Search Articles

View query in Help articles search
e.g. mhealth

Search Results (1 to 4 of 4 Results)

Download search results: CSV END BibTex RIS

Construction of Personalized Predictive Models for Missed Medication Doses Using Wearable Device Data: Prospective Observational Study

Construction of Personalized Predictive Models for Missed Medication Doses Using Wearable Device Data: Prospective Observational Study

Predictive models were constructed using Light Gradient Boosting Machine (Light GBM). Light GBM was selected due to its demonstrated high predictive performance on tabular data tasks similar to ours, its computational efficiency in terms of training speed and memory usage compared to other gradient boosting algorithms, and its built-in capability to provide feature importance rankings, which was utilized in our analysis.

Haru Iino, Hayato Kizaki, Shungo Imai, Satoko Hori

JMIR Form Res 2025;9:e72113

Download Citation: END BibTex RIS

Download PDF Download XML
Article has an altmetric score of 1

Machine Learning Model for Predicting Coronary Heart Disease Risk: Development and Validation Using Insights From a Japanese Population–Based Study

Machine Learning Model for Predicting Coronary Heart Disease Risk: Development and Validation Using Insights From a Japanese Population–Based Study

Light Gradient-Boosting Machine (Light GBM) is another efficient algorithm that works similarly to XGBoost but is designed to be faster and more scalable, especially when working with large datasets and many features. Both algorithms are known for their high performance in handling complex data and large-scale problems [9,27]. We used 5-fold cross-validation during model training to ensure robustness and mitigate overfitting. Hyperparameter optimization was conducted using a grid search approach.

Thien Vu, Yoshihiro Kokubo, Mai Inoue, Masaki Yamamoto, Attayeb Mohsen, Agustin Martin-Morales, Research Dawadi, Takao Inoue, Jie Ting Tay, Mari Yoshizaki, Naoki Watanabe, Yuki Kuriya, Chisa Matsumoto, Ahmed Arafa, Yoko M Nakao, Yuka Kato, Masayuki Teramoto, Michihiro Araki

JMIR Cardio 2025;9:e68066

Download Citation: END BibTex RIS

Download PDF Download XML
Article has an altmetric score of 2

Identifying the Relative Importance of Factors Influencing Medication Compliance in General Patients Using Regularized Logistic Regression and LightGBM: Web-Based Survey Analysis

Identifying the Relative Importance of Factors Influencing Medication Compliance in General Patients Using Regularized Logistic Regression and LightGBM: Web-Based Survey Analysis

To address this issue, we use a recently developed model, Light GBM, which combines multiple decision trees and offers the advantages of high accuracy and low computational cost [42,43]. Using this model, the contribution of each variable to the response variable can be quantified as feature importance during model construction, facilitating an objective understanding of the importance of factors.

Haru Iino, Hayato Kizaki, Shungo Imai, Satoko Hori

JMIR Form Res 2024;8:e65882

Download Citation: END BibTex RIS

Download PDF Download XML
Article has an altmetric score of 1

Predicting Abnormalities in Laboratory Values of Patients in the Intensive Care Unit Using Different Deep Learning Models: Comparative Study

Predicting Abnormalities in Laboratory Values of Patients in the Intensive Care Unit Using Different Deep Learning Models: Comparative Study

Third, we experimented with non-DL methods like Light GBM as well as 4 DL algorithms for time series classification. The DL-based method stacks models through mapping and processing functions between the models, using gradient descent or momentum methods to optimize fit.

Ahmad Ayad, Ahmed Hallawa, Arne Peine, Lukas Martin, Lejla Begic Fazlic, Guido Dartmann, Gernot Marx, Anke Schmeink

JMIR Med Inform 2022;10(8):e37658

Download Citation: END BibTex RIS

Download PDF Download XML
Article has an altmetric score of 3