Unifying Diagnosis Identification and Prediction Method Embedding the Disease Ontology Structure From Electronic Medical Records

Abstract

ObjectiveThe reasonable classification of a large number of distinct diagnosis codes can clarify patient diagnostic information and help clinicians to improve their ability to assign and target treatment for primary diseases. Our objective is to identify and predict a unifying diagnosis (UD) from electronic medical records (EMRs).MethodsWe screened 4,418 sepsis patients from a public MIMIC-III database and extracted their diagnostic information for UD identification, their demographic information, laboratory examination information, chief complaint, and history of present illness information for UD prediction. We proposed a data-driven UD identification and prediction method (UDIPM) embedding the disease ontology structure. First, we designed a set similarity measure method embedding the disease ontology structure to generate a patient similarity matrix. Second, we applied affinity propagation clustering to divide patients into different clusters, and extracted a typical diagnosis code co-occurrence pattern from each cluster. Furthermore, we identified a UD by fusing visual analysis and a conditional co-occurrence matrix. Finally, we trained five classifiers in combination with feature fusion and feature selection method to unify the diagnosis prediction.ResultsThe experimental results on a public electronic medical record dataset showed that the UDIPM could extracted a typical diagnosis code co-occurrence pattern effectively, identified and predicted a UD based on patients' diagnostic and admission information, and outperformed other fusion methods overall.ConclusionsThe accurate identification and prediction of the UD from a large number of distinct diagnosis codes and multi-source heterogeneous patient admission information in EMRs can provide a data-driven approach to assist better coding integration of diagnosis.

Domain Knowledge-Driven Generation of Synthetic Healthcare Data

“…The framework uses an Autoencoder as the representation learning module, then a GAN is used for generating data while we have the clinical validity as a ruling-out mechanism. We aim to integrate state-of-the-art representation learning techniques such as graph neural networks (GNNs) and graph convolutional transformers (GCTs) to extract latent structures and relations from EHR data [3].…”

Untitled

“…The intersection of Big Data with cutting-edge technology heralds a new era of healthcare, where datadriven insights lead to more informed decision-making, optimized health outcomes, and the realization of a truly personalized medicine paradigm. Moreover, the future of healthcare Big Data analytics will likely be characterized by even more sophisticated AI applications, including natural language processing and deep learning, further enhancing the ability to derive actionable insights from complex data sets (Chen, Guo, Lu, & Ding, 2022;Joos et al, 2019;Malhi, Bell, Boyce, Mulder, & Porter, 2020). Additionally, the development of more advanced interoperability standards and secure data exchange protocols will continue to facilitate the efficient and ethical use of healthcare data.…”

“…2020 Emphasis on the need for robust data analytics capabilities and sophisticated technology infrastructures to harness Big Data effectively (Malhi, Bell, Boyce, Mulder, & Porter, 2020). 2022 Further advancements in AI applications and the development of more advanced interoperability standards and secure data exchange protocols (Chen, Guo, Lu, & Ding, 2022).…”

Paradigm shift required for translational research on the brain

“…Notably, all multiomics, neuroimaging, and AI methods were not integrated; however, there were some uses of partial integration for clinical neuroscience. For example, multimodal neuroimaging (MRI and PET) and machine learning have been integrated to predict psychiatric disorders and neurodegenerative diseases 205 – 207 . PET and DL (convolutional neural network) have been integrated to differentiate patients with AD 208 .…”