Uncertainty rule generation on a home care database of heart failure patients

2013 IEEE International Conference on Healthcare Informatics

Burns

Wang

2013

Children diagnosed with cerebral palsy (CP) appear to be at high risk for developing neurobehavioral and motor disorders. The most common disorders for these children are impaired visual-perception skills and motor planning. Besides, they often have impaired executive functions, which can contribute to problematic emotional adjustment such as depression. Additionally, literature suggests that the tendency to develop these cognitive impairments and emotional abnormalities in pediatric CP is influenced by age and IQ. Because there are many other medical co-morbidities that can occur with CP (e.g., seizures and shunt placement), prediction of what percentages of patients will incur cognitive impairment and emotional abnormality is a difficult task. The purpose of this study was to investigate the associations between possible factors mentioned above, and neurobehavioral and motor disorders from a clinical database of pediatric subjects diagnosed with CP. The study resulted in 22 rules that can predict negative outcomes. These rules reinforced the growing body of literature supporting a link between CP, executive dysfunction, and subsequent neurobehavioral problems. The antecedents and consequents of some association rules were single factors, while other statistical associations were interactions of factor combinations. Further research is needed to include children’s comprehensive treatment and medication history in order to determine additional impacts on their neurobehavioral and motor disorders.

Section: Association Rule Miningmentioning

confidence: 99%

Mining Association Rules for Neurobehavioral and Motor Disorders in Children Diagnosed with Cerebral Palsy

2013 IEEE International Conference on Healthcare Informatics

Burns

Wang

2013

“…ARM has been used before in healthcare settings, such as heart disease prediction [7], healthcare auditing [8], and neurological diagnosis [9] with the following advantages: (1) unlike conventional statistical analysis that only indicates whether the relationship is significant or not (e.g., using p-value), ARM gives each rule a confidence value that determines its strength more quantitatively; (2) a rule composed of an antecedent and a consequent that provides a direction of the relationship; (3) the antecedent and consequent can consist of one or more factors, providing advanced knowledge of complex factor interactions instead of a monotonic relationship (e.g., logistic regression) [10]; and, (4) ARM accepts user-specified inputs, which ensure the strength of each rule to optimize the mining results. However, using ARM in decision support for PH has never been investigated.…”

Section: Methods and Proceduresmentioning

confidence: 99%

PHARM - Association Rule Mining for Predictive Health

Martin

et al. 2014

IFMBE Proceedings

Predictive health is a new and innovative healthcare model that focuses on maintaining health rather than treating diseases. Such a model may benefit from computer-based decision support systems, which provide more quantitative health assessment, enabling more objective advice and action plans from predictive health providers. However, data mining for predictive health is more challenging compared to that for diseases. This is a reason why there are relatively fewer predictive health decision support systems embedded with data mining. The purpose of this study is to research and develop an interactive decision support system, called PHARM, in conjunction with Emory Center for Health Discovery and Well Being (CHDWB®). PHARM adopts association rule mining to generate quantitative and objective rules for health assessment and prediction. A case study results in 12 rules that predict mental illness based on five psychological factors. This study shows the value and usability of the decision support system to prevent the development of potential illness and to prioritize advice and action plans for reducing disease risks.

“…For example, in the prediction of heart disease, Konias et al , proposed an uncertainty rule generator (URG) to discover rules for home-care monitoring from congestive heart failure patients [11]. Auditing medical abusive and fraudulent behavior is another important application of ARM.…”

Section: Causal-based Rule Selectionmentioning

confidence: 99%

Improving personalized clinical risk prediction based on causality-based association rules

Proceedings of the 6th ACM Conference on Bioinformatics, Computational Biology and Health Informatics

Wang

2015

Developing clinical risk prediction models is one of the main tasks of healthcare data mining. Advanced data collection techniques in current Big Data era have created an emerging and urgent need for scalable, computer-based data mining methods. These methods can turn data into useful, personalized decision support knowledge in a flexible, cost-effective, and productive way. In our previous study, we developed a tool, called icuARM- II, that can generate personalized clinical risk prediction evidence using a temporal rule mining framework. However, the generation of final risk prediction possibility with icuARM-II still relied on human interpretation, which was subjective and, most of time, biased. In this study, we propose a new mechanism to improve icuARM-II’s rule selection by including the concept of causal analysis. The generated risk prediction is quantitatively assessed using calibration statistics. To evaluate the performance of the new rule selection mechanism, we conducted a case study to predict short-term intensive care unit mortality based on personalized lab testing abnormalities. Our results demonstrated a better-calibrated ICU risk prediction using the new causality-base rule selection solution by comparing with conventional confidence-only rule selection methods.