Journal Articles

Machine Learning: New opportunities for tumor diagnosis and prognostic evaluation

Lead Editor:
    Dr Wenjie Shi University Magdeburg Germany


Background: Early detection and treatment are critical factors in improving the prognosis of tumor patients. However, the interpretation and translation of massive clinical data often require a large number of labor costs and rely on the experience of clinicians, which inevitably leads to bias in the interpretation of results. Thanks to the interdisciplinary cooperation mode of AI technology, machine learning-based medical-industrial cross-study has made breakthroughs in the direction of tumor target identification and prognosis assessment. In particular, the relevant models developed based on machine learning algorithms have positive guiding significance for early tumor signal recognition. Goal: Our aim is to explore the benefits of machine learning or deep learning algorithms in processing clinical data from oncology patients and to reveal potential markers for early tumor detection and prognostic evaluation. These markers will be screened and validated in internal and external datasets for further clinical applications. In addition, artificial intelligence diagnostic and prognostic models based on machine learning algorithms are equally interesting, with the help of which clinical decision-making can be better assisted. In addition, we also hope to be able to extract tumor image features through deep learning algorithms, which will have a positive impact on the promotion of intelligent diagnosis of tumor images. Scope: Original Research, Review, Mini Review, Opinion, and Perspective articles that describe and cover the recent advances made in tumor diagnosis( therapy) and machine learning, are considered. This research topic will include but is not limited to • Identification and validation of candidate clinical risk factors • Construction and validation of prediction model for tumor patients • New strategies for tumor diagnosis based on RNAseq data or clinical data


Submission deadline:

13/03/2025


Print ISSN: 1792-1074
Online ISSN: 1792-1082

Sign up for eToc alerts

Recommend to Library