Gradient Boosted Tree Approaches for Mapping European Organization for Research and Treatment of Cancer Quality of Life Questionnaire Core 30 Onto 5-Level Version of EQ-5D Index for Patients With Cancer

Hagiwara, Yasuhiro; Shiroiwa, Takeru; Taira, Naruto; Kawahara, Takuya; Konomura, Keiko; Noto, Shinichi; Fukuda, Takashi; Shimozuma, Kojiro

doi:10.1016/j.jval.2022.07.020

Cited by 6 publications

(4 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A notable strength of GBR models lies in their robustness against outliers, a feature that proves exceptionally beneficial in accommodating the diverse and fluctuating characteristics observed among donors. 30,31 With the application of GBR to predict CD34+ cell yield, the model identified pre-apheresis CD34+ cell count and processed blood volume as key predictors, contributing significantly to its predictive power. However, the enhancement in model performance was marginal.…”

Section: Discussionmentioning

confidence: 99%

“…The adoption of GBR offers a multitude of advantages, especially in dissecting complex relationships, uncovering the nuances of variable interactions, and ensuring high precision in predictions. A notable strength of GBR models lies in their robustness against outliers, a feature that proves exceptionally beneficial in accommodating the diverse and fluctuating characteristics observed among donors 30,31 …”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

CD34+ cell yield among healthy donors: Large‐scale model development and validation

Alswied,

Daniel,

Chen

et al. 2024

J of Clinical Apheresis

View full text Add to dashboard Cite

BackgroundSuccessful engraftment in hematopoietic stem cell transplantation necessitates the collection of an adequate dose of CD34+ cells. Thus, the precise estimation of CD34+ cells harvested via apheresis is critical. Current CD34+ cell yield prediction models have limited reproducibility. This study aims to develop a more reliable and universally applicable model by utilizing a large dataset, enhancing yield predictions, optimizing the collection process, and improving clinical outcomes.Materials and MethodsA secondary analysis was conducted using the Center for International Blood and Marrow Transplant Research database, involving data from over 17 000 healthy donors who underwent filgrastim‐mobilized hematopoietic progenitor cell apheresis. Linear regression, gradient boosting regressor, and logistic regression classification models were employed to predict CD34+ cell yield.ResultsKey predictors identified include pre‐apheresis CD34+ cell count, weight, age, sex, and blood volume processed. The linear regression model achieved a coefficient of determination (R2) value of 0.66 and a correlation coefficient (r) of 0.81. The gradient boosting regressor model demonstrated marginally improved results with an R2 value of 0.67 and an r value of 0.82. The logistic regression classification model achieved a predictive accuracy of 96% at the 200 × 106 CD34+ cell count threshold. At thresholds of 400, 600, 800, and 1000 × 106 CD34+ cell count, the accuracies were 88%, 83%, 83%, and 88%, respectively. The model demonstrated a high area under the receiver operator curve scores ranging from 0.90 to 0.93.ConclusionThis study introduces advanced predictive models for estimating CD34+ cell yield, with the logistic regression classification model demonstrating remarkable accuracy and practical utility.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

CD34+ cell yield among healthy donors: Large‐scale model development and validation

Alswied,

Daniel,

Chen

et al. 2024

J of Clinical Apheresis

View full text Add to dashboard Cite

show abstract

“…1(b) demonstrate the testing of different input cases, including combinations and single sensor modalities, using two types of models: tree-based 23 and gradient boosting (GB)-tree-based approaches 24,25 , with 32-fold crossvalidation. These models are widely used and effective in various healthcare research studies 20,[26][27][28][29] . The evaluation metric R-Squared (R 2 ) was utilized to measure the correlation distribution between the sensor modalities and glucose data 30 .…”

Section: Investigating the Correlation Between Sensor Modalities And ...mentioning

confidence: 99%

From Data to Insight: Predicting Interstitial Glucose in Healthy Cohort with Non-invasive Sensor Technology and Machine Learning

Huang,

Schmelter,

Seitzer

et al. 2023

Preprint

View full text Add to dashboard Cite

Continuous glucose monitoring (CGM) has transformed the care of diabetes mellitus patients. It is increasingly used to support nutritional management in various pathophysiologic conditions, including obesity and migraine, where avoiding postprandial hyperglycemia is critical to prevent hyperinsulinemia and low glucose levels after meal intake. However, the current CGM devices have significant limitations, such as invasiveness, availability, high cost, and limited shelf life, which must be overcome for broader use, specifically in disease prevention and obesity management. Therefore, we collected over 15,500 interstitial glucose measurements by CGM with a large amount of corresponding multimodal non-invasive wearable sensor data for healthy cohorts and used the machine learning (ML) approach to discover their correlations and accurately predict the postprandial glucose response (PPGR) in real-time over ten days, with an average Root Mean Squared Error (RMSE) of 18.49 ± 0.1 mg/dL and an average Mean Absolute Percentage Error (MAPE) of 15.58 ± 0.09%. It demonstrated that ML could facilitate non-invasive blood glucose measurements and opened new opportunities for efficient and objective nutritional-based disease prevention.

show abstract

“…Commonly used ML methods for cancer analysis include linear regression, logistic regression, 7 decision trees, random forests, support vector machines, 8 neural networks, k-means clustering, principal component analysis, 9 naïve Bayes, gradient boosting, 10 and so on. However, ML methods suffer several shortcomings.…”

mentioning

confidence: 99%

Challenges of Deep Learning in Cancers

Zhang

Hong

2023

Technol Cancer Res Treat

View full text Add to dashboard Cite

Gradient Boosted Tree Approaches for Mapping European Organization for Research and Treatment of Cancer Quality of Life Questionnaire Core 30 Onto 5-Level Version of EQ-5D Index for Patients With Cancer

Cited by 6 publications

References 31 publications

CD34+ cell yield among healthy donors: Large‐scale model development and validation

CD34+ cell yield among healthy donors: Large‐scale model development and validation

From Data to Insight: Predicting Interstitial Glucose in Healthy Cohort with Non-invasive Sensor Technology and Machine Learning

Challenges of Deep Learning in Cancers

Contact Info

Product

Resources

About