Peter Watkinson

Munib Mesinovic, Peter Watkinson, Tingting Zhu

Recent advancements in AI applications to healthcare have shown incredible promise in surpassing human performance in diagnosis and disease prognosis. With the increasing complexity of AI models, however, concerns regarding their opacity, potential biases, and the need for interpretability. To ensure trust and reliability in AI systems, especially in clinical risk prediction models, explainability becomes crucial. Explainability is usually referred to as an AI system's ability to provide a robust interpretation of its decision-making logic or the decisions themselves to human stakeholders. In clinical risk prediction, other aspects of explainability like fairness, bias, trust, and transparency also represent important concepts beyond just interpretability. In this review, we address the relationship between these concepts as they are often used together or interchangeably. This review also discusses recent progress in developing explainable models for clinical risk prediction, highlighting the importance of quantitative and clinical evaluation and validation across multiple common modalities in clinical practice. It emphasizes the need for external validation and the combination of diverse interpretability methods to enhance trust and fairness. Adopting rigorous testing, such as using synthetic datasets with known generative factors, can further improve the reliability of explainability methods. Open access and code-sharing resources are essential for transparency and reproducibility, enabling the growth and trustworthiness of explainable research. While challenges exist, an end-to-end approach to explainability in clinical risk prediction, incorporating stakeholders from clinicians to developers, is essential for success.

Munib Mesinovic, Peter Watkinson, Tingting Zhu

Machine learning applications for longitudinal electronic health records often forecast the risk of events at fixed time points, whereas survival analysis achieves dynamic risk prediction by estimating time-to-event distributions. Here, we propose a novel conditional variational autoencoder-based method, DySurv, which uses a combination of static and longitudinal measurements from electronic health records to estimate the individual risk of death dynamically. DySurv directly estimates the cumulative risk incidence function without making any parametric assumptions on the underlying stochastic process of the time-to-event. We evaluate DySurv on 6 time-to-event benchmark datasets in healthcare, as well as 2 real-world intensive care unit (ICU) electronic health records (EHR) datasets extracted from the eICU Collaborative Research (eICU) and the Medical Information Mart for Intensive Care database (MIMIC-IV). DySurv outperforms other existing statistical and deep learning approaches to time-to-event analysis across concordance and other metrics. It achieves time-dependent concordance of over 60% in the eICU case. It is also over 12% more accurate and 22% more sensitive than in-use ICU scores like Acute Physiology and Chronic Health Evaluation (APACHE) and Sequential Organ Failure Assessment (SOFA) scores. The predictive capacity of DySurv is consistent and the survival estimates remain disentangled across different datasets. Our interdisciplinary framework successfully incorporates deep learning, survival analysis, and intensive care to create a novel method for time-to-event prediction from longitudinal health records. We test our method on several held-out test sets from a variety of healthcare datasets and compare it to existing in-use clinical risk scoring benchmarks.

Munib Mesinovic, Soheila Molaei, Peter Watkinson et al.

Learning from longitudinal electronic health records is limited if it does not capture the temporal trajectories of the patient's state in a clinical setting. Graph models allow us to capture the hidden dependencies of the multivariate time-series when the graphs are constructed in a similar dynamic manner. Previous dynamic graph models require a pre-defined and/or static graph structure, which is unknown in most cases, or they only capture the spatial relations between the features. Furthermore in healthcare, the interpretability of the model is an essential requirement to build trust with clinicians. In addition to previously proposed attention mechanisms, there has not been an interpretable dynamic graph framework for data from multivariate electronic health records (EHRs). Here, we propose DynaGraph, an end-to-end interpretable contrastive graph model that learns the dynamics of multivariate time-series EHRs as part of optimisation. We validate our model in four real-world clinical datasets, ranging from primary care to secondary care settings with broad demographics, in challenging settings where tasks are imbalanced and multi-labelled. Compared to state-of-the-art models, DynaGraph achieves significant improvements in balanced accuracy and sensitivity over the nearest complex competitors in time-series or dynamic graph modelling across three ICU and one primary care datasets. Through a pseudo-attention approach to graph construction, our model also indicates the importance of clinical covariates over time, providing means for clinical validation.

Munib Mesinovic, Peter Watkinson, Tingting Zhu

Heart attack remain one of the greatest contributors to mortality in the United States and globally. Patients admitted to the intensive care unit (ICU) with diagnosed heart attack (myocardial infarction or MI) are at higher risk of death. In this study, we use two retrospective cohorts extracted from the eICU and MIMIC-IV databases, to develop a novel pseudo-dynamic machine learning framework for mortality prediction in the ICU with interpretability and clinical risk analysis. The method provides accurate prediction for ICU patients up to 24 hours before the event and provide time-resolved interpretability results. The performance of the framework relying on extreme gradient boosting was evaluated on a held-out test set from eICU, and externally validated on the MIMIC-IV cohort using the most important features identified by time-resolved Shapley values achieving AUCs of 91.0 (balanced accuracy of 82.3) for 6-hour prediction of mortality respectively. We show that our framework successfully leverages time-series physiological measurements by translating them into stacked static prediction problems to be robustly predictive through time in the ICU stay and can offer clinical insight from time-resolved interpretability

Henrique Aguiar, Mauro Santos, Peter Watkinson et al.

Recent years have seen an increased focus into the tasks of predicting hospital inpatient risk of deterioration and trajectory evolution due to the availability of electronic patient data. A common approach to these problems involves clustering patients time-series information such as vital sign observations) to determine dissimilar subgroups of the patient population. Most clustering methods assume time-invariance of vital-signs and are unable to provide interpretability in clusters that is clinically relevant, for instance, event or outcome information. In this work, we evaluate three different clustering models on a large hospital dataset of vital-sign observations from patients suffering from Chronic Obstructive Pulmonary Disease. We further propose novel modifications to deal with unevenly sampled time-series data and unbalanced class distribution to improve phenotype separation. Lastly, we discuss further avenues of investigation for models to learn patient subgroups with distinct behaviour and phenotype.

Rasheed el-Bouri, David Eyre, Peter Watkinson et al.

Accurate and reliable prediction of hospital admission location is important due to resource-constraints and space availability in a clinical setting, particularly when dealing with patients who come from the emergency department. In this work we propose a student-teacher network via reinforcement learning to deal with this specific problem. A representation of the weights of the student network is treated as the state and is fed as an input to the teacher network. The teacher network's action is to select the most appropriate batch of data to train the student network on from a training set sorted according to entropy. By validating on three datasets, not only do we show that our approach outperforms state-of-the-art methods on tabular data and performs competitively on image recognition, but also that novel curricula are learned by the teacher network. We demonstrate experimentally that the teacher network can actively learn about the student network and guide it to achieve better performance than if trained alone.