Transformers in Healthcare: A Survey

Abstract

With Artificial Intelligence (AI) increasingly permeating various aspects of society, including healthcare, the adoption of the Transformers neural network architecture is rapidly changing many applications. Transformer is a type of deep learning architecture initially developed to solve general-purpose Natural Language Processing (NLP) tasks and has subsequently been adapted in many fields, including healthcare. In this survey paper, we provide an overview of how this architecture has been adopted to analyze various forms of data, including medical imaging, structured and unstructured Electronic Health Records (EHR), social media, physiological signals, and biomolecular sequences. Those models could help in clinical diagnosis, report generation, data reconstruction, and drug/protein synthesis. We identified relevant studies using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. We also discuss the benefits and limitations of using transformers in healthcare and examine issues such as computational cost, model interpretability, fairness, alignment with human values, ethical implications, and environmental impact.

References in corpus (24)

• Training language models to follow instructions with human feedback
• TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation
• NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding
• Cross-lingual Language Model Pretraining
• BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining
• Mamba: Linear-Time Sequence Modeling with Selective State Spaces
• Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)
• REFUGE Challenge: A Unified Framework for Evaluating Automated Methods for Glaucoma Assessment from Fundus Photographs
• A large annotated medical image dataset for the development and evaluation of segmentation algorithms
• BrainTorrent: A Peer-to-Peer Environment for Decentralized Federated Learning
• FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning
• DEPTWEET: A Typology for Social Media Texts to Detect Depression Severities
• XLSor: A Robust and Accurate Lung Segmentor on Chest X-Rays Using Criss-Cross Attention and Customized Radiorealistic Abnormalities Generation
• SpecTr: Spectral Transformer for Hyperspectral Pathology Image Segmentation
• PTNet: A High-Resolution Infant MRI Synthesizer Based on Transformer
• Eformer: Edge Enhancement based Transformer for Medical Image Denoising
• TransClaw U-Net: Claw U-Net with Transformers for Medical Image Segmentation
• Holistically Explainable Vision Transformers
• ReconFormer: Accelerated MRI Reconstruction Using Recurrent Transformer
• Detecting Adverse Drug Reactions from Twitter through Domain-Specific Preprocessing and BERT Ensembling
• Transformer Networks for Data Augmentation of Human Physical Activity Recognition
• Low-Dose CT Denoising via Sinogram Inner-Structure Transformer
• Spach Transformer: Spatial and Channel-wise Transformer Based on Local and Global Self-attentions for PET Image Denoising
• A Deep Learning Approach Using Masked Image Modeling for Reconstruction of Undersampled K-spaces

Cited by in corpus (3)

• Advanced Deep Learning and Large Language Models: Comprehensive Insights for Cancer Detection
• CogniAlign: Word-Level Multimodal Speech Alignment with Gated Cross-Attention for Alzheimer's Detection
• Interpretable Auto Window Setting for Deep-Learning-Based CT Analysis