LLM is Not All You Need: A Systematic Evaluation of ML vs. Foundation Models for text and image based Medical Classification

TL;DR

This study systematically compares traditional ML models with foundation models for medical classification across text and image data, revealing that classical ML often outperforms modern transformer-based models in many scenarios.

Contribution

It provides a comprehensive benchmark demonstrating that traditional ML models remain highly effective, and that PEFT strategies may not always improve foundation model performance in medical tasks.

Findings

Classical ML models outperform foundation models on most tasks.

LoRA-tuned models perform poorly with minimal fine-tuning.

Foundation models show competitive results only in certain image classification tasks.

Abstract

The combination of multimodal Vision-Language Models (VLMs) and Large Language Models (LLMs) opens up new possibilities for medical classification. This work offers a rigorous, unified benchmark by using four publicly available datasets covering text and image modalities (binary and multiclass complexity) that contrasts traditional Machine Learning (ML) with contemporary transformer-based techniques. We evaluated three model classes for each task: Classical ML (LR, LightGBM, ResNet-50), Prompt-Based LLMs/VLMs (Gemini 2.5), and Fine-Tuned PEFT Models (LoRA-adapted Gemma3 variants). All experiments used consistent data splits and aligned metrics. According to our results, traditional machine learning (ML) models set a high standard by consistently achieving the best overall performance across most medical categorization tasks. This was especially true for structured text-based datasets, where the classical models performed exceptionally well. In stark contrast, the LoRA-tuned Gemma variants consistently showed the worst performance across all text and image experiments, failing to generalize from the minimal fine-tuning provided. However, the zero-shot LLM/VLM pipelines (Gemini 2.5) had mixed results; they performed poorly on text-based tasks, but demonstrated competitive performance on the multiclass image task, matching the classical ResNet-50 baseline. These results demonstrate that in many medical categorization scenarios, established machine learning models continue to be the most reliable option. The experiment suggests that foundation models are not universally superior and that the effectiveness of Parameter-Efficient Fine-Tuning (PEFT) is highly dependent on the adaptation strategy, as minimal fine-tuning proved detrimental in this study.