Representation Learning for Electronic Health Records

Weng, Wei-Hung; Szolovits, Peter

doi:10.48550/arxiv.1909.09248

Cited by 3 publications

(4 citation statements)

References 85 publications

(139 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Second, the epistemic equity of the models used to guide clinical care -our concern here -is obviously not the only kind of equity healthcare must consider. Unwarranted variation in clinical outcomes may arise from a wide diversity of procedural, cultural, social, economic, political, and regulatory factors that operate outside the realm of evidence-guided practice and need to be addressed independently from it 4,14,20,21,[21][22][23][24][25][26][27][28][29][30] . In focusing on epistemic equity we are not denying the importance of other kinds.…”

Section: Discussionmentioning

confidence: 99%

“…This approach is applicable to any model, whether conventional or machine learning-based, any metric of performance and its disparity, and any method of representation learning [14][15][16][17] . It leaves the nature of the remediation open, to be chosen as specific circumstances dictate, and distinguishes remediation from the calibration used to guide it.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Representational Ethical Model Calibration

Carruthers¹,

Straw²,

Ruffle³

et al. 2022

Preprint

View full text Add to dashboard Cite

Equity is widely held to be fundamental to the ethics of healthcare. In the context of clinical decision-making, it rests on the comparative fidelity of the intelligence -evidence-based or intuitive -guiding the management of each individual patient. Though brought to recent attention by the individuating power of contemporary machine learning, such epistemic equity arises in the context of any decision guidance, whether traditional or innovative. Yet no general framework for its quantification, let alone assurance, currently exists. Here we formulate epistemic equity in terms of model fidelity evaluated over learnt multi-dimensional representations of identity crafted to maximise the captured diversity of the population, introducing a comprehensive framework for Representational Ethical Model Calibration. We demonstrate use of the framework on large-scale multimodal data from UK Biobank to derive diverse representations of the population, quantify model performance, and institute responsive remediation. We offer our approach as a principled solution to quantifying and assuring epistemic equity in healthcare, with applications across the research, clinical, and regulatory domains.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Representational Ethical Model Calibration

Carruthers¹,

Straw²,

Ruffle³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Electronic health record (EHR) is a collection of patient and population electronically stored health information in a digital format that may include demographics, medical history, medication and allergies, immunization status, laboratory test results, radiology images, vital signs, personal statistics like age and weight, and billing information. One can check [219,261] for details about EHR with deep learning. Assessing such records may be restricted to limited organizations, which hinders its widespread to the public.…”

Section: Unstructured Data For Pre-trained Language Modelsmentioning

confidence: 99%

Pre-trained Language Models in Biomedical Domain: A Systematic Survey

Wang¹,

Xie²,

Pei³

et al. 2021

Preprint

View full text Add to dashboard Cite

Pre-trained language models (PLMs) have been the de facto paradigm for most natural language processing (NLP) tasks. This also benefits biomedical domain: researchers from informatics, medicine, and computer science (CS) communities proposes various PLMs trained on biomedical datasets, e.g., biomedical text, electronic health records, protein, and DNA sequences for various biomedical tasks. However, the cross-discipline characteristics of biomedical PLMs hinder their spreading among communities; some existing works are isolated from each other without comprehensive comparison and discussions. It expects a survey that not only systematically reviews recent advances of biomedical PLMs and their applications but also standardizes terminology and benchmarks. In this paper, we summarize the recent progress of pre-trained language models in the biomedical domain and their applications in biomedical downstream tasks. Particularly, we discuss the motivations and propose a taxonomy of existing biomedical PLMs. Their applications in biomedical downstream tasks are exhaustively discussed. At last, we illustrate various limitations and future trends, which we hope can provide inspiration for the future research of the research community.CCS Concepts: • Computing methodologies → Natural language processing; Natural language generation; Neural networks; Bio-inspired approaches.

show abstract

“…For instance, it has been employed in analysis of electronic health records in [6] to enable personalized disease progression prediction. More recently, self-supervised learning of electronic health records was employed to facilitate downstream tasks such as patient similarity and disease prediction [7].…”

Section: Introductionmentioning

confidence: 99%

EmbedGEM: A framework to evaluate the utility of embeddings for genetic discovery

Mukherjee,

McCaw,

Pei

et al. 2023

Preprint

View full text Add to dashboard Cite

Machine learning derived embeddings are a compressed representation of high content data modalities obtained through deep learning models[1]. Embeddings have been hypothesized to capture detailed information about disease states and have been qualitatively shown to be useful in genetic discovery. Despite their promise, embeddings have some drawbacks: i) they are often confounded by covariates, and ii) their disease relevance is hard to ascertain. In this work we describe a framework to systematically evaluate the utility of embeddings in genetic discovery called EmbedGEM (EmbeddingGeneticEvaluationMethods). Although, motivated by applications to embeddings, EmbedGEM is equally applicable for other multivariate traits as well.EmbedGEM focuses on comparing embeddings along two axes: i) heritability of the embeddings, and ii) ability to identify ‘disease relevant’ variants. We use the number of genome-wide significant signals and mean/median chi-square statistic as a proxy for the heritability of multivariate traits. To evaluate disease relevance, we compute polygenic risk scores for each orthogonalized component of the embedding (or multivariate comparators) and evaluate their association with a held-out set of patients with high-confidence disease traits. While we introduce some relatively straightforward ways to evaluate heritability and disease relevance, we foresee that our framework can be easily extended by adding more metrics.We demonstrate the utility of EmbedGEM by using it to evaluate embedding and non-embedding traits in two separate datasets: i) a synthetic dataset simulated to demonstrate the ability of the framework to correctly rank traits based on their heritability and disease relevance, ii) data from the UK Biobank focused on NAFLD relevant traits. EmbedGEM is implemented in the form of an easy to use Python-based workflow (https://github.com/insitro/EmbedGEM).

show abstract

Representation Learning for Electronic Health Records

Cited by 3 publications

References 85 publications

Representational Ethical Model Calibration

Representational Ethical Model Calibration

Pre-trained Language Models in Biomedical Domain: A Systematic Survey

EmbedGEM: A framework to evaluate the utility of embeddings for genetic discovery

Contact Info

Product

Resources

About