Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

PREBA: Surgical Duration Prediction via PCA-Weighted Retrieval-Augmented LLMs and Bayesian Averaging Aggregation

Wanyin Wu, Kanxue Li, Baosheng Yu, Haoyun Zhao, Yibing Zhan, Dapeng Tao, Hua Jin

Abstract

Accurate prediction of surgical duration is pivotal for hospital resource management. Although recent supervised learning approaches-from machine learning (ML) to fine-tuned large language models (LLMs)-have shown strong performance, they remain constrained by the need for high-quality labeled data and computationally intensive training. In contrast, zero-shot LLM inference offers a promising training-free alternative but it lacks grounding in institution-specific clinical context (e.g., local demographics and case-mix distributions), making its predictions clinically misaligned and prone to instability. To address these limitations, we present PREBA, a retrieval-augmented framework that integrates PCA-weighted retrieval and Bayesian averaging aggregation to ground LLM predictions in institution-specific clinical evidence and statistical priors. The core of PREBA is to construct an evidence-based prompt for the LLM, comprising (1) the most clinically similar historical surgical cases and (2) clinical statistical priors. To achieve this, PREBA first encodes heterogeneous clinical features into a unified representation space enabling systematic retrieval. It then performs PCA-weighted retrieval to identify clinically relevant historical cases, which form the evidence context supplied to the LLM. Finally, PREBA applies Bayesian averaging to fuse multi-round LLM predictions with population-level statistical priors, yielding calibrated and clinically plausible duration estimates. We evaluate PREBA on two real-world clinical datasets using three state-of-the-art LLMs, including Qwen3, DeepSeek-R1, and HuatuoGPT-o1. PREBA significantly improves performance-for instance, reducing MAE by up to 40% and raising R^2 from -0.13 to 0.62 over zero-shot inference-and it achieves accuracy competitive with supervised ML methods, demonstrating strong effectiveness and generalization.

PREBA: Surgical Duration Prediction via PCA-Weighted Retrieval-Augmented LLMs and Bayesian Averaging Aggregation

Abstract

Accurate prediction of surgical duration is pivotal for hospital resource management. Although recent supervised learning approaches-from machine learning (ML) to fine-tuned large language models (LLMs)-have shown strong performance, they remain constrained by the need for high-quality labeled data and computationally intensive training. In contrast, zero-shot LLM inference offers a promising training-free alternative but it lacks grounding in institution-specific clinical context (e.g., local demographics and case-mix distributions), making its predictions clinically misaligned and prone to instability. To address these limitations, we present PREBA, a retrieval-augmented framework that integrates PCA-weighted retrieval and Bayesian averaging aggregation to ground LLM predictions in institution-specific clinical evidence and statistical priors. The core of PREBA is to construct an evidence-based prompt for the LLM, comprising (1) the most clinically similar historical surgical cases and (2) clinical statistical priors. To achieve this, PREBA first encodes heterogeneous clinical features into a unified representation space enabling systematic retrieval. It then performs PCA-weighted retrieval to identify clinically relevant historical cases, which form the evidence context supplied to the LLM. Finally, PREBA applies Bayesian averaging to fuse multi-round LLM predictions with population-level statistical priors, yielding calibrated and clinically plausible duration estimates. We evaluate PREBA on two real-world clinical datasets using three state-of-the-art LLMs, including Qwen3, DeepSeek-R1, and HuatuoGPT-o1. PREBA significantly improves performance-for instance, reducing MAE by up to 40% and raising R^2 from -0.13 to 0.62 over zero-shot inference-and it achieves accuracy competitive with supervised ML methods, demonstrating strong effectiveness and generalization.
Paper Structure (32 sections, 13 equations, 8 figures, 10 tables)

This paper contains 32 sections, 13 equations, 8 figures, 10 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Machine Learning-based Surgical Duration Prediction
  4. Surgical Duration Prediction Methods Based on LLMs
  5. Method
  6. Problem Definition
  7. Heterogeneous Biomedical Feature Embedding
  8. Type-Specific Feature Encoding
  9. Dimension Normalization
  10. PCA-Weighted Retrieval-Augmented Generation
  11. Data-Driven Feature Weighting via PCA
  12. Similarity Retrieval with Clinical Post-Processing
  13. LLM-Based Prediction Generation
  14. Bayesian Averaging Aggregation
  15. Experiment
  16. ...and 17 more sections

Figures (8)

  • Figure 1: The proposed PREBA framework. for surgical duration prediction, consisting of three key modules: (i) Heterogeneous Biomedical Feature Embedding, (ii) PCA-Weighted Retrieval-Augmented Generation, and (iii) Bayesian Averaging Aggregation.
  • Figure 2: PCA-based feature importance analysis showing the top 20 clinical features ranked by their contribution to surgical duration prediction.
  • Figure 3: Key characteristics of In-hospital Dataset. (a) Patient and Surgical Characteristics: distributions of gender, age, and surgical grade. (b) Surgical duration distribution with key statistics. (c) Department-stratified duration patterns across 10 selected clinical departments.
  • Figure 4: Structured prompt template for retrieval-augmented surgical duration prediction. The prompt integrates (1) system role definition, (2) similar case demonstrations retrieved via PCA-weighted similarity, (3) statistical priors from historical data, and (4) the query case.
  • Figure 5: N-Shot Ablation Study. Unified Performance-Efficiency Analysis on Qwen3-8B. Comprehensive visualization showing MAE (blue) and RMSE (green) on left axis, R² (red) and MAPE (orange) on right axis, with inference time color gradient (light to dark) displayed above the x-axis.
  • ...and 3 more figures