Explainable data-driven modeling of patient satisfaction survey data

Liu, Ning; Kumara, Soundar; Reich, Eric

doi:10.1109/bigdata.2017.8258391

Cited by 7 publications

(4 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tree-based models can provide feature importance at a global level but not in a specific case. The local interpretable model-agnostic explanations (LIME) algorithm is developed to identify an interpretable model that is locally faithful for each individual prediction [27,28]. It provides relative feature contributions for a single instance of the prediction result.…”

Section: Methodsmentioning

confidence: 99%

Development of Prediction Models Using Machine Learning Algorithms for Girls with Suspected Central Precocious Puberty: Retrospective Study

Pan¹,

Liu²,

Mao³

et al. 2019

JMIR Med Inform

View full text Add to dashboard Cite

BackgroundCentral precocious puberty (CPP) in girls seriously affects their physical and mental development in childhood. The method of diagnosis—gonadotropin-releasing hormone (GnRH)–stimulation test or GnRH analogue (GnRHa)–stimulation test—is expensive and makes patients uncomfortable due to the need for repeated blood sampling.ObjectiveWe aimed to combine multiple CPP–related features and construct machine learning models to predict response to the GnRHa-stimulation test.MethodsIn this retrospective study, we analyzed clinical and laboratory data of 1757 girls who underwent a GnRHa test in order to develop XGBoost and random forest classifiers for prediction of response to the GnRHa test. The local interpretable model-agnostic explanations (LIME) algorithm was used with the black-box classifiers to increase their interpretability. We measured sensitivity, specificity, and area under receiver operating characteristic (AUC) of the models.ResultsBoth the XGBoost and random forest models achieved good performance in distinguishing between positive and negative responses, with the AUC ranging from 0.88 to 0.90, sensitivity ranging from 77.91% to 77.94%, and specificity ranging from 84.32% to 87.66%. Basal serum luteinizing hormone, follicle-stimulating hormone, and insulin-like growth factor-I levels were found to be the three most important factors. In the interpretable models of LIME, the abovementioned variables made high contributions to the prediction probability.ConclusionsThe prediction models we developed can help diagnose CPP and may be used as a prescreening tool before the GnRHa-stimulation test.

show abstract

Section: Methodsmentioning

confidence: 99%

Development of Prediction Models Using Machine Learning Algorithms for Girls with Suspected Central Precocious Puberty: Retrospective Study

Pan¹,

Liu²,

Mao³

et al. 2019

JMIR Med Inform

View full text Add to dashboard Cite

show abstract

“…To overcome the disadvantages of the black-box machine learning model and provide physicians with more information on the prediction model in clinical practice, we used the local interpretable model-agnostic explanations (LIME) algorithm to interpret feature contributions for each prediction [19,29,30]. LIME analysis revealed the probability score as well as the cutoff for prediction by the model.…”

Section: Model Interpretationmentioning

confidence: 99%

Development and Validation of Clinical Diagnostic Model for Girls with Central Precocious Puberty: Machine-learning Approaches

Huynh

Huang

et al. 2022

PLoS ONE

View full text Add to dashboard Cite

Background A brief gonadotropin-releasing hormone analogues (GnRHa) stimulation test which solely focused on LH 30-minute post-stimulation was considered to identify girls with central precocious puberty (CPP). However, it was tested using traditional statistical methods. With advanced computer science, we aimed to develop a machine learning-based diagnostic model that processed baseline CPP-related variables and a brief GnRHa stimulation test for CPP diagnosis. Methods We recruited girls suspected of precocious puberty and underwent a GnRHa stimulation test at Children Hospital 2, Vietnam, and Cathay General Hospital, Taiwan. Clinical data, bone age measurement, and 30-min post-stimulation blood test were used to build up the predictive model. The candidate model was developed by different machine learning algorithms that were mainly evaluated by sensitivity, specificity, the area under the receiver operator characteristic curve (AUC), and F1-score in internal and external validation data to classify girls as CPP and non-CPP at different time-points (0-min, 30-min, 60-min, and 120-min post-stimulation). Results Among the 614 girls diagnosed with PP, 524 (85.3%) had CPP. The random forest algorithm yielded the highest value of F1-score (0.976), specificity (0.893), positive predicted value (0.987), and relatively high value of AUC (0.972) that contributed to high probability to identify CPP. The performance metrics of the 30-min post-stimulation diagnostic model including sensitivity and specificity surpassed those of the 0-minute model (0-min) and were equivalent to those of the model obtained 60-min and 120-min post-stimulation. Hence, our machine learning-based model helps shorten the stimulation test to 30 minutes after GnRHa injection, in general, it requires 120 minutes for a completed GnRHa stimulation test. Conclusions We developed a diagnostic model based on clinical features and a single sample 30-minute post-stimulation to identify CPP in girls that can reduce distress for children caused by multiple blood samplings.

show abstract

“…Some research has touched on the differences between decision maker perspectives on these different measurements, but the results remain limited. Liu, et al [27] for instance demonstrated challenges with interpretations of patient satisfaction measurements. They conclude that without more development on the satisfaction measure practitioners would face difficulty with maximizing patient satisfaction.…”

Section: Literature Reviewmentioning

confidence: 99%

A Thematic Analysis of Provider Comparisons of Telemedicine Satisfaction Measures

Garcia¹,

Kallio²,

Adelakun³

2022

Proceedings of the Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

Satisfaction remains one of the most frequently used and inconsistent measures in Information Systems research. These inconsistencies can create challenges for interpreting the results of satisfaction measures. These challenges are noticeable in the telemedicine literature where researchers often rely on single item measures of overall satisfaction. While researchers have attempted to address these issues by studying satisfaction's measurements and methodologies there remain gaps in the knowledge on how variations in measures may be interpreted regarding decision making. This research seeks to contribute to the knowledge in this area by investigating medical provider perspectives on single versus multidimensional measures of telemedicine satisfaction. Through a thematic analysis this research shows variations and similarities in decision making between measures across eleven themes. The results show not only variations in views but indicate subjective experiential interpretations of results. Findings along with implications for researchers and medical providers are discussed.

show abstract

Explainable data-driven modeling of patient satisfaction survey data

Cited by 7 publications

References 24 publications

Development of Prediction Models Using Machine Learning Algorithms for Girls with Suspected Central Precocious Puberty: Retrospective Study

Development of Prediction Models Using Machine Learning Algorithms for Girls with Suspected Central Precocious Puberty: Retrospective Study

Development and Validation of Clinical Diagnostic Model for Girls with Central Precocious Puberty: Machine-learning Approaches

A Thematic Analysis of Provider Comparisons of Telemedicine Satisfaction Measures

Contact Info

Product

Resources

About