Machine learning models to detect and predict patient safety events using electronic health records: A systematic review

Deimazar, Ghasem; Sheikhtaheri, Abbas

doi:10.1016/j.ijmedinf.2023.105246

Cited by 10 publications

(3 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The most selected phenotypical features were therapeutic indications (n = 10) [ 13 , 14 , 15 , 19 , 20 , 21 , 22 , 23 , 24 , 25 ]. These features were extracted from various sources, including SIDER 4 [ 35 , 43 , 45 ], Liu’s dataset [ 34 , 35 , 40 , 43 , 44 , 45 , 46 ], SIDER [ 36 , 42 ], DrugBank [ 41 ], National Drug File-Reference Terminology (NDF-RT) [ 41 ], Bio2RDF v2 [ 35 ].…”

Section: Resultsmentioning

confidence: 99%

“…Existing machine learning-based approaches have rigorously examined hundreds of side effects and the probability of their occurrence [ 13 , 14 ]. This critical role of machine learning in side effect prediction entails developing models that predict outcomes based on the available data [ 1 , 15 ]. Machine learning techniques use drug properties and well-labeled side effects to predict drug-related side effects and build models for targeted predictions [ 16 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Techniques for Predicting Drug-Related Side Effects: A Scoping Review

Toni,

Ayatollahi,

Abbaszadeh

et al. 2024

Pharmaceuticals

View full text Add to dashboard Cite

Background: Drug safety relies on advanced methods for timely and accurate prediction of side effects. To tackle this requirement, this scoping review examines machine-learning approaches for predicting drug-related side effects with a particular focus on chemical, biological, and phenotypical features. Methods: This was a scoping review in which a comprehensive search was conducted in various databases from 1 January 2013 to 31 December 2023. Results: The results showed the widespread use of Random Forest, k-nearest neighbor, and support vector machine algorithms. Ensemble methods, particularly random forest, emphasized the significance of integrating chemical and biological features in predicting drug-related side effects. Conclusions: This review article emphasized the significance of considering a variety of features, datasets, and machine learning algorithms for predicting drug-related side effects. Ensemble methods and Random Forest showed the best performance and combining chemical and biological features improved prediction. The results suggested that machine learning techniques have some potential to improve drug development and trials. Future work should focus on specific feature types, selection techniques, and graph-based methods for even better prediction.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Machine Learning Techniques for Predicting Drug-Related Side Effects: A Scoping Review

Toni,

Ayatollahi,

Abbaszadeh

et al. 2024

Pharmaceuticals

View full text Add to dashboard Cite

show abstract

“…However, instead of giving real values between 0 and 1, it gives values between 0 and 1. Logistic regression is similar to linear regression except for the way it is used [6]. Linear regression is used to solve regression problems, while logistic regression is used to solve distribution problems.…”

Section: Logistic Regressionmentioning

confidence: 99%

Promoting Brain Health Through Machine Learning to Predict Stroke Risk

Kumar

2024

IJSREM

View full text Add to dashboard Cite

Stroke is a serious disease that can lead to serious consequences if not diagnosed and treated in time. The project focuses on using machine learning algorithms to analyze different types of data, including medical history, lifestyle and physical characteristics, to create powerful predictive models. Methods include preprocessing and data cleaning, product removal, and options to improve model accuracy. Various machine learning algorithms such as decision trees, support vector machines, and neural networks will be applied and compared to determine which is best for batting prediction [1]. The model will be trained with historical data and its performance will be evaluated with metrics such as demand, specificity and accuracy. The potential impact of this study includes early identification of individuals at high risk of stroke and provision of timely intervention and prevention. The development of effective predictive models can help reduce the burden of stroke-related morbidity and mortality. By combining architectural models with health applications, the program demonstrates the collaboration of today's technology in solving important health problems. Key Words: Brain Strokes, Early Detection, Predictive Model, Machine Learning Techniques, Medical Histories, Lifestyle Factors, Physiological Parameters, Preprocessing, Feature Extraction, Feature Selection, ML Algorithms, Healthcare Applications, Engineering Principles, Interdisciplinary Approach.

show abstract