Using data mining to segment healthcare markets from patients' preference perspectives

Liu, Sandra S.; Chen, Jie

doi:10.1108/09526860910944610

Cited by 24 publications

(18 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The most important priorities for quality improvement vary based on individual health and medical needs 27 28. However, current results from patient-reported feedback fall short of indicating what different patient groups' need and value.…”

Section: Enhancing Use Of Patient-reported Feedbackmentioning

confidence: 92%

Can we use patient-reported feedback to drive change? The challenges of using patient-reported feedback and how they might be addressed

et al. 2016

View full text Add to dashboard Cite

Section: Enhancing Use Of Patient-reported Feedbackmentioning

confidence: 92%

Can we use patient-reported feedback to drive change? The challenges of using patient-reported feedback and how they might be addressed

et al. 2016

View full text Add to dashboard Cite

“…4 Diversity: Health market segmentation studies range from analysis of clinical populations (Newcomer et al, 2012;Axen et al, 2011;Kim et al, 2013) to segmentation studies on survey data (Liu and Chen, 2009;Suragh et al, 2013;Moss et al, 2009;Kolodinski and Reynolds, 2009;& Berg et al, 2010). Of the papers that used survey data, two looked at college student substance abuse behaviors (Berg, 2010;Suragh, 2013), one looked at customer preference for healthcare service and clustered patients based on their preference and demographic attributes (Liu, 2009), and the last two used large survey data from a combination of the Behavioral Risk Factor Surveillance System (BRFSS), US Department of Agriculture funded nationwide polls, and a mix of public and US Census data (Moss, 2009;Kolodinski and Reynolds, 2009).…”

Section: Literature Reviewmentioning

confidence: 99%

“…Both Suragh et al (2013) and Berg et al (2009) borrow from the tobacco industry and Kolodinsky et al (2009) borrow survey methods from the food industry. Liu and Chen (2009) and Kent et al (2014) conducted market segmentation using different approaches but each applied multiple clustering techniques to verify the results. The prior used survey data while the latter was based on secondary use data from a variety of studies.…”

Section: Literature Reviewmentioning

confidence: 99%

“…The prior used survey data while the latter was based on secondary use data from a variety of studies. Liu and Chen (2009) used a mix of hierarchical and non-hierarchical methods and ultimately settled on a hierarchical clustering method that reduced the attributes from 24 to 5 yielding 3 distinct clusters. Kent et al (2014) applied and compared three different methods to five real data sets and 4 randomly generated data sets to test reproducibility, likeness of outputs, and ease of use.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Data analytics in health promotion: Health market segmentation and classification of total joint replacement surgery patients

Swenson

Bastian

Nembhard

2016

Expert Systems with Applications

View full text Add to dashboard Cite

Providing insight into healthcare consumers' behaviors and attitudes is critical information in an environment where healthcare delivery is moving rapidly towards patient-centered care. We apply a two-stage methodology using both supervised and unsupervised machine learning methods to a patient data set from the electronic medical records of an academic medical center located in central Pennsylvania. The data are from patients who had total joint replacement surgery between December 2013 and September 2015. Two clustering methods and four classification algorithms were applied to the data set. Patients cluster into six distinct health market segments from which the cluster assignment is used as the response variable in supervised learning to classify patients. The classification model accurately predicts the cluster assignment for out-of-sample patients, while offering insight into patient behaviors and attributes to help clinicians, health marketers, and healthcare consumers move toward the goal of patientcentered and value-based healthcare.

show abstract

“…There is limited use of data mining techniques to explore healthcare services in relation to patients' perceptions. Comparing traditional methods with data mining though, indicates at least the potential of applying data mining methods to understand patient healthcare preferences [5].…”

Section: Introductionmentioning

confidence: 99%

Application of data mining techniques to determine patient satisfaction

Galatas

Zikos

Makedon

2013

Proceedings of the 6th International Conference on PErvasive Technologies Related to Assistive Environments

View full text Add to dashboard Cite

This study applies unsupervised machine learning techniques for classification and clustering to a collection of descriptive variables from 10,442 lung cancer patient records in the Surveillance, Epidemiology, and End Results (SEER) program database. The goal is to automatically classify lung cancer patients into groups based on clinically measurable disease-specific variables in order to estimate survival. Variables selected as inputs for machine learning include Number of Primaries, Age, Grade, Tumor Size, Stage, and TNM, which are numeric or can readily be converted to numeric type. Minimal up-front processing of the data enables exploring the out-of-the-box capabilities of established unsupervised learning techniques, with little human intervention through the entire process. The output of the techniques is used to predict survival time, with the efficacy of the prediction representing a proxy for the usefulness of the classification. A basic single variable linear regression against each unsupervised output is applied, and the associated Root Mean Squared Error (RMSE) value is calculated as a metric to compare between the outputs. The results show that self-ordering maps exhibit the best performance, while k-Means performs the best of the simpler classification techniques. Predicting against the full data set, it is found that their respective RMSE values (15.591 for self-ordering maps and 16.193 for k-Means) are comparable to supervised regression techniques, such as Gradient Boosting Machine (RMSE of 15.048). We conclude that unsupervised data analysis techniques may be of use to classify patients by defining the classes as effective proxies for survival prediction.

show abstract

Using data mining to segment healthcare markets from patients' preference perspectives

Cited by 24 publications

References 24 publications

Can we use patient-reported feedback to drive change? The challenges of using patient-reported feedback and how they might be addressed

Can we use patient-reported feedback to drive change? The challenges of using patient-reported feedback and how they might be addressed

Data analytics in health promotion: Health market segmentation and classification of total joint replacement surgery patients

Application of data mining techniques to determine patient satisfaction

Contact Info

Product

Resources

About