Development and Assessment of a New Framework for Disease Surveillance, Prediction, and Risk Adjustment

Ellis, Randall P.; Hsu, Heather E.; Siracuse, Jeffrey J.; Walkey, Allan J.; Lasser, Karen E.; Jacobson, Brian C.; Andriola, Corinne; Hoagland, Alex; Liu, Ying; Song, Chenlu; Kuo, Tzu‐Chun; Ash, Arlene S.

doi:10.1001/jamahealthforum.2022.0276

Cited by 6 publications

(16 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Enrollees with no diagnoses were overpaid by more than $2000 in the HHS HCC model. As previously described, 5 the additive DXI model substantially outperformed the HHS HCC model across the spectrum of common to rare diagnoses.…”

Section: Rare Diagnosessupporting

confidence: 58%

“…We used data from 2016 to 2018 of the Merative (formerly IBM) MarketScan Commercial Claims and Encounters Database including 65 901 460 person-years of enrollees 64 years and younger and enrolled in noncapitated commercial insurance plans with medical, pharmacy, and behavioral health benefits. We randomly split the data 90% to 10% for model development and validation, respectively, and used weighted least-squares regression to predict (concurrent) total spending top-coded at $250 000 per person-year, weighting by fraction of the year eligible . The Boston University Institutional Review Board exempted this study of deidentified data from review and informed consent.…”

Section: Methodsmentioning

confidence: 99%

“…We had previously used expert clinician review to assign all 72 000 US International Statistical Classification of Diseases, Tenth Revision, Clinical Modification ( ICD - 10 - CM ) billable diagnosis codes and their unbillable root codes to at least 1 and up to 7 diagnostic clusters (ie, DXIs) . We grouped diagnoses into the same DXI when they were clinically related and had similar costs and clinical implications (for example, pneumonia due to organism A vs organism B) .…”

Section: Methodsmentioning

confidence: 99%

“…In this study, we address all these concerns with a novel ML algorithm that continues to follow the recently reaffirmed 10 principles (eTable 1 in Supplement 1). This article enhances the utility of the Diagnostic Items (DXIs) diagnostic clustering system and refines both HHS HCC Marketplace modeling logic and the original Diagnostic Cost Group (DCG) framework for predicting health care spending . To address gameability concerns, we asked physician panels to score each DXI as to how comfortable they felt with its diagnoses being allowed to affect payment.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Novel Machine Learning Algorithm for Creating Risk-Adjusted Payment Formulas

Andriola,

Ellis,

Siracuse

et al. 2024

JAMA Health Forum

Self Cite

View full text Add to dashboard Cite

ImportanceModels predicting health care spending and other outcomes from administrative records are widely used to manage and pay for health care, despite well-documented deficiencies. New methods are needed that can incorporate more than 70 000 diagnoses without creating undesirable coding incentives.ObjectiveTo develop a machine learning (ML) algorithm, building on Diagnostic Item (DXI) categories and Diagnostic Cost Group (DCG) methods, that automates development of clinically credible and transparent predictive models for policymakers and clinicians.Design, Setting, and ParticipantsDXIs were organized into disease hierarchies and assigned an Appropriateness to Include (ATI) score to reflect vagueness and gameability concerns. A novel automated DCG algorithm iteratively assigned DXIs in 1 or more disease hierarchies to DCGs, identifying sets of DXIs with the largest regression coefficient as dominant; presence of a previously identified dominating DXI removed lower-ranked ones before the next iteration. The Merative MarketScan Commercial Claims and Encounters Database for commercial health insurance enrollees 64 years and younger was used. Data from January 2016 through December 2018 were randomly split 90% to 10% for model development and validation, respectively. Deidentified claims and enrollment data were delivered by Merative the following November in each calendar year and analyzed from November 2020 to January 2024.Main Outcome and MeasuresConcurrent top-coded total health care cost. Model performance was assessed using validation sample weighted least-squares regression, mean absolute errors, and mean errors for rare and common diagnoses.ResultsThis study included 35 245 586 commercial health insurance enrollees 64 years and younger (65 901 460 person-years) and relied on 19 clinicians who provided reviews in the base model. The algorithm implemented 218 clinician-specified hierarchies compared with the US Department of Health and Human Services (HHS) hierarchical condition category (HCC) model’s 64 hierarchies. The base model that dropped vague and gameable DXIs reduced the number of parameters by 80% (1624 of 3150), achieved an R2 of 0.535, and kept mean predicted spending within 12% ($3843 of $31 313) of actual spending for the 3% of people with rare diseases. In contrast, the HHS HCC model had an R2 of 0.428 and underpaid this group by 33% ($10 354 of $31 313).Conclusions and RelevanceIn this study, by automating DXI clustering within clinically specified hierarchies, this algorithm built clinically interpretable risk models in large datasets while addressing diagnostic vagueness and gameability concerns.

show abstract

Section: Rare Diagnosessupporting

confidence: 58%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Novel Machine Learning Algorithm for Creating Risk-Adjusted Payment Formulas

Andriola,

Ellis,

Siracuse

et al. 2024

JAMA Health Forum

Self Cite

View full text Add to dashboard Cite

show abstract

“…We use these four metrics that are widely used to evaluate RA models (Ellis et al, 2022): R-squared (R 2 ), also known as Coefficient of Determination, is the proportion of total variance of the target variable explained variance by the model. The exact formula is as follows:…”

Section: Evaluation Metricsmentioning

confidence: 99%

A Data-driven Approach to Revamp the ACO Risk Adjustment Model

Park¹,

Buchan²,

Piconne³

et al. 2023

Preprint

View full text Add to dashboard Cite

Accountable Care Organizations (ACOs) involve groups of healthcare providers who voluntarily come together to deliver coordinated, high-quality care to aligned beneficiaries. Many ACOs, such as the Medicare Shared Savings Program and the ACO REACH program, can participate in alternative payment models that differ from the prevalent Fee-for-Service model. In these alternative payment models, providers and payers share financial risk to align the ACOs' financial incentives with the dual aims of reducing the total cost of care and improving the quality of care. In other words, ACOs could profit by keeping their patients healthy and preventing unnecessary hospitalization. However, to make this financial structure work as intended, there needs to be a Risk Adjustment (RA) model to change reimbursement proportional to a beneficiary's risk; otherwise, ACOs may enroll only healthy patients, i.e., adverse selection. While most ACOs adopt RA models for this reason, the original RA methodology has mostly stayed the same over the last several decades. As a result, some ACO participants have found ways to ``game'' the system: to receive disproportional payments for the risk they bear. To mitigate the waste, the federal government has added various post-adjustment mechanisms, such as mixing the risk-adjusted benchmark with historical spending, adjusting by a coding intensity factor, capping risk score growth rate, and incorporating health equity incentives. Unfortunately, those mechanisms build on top of each other in nonlinear and discontinuous ways, causing their actual effects - and efficacy - to be difficult to disentangle and evaluate. In this paper, we will summarize our lessons from operating one of the most successful ACOs in the nation to help rebuild the RA model based on a data-driven approach. Next, we outline the characteristics of an ideal RA model. Then, we propose a new one that addresses such requirements, eliminating the need for a multi-step process involving nonlinear and discontinuous staging. Finally, we provide experimental results by applying this model to our ACO data and comparing them with the current RA implementation.

show abstract

Patterns of Morbidity Across the Lifespan

Lemke,

Forrest,

Leff

et al. 2023

Medical Care

View full text Add to dashboard Cite

Background: Classification systems to segment such patients into subgroups for purposes of care management and population analytics should balance administrative simplicity with clinical meaning and measurement precision. Objective: To describe and empirically apply a new clinically relevant population segmentation framework applicable to all payers and all ages across the lifespan. Research Design and Subjects: Cross-sectional analyses using insurance claims database for 3.31 Million commercially insured and 1.05 Million Medicaid enrollees under 65 years old; and 5.27 Million Medicare fee-for-service beneficiaries aged 65 and older. Measures: The “Patient Need Groups” (PNGs) framework, we developed, classifies each person within the entire 0–100+ aged population into one of 11 mutually exclusive need-based categories. For each PNG segment, we documented a range of clinical and resource endpoints, including health care resource use, avoidable emergency department visits, hospitalizations, behavioral health conditions, and social need factors. Results: The PNG categories included: (1) nonuser, (2) low-need child, (3) low-need adult, (4) low-complexity multimorbidity, (5) medium-complexity multimorbidity, (6) low-complexity pregnancy, (7) high-complexity pregnancy, (8) dominant psychiatric/behavioral condition, (9) dominant major chronic condition, (10) high-complexity multimorbidity, and (11) frailty. Each PNG evidenced a characteristic age-related trajectory across the full lifespan. In addition to offering clinically cogent groupings, large percentages (29%–62%) of patients in two pregnancy and high-complexity multimorbidity and frailty PNGs were in a high-risk subgroup (upper 10%) of potential future health care utilization. Conclusions: The PNG population segmentation approach represents a comprehensive measurement framework that captures and categorizes available electronic health care data to characterize individuals of all ages based on their needs.

show abstract

Development and Assessment of a New Framework for Disease Surveillance, Prediction, and Risk Adjustment

Abstract: This diagnostic modeling study develops an ICD-10-CM –based classification framework for predicting diverse health care payment, quality, and performance outcomes.

Cited by 6 publications

References 15 publications

A Novel Machine Learning Algorithm for Creating Risk-Adjusted Payment Formulas

A Novel Machine Learning Algorithm for Creating Risk-Adjusted Payment Formulas

A Data-driven Approach to Revamp the ACO Risk Adjustment Model

Patterns of Morbidity Across the Lifespan

Contact Info

Product

Resources

About