Implementing high‐dimensional propensity score principles to improve confounder adjustment in
            UK
            electronic health records

Recent advancement in EHR-based (Electronic Health Record) systems has resulted in producing data at an unprecedented rate. The complex, growing, and high-dimensional data available in EHRs creates great opportunities for machine learning techniques such as clustering. Cluster analysis often requires dimension reduction to achieve efficient processing time and mitigate the curse of dimensionality. Given a wide range of techniques for dimension reduction and cluster analysis, it is not straightforward to identify which combination of techniques from both families leads to the desired result. The ability to derive useful and precise insights from EHRs requires a deeper understanding of the data, intermediary results, configuration parameters, and analysis processes. Although these tasks are often tackled separately in existing studies, we present a visual analytics (VA) system, called Visual Analytics for Cluster Analysis and Dimension Reduction of High Dimensional Electronic Health Records (VALENCIA), to address the challenges of high-dimensional EHRs in a single system. VALENCIA brings a wide range of cluster analysis and dimension reduction techniques, integrate them seamlessly, and make them accessible to users through interactive visualizations. It offers a balanced distribution of processing load between users and the system to facilitate the performance of high-level cognitive tasks in such a way that would be difficult without the aid of a VA system. Through a real case study, we have demonstrated how VALENCIA can be used to analyze the healthcare administrative dataset stored at ICES. This research also highlights what needs to be considered in the future when developing VA systems that are designed to derive deep and novel insights into EHRs.

Download Full-text

Learning and Visualizing Chronic Latent Representations Using Electronic Health Records

10.21203/rs.3.rs-968569/v1 ◽

2021 ◽

Author(s):

David Chushig-Muzo ◽

Cristina Soguero-Ruiz ◽

Pablo de Miguel Bohoyo ◽

Inmaculada Mora-Jiménez

Keyword(s):

Health Status ◽

Electronic Health Records ◽

Chronic Conditions ◽

Dimensional Space ◽

High Dimensional ◽

Diabetic Patients ◽

Two Dimensional ◽

Health Records ◽

Electronic Health ◽

Latent Representations

Abstract Background: Nowadays, patients with chronic diseases such as diabetes and hypertension have reached alarming numbers worldwide. These diseases increase the risk of developing acute complications and involve a substantial economic burden and demand for health resources. The widespread adoption of Electronic Health Records (EHRs) is opening great opportunities for supporting decision-making. Nevertheless, data extracted from EHRs are complex (heterogeneous, high-dimensional and usually noisy), hampering the knowledge extraction with conventional approaches. Methods: We propose the use of the Denoising Autoencoder (DAE), a Machine Learning (ML) technique allowing to transform high-dimensional data into latent representations (LRs), thus addressing the main challenges with clinical data. We explore in this work how the combination of LRs with a visualization method can be used to map the patient data in a two-dimensional space, gaining knowledge about the distribution of patients with different chronic conditions. Furthermore, this representation can be also used to characterize the patient's health status evolution, which is of paramount importance in the clinical setting. Results: To obtain clinical LRs, we considered real-world data extracted from EHRs linked to the University Hospital of Fuenlabrada in Spain. Experimental results showed the great potential of DAEs to identify patients with clinical patterns linked to hypertension, diabetes and multimorbidity. The procedure allowed us to find patients with the same main chronic disease but different clinical characteristics. Thus, we identified two kinds of diabetic patients with differences in their drug therapy (insulin and non-insulin dependant), and also a group of women affected by hypertension and gestational diabetes. We also present a proof of concept for mapping the health status evolution of synthetic patients when considering the most significant diagnoses and drugs associated with chronic patients. Conclusions: Our results highlighted the value of ML techniques to extract clinical knowledge, supporting the identification of patients with certain chronic conditions. Furthermore, the patient's health status progression on the two-dimensional space might be used as a tool for clinicians aiming to characterize health conditions and identify their more relevant clinical codes.

Download Full-text

A Stochastic Multivariate Irregularly Sampled Time Series Imputation Method for Electronic Health Records

BioMedInformatics ◽

10.3390/biomedinformatics1030011 ◽

2021 ◽

Vol 1 (3) ◽

pp. 166-181

Author(s):

Muhammad Adib Uz Zaman ◽

Dongping Du

Keyword(s):

Neural Networks ◽

Time Series ◽

Electronic Health Records ◽

Missing Values ◽

Time Series Data ◽

Temporal Information ◽

Series Data ◽

High Dimensional ◽

Health Records ◽

Electronic Health

Electronic health records (EHRs) can be very difficult to analyze since they usually contain many missing values. To build an efficient predictive model, a complete dataset is necessary. An EHR usually contains high-dimensional longitudinal time series data. Most commonly used imputation methods do not consider the importance of temporal information embedded in EHR data. Besides, most time-dependent neural networks such as recurrent neural networks (RNNs) inherently consider the time steps to be equal, which in many cases, is not appropriate. This study presents a method using the gated recurrent unit (GRU), neural ordinary differential equations (ODEs), and Bayesian estimation to incorporate the temporal information and impute sporadically observed time series measurements in high-dimensional EHR data.

Download Full-text

A Nuisance-Free Inference Procedure Accounting for the Unknown Missingness with Application to Electronic Health Records

Entropy ◽

10.3390/e22101154 ◽

2020 ◽

Vol 22 (10) ◽

pp. 1154

Author(s):

Jiwei Zhao ◽

Chi Chen

Keyword(s):

Electronic Health Records ◽

Missing Values ◽

Outcome Variable ◽

High Dimensional ◽

Real World Data ◽

Inference Procedure ◽

Health Records ◽

Missingness Mechanism ◽

Patient Reported ◽

Electronic Health

We study how to conduct statistical inference in a regression model where the outcome variable is prone to missing values and the missingness mechanism is unknown. The model we consider might be a traditional setting or a modern high-dimensional setting where the sparsity assumption is usually imposed and the regularization technique is popularly used. Motivated by the fact that the missingness mechanism, albeit usually treated as a nuisance, is difficult to specify correctly, we adopt the conditional likelihood approach so that the nuisance can be completely ignored throughout our procedure. We establish the asymptotic theory of the proposed estimator and develop an easy-to-implement algorithm via some data manipulation strategy. In particular, under the high-dimensional setting where regularization is needed, we propose a data perturbation method for the post-selection inference. The proposed methodology is especially appealing when the true missingness mechanism tends to be missing not at random, e.g., patient reported outcomes or real world data such as electronic health records. The performance of the proposed method is evaluated by comprehensive simulation experiments as well as a study of the albumin level in the MIMIC-III database.

Download Full-text

Early Detection of Health Changes in the Elderly Using In-Home Multi-Sensor Data Streams

ACM Transactions on Computing for Healthcare ◽

10.1145/3448671 ◽

2021 ◽

Vol 2 (3) ◽

pp. 1-23

Author(s):

Wenlong Wu ◽

James M. Keller ◽

Marjorie Skubic ◽

Mihail Popescu ◽

Kari R. Lane

Keyword(s):

Electronic Health Records ◽

Strong Support ◽

Feature Space ◽

The Elderly ◽

Sensor Data ◽

High Dimensional ◽

Health Records ◽

Health Events ◽

Health Changes ◽

Electronic Health

The rapid aging of the population worldwide requires increased attention from healthcare providers and the entire society. For the elderly to live independently, many health issues related to old age, such as frailty and risk of falling, need increased attention and monitoring. When monitoring daily routines for older adults, it is desirable to detect the early signs of health changes before serious health events, such as hospitalizations, happen so that timely and adequate preventive care may be provided. By deploying multi-sensor systems in homes of the elderly, we can track trajectories of daily behaviors in a feature space defined using the sensor data. In this article, we investigate a methodology for tracking the evolution of the behavior trajectories over long periods (years) using high-dimensional streaming clustering and provide very early indicators of changes in health. If we assume that habitual behaviors correspond to clusters in feature space and diseases produce a change in behavior, albeit not highly specific, tracking trajectory deviations can provide hints of early illness. Retrospectively, we visualize the streaming clustering results and track how the behavior clusters evolve in feature space with the help of two dimension-reduction algorithms: Principal Component Analysis and t-distributed Stochastic Neighbor Embedding. Moreover, our tracking algorithm in the original high-dimensional feature space generates early health warning alerts if a negative trend is detected in the behavior trajectory. We validated our algorithm on synthetic data and tested it on a pilot dataset of four TigerPlace residents monitored with a collection of motion, bed, and depth sensors over 10 years. We used the TigerPlace electronic health records to understand the residents’ behavior patterns and to evaluate the health warnings generated by our algorithm. The results obtained on the TigerPlace dataset show that most of the warnings produced by our algorithm can be linked to health events documented in the electronic health records, providing strong support for a prospective deployment of the approach.

Download Full-text