2026-10-10T06:53:07Z https://api.figshare.com/v2/oai

oai:figshare.com:article/34040306 2026-10-01T06:10:05Z category_7 category_16 category_734 category_931 category_122 portal_81 item_type_6 month_year_10_2026

Additional file 1 of A transfer learning-based hybrid deep- and machine-learning regression approach for predicting the postoperative pulmonary function Wenfang Wang (2005924) Yingli Sun (342489) Haihong Ma (25153349) Ming Li (25153352) Medicine Physiology Biological Sciences not elsewhere classified Information Systems not elsewhere classified Mental Health Deep learning Regression analysis Respiratory function tests Tomography (x-ray computed) Transfer machine learning Additional file 1: Supplementary Table S1. Radiomics features selected to establish the R+E model for predicting FVC (n=10) and FEV1 (n=9). Supplementary Table S2. Threshold-based classification performance of the D+E model in the external test set. Supplementary Figure S1. Model interpretation using SHAP visualizations for (a) FVC and (b) FEV1. The SHAP summary plots show the top 20 most important features, ranked by their impact on the model output. Each dot represents a single sample, with the color indicating the feature value (red: high; blue: low). The position along the x-axis reflects the magnitude and direction of the feature contribution. 2026-09-30T05:00:00Z Text Journal contribution 10.6084/m9.figshare.34040306.v1 https://figshare.com/articles/journal_contribution/Additional_file_1_of_A_transfer_learning-based_hybrid_deep-_and_machine-learning_regression_approach_for_predicting_the_postoperative_pulmonary_function/34040306 CC BY