Local control for identifying subgroups of interest in observational research: persistence of treatment for major depressive disorder

Risk controlled decision trees and random forests for precision Medicine

Statistical methods generating individualized treatment rules (ITRs) often focus on maximizing expected benefit, but these rules may expose patients to excess risk. For instance, aggressive treatment of type 2 diabetes (T2D) with insulin therapies may result in an ITR which controls blood glucose levels but increases rates of hypoglycemia, diminishing the appeal of the ITR. This work proposes two methods to identify risk-controlled ITRs (rcITR), a class of ITR which maximizes a benefit while controlling risk at a prespecified threshold. A novel penalized recursive partitioning algorithm is developed which optimizes an unconstrained, penalized value function. The final rule is a risk-controlled decision tree (rcDT) that is easily interpretable. A natural extension of the rcDT model, risk controlled random forests (rcRF), is also proposed. Simulation studies demonstrate the robustness of rcRF modeling. Three variable importance measures are proposed to further guide clinical decision-making. Both rcDT and rcRF procedures can be applied to data from randomized controlled trials or observational studies. An extensive simulation study interrogates the performance of the proposed methods. A data analysis of the DURABLE diabetes trial in which two therapeutics were compared is additionally presented. An R package implements the proposed methods ( https://github.com/kdoub5ha/rcITR).

Predicting optimal treatment regimens for patients with HR+/HER2- breast cancer using machine learning based on electronic health records

Aim: To predict optimal treatments maximizing overall survival (OS) and time to treatment discontinuation (TTD) for patients with metastatic breast cancer (MBC) using machine learning methods on electronic health records. Patients/methods: Adult females with HR+/HER2- MBC on first- or second-line systemic therapy were eligible. Random survival forest (RSF) models were used to predict optimal regimen classes for individual patients and each line of therapy based on baseline characteristics. Results: RSF models suggested greater use of CDK4 & 6 inhibitor-based therapies may maximize OS and TTD. RSF-predicted optimal treatments demonstrated longer OS and TTD compared with nonoptimal treatments across line of therapy (hazard ratios = 0.44∼0.79). Conclusion: RSF may help inform optimal treatment choices and improve outcomes for patients with HR+/HER2- MBC.

Assessing and communicating heterogeneity of treatment effects for patient subpopulations: The hardest problem there is

Heterogeneity is an enormously complex problem because there are so many dimensions and variables that can be considered when assessing which ones may influence an efficacy or safety outcome for an individual patient. This is difficult in randomized controlled trials and even more so in observational settings. An alternative approach is presented in which the individual patient becomes the "subgroup," and similar patients are identified in the clinical trial database or electronic medical record that can be used to predict how that individual patient may respond to treatment.

LocalControl: An R Package for Comparative Safety and Effectiveness Research

The LocalControl R package implements novel approaches to address biases and confounding when comparing treatments or exposures in observational studies of outcomes. While designed and appropriate for use in comparative safety and effectiveness research involving medicine and the life sciences, the package can be used in other situations involving outcomes with multiple confounders. LocalControl is an open-source tool for researchers whose aim is to generate high quality evidence using observational data. The package implements a family of methods for non-parametric bias correction when comparing treatments in observational studies, including survival analysis settings, where competing risks and/or censoring may be present. The approach extends to bias-corrected personalized predictions of treatment outcome differences, and analysis of heterogeneity of treatment effect-sizes across patient subgroups.

Retrospective assessment of patient characteristics and healthcare costs prior to a diagnosis of Alzheimer's disease in an administrative claims database

Background

The objective of this study was to examine patient characteristics and health care resource utilization (HCRU) in the 36 months prior to a confirmatory diagnosis of Alzheimer’s disease (AD) compared to a matched cohort without dementia during the same time interval.

Methods

Patients newly diagnosed with AD (with ≥2 claims) were identified between January 1, 2013 to September 31, 2015, and the date of the second claim for AD was defined as the index date. Patients were enrolled for at least 36 months prior to index date. The AD cohort was matched to a cohort with no AD or dementia codes (1:3) on age, gender, race/ethnicity, and enrollment duration prior to the index date. Descriptive analyses were used to summarize patient characteristics, HCRU, and healthcare costs prior to the confirmatory AD diagnosis. The classification and regression tree analysis and logistic regression were used to identify factors associated with the AD diagnosis.

Results

The AD cohort (N = 16,494) had significantly higher comorbidity indices and greater odds of comorbid mental and behavioral diagnoses, including mild cognitive impairment, mood and anxiety disorders, behavioral disturbances, and cerebrovascular disease, heart disease, urinary tract infections, and pneumonia than the matched non-AD or dementia cohort (N = 49,482). During the six-month period before the confirmatory AD diagnosis, AD medication use and diagnosis of mild cognitive impairment, Parkinson’s disease, or mood disorder were the strongest predictors of a subsequent confirmatory diagnosis of AD. Greater HCRU and healthcare costs were observed for the AD cohort primarily during the six-month period before the confirmatory AD diagnosis.

Conclusion

The results of this study demonstrated a higher comorbidity burden and higher costs for patients prior to a diagnosis of AD in comparison to the matched cohort. Several comorbidities were associated with a subsequent diagnosis of AD.

Electronic supplementary material

The online version of this article (10.1186/s12877-018-0920-2) contains supplementary material, which is available to authorized users.

An Algorithm for Generating Individualized Treatment Decision Trees and Random Forests

With new treatments and novel technology available, precision medicine has become a key topic in the new era of healthcare. Traditional statistical methods for precision medicine focus on subgroup discovery through identifying interactions between a few markers and treatment regimes. However, given the large scale and high dimensionality of modern data sets, it is difficult to detect the interactions between treatment and high dimensional covariates. Recently, novel approaches have emerged that seek to directly estimate individualized treatment rules (ITR) via maximizing the expected clinical reward by using, for example, support vector machines (SVM) or decision trees. The latter enjoys great popularity in clinical practice due to its interpretability. In this paper, we propose a new reward function and a novel decision tree algorithm to directly maximize rewards. We further improve a single tree decision rule by an ensemble decision tree algorithm, ITR random forests. Our final decision rule is an average over single decision trees and it is a soft probability rather than a hard choice. Depending on how strong the treatment recommendation is, physicians can make decisions based on our model along with their own judgment and experience. Performance of ITR forest and tree methods is assessed through simulations along with applications to a randomized controlled trial (RCT) of 1385 patients with diabetes and an EMR cohort of 5177 patients with diabetes. ITR forest and tree methods are implemented using statistical software R (https://github.com/kdoub5ha/ITR.Forest).

Patient similarity for precision medicine: A systematic review

Evidence-based medicine is the most prevalent paradigm adopted by physicians. Clinical practice guidelines typically define a set of recommendations together with eligibility criteria that restrict their applicability to a specific group of patients. The ever-growing size and availability of health-related data is currently challenging the broad definitions of guideline-defined patient groups. Precision medicine leverages on genetic, phenotypic, or psychosocial characteristics to provide precise identification of patient subsets for treatment targeting. Defining a patient similarity measure is thus an essential step to allow stratification of patients into clinically-meaningful subgroups. The present review investigates the use of patient similarity as a tool to enable precision medicine. 279 articles were analyzed along four dimensions: data types considered, clinical domains of application, data analysis methods, and translational stage of findings. Cancer-related research employing molecular profiling and standard data analysis techniques such as clustering constitute the majority of the retrieved studies. Chronic and psychiatric diseases follow as the second most represented clinical domains. Interestingly, almost one quarter of the studies analyzed presented a novel methodology, with the most advanced employing data integration strategies and being portable to different clinical domains. Integration of such techniques into decision support systems constitutes and interesting trend for future research.

Identification of Clinically Meaningful Plasma Transfusion Subgroups Using Unsupervised Random Forest Clustering

Statistical techniques such as propensity score matching and instrumental variable are commonly employed to "simulate" randomization and adjust for measured confounders in comparative effectiveness research. Despite such adjustments, the results of these methods apply essentially to an "average" patient. However, as patients show significant heterogeneity in their responses to treatments, this average effect is of limited value. It does not account for individual level variabilities, which can deviate substantially from the population average. To address this critical problem, we present a framework that allows the discovery of clinically meaningful homogeneous subgroups with differential effects of plasma transfusion using unsupervised random forest clustering. Subgroup analysis using two blood transfusion datasets show that considerable variablilities exist between the subgroups and population in both the treatment effect of plasma transfusion on bleeding and mortality and risk factors for these outcomes. These results support the customization of blood transfusion therapy for the individual patient.

Estimating optimal treatment regimes via subgroup identification in randomized control trials and observational studies

With new treatments and novel technology available, personalized medicine has become an important piece in the new era of medical product development. Traditional statistics methods for personalized medicine and subgroup identification primarily focus on single treatment or two arm randomized control trials. Motivated by the recent development of outcome weighted learning framework, we propose an alternative algorithm to search treatment assignments which has a connection with subgroup identification problems. Our method focuses on applications from clinical trials to generate easy to interpret results. This framework is able to handle two or more than two treatments from both randomized control trials and observational studies. We implement our algorithm in C++ and connect it with R. Its performance is evaluated by simulations, and we apply our method to a dataset from a diabetes study. Copyright © 2016 John Wiley & Sons, Ltd.

Simple subgroup approximations to optimal treatment regimes from randomized clinical trial data

We consider the use of randomized clinical trial (RCT) data to identify simple treatment regimes based on some subset of the covariate space, A. The optimal subset, A, is selected by maximizing the expected outcome under a treat-if-in-A regime, and is restricted to be a simple, as it is desirable that treatment decisions be made with only a limited amount of patient information required. We consider a two-stage procedure. In stage 1, non-parametric regression is used to estimate treatment effects for each subject, and in stage 2 these treatment effect estimates are used to systematically evaluate many subgroups of a simple, prespecified form to identify A. The proposed methods were found to perform favorably compared with two existing methods in simulations, and were applied to prehypertension data from an RCT.