Demographic and ocular features. by Mingxi Shao (10066570)

“…The XGBoost or KNN model using TAS alone achieved the highest AUC (0.74) in five-fold cross-validation.</p><p>Conclusion</p><p>The decrease in TAS levels and the increase in H₂O₂ and MDA levels are found to be correlated with PCG, and the results indicate that oxidative stress plays a part in congenital glaucoma onset.…”

Machine learning model to diagnose PCG. by Mingxi Shao (10066570)

“…The XGBoost or KNN model using TAS alone achieved the highest AUC (0.74) in five-fold cross-validation.</p><p>Conclusion</p><p>The decrease in TAS levels and the increase in H₂O₂ and MDA levels are found to be correlated with PCG, and the results indicate that oxidative stress plays a part in congenital glaucoma onset.…”

ROC curves of TAS + SOD + MDA to diagnose PCG. by Mingxi Shao (10066570)

“…The XGBoost or KNN model using TAS alone achieved the highest AUC (0.74) in five-fold cross-validation.</p><p>Conclusion</p><p>The decrease in TAS levels and the increase in H₂O₂ and MDA levels are found to be correlated with PCG, and the results indicate that oxidative stress plays a part in congenital glaucoma onset.…”

Characteristics of women at admission. by Guiyou Yang (10259597)

“…The AUC-PRC values (0.2–0.4) of the fullPIERS model remained low (i.e., close to the daily fraction of adverse outcomes, indicating low discriminative capacity). …”

Data Sheet 1_Altered static and dynamic spontaneous brain activity in patients with dysthyroid optic neuropathy: a resting-state fMRI study.docx by Jinling Lu (424449)

Development of a machine learning method for predicting neutrophil-specific functional genes. by Guihua Wang (286390)

“…<p>(A) NeuRGI model training workflow involved: 1) extracting gene features from various databases. 2) using genes of neutrophil-related genes as positives and PU-learning as negatives. 3) balancing the training set with under-sampling and training the NeuRGI random forest model with 10-fold cross-validation, then employing a Gaussian Mixture Model (GMM) with NeuRGI scores to identify potential positives. 4) using OntoVAE for <i>in silico</i> knockout of GMM-classified genes to find key regulatory factors for guiding follow-up experiments. …”