in the year following surgery. Risk factors associated with super-utilization of health care included hemiplegia/paraplegia (odds ratio, 5.2; 95% CI, 4.4-6.2), weight loss (odds ratio, 3.5; 95% CI, 2.9-4.2), and congestive heart failure with chronic kidney disease stages I to IV (odds ratio, 3.4; 95% CI, 3.0-3.9).

Conclusions and relevance

Super-utilizers comprised only a small fraction of the surgical population yet were responsible for a disproportionate amount of Medicare expenditure. Certain subpopulations were associated with super-utilization of health care following surgical intervention despite having lower overall use in the preoperative period.

SUBMITTER: Hyer JM

PROVIDER: S-EPMC6694398 | biostudies-literature | 2019 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Novel Machine Learning Approach to Identify Preoperative Risk Factors Associated With Super-Utilization of Medicare Expenditure Following Surgery.

Hyer J Madison JM Ejaz Aslam A Tsilimigras Diamantis I DI Paredes Anghela Z AZ Mehta Rittal R Pawlik Timothy M TM

JAMA surgery 20191101 11

<h4>Importance</h4>Typically defined as the top 5% of health care users, super-utilizers are responsible for an estimated 40% to 55% of all health care costs. Little is known about which factors may be associated with increased risk of long-term postoperative super-utilization.<h4>Objective</h4>To identify clusters of patients with distinct constellations of clinical and comorbid patterns who may be associated with an elevated risk of super-utilization in the year following elective surgery.<h4> ...[more]

PMID: 31411664

Similar Datasets

Project description:ImportanceLow-risk elective surgical procedures are common, but there are no clear guidelines for when preoperative consultations are required. Such consultations may therefore represent a substantial discretionary service.ObjectiveTo assess temporal trends, explanatory factors, and geographic variation for preoperative consultation in Medicare beneficiaries undergoing cataract surgery, a common low-risk elective procedure.Design, setting, and participantsCohort study using a 5% national random sample of Medicare part B claims data including a cohort of 556,637 patients 66 years or older who underwent cataract surgery from 1995 to 2006. Temporal trends in consultations were evaluated within this entire cohort, whereas explanatory factors and geographic variation were evaluated within the 89,817 individuals who underwent surgery from 2005 to 2006.Main outcomes and measuresSeparately billed preoperative consultations (performed by family practitioners, general internists, pulmonologists, endocrinologists, cardiologists, nurse practitioners, or anesthesiologists) within 42 days before index surgery.ResultsThe frequency of preoperative consultations increased from 11.3% in 1998 to 18.4% in 2006. Among individuals who underwent surgery in 2005 to 2006, hierarchical logistic regression modeling found several factors to be associated with preoperative consultation, including increased age (75-84 years vs 66-74 years: adjusted odds ratio [AOR], 1.09 [95% CI, 1.04-1.13]), race (African American race vs other: AOR, 0.71 [95% CI, 0.65-0.78]), urban residence (urban residence vs isolated rural town: AOR, 1.64 [95% CI, 1.49-1.81]), facility type (outpatient hospital vs ambulatory surgical facility: AOR, 1.10 [95% CI, 1.05-1.15]), anesthesia provider (anesthesiologist vs non-medically directed nurse anesthetist: AOR, 1.16 [95% CI, 1.10-1.24), and geographic region (Northeast vs South: AOR, 3.09 [95% CI, 2.33-4.10]). The burden of comorbidity was associated with consultation, but the effect size was small (<10%). Variation in frequency of consultation across hospital referral regions was substantial (median [range], 12% [0-69%]), even after accounting for differences in patient-level, anesthesia provider-level, and facility-level characteristics.Conclusions and relevanceBetween 1995 and 2006, the frequency of preoperative consultation for cataract surgery increased substantially. Referrals for consultation seem to be primarily driven by nonmedical factors, with substantial geographic variation.

Project description:PurposeDelaying cataract surgery is associated with an increased risk of falls, but whether routine preoperative testing delays cataract surgery long enough to cause clinical harm is unknown. We sought to determine whether the use of routine preoperative testing leads to harm in the form of delayed surgery and falls in Medicare beneficiaries awaiting cataract surgery.DesignRetrospective, observational cohort study using 2006-2014 Medicare claims.ParticipantsMedicare beneficiaries 66+ years of age with a Current Procedural Terminology claim for ocular biometry.MethodsWe measured the mean and median number of days between biometry and cataract surgery, calculated the proportion of patients waiting ≥ 30 days or ≥ 90 days for surgery, and determined the odds of sustaining a fall within 90 days of biometry among patients of high-testing physicians (testing performed in ≥ 75% of their patients) compared with patients of low-testing physicians. We also estimated the number of days of delay attributable to high-testing physicians.Main outcome measuresIncidence of falls occurring between biometry and surgery, odds of falling within 90 days of biometry, and estimated delay associated with physician testing behavior.ResultsOf 248 345 beneficiaries, 16.4% were patients of high-testing physicians. More patients of high-testing physicians waited ≥ 30 days and ≥ 90 days to undergo surgery (31.4% and 8.2% vs. 25.0% and 5.5%, respectively; P < 0.0001 for both). Falls before surgery in patients of high-testing physicians increased by 43% within the 90 days after ocular biometry (1.0% vs. 0.7%; P < 0.0001). The adjusted odds ratio of falling within 90 days of biometry in patients of high-testing physicians versus low-testing physicians was 1.10 (95% confidence interval [CI], 1.03-1.19; P = 0.008). After adjusting for surgical wait time, the odds ratio decreased to 1.07 (95% CI, 1.00-1.15; P = 0.06). The delay associated with having a high-testing physician was approximately 8 days (estimate, 7.97 days; 95% CI, 6.40-9.55 days; P < 0.0001). Other factors associated with delayed surgery included patient race (non-White), Northeast region, ophthalmologist ≤ 40 years of age, and low surgical volume.ConclusionsOveruse of routine preoperative medical testing by high-testing physicians is associated with delayed surgery and increased falls in cataract patients awaiting surgery.

Project description:ObjectivesMedicare beneficiaries recovering from a critical illness are increasingly being discharged home instead of to post-acute care facilities. Rehabilitation services are commonly recommended for intensive care unit (ICU) survivors; however, little is known about the frequency and dose of home-based rehabilitation in this population.DesignRetrospective analysis of 2012 Medicare hospital and home health (HH) claims data, linked with assessment data from the Medicare Outcomes and Assessment Information Set.SettingParticipant homes.ParticipantsMedicare beneficiaries recovering from an ICU stay longer than 24 hours, who were discharged directly home with HH services within 7 days of discharge and survived without readmission or hospice transfer for at least 30 days (n = 3,176).MeasurementsCount of rehabilitation visits received during HH care episode.ResultsA total of 19,564 rehabilitation visits were delivered to ICU survivors over 118,145 person-days in HH settings, a rate of 1.16 visits per week. One-third of ICU survivors received no rehabilitation visits during HH care. In adjusted models, those with the highest baseline disability received 30% more visits (rate ratio [RR] = 1.30; 95% confidence interval [CI] = 1.17-1.45) than those with the least disability. Conversely, an inverse relationship was found between multimorbidity (Elixhauser scores) and count of rehabilitation visits received; those with the highest tertile of Elixhauser scores received 11% fewer visits (RR = .89; 95% CI = .81-.99) than those in the lowest tertile. Participants living in a rural setting (vs urban) received 6% fewer visits (RR = .94; 95% CI = .91-.98); those who lived alone received 11% fewer visits (RR = .89; 95% CI = .82-.96) than those who lived with others.ConclusionOn average, Medicare beneficiaries discharged home after a critical illness receive few rehabilitation visits in the early post-hospitalization period. Those who had more comorbidities, who lived alone, or who lived in rural settings received even fewer visits, suggesting a need for their consideration during discharge planning. J Am Geriatr Soc 68:1512-1519, 2020.

Project description:BackgroundThere is growing interest in transitioning various surgical procedures to the outpatient care setting. However, for Medicare patients, the site of service for surgical procedures is influenced by regulations within the Inpatient and Outpatient Prospective Payment Systems. The purpose of this study is to quantify changes in utilization of outpatient spine surgery within the Medicare population, as well as to determine changes in outpatient volume after removal of a procedure from the "inpatient-only" list.MethodsThis is a cross-sectional study of Medicare billing database information for selected spine procedures included in the Medicare Physician/Supplier Procedure Summary (PSPS) public use files from 2010-2021. These files include aggregated data from Medicare Part B fee-for-service claims, published yearly. Procedures from Healthcare Common Procedural Coding System (HCPCS) code ranges 22010-22899 and 62380-63103 were selected for analysis, limited to surgical services delivered in the inpatient, hospital outpatient department (HOPD), and ambulatory surgical center (ASC) settings. For each HCPCS code included, estimates of the total number of services and corresponding changes in volume were calculated.ResultsWithin the range of codes included in the study, the total number of outpatient spine procedures rose approximately 193% from 2010 to 2021, with compound annual growth rate (CAGR) for outpatient procedures per year of 9.9% for HOPDs and 15.7% for ASCs (-2.2% for inpatient procedures). Within this period, the ASC list grew from 12 procedures to 58 procedures. In 2021, the highest volume ASC procedure was HCPCS 63047, at approximately 4970 procedures.ConclusionsThis study demonstrates a trend of increasing utilization of HOPDs and ASCs for spine procedures among Medicare beneficiaries from 2010 to 2021. Though HOPDs are currently more widely utilized, the ongoing additions of spine procedures to the ASC covered procedures list may shift this balance.

Dataset Information

Novel Machine Learning Approach to Identify Preoperative Risk Factors Associated With Super-Utilization of Medicare Expenditure Following Surgery.

Importance

Objective

Design, setting, and participants

Main outcome and measures

Results

Conclusions and relevance

Publications

Novel Machine Learning Approach to Identify Preoperative Risk Factors Associated With Super-Utilization of Medicare Expenditure Following Surgery.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets