Uncertainty in lung cancer stage for survival estimation via set-valued classification.

The difficulty in identifying cancer stage in health care claims data has limited oncology quality of care and health outcomes research. We fit prediction algorithms for classifying lung cancer stage into three classes (stages I/II, stage III, and stage IV) using claims data, and then demonstrate a method for incorporating the classification uncertainty in survival estimation. Leveraging set-valued classification and split conformal inference, we show how a fixed algorithm developed in one cohort of data may be deployed in another, while rigorously accounting for uncertainty from the initial classification step. We demonstrate this process using SEER cancer registry data linked with Medicare claims data.

Comparing risk adjustment estimation methods under data availability constraints.

The Italian National Healthcare Service relies on per capita allocation for healthcare funds, despite having a highly detailed and wide range of data to potentially build a complex risk-adjustment formula. However, heterogeneity in data availability limits the development of a national model. This paper implements and ealuates machine learning (ML) and standard risk-adjustment models on different data scenarios that a Region or Country may face, to optimize information with the most predictive model. We show that ML achieves a small but generally statistically insignificant improvement of adjusted R2 and mean squared error with fine data granularity compared to linear regression, while in coarse granularity and poor range of variables scenario no differences were observed. The advantage of ML algorithms is greater in the coarse granularity and fair/rich range of variables set and limited with fine granularity scenarios. The inclusion of detailed morbidity- and pharmacy-based adjustors generally increases fit, although the trade-off of creating adverse economic incentives must be considered.

Computational health economics for identification of unprofitable health care enrollees.

Health insurers may attempt to design their health plans to attract profitable enrollees while deterring unprofitable ones. Such insurers would not be delivering socially efficient levels of care by providing health plans that maximize societal benefit, but rather intentionally distorting plan benefits to avoid high-cost enrollees, potentially to the detriment of health and efficiency. In this work, we focus on a specific component of health plan design at risk for health insurer distortion in the Health Insurance Marketplaces: the prescription drug formulary. We introduce an ensembled machine learning function to determine whether drug utilization variables are predictive of a new measure of enrollee unprofitability we derive, and thus vulnerable to distortions by insurers. Our implementation also contains a unique application-specific variable selection tool. This study demonstrates that super learning is effective in extracting the relevant signal for this prediction problem, and that a small number of drug variables can be used to identify unprofitable enrollees. The results are both encouraging and concerning. While risk adjustment appears to have been reasonably successful at weakening the relationship between therapeutic-class-specific drug utilization and unprofitability, some classes remain predictive of insurer losses. The vulnerable enrollees whose prescription drug regimens include drugs in these classes may need special protection from regulators in health insurance market design.

Hospitalizations reduce health care utilization of household members.

OBJECTIVE: To examine whether the financial burden of hospitalizations affects the health care utilization of household members of the admitted patient. DATA SOURCES: We utilized health care claims data from the Massachusetts All-Payer Claims Database, 2010-2015, to identify emergency hospitalizations of patients on family insurance plans and the health care utilization of the family members on those plans. STUDY DESIGN: We used an event-study analysis to compare health care spending and utilization of family members of a hospitalized individual and family members of an individual who was hospitalized 1 year later. We examine whether such hospitalizations were associated with changes in medical spending, the frequency of ambulatory office visits, other ambulatory care, and preventive care. DATA COLLECTION/EXTRACTION METHODS: The analyses include household members of patients with an emergency admission and a length of stay between 5 and 90 days. PRINCIPAL FINDINGS: Unexpected hospital admissions reduced household members' health care spending and utilization by more than 6.4% (95% confidence interval [CI]: -8.2%, -4.5%) on average in the year following the hospitalization. Household members had fewer ambulatory visits with primary care physicians (PCPs), fewer referrals to specialists, and reduced utilization of other ambulatory care, including high-value preventive services. These changes were observed for both children and adults and were exacerbated if members of the household had previously been on Medicaid. The reduction in utilization was less pronounced when the admitted patient and household member shared the same PCP and when their health insurance plan had a family deductible. CONCLUSIONS: Compared with families without a hospitalized family member, family members of hospitalized individuals reduced their medical spending and utilization, including a substantial reduction in the use of preventive care. This study highlights the challenges of providing continuity in care when families face financial hardship.

COVID-19 pandemic in the United States.

OBJECTIVES: The paper highlights US health policy and technology responses to the COVID-19 pandemic from January 1, 2020 - August 9, 2020. METHODS: A review of primary data sources in the US was conducted. The data were summarized to describe national and state-level trends in the spread of COVID-19 and in policy and technology solutions. RESULTS: COVID-19 cases and deaths initially peaked in late March and April, but after a brief reduction in June cases and deaths began rising again during July and continued to climb into early August. The US policy response is best characterized by its federalist, decentralized nature. The national government has led in terms of economic and fiscal response, increasing funding for scientific research into testing, treatment, and vaccines, and in creating more favorable regulations for the use of telemedicine. State governments have been responsible for many of the containment, testing, and treatment responses, often with little federal government support. Policies that favor economic re-opening are often followed by increases in state-level case numbers, which are then followed by stricter containment measures, such as mask wearing or pausing re-opening plans. CONCLUSIONS: While all US states have begun to "re-open" economic activities, this trend appears to be largely driven by social tensions and economic motivations rather than an ability to effectively test and surveil populations.

Classifying Stage IV Lung Cancer From Health Care Claims: A Comparison of Multiple Analytic Approaches.

PURPOSE: Cancer stage is a key determinant of outcomes; however, stage is not available in claims-based data sources used for real-world evaluations. We compare multiple methods for classifying lung cancer stage from claims data. METHODS: Our study used the linked SEER-Medicare data. The patient samples included fee-for-service Medicare beneficiaries diagnosed with lung cancer from 2010 to 2011 (development cohort) and 2012 to 2013 (validation cohort) who received chemotherapy. Classification algorithms considered Medicare Part A and B claims for care in the 3 months before and after chemotherapy initiation. We developed a clinical algorithm to predict stage IV (v I to III) cancer on the basis of treatment patterns (surgery, radiotherapy, chemotherapy). We also considered an ensemble of claims-based machine learning algorithms. Classification methods were trained in the development cohort, and performance was measured in both cohorts. The SEER data were the gold standard for cancer stage. RESULTS: Development and validation cohorts included 14,760 and 14,620 patients with lung cancer, respectively. Validation analyses assessed clinical, random forest, and simple logistic regression algorithms. The best performing classifier within the development cohort was the random forests, but this performance was not replicated in validation analysis. Logistic regression had stable performance across cohorts. Compared with the clinical algorithm, the 14-variable logistic regression algorithm demonstrated higher accuracy in both the development (77% v 71%) and validation cohorts (77% v 73%), with improved specificity for stage IV disease. CONCLUSION: Machine learning algorithms have potential to improve lung cancer stage classification but may be prone to overfitting. Use of ensembles, cross-validation, and external validation can aid generalizability. Degradation of accuracy between development and validation cohorts suggests the need for caution in implementing machine learning in research or care delivery.

Data transformations to improve the performance of health plan payment methods.

The conventional method for developing health care plan payment systems uses observed data to study alternative algorithms and set incentives for the health care system. In this paper, we take a different approach and transform the input data rather than the algorithm, so that the data used reflect the desired spending levels rather than the observed spending levels. We present a general economic model that incorporates the previously overlooked two-way relationship between health plan payment and insurer actions. We then demonstrate our systematic approach for data transformations in two Medicare applications: underprovision of care for individuals with chronic illnesses and health care disparities by geographic income levels. Empirically comparing our method to two other common approaches shows that the "side effects" of these approaches vary by context, and that data transformation is an effective tool for addressing misallocations in individual health insurance markets.

Mental Health Risk Adjustment with Clinical Categories and Machine Learning.

OBJECTIVE: To propose nonparametric ensemble machine learning for mental health and substance use disorders (MHSUD) spending risk adjustment formulas, including considering Clinical Classification Software (CCS) categories as diagnostic covariates over the commonly used Hierarchical Condition Category (HCC) system. DATA SOURCES: 2012-2013 Truven MarketScan database. STUDY DESIGN: We implement 21 algorithms to predict MHSUD spending, as well as a weighted combination of these algorithms called super learning. The algorithm collection included seven unique algorithms that were supplied with three differing sets of MHSUD-related predictors alongside demographic covariates: HCC, CCS, and HCC + CCS diagnostic variables. Performance was evaluated based on cross-validated R2 and predictive ratios. PRINCIPAL FINDINGS: Results show that super learning had the best performance based on both metrics. The top single algorithm was random forests, which improved on ordinary least squares regression by 10 percent with respect to relative efficiency. CCS categories-based formulas were generally more predictive of MHSUD spending compared to HCC-based formulas. CONCLUSIONS: Literature supports the potential benefit of implementing a separate MHSUD spending risk adjustment formula. Our results suggest there is an incentive to explore machine learning for MHSUD-specific risk adjustment, as well as considering CCS categories over HCCs.

Sample Selection for Medicare Risk Adjustment Due to Systematically Missing Data.

OBJECTIVE: To assess the issue of nonrepresentative sampling in Medicare Advantage (MA) risk adjustment. DATA SOURCES: Medicare enrollment and claims data from 2008 to 2011. DATA EXTRACTION: Risk adjustment predictor variables were created from 2008 to 2010 Part A and B claims and the Medicare Beneficiary Summary File. Spending is based on 2009-2011 Part A and B, Durable Medical Equipment, and Home Health Agency claims files. STUDY DESIGN: A propensity-score matched sample of Traditional Medicare (TM) beneficiaries who resembled MA enrollees was created. Risk adjustment formulas were estimated using multiple techniques, and performance was evaluated based on R2 , predictive ratios, and formula coefficients in the matched sample and a random sample of TM beneficiaries. PRINCIPAL FINDINGS: Matching improved balance on observables, but performance metrics were similar when comparing risk adjustment formula results fit on and evaluated in the matched sample versus fit on the random sample and evaluated in the matched sample. CONCLUSIONS: Fitting MA risk adjustment formulas on a random sample versus a matched sample yields little difference in MA plan payments. This does not rule out potential improvements via the matching method should reliable MA encounter data and additional variables become available for risk adjustment.

Classifying Lung Cancer Severity with Ensemble Machine Learning in Health Care Claims Data.

Research in oncology quality of care and health outcomes has been limited by the difficulty of identifying cancer stage in health care claims data. Using linked cancer registry and Medicare claims data, we develop a tool for classifying lung cancer patients receiving chemotherapy into early vs. late stage cancer by (i) deploying ensemble machine learning for prediction, (ii) establishing a set of classification rules for the predicted probabilities, and (iii) considering an augmented set of administrative claims data. We find our ensemble machine learning algorithm with a classification rule defined by the median substantially outperforms an existing clinical decision tree for this problem, yielding full sample performance of 93% sensitivity, 92% specificity, and 93% accuracy. This work has the potential for broad applicability as provider organizations, payers, and policy makers seek to measure quality and outcomes of cancer care and improve on risk adjustment methods.

Accountability across the Continuum: The Participation of Postacute Care Providers in Accountable Care Organizations.

OBJECTIVE: To examine the extent to which accountable care organizations (ACOs) formally incorporate postacute care providers. DATA SOURCES: The National Survey of ACOs (N = 269, response rate 66 percent). STUDY DESIGN: We report statistics on ACOs' formal inclusion of postacute care providers and the organizational characteristics and clinical capabilities of ACOs that have postacute care. PRINCIPAL FINDINGS: Half of ACOs formally include at least one postacute service, with inclusion at higher rates in ACOs with commercial (64 percent) and Medicaid contracts (70 percent) compared to ACOs with Medicare contracts only (45 percent). ACOs that have a formal relationship with a postacute provider are more likely to have advanced transition management, end of life planning, readmission prevention, and care management capabilities. CONCLUSIONS: Many ACOs have not formally engaged postacute care, which may leave room to improve service integration and care management.