# Analysing Environmental Efficiency in AI for X-Ray Diagnosis

arXiv: https://arxiv.org/abs/2511.07436 · HTML: https://mlsanity.com/paper/2511.07436/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 44 references that are in the map.
- First posted on arXiv 31 Oct 2025.

## Builds on (most cited first, 20 of 20)

- [Prompt Injection attack against LLM-integrated Applications](https://mlsanity.com/paper/2306.05499/) (2023)
- [Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Model](https://mlsanity.com/paper/2211.02001/) (2022)
- [COVID-Net: A Tailored Deep Convolutional Neural Network Design for Detection of COVID-19 Cases from Chest X-Ray Images](https://mlsanity.com/paper/2003.09871/) (2020)
- [Power Hungry Processing: Watts Driving the Cost of AI Deployment?](https://mlsanity.com/paper/2311.16863/) (2023)
- [How Hungry is AI? Benchmarking Energy, Water, and Carbon Footprint of LLM Inference](https://mlsanity.com/paper/2505.09598/) (2025)
- [Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Models](https://mlsanity.com/paper/2406.02061/) (2024)
- [XrayGPT: Chest Radiographs Summarization using Medical Vision-Language Models](https://mlsanity.com/paper/2306.07971/) (2023)
- [LLM Censorship: A Machine Learning Challenge or a Computer Security Problem?](https://mlsanity.com/paper/2307.10719/) (2023)
- [The Larger the Better? Improved LLM Code-Generation via Budget Reallocation](https://mlsanity.com/paper/2404.00725/) (2024)
- [What is the Role of Small Models in the LLM Era: A Survey](https://mlsanity.com/paper/2409.06857/) (2024)
- [ChatCAD+: Towards a Universal and Reliable Interactive CAD using LLMs](https://mlsanity.com/paper/2305.15964/) (2023)
- [Retrieval Augmented Chest X-Ray Report Generation using OpenAI GPT models](https://mlsanity.com/paper/2305.03660/) (2023)
- [CARES: Comprehensive Evaluation of Safety and Adversarial Robustness in Medical LLMs](https://mlsanity.com/paper/2505.11413/) (2025)
- [FactCheXcker: Mitigating Measurement Hallucinations in Chest X-ray Report Generation Models](https://mlsanity.com/paper/2411.18672/) (2024)
- [COVIDx CXR-3: A Large-Scale, Open-Source Benchmark Dataset of Chest X-ray Images for Computer-Aided COVID-19 Diagnostics](https://mlsanity.com/paper/2206.03671/) (2022)
- [RadioRAG: Online Retrieval-augmented Generation for Radiology Question Answering](https://mlsanity.com/paper/2407.15621/) (2024)
- [LLMs' Classification Performance is Overclaimed](https://mlsanity.com/paper/2406.16203/) (2024)
- [OpenAI ChatGPT interprets Radiological Images: GPT-4 as a Medical Doctor for a Fast Check-Up](https://mlsanity.com/paper/2501.06269/) (2025)
- [Comparative Analysis of Deep Learning Architectures for Breast Region Segmentation with a Novel Breast Boundary Proposal](https://mlsanity.com/paper/2410.02337/) (2024)
- [Carbon Intensity-Aware Adaptive Inference of DNNs](https://mlsanity.com/paper/2403.15824/) (2024)

## Built on by (most cited first, 1 of 1)

- [Why Trust Your Agent? Empirical Security Gains from TRiSM-Guided Agentic Workflows in Healthcare](https://mlsanity.com/paper/2606.28666/) (2026)

## Abstract (arXiv)

The integration of AI tools into medical applications has aimed to improve the efficiency of diagnosis. The emergence of large language models (LLMs), such as ChatGPT and Claude, has expanded this integration even further despite a concern for their environmental impact. Because of LLM versatility and ease of use through APIs, these larger models are often utilised even though smaller, custom models can be used instead. In this paper, LLMs and small discriminative models are integrated into a Mendix application to detect Covid-19 in chest X-rays. These discriminative models are also used to provide knowledge bases for LLMs to improve accuracy. This provides a benchmark study of 14 different model configurations for comparison of diagnostic accuracy and environmental impact. The findings indicated that while smaller models reduced the carbon footprint of the application, the output was biased towards a positive diagnosis and the output probabilities were lacking confidence. Meanwhile, restricting LLMs to only give probabilistic output caused poor performance in both accuracy and carbon footprint, demonstrating the risk of using LLMs as a universal AI solution. While using the smaller LLM GPT-4.1-Nano reduced the carbon footprint by 94.2% compared to the larger models, this was still disproportionate to the discriminative models; the most efficient solution was the Covid-Net model. Although it had a larger carbon footprint than other small models, its carbon footprint was 99.9% less than when using GPT-4.5-Preview, whilst achieving an accuracy of 95.5%, the highest of all models examined. This paper contributes to knowledge by comparing generative and discriminative models in Covid-19 detection as well as highlighting the environmental risk of using generative tools for classification tasks.