首页|Abdullah Gul University Reports Findings in Cancer (Building a challenging medic al dataset for comparative evaluation of classifier capabilities)
Abdullah Gul University Reports Findings in Cancer (Building a challenging medic al dataset for comparative evaluation of classifier capabilities)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Cancer is the subject of a report. According to news reporting originating from Kayseri, Turkey, by Ne wsRx correspondents, research stated, “Since the 2000s, digitalization has been a crucial transformation in our lives. Nevertheless, digitalization brings a bul k of unstructured textual data to be processed, including articles, clinical rec ords, web pages, and shared social media posts.” Our news editors obtained a quote from the research from Abdullah Gul University , “As a critical analysis, the classification task classifies the given textual entities into correct categories. Categorizing documents from different domains is straightforward since the instances are unlikely to contain similar contexts. However, document classification in a single domain is more complicated due to sharing the same context. Thus, we aim to classify medical articles about four c ommon cancer types (Leukemia, Non-Hodgkin Lymphoma, Bladder Cancer, and Thyroid Cancer) by constructing machine learning and deep learning models. We used 383,9 14 medical articles about four common cancer types collected by the PubMed API. To build classification models, we split the dataset into 70% as t raining, 20% as testing, and 10% as validation. We b uilt widely used machine-learning (Logistic Regression, XGBoost, CatBoost, and R andom Forest Classifiers) and modern deep-learning (convolutional neural network s - CNN, long shortterm memory - LSTM, and gated recurrent unit - GRU) models. We computed the average classification performances (precision, recall, F-score) to evaluate the models over ten distinct dataset splits. The bestperforming de ep learning model(s) yielded a superior F1 score of 98%. However, t raditional machine learning models also achieved reasonably high F1 scores, 95% for the worst-performing case.”
KayseriTurkeyEurasiaCancerCyborg sEmerging TechnologiesHealth and MedicineMachine LearningOncology
NETL
NSTL
