Dataset Information

Determining hypertensive patients' beliefs towards medication and associations with medication adherence using machine learning methods.

ABSTRACT: Background:This study assesses the feasibility of using machine learning methods such as Random Forests (RF), Artificial Neural Networks (ANN), Support Vector Regression (SVR) and Self-Organizing Feature Maps (SOM) to identify and determine factors associated with hypertensive patients' adherence levels. Hypertension is the medical term for systolic and diastolic blood pressure higher than 140/90 mmHg. A conventional medication adherence scale was used to identify patients' adherence to their prescribed medication. Using machine learning applications to predict precise numeric adherence scores in hypertensive patients has not yet been reported in the literature. Methods:Data from 160 hypertensive patients from a tertiary hospital in Kuala Lumpur, Malaysia, were used in this study. Variables were ranked based on their significance to adherence levels using the RF variable importance method. The backward elimination method was then performed using RF to obtain the variables significantly associated with the patients' adherence levels. RF, SVR and ANN models were developed to predict adherence using the identified significant variables. Visualizations of the relationships between hypertensive patients' adherence levels and variables were generated using SOM. Result:Machine learning models constructed using the selected variables reported RMSE values of 1.42 for ANN, 1.53 for RF, and 1.55 for SVR. The accuracy of the dichotomised scores, calculated based on a percentage of correctly identified adherence values, was used as an additional model performance measure, resulting in accuracies of 65% (ANN), 78% (RF) and 79% (SVR), respectively. The Wilcoxon signed ranked test reported that there was no significant difference between the predictions of the machine learning models and the actual scores. The significant variables identified from the RF variable importance method were educational level, marital status, General Overuse, monthly income, and Specific Concern. Conclusion:This study suggests an effective alternative to conventional methods in identifying the key variables to understand hypertensive patients' adherence levels. This can be used as a tool to educate patients on the importance of medication in managing hypertension.

SUBMITTER: Aziz F

PROVIDER: S-EPMC7075362 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Determining hypertensive patients' beliefs towards medication and associations with medication adherence using machine learning methods.

Aziz Firdaus F Malek Sorayya S Mhd Ali Adliah A Wong Mee Sieng MS Mosleh Mogeeb M Milow Pozi P

PeerJ 20200313

<h4>Background</h4>This study assesses the feasibility of using machine learning methods such as Random Forests (RF), Artificial Neural Networks (ANN), Support Vector Regression (SVR) and Self-Organizing Feature Maps (SOM) to identify and determine factors associated with hypertensive patients' adherence levels. Hypertension is the medical term for systolic and diastolic blood pressure higher than 140/90 mmHg. A conventional medication adherence scale was used to identify patients' adherence to ...[more]

PMID: 32206445

Similar Datasets

Project description:BackgroundOpioid Use Disorder (OUD) and opioid overdose (OD) impose huge social and economic burdens on society and health care systems. Research suggests that Medication for Opioid Use Disorder (MOUD) is effective in the treatment of OUD. We use machine learning to investigate the association between patient's adherence to prescribed MOUD along with other risk factors in patients diagnosed with OUD and potential OD following the treatment.MethodsWe used longitudinal Medicaid claims for two selected US states to subset a total of 26,685 patients with OUD diagnosis and appropriate Medicaid coverage between 2015 and 2018. We considered patient age, sex, region level socio-economic data, past comorbidities, MOUD prescription type and other selected prescribed medications along with the Proportion of Days Covered (PDC) as a proxy for adherence to MOUD as predictive variables for our model, and overdose events as the dependent variable. We applied four different machine learning classifiers and compared their performance, focusing on the importance and effect of PDC as a variable. We also calculated results based on risk stratification, where our models separate high risk individuals from low risk, to assess usefulness in clinical decision-making.ResultsAmong the selected classifiers, the XGBoost classifier has the highest AUC (0.77) closely followed by the Logistic Regression (LR). The LR has the best stratification result: patients in the top 10% of risk scores account for 35.37% of overdose events over the next 12 month observation period. PDC score calculated over the treatment window is one of the most important features, with better PDC lowering risk of OD, as expected. In terms of risk stratification results, of the 35.37% of overdose events that the predictive model could detect within the top 10% of risk scores, 72.3% of these cases were non-adherent in terms of their medication (PDC <0.8). Targeting the top 10% outcome of the predictive model could decrease the total number of OD events by 10.4%.ConclusionsThe best performing models allow identification of, and focus on, those at high risk of opioid overdose. With MOUD being included for the first time as a factor of interest, and being identified as a significant factor, outreach activities related to MOUD can be targeted at those at highest risk.

Project description:BackgroundEmpirical research and health policies on asthma have focused on children and young adults, even though asthma morbidity and mortality are higher among older asthmatics.ObjectiveTo explore the relationship of asthma-related beliefs and self-reported controller medication adherence in older asthmatics.DesignAn observational study of asthma beliefs and self-management among older adults.ParticipantsAsthmatics ages ? 60 years (N?=?324, mean age 67.4 ± 6.8, 28 % white, 32 % black, 30 % Hispanic) were recruited from primary care practices in New York City and Chicago.Main measuresSelf-reported controller medication adherence was assessed using the Medication Adherence Report Scale. Based on the Common Sense Model of Self-Regulation, patients were asked if they believe they only have asthma with symptoms, their physician can cure their asthma, and if their asthma will persist. Beliefs on the benefit, necessity and concerns of treatment use were also assessed. Multivariate logistic regression was used to examine the association of beliefs with self-reported medication adherence.Key resultsThe majority (57.0 %) of patients reported poor adherence. Poor self-reported adherence was more common among those with erroneous beliefs about asthma illness and treatments, including the "no symptoms, no asthma" belief (58.7 % vs. 31.7 %, respectively, p?<?0.001), "will not always have asthma" belief (34.8 % vs. 12.5 %, p?<?0.001), and the "MD can cure asthma" belief (21.7 % vs. 9.6 %, p?=?0.01). Adjusting for illness beliefs, treatment beliefs and demographics, patients with a "no symptoms, no asthma" belief had lower odds of having good self-reported adherence (odds ratio [OR] 0.45, 95 % confidence interval [CI] 0.23-0.86), as did those with negative beliefs about the benefits (OR 0.73, 95 % CI 0.57-0.94) and necessity (OR 0.89, 95 % CI 0.83-0.96) of treatment.ConclusionsIllness and treatment beliefs have a strong influence on self-reported medication adherence in older asthmatics. Interventions to improve medication adherence in older asthmatics by modifying illness and treatment beliefs warrant study.

Dataset Information

Determining hypertensive patients' beliefs towards medication and associations with medication adherence using machine learning methods.

Publications

Determining hypertensive patients' beliefs towards medication and associations with medication adherence using machine learning methods.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets