Fusion of medical imaging and electronic health records using deep learning: a systematic review and implementation guidelines

Abstract

Advancements in deep learning techniques carry the potential to make significant contributions to healthcare, particularly in fields that utilize medical imaging for diagnosis, prognosis, and treatment decisions. The current state-of-the-art deep learning models for radiology applications consider only pixel-value information without data informing clinical context. Yet in practice, pertinent and accurate non-imaging data based on the clinical history and laboratory data enable physicians to interpret imaging findings in the appropriate clinical context, leading to a higher diagnostic accuracy, informative clinical decision making, and improved patient outcomes. To achieve a similar goal using deep learning, medical imaging pixel-based models must also achieve the capability to process contextual data from electronic health records (EHR) in addition to pixel data. In this paper, we describe different data fusion techniques that can be applied to combine medical imaging with EHR, and systematically review medical data fusion literature published between 2012 and 2020. We conducted a systematic search on PubMed and Scopus for original research articles leveraging deep learning for fusion of multimodality data. In total, we screened 985 studies and extracted data from 17 papers. By means of this systematic review, we present current knowledge, summarize important results and provide implementation guidelines to serve as a reference for researchers interested in the application of multimodal fusion in medical imaging.

Keywords: Data integration; Machine learning; Medical imaging.

Fig. 1. Timeline of publications in deep learning for medical imaging.

Timeline showing growth in publications on deep learning for medical imaging, found by using the same search criteria on PubMed and Scopus. The figure shows that fusion has only constituted a small, but growing, subset of medical deep learning literature.

Fig. 2. Fusion strategies using deep learning.

Model architecture for different fusion strategies. Early fusion (left figure) concatenates original or extracted features at the input level. Joint fusion (middle figure) also joins features at the input level, but the loss is propagated back to the feature extracting model. Late fusion (right figure) aggregates predictions at the decision level.

Fig. 3. PRISMA flowchart of the study selection process.

Two authors independently screened all records for eligibility. Seventeen studies were included in the systematic review.