Machine-learning derived identification of prognostic signature to forecast head and neck squamous cell carcinoma prognosis and drug response DOI Creative Commons
Shoukang Li, Hai‐Ying Sun, Yuan Tian

et al.

Frontiers in Immunology, Journal Year: 2024, Volume and Issue: 15

Published: Dec. 19, 2024

Head and neck squamous cell carcinoma (HNSCC), a highly heterogeneous malignancy is often associated with unfavorable prognosis. Due to its unique anatomical position the absence of effective early inspection methods, surgical intervention alone frequently inadequate for achieving complete remission. Therefore, identification reliable biomarker crucial enhance accuracy screening treatment strategies HNSCC.

Language: Английский

Single-cell transcriptomic analysis reveals efferocytosis signature predicting immunotherapy response in hepatocellular carcinoma DOI

Longhu Li,

Guangyao Li,

Wangfeng Zhai

et al.

Digestive and Liver Disease, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 1, 2025

Language: Английский

Citations

0
Machine learning for temporary stoma after intestinal resection in surgical decision-making of Crohn’s disease DOI Creative Commons
Fang‐Tao Wang,

Lin Yin,

Renyuan Gao

et al.

BMC Gastroenterology, Journal Year: 2025, Volume and Issue: 25(1)

Published: Feb. 25, 2025

Crohn's disease (CD) often necessitates surgical intervention, with temporary stoma creation after intestinal resection (IR) being a crucial decision. This study aimed to construct novel models based on machine learning (ML) predict formation IR for CD. Patient data who underwent CD at our center between July 2017 and March 2023 were collected inclusion in this retrospective study. Eligible patients randomly divided into training validation cohorts. Feature selection was executed using the least absolute shrinkage operator. We employed three ML algorithms including traditional logistic regression, random forest XG-Boost create prediction models. The area under curve (AUC), accuracy, sensitivity, specificity, precision, recall, F1 score used evaluate these SHapley Additive exPlanation (SHAP) approach assess feature importance. A total of 252 included study, 150 whom IR. Eight independent predictors emerged as most valuable features. An AUC 0.886 0.998 noted among algorithms. (RF) demonstrated optimal performance (0.998 cohort 0.780 cohort). By employing SHAP method, we identified variables that contributed model their correlation proposed RF showed good predictive ability identifying high risk CD, which can assist decision-making management, provide personalized guidance formation, improve patient outcomes.

Language: Английский

Citations

0
Machine Learning of Laboratory Data in Predicting 30-Day Mortality for Adult Hemophagocytic Lymphohistiocytosis DOI
Jun Zhou, Mengxiao Xie, Ning Dong

et al.

Journal of Clinical Immunology, Journal Year: 2024, Volume and Issue: 45(1)

Published: Sept. 20, 2024

Language: Английский

Citations

2
Machine-learning derived identification of prognostic signature to forecast head and neck squamous cell carcinoma prognosis and drug response DOI Creative Commons
Shoukang Li, Hai‐Ying Sun, Yuan Tian

et al.

Frontiers in Immunology, Journal Year: 2024, Volume and Issue: 15

Published: Dec. 19, 2024

Head and neck squamous cell carcinoma (HNSCC), a highly heterogeneous malignancy is often associated with unfavorable prognosis. Due to its unique anatomical position the absence of effective early inspection methods, surgical intervention alone frequently inadequate for achieving complete remission. Therefore, identification reliable biomarker crucial enhance accuracy screening treatment strategies HNSCC.

Language: Английский

Citations

0