A Collection of Innovations in Medical AI for patient records in 2024

TL;DR

The paper argues that AI in healthcare evolves faster than traditional peer-reviewed publishing can capture, and proposes an annualized citation framework to spotlight the latest breakthroughs each year. It surveys 2024 advances in biomedical LLMs and EHR foundation models, highlighting scalable architectures (e.g., EHRMamba), time-to-event modeling (MOTOR), and domain-specific models (MediSwift, BMRetriever, BioMedLM, MetaGP) that push efficiency and interoperability. It also emphasizes data standards (MEDS) and evaluation benchmarks (CliBench, EHRNoteQA, LongHealth) as essential for reproducibility and trustworthy deployment, and surveys AI applications from predictive analytics to clinical decision support, while noting challenges in fairness, coding accuracy, and workflow integration. The proposed annualized framework aims to keep AI healthcare research current and actionable, aligning scholarly communication with the field’s rapid evolution and supporting safer, more effective translation into patient care.

Abstract

The field of Artificial Intelligence in healthcare is evolving at an unprecedented pace, driven by rapid advancements in machine learning and the recent breakthroughs in large language models. While these innovations hold immense potential to transform clinical decision making, diagnostics, and patient care, the accelerating speed of AI development has outpaced traditional academic publishing cycles. As a result, many scholarly contributions quickly become outdated, failing to capture the latest state of the art methodologies and their real world implications. This paper advocates for a new category of academic publications an annualized citation framework that prioritizes the most recent AI driven healthcare innovations. By systematically referencing the breakthroughs of the year, such papers would ensure that research remains current, fostering a more adaptive and informed discourse. This approach not only enhances the relevance of AI research in healthcare but also provides a more accurate reflection of the fields ongoing evolution.