Abstract
Depression is a common mental illness with complex and heterogeneous progression dynamics. Risk grouping of depression treatment population based on their longitudinal patterns has the potential to enable cost-effective monitoring policy design. This paper establishes a rule-based method to identify a set of risk predictive patterns from person-level longitudinal disease measurements by integrating the data transformation, rule discovery and rule evaluation. We further extend the identified rules to create rule-based monitoring strategies to adaptively monitor individuals with different disease severities. We applied the rule-based method on an electronic health record (EHR) dataset of depression treatment population containing person-level longitudinal Patient Health Questionnaire (PHQ)-9 scores for assessing depression severity. 12 risk predictive rules are identified, and the rule-based prognostic model based on identified rules enables more accurate prediction of disease severity than other prognostic models including RuleFit, logistic regression and Support Vector Machine. Two rule-based monitoring strategies outperform the latest PHQ-9 based monitoring strategy by providing higher sensitivity and specificity. The rule-based method can lead to a better understanding of disease dynamics, achieving more accurate prognostics of disease progressions, personalizing follow-up intervals, and designing cost-effective monitoring of patients in clinical practice.
Highlights
The extended use of Electronic Health Record (EHR) provides an abundance of clinical measurements that may help to predict patients’ disease progressions
It can be observed that age, sex and the latest Patient Health Questionnaire (PHQ)-9 score are important risk factors in the identified rules, which are consistent with the significant risk factors identified from the logistic model, as shown in eAppendix 3 (Supplementary eTable 2)
It finds that (1) males with a less severe depression trajectory (mean score on the 9th question lower than 0.71 and fewer than 38% observations being in moderately severe depression (15 ≤ PHQ-9 < 20)) are less likely to have depression in the future, and (2) patients in young and middle adulthoods having more than 23% severe depression measurements on their PHQ-9 records are more likely to be depressed in the future
Summary
The extended use of Electronic Health Record (EHR) provides an abundance of clinical measurements that may help to predict patients’ disease progressions. Statistical analysis of the EHR data has the potential to identify risk predictive factors for disease progression and provide accurate prognostics for patients’ health outcomes. Recent advances in machine learning have provided a variety of prognostic models, such as logistic regression, support vector machine (SVM), and random forest These prognostic models for predicting individuals’ disease progressions from EHR data are inadequately implemented in practice due to the following challenges. The aim of this study is to establish a rule-based analytic framework to identify a set of risk predictive longitudinal patterns from the EHR data to personalize depression prognostics and adaptive monitoring. We extend the identified rules to create rule-based monitoring strategies and adaptively monitor the testing population
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
