<?xml version="1.0" encoding="UTF-8" ?><rss version="2.0">
<channel>
<title>Journal of Artificial Intelligence - Current Issue</title>
<link>https://scialert.net</link>
<description>Journal of Artificial Intelligence</description>
<language>en-us</language>
<copyright>Science Alert</copyright>
<pubDate>Fri, 12 Jun 2026 18:11:57 +0200</pubDate>
<lastBuildDate>Fri, 12 Jun 2026 18:14:14 +0200</lastBuildDate>
<generator>RssPublisher 0.2.0 beta</generator>
<image>
<url>https://scialert.net/images/logo.gif</url>
<title>Journal of Artificial Intelligence - Current Issue</title>
<link>https://scialert.net</link>
<height>41</height>
<width>233</width>
<description>Journal of Artificial Intelligence</description>
</image>
<item>
Machine Learning in Haematological Malignancies: From Early Detection to Precision Therapy<title><![CDATA[Machine Learning in Haematological Malignancies: From Early Detection to Precision Therapy]]></title> 
<description><![CDATA[Haematological malignancies, including leukaemia, lymphoma and multiple myeloma, constitute a significant global cancer burden and remain the leading causes of cancer-related mortality. While advances in molecular profiling, cytogenetics and immunophenotyping have enhanced disease classification and risk stratification, these approaches are often costly, time-intensive and subject to interpretive variability. Machine Learning (ML), a core domain of artificial intelligence, is emerging as a transformative tool in haematology, offering scalable solutions for diagnosis, prognostication and therapeutic decision-making. This review synthesizes evidence from recent applications of ML in haematological malignancies, focusing on diagnostic imaging models, multi-modal data integration frameworks, prognostic algorithms utilizing multi-omics datasets and predictive platforms for therapy optimization and transplantation outcomes. Convolutional neural networks demonstrate high accuracy in classifying malignant cells from peripheral blood smears and histopathology, reducing inter-observer variability and improving workflow efficiency. Multi-modal systems integrating imaging, genomic and clinical variables enhance diagnostic precision. Prognostic ML models outperform conventional scoring systems in predicting survival, relapse risk and treatment response. Deep learning architectures, including autoencoders, uncover latent biological signatures linked to disease progression and drug resistance. In therapeutics, ML supports dose optimization, toxicity prediction and drug-response forecasting. Predictive tools in hematopoietic stem cell transplantation further improve patient selection and risk stratification. Machine learning is redefining precision oncology in haematological malignancies by improving diagnostic reproducibility, refining prognostic accuracy and enabling individualized therapy. Its continued integration into clinical workflows holds promise for better outcomes and more efficient haematologic cancer care.]]></description>
<link>https://scialert.net/abstract/?doi=jai.2026.1.10</link> 
<pubDate>12 June, 2026</pubDate>
</item>
</channel>
</rss>