Search

Objective In preference-sensitive conditions such as back pain, there can be high levels of variability in the trajectory of patient care. We sought to develop a methodology that extracts a realistic and comprehensive understanding of the patient journey using medical and pharmaceutical insurance claims data. Materials and Methods We processed a sample of 10 000 patient episodes (comprised of 113 215 back pain–related claims) into strings of characters, where each letter corresponds to a distinct encounter with the healthcare system. We customized the Levenshtein edit distance algorithm to evaluate the level of similarity between each pair of episodes based on both their content (types of events) and ordering (sequence of events). We then used clustering to extract the main variations of the patient journey. Results The algorithm resulted in 12 comprehensive and clinically distinct patterns (clusters) of patient journeys that represent the main ways patients are diagnosed and treated for back pain. We further characterized demographic and utilization metrics for each cluster and observed clear differentiation between the clusters in terms of both clinical content and patient characteristics. Discussion Despite being a complex and often noisy data source, administrative claims provide a unique longitudinal overview of patient care across multiple service providers and locations. This methodology leverages claims to capture a data-driven understanding of how patients traverse the healthcare system. Conclusions When tailored to various conditions and patient settings, this methodology can provide accurate overviews of patient journeys and facilitate a shift toward high-quality practice patterns.

This case uses player evaluation and personnel decision making in Major League Baseball (MLB) to introduce many of the key steps of data analytics projects. The data analytics process is a unique c...

When preparing administrative medical and pharmacy claims data for analysis, decisions about data clean up and analytical approach need to be made. However, information about the effects of various modelling decisions on adherence measures such as the medication possession ratio (MPR) is limited. We address this gap with this study. We utilized cross-sectional administrative claims data for commercially insured members filling at least two prescriptions for drugs within five classes of hypertension medication between 2008 and 2010. We divided nine modelling decisions into three categories: data scrubbing, study design, and MPR definition/calculations. We defined the base-case settings with commonly used values, varied each modelling decision singly and in combination, and measured the effects on the MPR. Claims data for 358,418 individuals were available for analysis. Two modelling decisions were found to be highly influential, each yielding a difference of over 25 percentage points from the base case: the decision of whether to use interval- or prescription-based study periods, and the decision of how to handle overlapping prescription claims. The effect of other decisions was smaller, with a difference of 1–9 percentage points from the base case. Some of the decisions considered had a large impact on the MPR. Therefore, it is important for researchers to standardize approaches for study period length and overlapping prescription claims. We also conclude that transparent reporting of modelling decisions will facilitate the interpretation of results and comparisons across studies.

We explore whether free agents in Major League Baseball meet the expectations set forth by newly signed contracts. The value and duration of these contracts are negotiated between the player and his agent and the signing team and are based primarily on the player's performance to date, projected future performance, and potential marketing value to the team. We develop two classes of models to explore this problem using a variety of regression- and tree-based machine learning algorithms. The market model uses player and team data to predict the market value of a player's performance i.e., average contract salary. The performance model uses the same data to predict wins above replacement as a surrogate for overall player performance. We translate this measure into dollars using position-based conversion factors. Analysis of these models demonstrates that the performance model more consistently predicts and assesses player value with respect to their free agent contracts. Together, these models can be used to target or avoid free agents or other players whose performance-based value differs significantly from their market value. © 2016 Wiley Periodicals, Inc. Statistical Analysis and Data Mining: The ASA Data Science Journal, 2016

Cohort comparison studies have traditionally been hypothesis driven and conducted in carefully controlled environments (such as clinical trials). Given two groups of event sequence data, researchers test a single hypothesis (e.g., does the group taking Medication A exhibit more deaths than the group taking Medication B?). Recently, however, researchers have been moving toward more exploratory methods of retrospective analysis with existing data. In this article, we begin by showing that the task of cohort comparison is specific enough to support automatic computation against a bounded set of potential questions and objectives, a method that we refer to as High-Volume Hypothesis Testing (HVHT). From this starting point, we demonstrate that the diversity of these objectives, both across and within different domains, as well as the inherent complexities of real-world datasets, still requires human involvement to determine meaningful insights. We explore how visualization and interaction better support the task of exploratory data analysis and the understanding of HVHT results (how significant they are, why they are meaningful, and whether the entire dataset has been exhaustively explored). Through interviews and case studies with domain experts, we iteratively design and implement visualization and interaction techniques in a visual analytics tool, CoCo. As a result of our evaluation, we propose six design guidelines for enabling users to explore large result sets of HVHT systematically and flexibly in order to glean meaningful insights more quickly. Finally, we illustrate the utility of this method with three case studies in the medical domain.

Artificial Intelligence, especially deep learning based approaches, has been criticized for its \black-box" approach in recent years. The lack of interpretability of their performance makes people uncomfortable when applying these models in critical situations. In this study, we aim to contribute to the interpretability of the deep learning model in predicting healthcare costs. We propose to use long short-term memory based recurrent neural network to incorporate the sequential information for more accurate healthcare cost predictions. We first compare the performance of our deep learning approach with traditional machine learning methods including linear regression, lasso regression, ridge regression, and random forest. Among all the methods, deep learning shows the best performance. The superior performance of the deep learning model is further confirmed in subgroup analyses of patients. We then propose a novel interpretation method to examine how the deep learning model performs differently from other methods when facing fluctuations in the monthly costs. We find that while most traditional prediction models are getting worse with greater fluctuation in the data, the deep learning model can incorporate the fluctuation information and gain in prediction accuracy. Our work makes important contributions to the interpretability of deep learning models for more accurate prediction of healthcare costs.

The rising cost of health care is one of the world's most important problems. Accordingly, predicting such costs with accuracy is a significant first step in addressing this problem. Since the 1980s, there has been research on the predictive modeling of medical costs based on (health insurance) claims data using heuristic rules and regression methods. These methods, however, have not been appropriately validated using populations that the methods have not seen. We utilize modern data-mining methods, specifically classification trees and clustering algorithms, along with claims data from over 800,000 insured individuals over three years, to provide rigorously validated predictions of health-care costs in the third year, based on medical and cost data from the first two years. We quantify the accuracy of our predictions using unseen (out-of-sample) data from over 200,000 members. The key findings are: (a) our data-mining methods provide accurate predictions of medical costs and represent a powerful tool for prediction of health-care costs, (b) the pattern of past cost data is a strong predictor of future costs, and (c) medical information only contributes to accurate prediction of medical costs of high-cost members.