This paper explores the development and evaluation of a multimodal system for survival prediction in clinical settings, leveraging both structured electronic health records and unstructured clinical notes. The core objective is to enhance the accuracy and reliability of survival predictions in Intensive Care Units by integrating diverse data types through advanced machine learning models. The system combines the novel architecture of Tabular Transformers, adapted to process structured data such as patient demographics, medical history, and diagnoses, with Multi-Layer Perceptrons for text embeddings obtained from BioClinicalBERT, a specialized model for clinical narratives. These models’ integration aims to capture the complex and multifaceted nature of patient profiles, thereby improving prediction performance. The finalized system, a Logistic Regression instance that aggregates the obtained predictions, demonstrates superior performance on evaluation metrics, highlighting the system’s ability to identify high-risk patients. Comprehensive benchmarking against decision trees, standalone MLPs, and various configurations underscored the robustness of the proposed system. This research highlights the transformative potential of multimodal data integration in medical predictive modeling. Thus, medical professionals can guide their efforts and prioritization of patient care, enabling more efficient and targeted allocation of resources during triage.

Numerous text classification tasks inherently possess hierarchical structures among classes, often overlooked in traditional classification paradigms. This study introduces novel approaches for hierarchical text classification using Large Language Models (LLMs), exploiting taxonomies to improve accuracy and traceability in a zero-shot setting. We propose two hierarchical classification methods, namely (i) single-path and (ii) path-traversal, which all leverage the hierarchical class structures inherent in the target classes (e.g., a bird is a type of animal that belongs to a species) and improve naïve hierarchical text classification from literature. We implement them as prompts for generative models such as OpenAI GPTs and benchmark them against discriminative language models (BERT and RoBERTa). We measure the classification performance (precision, recall, and F1-score) vs. computational efficiency (time and cost). Throughout the evaluations of the classification methods on two diverse datasets, namely ComFaSyn, containing mental health patients’ diary entries, and DBpedia, containing structured information extracted from Wikipedia, we observed that our methods, without any form of fine-tuning and few-shot examples, achieve comparable results to flat classification and existing methods from literature with minimal increases in the prompts and processing time.