EHR-ML: A data-driven framework for designing machine learning applications with electronic health records

Abstract

The healthcare landscape is experiencing a transformation with the integration of Artificial Intelligence (AI) into traditional analytic workflows. However, its integration faces challenges resulting in a crisis of generalisability. Key obstacles include; 1) Insufficient consideration of local contextual factors, such as institution-specific data formats, practices, and protocols, which can lead to variability in clinical practices across different institutions. 2) ad-hoc data preparation and design of machine learning strategies. 3) manual subjective adjustment of design parameters resulting in sub-optimal performance. 4) EHR specific challenges regarding data biases affecting the model outcomes and unique intermittent temporal nature of the data necessitating specialised handling 5) lack of cross-institutional data validations. To address these challenges, EHR-ML, provides an easy to use structured framework for designing optimum machine learning applications in a data-driven manner. The framework supports ingestion of local institutional electronic health records (EHRs) and process standardisation. The study design and parameter optimisation is done in a fully data-driven evidence-based approach. It seamlessly integrating with existing quality control tools. To handle the unique characteristics of the EHR data, it offers customisable ensemble models. It enables the acquisition of EHR data from diverse systems and harmonise them into common formats following international standards. The effectiveness of the EHR-ML is demonstrated through a series of case studies. These studies highlight its capability to develop high-performance models in a fully automated manner, consistently surpassing the performance of traditional methodologies. Furthermore, they exhibited strong generalisability across diverse healthcare settings. EHR-ML enhances the clinical relevance and accuracy of predictive models by incorporating local context into machine learning applications. Additionally, by providing an user-friendly fully-automated framework, it facilitates rapid hypothesis testing aimed to generate localised biomedical knowledge. The graphical abstract illustrates the architecture and key components of EHR-ML, a machine learning framework designed for predictive modelling using EHR. A) Patient Timeline: This segment shows the key concepts in longitudinal patient timeline such as hospital admission to discharge, and ICU admission. It also shows data windows for collecting data for modelling purposes. The data collected during these windows is used for training machine learning models to predict clinical outcomes, such as mortality and length of stay (LOS). B) Ensemble Architecture: The proposed ensemble learning framework integrates multiple machine learning models organised in two different layers where the model outputs from layer-one are combined to generate predictions in the second-layer. C-F) These sections visualise different analyses that are part of the EHR-ML analytics suite including Class Ratio Analysis, Sample Size Analysis, Data Window Analysis, and Standardisation Analysis. In essence, EHR-ML framework facilitates seamless utilisation of institution-specific data for clinical outcome predictions using machine learning, addressing the challenge of generalisability in healthcare AI applications. • Provides a reproducible and easy to use standardised framework for designing tailored machine learning applications. • Performs parameter optimisation in a fully data-driven, evidence-based manner. • Facilitates utilisation of institutional electronic health records (EHRs). • It provides end-to-end processing of data starting from quality control to predictive modelling and validations. • Provides customisable ensemble models to handle the unique characteristics of the EHR.

Topics & Concepts