ClinicalBench: Can LLMs Beat Traditional ML Models in Clinical Prediction?
This work addresses the problem of evaluating LLMs for clinical applications, providing a benchmark to guide practitioners, but it is incremental as it compares existing methods on new data.
The paper tackles the question of whether large language models (LLMs) can outperform traditional machine learning models in clinical prediction tasks, finding that both general-purpose and medical LLMs, across various scales and strategies, cannot yet beat traditional models, highlighting deficiencies in clinical reasoning.
Large Language Models (LLMs) hold great promise to revolutionize current clinical systems for their superior capacities on medical text processing tasks and medical licensing exams. Meanwhile, traditional ML models such as SVM and XGBoost have still been mainly adopted in clinical prediction tasks. An emerging question is Can LLMs beat traditional ML models in clinical prediction? Thus, we build a new benchmark ClinicalBench to comprehensively study the clinical predictive modeling capacities of both general-purpose and medical LLMs, and compare them with traditional ML models. ClinicalBench embraces three common clinical prediction tasks, two databases, 14 general-purpose LLMs, 8 medical LLMs, and 11 traditional ML models. Through extensive empirical investigation, we discover that both general-purpose and medical LLMs, even with different model scales, diverse prompting or fine-tuning strategies, still cannot beat traditional ML models in clinical prediction yet, shedding light on their potential deficiency in clinical reasoning and decision-making. We call for caution when practitioners adopt LLMs in clinical applications. ClinicalBench can be utilized to bridge the gap between LLMs' development for healthcare and real-world clinical practice.