Artificial Breath Classification Using XGBoost Algorithm for Diabetes Detection

Paleczek, Anna; Grochala, Dominik; Rydosz, Artur

doi:10.3390/s21124187

Cited by 53 publications

(53 citation statements)

References 77 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Secondly, for high-dimensional scene data exploration (such as medical time-series data), the XGBoost algorithm cannot effectively eliminate noise variables ( 57 ). Therefore, we conducted a grid search to determine the algorithms of optimal dimensionality reduction and added randomness to improve robustness ( 58 ). Additionally, an increasing fraction of the training time in the LSTM model would reduce the number of iterations within the same total training time ( 59 ).…”

Section: Discussionmentioning

confidence: 99%

The innovative model based on artificial intelligence algorithms to predict recurrence risk of patients with postoperative breast cancer

Zeng

Liu²,

Chen³

et al. 2023

Front. Oncol.

View full text Add to dashboard Cite

PurposeThis study aimed to develop a machine learning model to retrospectively study and predict the recurrence risk of breast cancer patients after surgery by extracting the clinicopathological features of tumors from unstructured clinical electronic health record (EHR) data.MethodsThis retrospective cohort included 1,841 breast cancer patients who underwent surgical treatment. To extract the principal features associated with recurrence risk, the clinical notes and histopathology reports of patients were collected and feature engineering was used. Predictive models were next conducted based on this important information. All algorithms were implemented using Python software. The accuracy of prediction models was further verified in the test cohort. The area under the curve (AUC), precision, recall, and F1 score were adopted to evaluate the performance of each model.ResultsA training cohort with 1,289 patients and a test cohort with 552 patients were recruited. From 2011 to 2019, a total of 1,841 textual reports were included. For the prediction of recurrence risk, both LSTM, XGBoost, and SVM had favorable accuracies of 0.89, 0.86, and 0.78. The AUC values of the micro-average ROC curve corresponding to LSTM, XGBoost, and SVM were 0.98 ± 0.01, 0.97 ± 0.03, and 0.92 ± 0.06. Especially the LSTM model achieved superior execution than other models. The accuracy, F1 score, macro-avg F1 score (0.87), and weighted-avg F1 score (0.89) of the LSTM model produced higher values. All P values were statistically significant. Patients in the high-risk group predicted by our model performed more resistant to DNA damage and microtubule targeting drugs than those in the intermediate-risk group. The predicted low-risk patients were not statistically significant compared with intermediate- or high-risk patients due to the small sample size (188 low-risk patients were predicted via our model, and only two of them were administered chemotherapy alone after surgery). The prognosis of patients predicted by our model was consistent with the actual follow-up records.ConclusionsThe constructed model accurately predicted the recurrence risk of breast cancer patients from EHR data and certainly evaluated the chemoresistance and prognosis of patients. Therefore, our model can help clinicians to formulate the individualized management of breast cancer patients.

show abstract

Section: Discussionmentioning

confidence: 99%

The innovative model based on artificial intelligence algorithms to predict recurrence risk of patients with postoperative breast cancer

Zeng

Liu²,

Chen³

et al. 2023

Front. Oncol.

View full text Add to dashboard Cite

show abstract

“…The Python Data Analysis Library was used as an accurate and flexible data manipulation tool to first analyze the data. Next, a decision-tree-based method—extreme gradient boosting—was adopted [ 21 ]. This method was selected to deal with distributed problems, microwave theoretical analysis, and calculations owing to its advantages of high-speed dynamic response and memory ability.…”

Section: Methodsmentioning

confidence: 99%

Measurement of Complex Permittivity for Rapid Detection of Liquid Concentration Using a Reusable Octagon-Shaped Resonator Sensor

2023

View full text Add to dashboard Cite

Substrate-integrated waveguides (SIWs) are widely used in microwave systems owing to their low cost and ease of integration. In this study, an SIW-based resonator that reacts to the complex permittivity variation of solutions with dimensions of 79.2 mm × 59.8 mm is introduced. This octagon-shaped sensor can be installed on a preliminary monitoring system to test water quality by observing the parameter variations caused by external factors. The resonant structure was used to test different concentrations of ethanol–water and acetone–water mixtures for verification. The resonant frequency and quality factor (Q-factor) were found to vary with the relative complex permittivity of the liquid in the S-band, and the electric field distribution varied when liquid droplets were placed in the center of the substrate. The designed sensor operates at 2.45 GHz in the air, and the observed minimum resonant frequency shift with liquid was 15 MHz. The measurement error was approximately 3.1%, and the results reveal a relationship between the resonant frequency and temperature as well. Considering the observed sources of error, the measured relative permittivity is consistent with the actual values. The proposed sensor is economically convenient and suitable for various test environments.

show abstract

“…It can handle both classification and regression problems by selecting different baseline models, and the final result is achieved by adding new models to the existing model until its performance is no longer greatly improved. The main advantage of XGB is its speed, thanks to its parallel and cache‐aware computing [37] . Additionally, it includes a regularization term to prevent over‐fitting and shrinkage and column subsampling to further reduce the risk of over‐fitting.…”

Section: Methodsmentioning

confidence: 99%

Predicting GPR40 Agonists with A Deep Learning‐Based Ensemble Model

et al. 2023

View full text Add to dashboard Cite

Recent studies have identified G protein‐coupled receptor 40 (GPR40) as a promising target for treating type 2 diabetes mellitus, and GPR40 agonists have several superior effects over other hypoglycemic drugs, including cardiovascular protection and suppression of glucagon levels. In this study, we constructed an up‐to‐date GPR40 ligand dataset for training models and performed a systematic optimization of the ensemble model, resulting in a powerful ensemble model (ROC AUC: 0.9496) for distinguishing GPR40 agonists and non‐agonists. The ensemble model is divided into three layers, and the optimization process is carried out in each layer. We believe that these results will prove helpful for both the development of GPR40 agonists and ensemble models. All the data and models are available on GitHub. (https://github.com/Jiamin‐Yang/ensemble_model)

show abstract

Artificial Breath Classification Using XGBoost Algorithm for Diabetes Detection

Cited by 53 publications

References 77 publications

The innovative model based on artificial intelligence algorithms to predict recurrence risk of patients with postoperative breast cancer

The innovative model based on artificial intelligence algorithms to predict recurrence risk of patients with postoperative breast cancer

Measurement of Complex Permittivity for Rapid Detection of Liquid Concentration Using a Reusable Octagon-Shaped Resonator Sensor

Predicting GPR40 Agonists with A Deep Learning‐Based Ensemble Model

Contact Info

Product

Resources

About