Rough set theory based prognostic classification models for hospice referral.

BACKGROUND: This paper explores and evaluates the application of classical and dominance-based rough set theory (RST) for the development of data-driven prognostic classification models for hospice referral. In this work, rough set based models are compared with other data-driven methods with respect to two factors related to clinical credibility: accuracy and accessibility. Accessibility refers to the ability of the model to provide traceable, interpretable results and use data that is relevant and simple to collect. METHODS: We utilize retrospective data from 9,103 terminally ill patients to demonstrate the design and implementation RST- based models to identify potential hospice candidates. The classical rough set approach (CRSA) provides methods for knowledge acquisition, founded on the relational indiscernibility of objects in a decision table, to describe required conditions for membership in a concept class. On the other hand, the dominance-based rough set approach (DRSA) analyzes information based on the monotonic relationships between condition attributes values and their assignment to the decision class. CRSA decision rules for six-month patient survival classification were induced using the MODLEM algorithm. Dominance-based decision rules were extracted using the VC-DomLEM rule induction algorithm. RESULTS: The RST-based classifiers are compared with other predictive and rule based decision modeling techniques, namely logistic regression, support vector machines, random forests and C4.5. The RST-based classifiers demonstrate average AUC of 69.74 % with MODLEM and 71.73 % with VC-DomLEM, while the compared methods achieve average AUC of 74.21 % for logistic regression, 73.52 % for support vector machines, 74.59 % for random forests, and 70.88 % for C4.5. CONCLUSIONS: This paper contributes to the growing body of research in RST-based prognostic models. RST and its extensions posses features that enhance the accessibility of clinical decision support models. While the non-rule-based methods-logistic regression, support vector machines and random forests-were found to achieve higher AUC, the performance differential may be outweighed by the benefits of the rule-based methods, particularly in the case of VC-DomLEM. Developing prognostic models for hospice referrals is a challenging problem resulting in substandard performance for all of the evaluated classification methods.

Identifying homogenous subgroups for individual patient meta-analysis based on Rough Set Theory.

Failure to detect and manage heterogeneity between clinical trials included in meta-analysis may lead to misinterpretation of summary effect estimates. This may ultimately compromise the validity of the results of the meta-analysis. Typically, when heterogeneity between trials is detected, researchers use sensitivity or subgroup analysis to manage it. However, both methods fail to explain why heterogeneity existed in the first place. Here we propose a novel methodology that relies on Rough Set Theory (RST) to detect, explain, and manage the sources of heterogeneity applicable to meta-analysis performed on individual patient data (IPD). The method exploits the RST relations of discernibility and indiscernibility to create homogeneous groups of patients. We applied our methodology on a dataset of 1,111 patients enrolled in 9 randomized controlled trials studying the effect of two transplantation procedures in the management of hematologic malignancies. Our method was able to create three subgroups of patients with remarkably low statistical heterogeneity values (16.8%, 0% and 0% respectively). The proposed methodology has the potential to automatize and standardize the process of detecting and managing heterogeneity in IPD meta-analysis. Future work involves investigating the applications of the proposed methodology in analyzing treatment effects in patients belonging to different risk groups, which will ultimately assist in personalized healthcare decision making.

Towards a classification model to identify hospice candidates in terminally ill patients.

This paper presents a Rough Set Theory (RST) based classification model to identify hospice candidates within a group of terminally ill patients. Hospice care considerations are particularly valuable for terminally ill patients since they enable patients and their families to initiate end-of-life discussions and choose the most desired management strategy for the remainder of their lives. Unlike traditional data mining methodologies, our approach seeks to identify subgroups of patients possessing common characteristics that distinguish them from other subgroups in the dataset. Thus, heterogeneity in the data set is captured before the classification model is built. Object related reducts are used to obtain the minimum set of attributes that describe each subgroup existing in the dataset. As a result, a collection of decision rules is derived for classifying new patients based on the subgroup to which they belong. Results show improvements in the classification accuracy compared to a traditional RST methodology, in which patient diversity is not considered. We envision our work as a part of a comprehensive decision support system designed to facilitate end-of-life care decisions. Retrospective data from 9105 patients is used to demonstrate the design and implementation details of the classification model.

Rough Set Theory based prognostication of life expectancy for terminally ill patients.

We present a novel knowledge discovery methodology that relies on Rough Set Theory to predict the life expectancy of terminally ill patients in an effort to improve the hospice referral process. Life expectancy prognostication is particularly valuable for terminally ill patients since it enables them and their families to initiate end-of-life discussions and choose the most desired management strategy for the remainder of their lives. We utilize retrospective data from 9105 patients to demonstrate the design and implementation details of a series of classifiers developed to identify potential hospice candidates. Preliminary results confirm the efficacy of the proposed methodology. We envision our work as a part of a comprehensive decision support system designed to assist terminally ill patients in making end-of-life care decisions.

Designing patient-centric applications for chronic disease management.

Chronic diseases such as diabetes and heart disease are the leading causes of disability and death in the developed world. Technological interventions such as mobile applications have the ability to facilitate and motivate patients in chronic disease management, but these types of interventions present considerable design challenges. The primary objective of this paper is to present the challenges arising from the design and implementation of software applications aiming to assist patients in chronic disease management. We also outline preliminary results regarding a self-management application currently under development targeting young adults suffering from type 1 diabetes.