Machine Learning for Health Services Researchers

Doupé, Patrick; Faghmous, James H.; Basu, Sanjay

doi:10.1016/j.jval.2019.02.012

Cited by 200 publications

(134 citation statements)

References 30 publications

(27 reference statements)

Supporting

Mentioning

123

Contrasting

Unclassified

Order By: Relevance

“…Machine learning methods can learn complex structures by incorporating numerous variables with high dimensional data [9]. Excellent performance of these methods has been validated in health service [10] and health outcomes studies [11]. Regularized logistic regression (RLR), as the fundamental and most commonly used machine learning method, is a generalized linear regression model for probability analysis.…”

Section: Introductionmentioning

confidence: 99%

Stroke Prediction with Machine Learning Methods among Older Chinese

Fang

2020

IJERPH

View full text Add to dashboard Cite

Timely stroke diagnosis and intervention are necessary considering its high prevalence. Previous studies have mainly focused on stroke prediction with balanced data. Thus, this study aimed to develop machine learning models for predicting stroke with imbalanced data in an elderly population in China. Data were obtained from a prospective cohort that included 1131 participants (56 stroke patients and 1075 non-stroke participants) in 2012 and 2014, respectively. Data balancing techniques including random over-sampling (ROS), random under-sampling (RUS), and synthetic minority over-sampling technique (SMOTE) were used to process the imbalanced data in this study. Machine learning methods such as regularized logistic regression (RLR), support vector machine (SVM), and random forest (RF) were used to predict stroke with demographic, lifestyle, and clinical variables. Accuracy, sensitivity, specificity, and areas under the receiver operating characteristic curves (AUCs) were used for performance comparison. The top five variables for stroke prediction were selected for each machine learning method based on the SMOTE-balanced data set. The total prevalence of stroke was high in 2014 (4.95%), with men experiencing much higher prevalence than women (6.76% vs. 3.25%). The three machine learning methods performed poorly in the imbalanced data set with extremely low sensitivity (approximately 0.00) and AUC (approximately 0.50). After using data balancing techniques, the sensitivity and AUC considerably improved with moderate accuracy and specificity, and the maximum values for sensitivity and AUC reached 0.78 (95% CI, 0.73–0.83) for RF and 0.72 (95% CI, 0.71–0.73) for RLR. Using AUCs for RLR, SVM, and RF in the imbalanced data set as references, a significant improvement was observed in the AUCs of all three machine learning methods (p < 0.05) in the balanced data sets. Considering RLR in each data set as a reference, only RF in the imbalanced data set and SVM in the ROS-balanced data set were superior to RLR in terms of AUC. Sex, hypertension, and uric acid were common predictors in all three machine learning methods. Blood glucose level was included in both RLR and RF. Drinking, age and high-sensitivity C-reactive protein level, and low-density lipoprotein cholesterol level were also included in RLR, SVM, and RF, respectively. Our study suggests that machine learning methods with data balancing techniques are effective tools for stroke prediction with imbalanced data.

show abstract

Section: Introductionmentioning

confidence: 99%

Stroke Prediction with Machine Learning Methods among Older Chinese

Fang

2020

IJERPH

View full text Add to dashboard Cite

show abstract

“…Adapted from. 12 Tutorial: Machine Learning for Precision Medicine -Basu et al come using variables with few classes, rather than with multi-class or continuous variables, can often be modeled best through boosting. 8,9 Our statistical code illustrates both approaches, which are discussed further below.…”

Section: Bagging and Boostingmentioning

confidence: 99%

Machine Learning Methods for Precision Medicine Research Designed to Reduce Health Disparities: A Structured Tutorial

Basu¹,

Faghmous

Doupé³

2020

Ethn Dis

Self Cite

View full text Add to dashboard Cite

Precision medicine research designed to reduce health disparities often involves studying multi-level datasets to understand how diseases manifest disproportionately in one group over another, and how scarce health care resources can be directed precisely to those most at risk for disease. In this article, we provide a structured tutorial for medical and public health researchers on the application of machine learning methods to conduct precision medicine research designed to reduce health disparities. We review key terms and concepts for understanding machine learning papers, including supervised and unsupervised learning, regularization, cross-validation, bagging, and boosting. Metrics are reviewed for evaluating machine learners and major families of learning approaches, including tree-based learning, deep learning, and ensemble learning. We highlight the advantages and disadvantages of different learning approaches, describe strategies for interpreting “black box” models, and demonstrate the application of common methods in an example dataset with open-source statistical code in R.Ethn Dis. 2020;30(Suppl 1):217-228; doi:10.18865/ed.30.S1.217

show abstract

“…The ML random forest approach, fully described in the Supplementary Material, was applied to build predictive models [20]. The random forest algorithm [21] is a stochastic ensemble method that uses bagging, a combination of bootstrapping and aggregation of weak learners, more specifically, decision trees, seeking to detect patterns in data and use these to predict outcomes, in our case, NPS [19].…”

Section: Machine Learningmentioning

confidence: 99%

“…An example of this would be the calculation of the prevalence of NPS in population samples. While this design has been previously applied in cardiovascular research [17] and Alzheimer's disease neuroimaging [18], no examples have been reported of its use to measure features of dementia-related NPS at population level [19]. Therefore, the objective of this study was to construct and validate predictive models based on ML tools to identify the presence of psychotic and/or depressive symptoms in dementia-diagnosed patients from administrative and clinical databases that cover entire populations.…”

Section: Introductionmentioning

confidence: 99%

Validation of machine learning models to predict dementia-related neuropsychiatric symptoms in real-world data

Mar¹,

Gorostiza²,

Ibarrondo³

et al. 2020

Preprint

View full text Add to dashboard Cite

Background Neuropsychiatric symptoms (NPS) are the leading cause of the social burden of dementia but their role is underestimated. The objective of the study was to validate predictive models to separately identify psychotic and depressive symptoms in patients diagnosed with dementia using clinical databases representing the whole population (real-world data). Methods First, we searched the electronic health records of 4,003 patients with dementia to identify NPS. Second, machine learning (random forest) algorithms were applied to build in the training sample (N=3,003) separate predictive models for psychotic and depressive symptoms. In order to evaluate the classification ability of the models, the following statistics were calculated for each model: the area under the receiver operating curve (AUC), sensitivity, specificity, accuracy, no-information rate and Kappa index. Third, calibration and discrimination were assessed in the validation sample (N= 1,000) to assess the performance of the models. A calibration curve was drawn by plotting the predicted probabilities for groups on the x-axis and the mean observed values on the y-axis. Results Neuropsychiatric symptoms were noted in the electronic health record of 58% of patients. The AUC reached 0.80 for the psychotic symptoms model and 0.74 for the depressive symptoms model. The Kappa index and accuracy also showed better discrimination in the psychotic model. Calibration plots indicated that both types of model had less predictive accuracy when the probability of neuropsychiatric symptoms was < 25%. The most important variables in the psychotic symptom model were use of risperidone, level of sedation, quetiapine and haloperidol and the number of antipsychotics prescribed. In the depressive symptom model, the most important variable was number of antidepressants prescribed, use of escitalopram, level of sedation and age. Conclusions More than half of the sample had NPS as identified by the presence of key terms in the electronic health record. Although NPS are not encoded, they are treated with antipsychotics and antidepressants, which allows developing valid predictive models by joining machine learning tools and real-world data. Given their good performance, the predictive models can be used to estimate prevalence of NPS in population databases.

show abstract

Machine Learning for Health Services Researchers

Cited by 200 publications

References 30 publications

Stroke Prediction with Machine Learning Methods among Older Chinese

Stroke Prediction with Machine Learning Methods among Older Chinese

Machine Learning Methods for Precision Medicine Research Designed to Reduce Health Disparities: A Structured Tutorial

Validation of machine learning models to predict dementia-related neuropsychiatric symptoms in real-world data

Contact Info

Product

Resources

About