Predicting postoperative risks using large language models

Predicting postoperative risk can inform effective care management & planning. We explored large language models (LLMs) in predicting postoperative risk through clinical texts using various tuning strategies. Records spanning 84,875 patients from Barnes Jewish Hospital (BJH) between 2018 & 2021, with a mean duration of follow-up based on the length of postoperative ICU stay less than 7 days, were utilized. Methods were replicated on the MIMIC-III dataset. Outcomes included 30-day mortality, pulmonary embolism (PE) & pneumonia. Three domain adaptation & finetuning strategies were implemented for three LLMs (BioGPT, ClinicalBERT & BioClinicalBERT): self-supervised objectives; incorporating labels with semi-supervised fine-tuning; & foundational modelling through multi-task learning. Model performance was compared using the AUROC & AUPRC for classification tasks & MSE & R2 for regression tasks. Cohort had a mean age of 56.9 (sd: 16.8) years; 50.3% male; 74% White. Pre-trained LLMs outperformed traditional word embeddings, with absolute maximal gains of 38.3% for AUROC & 14% for AUPRC. Adapting models through self-supervised finetuning further improved performance by 3.2% for AUROC & 1.5% for AUPRC Incorporating labels into the finetuning procedure further boosted performances, with semi-supervised finetuning improving by 1.8% for AUROC & 2% for AUPRC & foundational modelling improving by 3.6% for AUROC & 2.6% for AUPRC compared to self-supervised finetuning. Pre-trained clinical LLMs offer opportunities for postoperative risk predictions with unseen data, & further improvements from finetuning suggests benefits in adapting pre-trained models to note-specific perioperative use cases. Incorporating labels can further boost performance. The superior performance of foundational models suggests the potential of task-agnostic learning towards the generalizable LLMs in perioperative care.