Predicting Health Care Cost Transitions Using a Multidimensional Adaptive Prediction Process

Machine Learning Improves the Identification of Individuals With Higher Morbidity and Avoidable Health Costs After Acute Coronary Syndromes

OBJECTIVES

Traditional risk scores improved the definition of the initial therapeutic strategy in acute coronary syndrome (ACS), but they were not designed for predicting long-term individual risks and costs. In parallel, attempts to directly predict costs from clinical variables in ACS had limited success. Thus, novel approaches to predict cardiovascular risk and health expenditure are urgently needed. Our objectives were to predict the risk of major/minor adverse cardiovascular events (MACE) and estimate assistance-related costs.

METHODS

We used a 2-step approach that: (1) predicted outcomes with a common pathophysiological substrate (MACE) by using machine learning (ML) or logistic regression (LR) and compared with existing risk scores; (2) derived costs associated with noncardiovascular deaths, dialysis, ambulatory-care-sensitive-hospitalizations (ACSH), strokes, and MACE. With consecutive ACS individuals (n = 1089) from 2 cohorts, we trained in 80% of the population and tested in 20% using a 4-fold cross-validation framework. The 29-variable model included socioeconomic, clinical/lab, and coronarography variables. Individual costs were estimated based on cause-specific hospitalization from the Brazilian Health Ministry perspective.

RESULTS

After up to 12 years follow-up (mean = 3.3 ± 3.1; MACE = 169), the gradient-boosting machine model was superior to LR and reached an area under the curve (AUROC) of 0.891 [95% CI 0.846-0.921] (test set), outperforming the Syntax Score II (AUROC = 0.635 [95% CI 0.569-0.699]). Individuals classified as high risk (>90th percentile) presented increased HbA1c and LDL-C both at <24 hours post-ACS and 1-year follow-up. High-risk individuals required 33.5% of total costs and showed 4.96-fold (95% CI 3.71-5.48, P < .00001) greater per capita costs compared with low-risk individuals, mostly owing to avoidable costs (ACSH). This 2-step approach was more successful for finding individuals incurring high costs than predicting costs directly from clinical variables.

CONCLUSION

ML methods predicted long-term risks and avoidable costs after ACS.

Predictive modeling to identify potential participants of a disease management program hypertension

BACKGROUND

Based on the premise of limited health-care resources, decision-makers pursue to allocate disease management programs (DMP) more targeted.

METHODS

Based on routine data from a private health insurance company, a prediction model was developed to estimate the individual risk for future in-patient stays of patients eligible for a DMP Hypertension. The database included anonymous claims data of 38,284 policyholders with a diagnosis in the year 2013. A cutoff point of ≥70% was used for selecting candidates with a risk for future hospitalization. Using a logistic regression model, we estimated the model's prognostic power, the occurrence of clinical events, and the resource use.

RESULTS

Overall, the final model shows acceptable prognostic power (detection rate = 64.3%; sensitivity = 68.7%; positive predictive value (PPV) = 64.1%, area under the curve (AUC) = 0.72). The comparison between the selected hypothetical DMP-group with a predicted (LOH) ≥70% showed additional costs of about 69% for the DMP-group compared to insure with a LOH <70%.

CONCLUSION

The predictive analytical approach may identify potential DMP participants with a high risk of increased health services utilization and in-patient stays.

Prediction of health care expenditure increase: how does pharmacotherapy contribute?

BACKGROUND

Rising health care costs are a major public health issue. Thus, accurately predicting future costs and understanding which factors contribute to increases in health care expenditures are important. The objective of this project was to predict patients healthcare costs development in the subsequent year and to identify factors contributing to this prediction, with a particular focus on the role of pharmacotherapy.

METHODS

We used 2014-2015 Swiss health insurance claims data on 373'264 adult patients to classify individuals' changes in health care costs. We performed extensive feature generation and developed predictive models using logistic regression, boosted decision trees and neural networks. Based on the decision tree model, we performed a detailed feature importance analysis and subgroup analysis, with an emphasis on drug classes.

RESULTS

The boosted decision tree model achieved an overall accuracy of 67.6% and an area under the curve-score of 0.74; the neural network and logistic regression models performed 0.4 and 1.9% worse, respectively. Feature engineering played a key role in capturing temporal patterns in the data. The number of features was reduced from 747 to 36 with only a 0.5% loss in the accuracy. In addition to hospitalisation and outpatient physician visits, 6 drug classes and the mode of drug administration were among the most important features. Patient subgroups with a high probability of increase (up to 88%) and decrease (up to 92%) were identified.

CONCLUSIONS

Pharmacotherapy provides important information for predicting cost increases in the total population. Moreover, its relative importance increases in combination with other features, including health care utilisation.

Health Savings Accounts: Consumer Contribution Strategies and Policy Implications

Background. Health savings accounts (HSAs) are tax-advantaged savings accounts available only to households with high-deductible health insurance. This article provides initial answers to two questions: 1) How should a household budget for its annual HSA contributions? 2) Do current contribution limits provide households with the flexibility to use HSAs efficiently? To answer these questions, we formulate the household’s problem as one of determining a contribution strategy for minimizing total expected discounted medical costs. Methods. We use the 2002–2014 Medical Expenditure Panel Survey to develop a novel data-driven model for forecasting a household’s health care costs based on its current cost percentile and other characteristics. A dynamic policy, in which the contribution each year brings the HSA balance up to a household-specific threshold, is derived. This is compared to a simpler static policy in which the target HSA balance is simply the plan’s out-of-pocket maximum, with contributions in any year capped by a limit. Results. We find that: 1) the dynamic policy can save a household up to 19% in costs compared to the static one that is a proxy for typical contribution behavior; and 2) the recommended contribution amounts for 9% to 11% of households in a given year materially exceed what is currently allowed by the federal government. Conclusions. The dynamic policy derived from our data-analytic framework is able to unlock significant tax savings for health care consumers. To allow all households to use HSAs in a tax-efficient manner, a two-tiered contribution policy is needed: Allow unlimited contributions up to some balance, and then impose restrictions thereafter. The resulting impact on overall tax receipts is estimated to be well below what is currently allowed by legislation.

Integrating Well-Being Information and the Multidimensional Adaptive Prediction Process to Estimate Individual-Level Future Health Care Expenditure Levels

Decades of research exist focusing on the utility of self-reported health risk and status data in health care cost predictive models. However, in many of these studies a limited number of self-reported measures were considered. Compounding this issue, prior research evaluated models specified with a single covariate vector and distribution. In this study, the authors incorporate well-being data into the Multidimensional Adaptive Prediction Process (MAPP) and then use a simulation analysis to highlight the value of these findings for future cost mitigation. Data were collected on employees and dependents of a nationally based employer over 36 months beginning in January 2010. The first 2 years of data (2010, 2011) were utilized in model development and selection; 51239 and 54085 members were included in 2010 and 2011, respectively. The final results were based on prospective prediction of 2012 cost levels using 2011 data. The well-being-augmented MAPP results showed a 5.7% and 13% improvement in accurate cost capture relative to a reference modeling approach and the first study of MAPP, respectively. The simulation analysis results demonstrated that reduced well-being risk across a population can help mitigate the expected upward cost trend. This research advances health care cost predictive modeling by incorporating well-being information within MAPP and then leveraging the results in a simulation analysis of well-being improvement.