Time-to-Event Predictive Modeling for Chronic Conditions Using Electronic Health Records

Lin, Yu; Chen, Hsinchun; Brown, Randall A.; Li, Shu Hsing; Yang, Hung Jen

doi:10.1109/mis.2014.18

Cited by 11 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many studies of predicting modelling techniques 10 have been conducted in the context of prospective cohort studies in which patients are followed up routinely by the investigators 11 . Wei, B. et al .…”

Section: Introductionmentioning

confidence: 99%

Electronic Health Record Driven Prediction for Gestational Diabetes Mellitus in Early Pregnancy

Qiu

Wang

et al. 2017

Sci Rep

View full text Add to dashboard Cite

Gestational diabetes mellitus (GDM) is conventionally confirmed with oral glucose tolerance test (OGTT) in 24 to 28 weeks of gestation, but it is still uncertain whether it can be predicted with secondary use of electronic health records (EHRs) in early pregnancy. To this purpose, the cost-sensitive hybrid model (CSHM) and five conventional machine learning methods are used to construct the predictive models, capturing the future risks of GDM in the temporally aggregated EHRs. The experimental data sources from a nested case-control study cohort, containing 33,935 gestational women in West China Second Hospital. After data cleaning, 4,378 cases and 50 attributes are stored and collected for the data set. Through selecting the most feasible method, the cost parameter of CSHM is adapted to deal with imbalance of the dataset. In the experiment, 3940 samples are used for training and the rest 438 samples for testing. Although the accuracy of positive samples is barely acceptable (62.16%), the results suggest that the vast majority (98.4%) of those predicted positive instances are real positives. To our knowledge, this is the first study to apply machine learning models with EHRs to predict GDM, which will facilitate personalized medicine in maternal health management in the future.

show abstract

Section: Introductionmentioning

confidence: 99%

Electronic Health Record Driven Prediction for Gestational Diabetes Mellitus in Early Pregnancy

Qiu

Wang

et al. 2017

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Lin et al [10] proposed a time-to-event approach for diagnosing the chronic illnesses that use EHR as a data source. This proposed framework helps the physician to predict the chronic condition of patients, expect if there are severe complications will occur, and plan for possible interventions for reducing event risks that will occur.…”

Section: Ehr Adoption For Diagnosis and Prediction Of Diseasesmentioning

confidence: 99%

“…As well, it is not scalable as automatic schemes of feature selection. Finally, comparing guideline-based method and other statistical methods for selecting features is necessary [10].…”

mentioning

confidence: 99%

Electronic Health Records: Applications, Techniques and Challenges

Zaied¹,

Elmogy²,

Elkader³

2015

IJCA

View full text Add to dashboard Cite

With the fast evolution of information technology, traditional healthcare is moving towards a more electronic stage. As a result, the e-Health term appears, and Electronic Health Records (EHRs) become a critical application of e-Health management systems. These computerized records have been widely used by clinicians, healthcare providers, patients, and health insurance companies for the purpose of creating, managing, and accessing the health information of patients everywhere. Moreover, these information resources can be shared by different healthcare parties for monitoring the patients' health, delivering effective treatments, and decreasing costs. In this paper, we present a survey of various EHR applications in e-Health systems. These applications include using EHRs for diagnosing, monitoring diseases, and selecting the most efficient paths of treatments. In addition, we discuss the usage of EHRs as a source for building a knowledge base for Clinical Decision Support Systems (CDSS). Finally, the challenges of EHR implementations in the healthcare environment and current research topics will be highlighted.

show abstract

“…In order to facilitate effective health management, prior literature has developed various approaches for providing decision support [57]: One major line of research focuses on risk scoring, where the probability of patient-specific health outcomes is estimated. Examples of such outcomes are mortality (e.g., [19]), hospitalization events (e.g., [45]), and hospital readmissions (e.g., [3,7,64]), but not the expected short-term progression of a disease. A different line of research is concerned with the design of treatment plans, namely the timing (e.g., [15]) and dosage of medication (e.g., [8,9,47]).…”

Section: Introductionmentioning

confidence: 99%

“…First, risk scoring predicts the probability of patient-specific health outcomes. Examples of health outcomes include the probability of, for instance, recovery (e.g., [36]), mortality (e.g., [19,65]), onset of a certain disease (e.g., [52]), hospitalization events (e.g., [45]), and hospital readmissions (e.g., [3,7,64]). Methodologically, this is usually formalized in either probabilistic models, such as survival models (e.g., [7]), or machine learning models, such as decision trees (e.g., [52]) or recurrent neural networks (e.g., [4]).…”

Section: Introductionmentioning

confidence: 99%

Longitudinal healthcare analytics for disease management: Empirical demonstration for low back pain

Mueller-Peltzer

Feuerriegel

Nielsen

et al. 2020

Decision Support Systems

View full text Add to dashboard Cite

Clinician guidelines recommend health management to tailor the form of care to the expected course of diseases. Hence, in order to decide upon a suitable treatment plan, health professionals benefit from decision support, i.e., predictions about how a disease is to evolve. In clinical practice, such a prediction model requires interpretability. Interpretability, however, is often precluded by complex dynamic models that would be capable of capturing the intrapersonal variability of disease trajectories. Therefore, we develop a cross-sectional ARMA model that allows for inference of the expected course of symptoms. Distinct from traditional time series models, it generalizes to cross-sectional settings and thus patient cohorts (i.e., it is estimated to multiple instead of single disease trajectories). Our model is evaluated according to a longitudinal 52-week study involving 928 patients with low back pain. It achieves a favorable prediction performance while maintaining interpretability. In sum, we provide decision support by informing health professionals about whether symptoms will have the tendency to stabilize or continue to be severe.

show abstract

Time-to-Event Predictive Modeling for Chronic Conditions Using Electronic Health Records

Abstract: An electronic health records-based timeto-event model identifies clinically validated risk factors associated with chronic care. Experiments suggest that EHR-based predictive modeling can effectively support decision making for chronic care patients.

Cited by 11 publications

References 9 publications

Electronic Health Record Driven Prediction for Gestational Diabetes Mellitus in Early Pregnancy

Electronic Health Record Driven Prediction for Gestational Diabetes Mellitus in Early Pregnancy

Electronic Health Records: Applications, Techniques and Challenges

Longitudinal healthcare analytics for disease management: Empirical demonstration for low back pain

Contact Info

Product

Resources

About