AI Article Synopsis
- The rapid increase in memory and computing power is leading to more complex and imbalanced datasets, particularly in clinical data where minority events are rare compared to the majority class.
- The authors propose a new framework for imbalanced classification using reinforcement learning, which utilizes dueling and double deep Q-learning methods and is tailored for multi-class scenarios.
- Their approach demonstrates superior performance over existing methods in real-world clinical case studies, promoting fairer classification and better predictions for minority classes.
Article Abstract
Unlabelled: With the rapid growth of memory and computing power, datasets are becoming increasingly complex and imbalanced. This is especially severe in the context of clinical data, where there may be one rare event for many cases in the majority class. We introduce an imbalanced classification framework, based on reinforcement learning, for training extremely imbalanced data sets, and extend it for use in multi-class settings. We combine dueling and double deep Q-learning architectures, and formulate a custom reward function and episode-training procedure, specifically with the capability of handling multi-class imbalanced training. Using real-world clinical case studies, we demonstrate that our proposed framework outperforms current state-of-the-art imbalanced learning methods, achieving more fair and balanced classification, while also significantly improving the prediction of minority classes.
Supplementary Information: The online version contains supplementary material available at 10.1007/s10994-023-06481-z.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11065699 | PMC |
| http://dx.doi.org/10.1007/s10994-023-06481-z | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Case report: Receptive labeling training in autism: conventional vs. technology-based approaches? a single case study.
Front Psychiatry
December 2024
Institute for Biomedical Research and Innovation (IRIB), National Research Council of Italy (CNR), Messina, Italy.
Background: Receptive language, the ability to comprehend and respond to spoken language, poses significant challenges for individuals with Autism Spectrum Disorder (ASD). To support communication in autistic children, interventions like Lovaas' simple-conditional method and Green's conditional-only method are commonly employed. Personalized approaches are essential due to the spectrum nature of autism.
View Article and Find Full Text PDFAdvanced AI and ML frameworks for transforming drug discovery and optimization: With innovative insights in polypharmacology, drug repurposing, combination therapy and nanomedicine.
Eur J Med Chem
December 2024
Department of Pharmaceutical Chemistry, Delhi Institute of Pharmaceutical Sciences and Research (DIPSAR), DPSRU, Pushp Vihar, New Delhi, 110017, India. Electronic address:
Artificial Intelligence (AI) and Machine Learning (ML) are transforming drug discovery by overcoming traditional challenges like high costs, time-consuming, and frequent failures. AI-driven approaches streamline key phases, including target identification, lead optimization, de novo drug design, and drug repurposing. Frameworks such as deep neural networks (DNNs), convolutional neural networks (CNNs), and deep reinforcement learning (DRL) models have shown promise in identifying drug targets, optimizing delivery systems, and accelerating drug repurposing.
View Article and Find Full Text PDFHow Dopamine Enables Learning from Aversion.
Curr Opin Behav Sci
February 2025
Feinberg School of Medicine, Department of Neuroscience, Northwestern University, Chicago, IL, USA.
Dopamine is heavily studied for its role in reward learning, but it is becoming increasingly appreciated that dopamine can also enable learning from aversion. Dopamine neurons modulate their firing and neurotransmitter release patterns in response to aversive outcomes. However, there is considerable heterogeneity in the timing and directionality of the modulation.
View Article and Find Full Text PDFPrecision autofocus in optical microscopy with liquid lenses controlled by deep reinforcement learning.
Microsyst Nanoeng
December 2024
School of Mechanical and Electrical Engineering, Soochow University, No.8 Jixue Road, Suzhou City, Jiangsu, 215000, China.
Microscopic imaging is a critical tool in scientific research, biomedical studies, and engineering applications, with an urgent need for system miniaturization and rapid, precision autofocus techniques. However, traditional microscopes and autofocus methods face hardware limitations and slow software speeds in achieving this goal. In response, this paper proposes the implementation of an adaptive Liquid Lens Microscope System utilizing Deep Reinforcement Learning-based Autofocus (DRLAF).
View Article and Find Full Text PDFIntegrating necroptosis into pan-cancer immunotherapy: a new era of personalized treatment.
Front Immunol
December 2024
Department of Thoracic Surgery, The Affiliated Huaian No.1 People's Hospital of Nanjing Medical University, Huai'an, China.
Introduction: Necroptosis has emerged as a promising biomarker for predicting immunotherapy responses across various cancer types. Its role in modulating immune activation and therapeutic outcomes offers potential for precision oncology.
Methods: A comprehensive pan-cancer analysis was performed using bulk RNA sequencing data to develop a necroptosis-related gene signature, termed Necroptosis.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!