Entry setting for LBP was associated with future health care utilization and costs. Consideration of where patients chose to enter care may be a strategy to improve outcomes and reduce costs.

Objective: To design and assess a method to leverage individuals' temporal data for predicting their healthcare cost. To achieve this goal, we first used patients' temporal data in their fine-grain form as opposed to coarse-grain form. Second, we devised novel spike detection features to extract temporal patterns that improve the performance of cost prediction. Third, we evaluated the effectiveness of different types of temporal features based on cost information, visit information and medical information for the prediction task. Materials and methods: We used three years of medical and pharmacy claims data from 2013 to 2016 from a healthcare insurer, where the first two years were used to build the model to predict the costs in the third year. To prepare the data for modeling and prediction, the time series data of cost, visit and medical information were extracted in the form of fine-grain features (i.e., segmenting each time series into a sequence of consecutive windows and representing each window by various statistics such as sum). Then, temporal patterns of the time series were extracted and added to fine-grain features using a novel set of spike detection features (i.e., the fluctuation of data points). Gradient Boosting was applied on the final set of extracted features. Moreover, the contribution of each type of data (i.e., cost, visit and medical) was assessed. We benchmarked the proposed predictors against extant methods including those that used coarse-grain features which represent each time series with various statistics such as sum and the most recent portion of the values in the entire series. All prediction performances were measured in terms of Mean Absolute Percentage Error (MAPE). Results: Gradient Boosting applied on fine-grain predictors outperformed coarse-grain predictors with a MAPE of 3.02 versus 8.14 (p<0.01). Enhancing the fine-grain features with the temporal pattern extraction features (i.e., spike detection features) further improved the MAPE to 2.04 (p<0.01). Removing cost, visit and medical status data resulted in MAPEs of 10.24, 2.22 and 2.07 respectively (p<0.01 for the first two comparisons and p=0.63 for the third comparison). Conclusions: Leveraging fine-grain temporal patterns for healthcare cost prediction significantly improves prediction performance. Enhancing fine-grain features with extraction of temporal cost and visit patterns significantly improved the performance. However, medical features did not have a significant effect on prediction performance. Gradient Boosting outperformed all other prediction models.

Physical therapy was used often by Medicaid enrollees with LBP. High rates of comorbidities were evident and associated with physical therapy use. Although few patients entered care in physical therapy, this pattern may be useful for managing costs.

Introduction: Physical therapy (PT) early in the management of low back pain (LBP) is associated with reductions in subsequent health care utilization and LBP-related costs. The objectives of this study were to 1) Examine differences among newly consulting patients with LBP who received a PT referral and those who did not, 2) examine differences between patients who participated in PT to those who did not, and 3) compare the impact of a PT referral and PT participation on LBP-related health care utilization and costs over 1 year.Methods: This was a retrospective cohort study using electronic medical records and claims data.

The HOME Program provides medical and behavioral health care for people with developmental disabilities across the lifespan. Its unique funding structure provides a fiscally viable, and replicable, means of supporting case management in a medical home setting, addressing system-level barriers that typically impede the implementation of the patient-centered medical home.