review · Artificial Intelligence Review
This paper presents the first review of Cost-Sensitive Learning (CSL) for addressing imbalanced medical data in machine learning models. Imbalanced data can lead to biased models that perform poorly on minority classes, impacting patient outcomes. The review analysed 173 papers published between 2010 and 2022, classifying them by publication trends, research types, medical sub-fields, CSL approaches, and evaluation methods. Key findings include a significant increase in publications since 2020, a preference for direct CSL approaches, and the prevalence of medical images as data types. The review also highlights the underutilisation of cost-related evaluation metrics and Python's popularity as a development tool.
Machine learning models can be biased and unreliable when trained on medical data where some conditions are much rarer than others. This review helps researchers understand how to use Cost-Sensitive Learning to build more accurate and dependable models, which is crucial for improving patient diagnosis and treatment.
This review synthesises research on Cost-Sensitive Learning (CSL) for imbalanced medical data, which is foundational for developing more robust machine learning applications in healthcare. Improved model reliability could benefit diagnostic tools, predictive analytics, and treatment recommendation systems. While the review itself is early-stage research, its findings can guide developers and researchers in creating more effective AI solutions for medical practitioners and healthcare organisations.
AI-generated from the published abstract. Always read the original work before citing.
Abstract Integrating Machine Learning (ML) in medicine has unlocked many opportunities to harness complex medical data, enhancing patient outcomes and advancing the field. However, the inherent imbalanced distribution of medical data poses a significant challenge, resulting in biased ML models that perform poorly on minority classes. Mitigating the impact of class imbalance has prompted researchers to explore various strategies, wherein Cost-Sensitive Learning (CSL) arises as a promising approach to improve the accuracy and reliability of ML models. This paper presents the first review of CSL for imbalanced medical data. A comprehensive exploration of the existing literature encompassed papers published from January 2010 to December 2022 and sourced from five major digital libraries. A total of 173 papers were selected, analysed, and classified based on key criteria, including publication years, channels and sources, research types, empirical types, medical sub-fields, medical tasks, CSL approaches, strengths and weaknesses of CSL, frequently used datasets and data types, evaluation metrics, and development tools. The results indicate a noteworthy publication rise, particularly since 2020, and a strong preference for CSL direct approaches. Data type analysis unveiled diverse modalities, with medical images prevailing. The underutilisation of cost-related metrics and the prevalence of Python as the primary programming tool are highlighted. The strengths and weaknesses analysis covered three aspects: CSL strategy, CSL approaches, and relevant works. This study serves as a valuable resource for researchers seeking to explore the current state of research, identify strengths and gaps in the existing literature and advance CSL’s application for imbalanced medical data.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1007/s10462-023-10652-8
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
