Review of ai bias challenges in medical disease detection
Fairness or Fallacy? Mapping the Landscape of AI Bias in Disease Detection
Artificial Intelligence
Summary
Medical AI helps doctors detect diseases but can be unfair or biased. The authors looked at recent studies to find how different types of AI bias affect medical diagnosis. They found gaps in how biases are detected and fixed. Their work points to the need for clearer AI decisions and diverse patient data to improve fairness and healthcare use.
What this means in practice
- •For healthcare ai developers: Identify bias categories relevant to disease detection models to improve fairness before deployment in clinical settings.
- •For medical device regulators: Use the reviewed criteria to evaluate AI tools for equitable performance across diverse patient populations.
A survey. It maps existing work.
Authors
Ghulam Mudassir, Hameed Ullah Khan, Ahmad Sami Al-Shamayleh, Muhammad Faizan Khan, Muhammad Muqtasid, Moamin Abughazala, Adnan Akhunzada
Abstract
Artificial intelligence (AI) has several transformative effects on healthcare, like to facilitate clinicians in disease detection and to manage patient care with enhanced precision. Due to the increasing complexity of medical data and the growing volume of diagnostic images, the substantial computational power needed to process such information creates both opportunities and challenges. To accomplish this objective, numerous methodologies have been proposed to integrate AI into disease detection systems. All these methodologies consider different aspects of clinical diagnosis, considering key parameters such as the type of AI model employed, the nature of input data, and the population demographics being analysed. In this paper, we review different state-of-the-art techniques which have been proposed for various areas of disease detection, specifically focusing on bias identification and mitigation. The proposed solutions are distinguished based on the type of input data they utilize, the architecture of model, and type of bias (algorithmic bias, demographic bias, model bias, and deployment bias). The time frame chosen to filter out relevant studies is between 2015 and 2026. Eventually, we review 23 related articles out of 64,389 analyzed from seven different digital libraries. The obtained results guide us to reach a conclusion with respect to state-of-the-art selected studies. Furthermore, these results reveal significant research gaps that can assist researchers in addressing AI-related bias in medical diagnosis. By prioritizing explainability, data diversity, and fairness in algorithmic design, as well as equitable access for affected patient populations, they can utilize available healthcare resources more effectively.