Explainable machine learning for neoplasms diagnosis via electrocardiograms: an externally validated study

Background: Neoplasms remains a leading cause of mortality worldwide, with timely diagnosis being crucial for improving patient outcomes. Current diagnostic methods are often invasive, costly, and inaccessible to many populations. Electrocardiogram (ECG) data, widely available and non-invasive, has the potential to serve as a tool for neoplasms diagnosis by using physiological changes in cardiovascular function associated with neoplastic prescences. Methods: This study explores the application of machine learning models to analyze ECG features for the diagnosis of neoplasms. We developed a pipeline integrating tree-based models with Shapley values for explainability. The model was trained and internally validated and externally validated on a second large-scale independent external cohort to ensure robustness and generalizability. Findings: The results demonstrate that ECG data can effectively capture neoplasms-associated cardiovascular changes, achieving high performance in both internal testing and external validation cohorts. Shapley values identified key ECG features influencing model predictions, revealing established and novel cardiovascular markers linked to neoplastic conditions. This non-invasive approach provides a cost-effective and scalable alternative for the diagnosis of neoplasms, particularly in resource-limited settings. Similarly, useful for the management of secondary cardiovascular effects given neoplasms therapies. Interpretation: This study highlights the feasibility of leveraging ECG signals and machine learning to enhance neoplasms diagnostics. By offering interpretable insights into cardio-neoplasms interactions, this approach bridges existing gaps in non-invasive diagnostics and has implications for integrating ECG-based tools into broader neoplasms diagnostic frameworks, as well as neoplasms therapy management.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers

Vision transformers (ViTs) can be trained using various learning paradigms, from fully supervised to self-supervised. Diverse training protocols often result in significantly different feature spaces, which are usually compared through alignment analysis. However, current alignment measures quantify this relationship in terms of a single scalar value, obscuring the distinctions between common and unique features in pairs of representations that share the same scalar alignment. We address this limitation by combining alignment analysis with concept discovery, which enables a breakdown of alignment into single concepts encoded in feature space. This fine-grained comparison reveals both universal and unique concepts across different representations, as well as the internal structure of concepts within each of them. Our methodological contributions address two key prerequisites for concept-based alignment: 1) For a description of the representation in terms of concepts that faithfully capture the geometry of the feature space, we define concepts as the most general structure they can possibly form - arbitrary manifolds, allowing hidden features to be described by their proximity to these manifolds. 2) To measure distances between concept proximity scores of two representations, we use a generalized Rand index and partition it for alignment between pairs of concepts. We confirm the superiority of our novel concept definition for alignment analysis over existing linear baselines in a sanity check. The concept-based alignment analysis of representations from four different ViTs reveals that increased supervision correlates with a reduction in the semantic structure of learned representations.

Electrocardiogram-based diagnosis of liver diseases: an externally validated and explainable machine learning approach

Background: Liver diseases are a major global health concern, often diagnosed using resource-intensive methods. Electrocardiogram (ECG) data, widely accessible and non-invasive, offers potential as a diagnostic tool for liver diseases, leveraging the physiological connections between cardiovascular and hepatic health. Methods: This study applies machine learning models to ECG data for the diagnosis of liver diseases. The pipeline, combining tree-based models with Shapley values for explainability, was trained, internally validated, and externally validated on an independent cohort, demonstrating robust generalizability. Findings: Our results demonstrate the potential of ECG to derive biomarkers to diagnose liver diseases. Shapley values revealed key ECG features contributing to model predictions, highlighting already known connections between cardiovascular biomarkers and hepatic conditions as well as providing new ones. Furthermore, our approach holds promise as a scalable and affordable solution for liver disease detection, particularly in resource-limited settings. Interpretation: This study underscores the feasibility of leveraging ECG features and machine learning to enhance the diagnosis of liver diseases. By providing interpretable insights into cardiovascular-liver interactions, the approach bridges existing gaps in non-invasive diagnostics, offering implications for broader systemic disease monitoring.

CardioLab: Laboratory Values Estimation and Monitoring from Electrocardiogram Signals -- A Multimodal Deep Learning Approach

Background: Laboratory values are fundamental to medical diagnosis and management, but acquiring these values can be costly, invasive, and time-consuming. While electrocardiogram (ECG) patterns have been linked to certain laboratory abnormalities, the comprehensive modeling of these relationships remains underexplored. Methods: We utilize MIMIC-IV dataset to develop multimodal deep-learning models to demonstrate the feasibility of estimating (real-time) and monitoring (predict at future intervals) laboratory value abnormalities from ECG waveforms, demographics, biometrics, and vital signs. Results: The models exhibit a strong predictive performance with AUROC scores above 0.70 in a statistically significant manner for 23 laboratory values in the estimation setting and up to 26 values in the monitoring setting. Most notably, the accurately predictable values encompassing abnormalities across diverse physiological categories such as cardiac, renal, hematological, metabolic, immunological and coagulation. To name examples, for estimation NTproBNP (>353 pg/mL) with 0.882, whereas for monitoring at 30 minutes Urea nitrogen (<6 mg/dL) with 0.851, at 60 minutes creatinine (<0.5 mg/dL) with 0.85, and at 120 minutes hemoglobin (>17.5 g/dL) with 0.821. Conclusions: This study provides first evidence for the feasibility of using ECG data alongside clinical routine data for the real-time estimation and monitoring of laboratory value abnormalities, which could provide a non-invasive, cost-effective supplement to traditional laboratory testing, with strong implications for enhanced patient monitoring and early intervention. Further validation could facilitate their integration into routine clinical practice.

Estimation of Cardiac and Non-cardiac Diagnosis from Electrocardiogram Features

Introduction: Ensuring timely and accurate diagnosis of medical conditions is paramount for effective patient care. Electrocardiogram (ECG) signals are fundamental for evaluating a patient's cardiac health and are readily available. Despite this, little attention has been given to the remarkable potential of ECG data in detecting non-cardiac conditions. Methods: In our study, we used publicly available datasets (MIMIC-IV-ECG-ICD and ECG-VIEW II) to investigate the feasibility of inferring general diagnostic conditions from ECG features. To this end, we trained a tree-based model (XGBoost) based on ECG features and basic demographic features to estimate a wide range of diagnoses, encompassing both cardiac and non-cardiac conditions. Results: Our results demonstrate the reliability of estimating 23 cardiac as well as 21 non-cardiac conditions above 0.7 AUROC in a statistically significant manner across a wide range of physiological categories. Our findings underscore the predictive potential of ECG data in identifying well-known cardiac conditions. However, even more striking, this research represents a pioneering effort in systematically expanding the scope of ECG-based diagnosis to conditions not traditionally associated with the cardiac system.

MDS-ED: Multimodal Decision Support in the Emergency Department -- a Benchmark Dataset for Diagnoses and Deterioration Prediction in Emergency Medicine

Background: Benchmarking medical decision support algorithms often struggles due to limited access to datasets, narrow prediction tasks, and restricted input modalities. These limitations affect their clinical relevance and performance in high-stakes areas like emergency care, complicating replication, validation, and improvement of benchmarks. Methods: We introduce a dataset based on MIMIC-IV, benchmarking protocol, and initial results for evaluating multimodal decision support in the emergency department (ED). We use diverse data modalities from the first 1.5 hours of patient arrival, including demographics, biometrics, vital signs, lab values, and electrocardiogram waveforms. We analyze 1443 clinical labels across two contexts: predicting diagnoses with ICD-10 codes and forecasting patient deterioration. Results: Our multimodal diagnostic model achieves an AUROC score over 0.8 in a statistically significant manner for 357 out of 1428 conditions, including cardiac issues like myocardial infarction and non-cardiac conditions such as renal disease and diabetes. The deterioration model scores above 0.8 in a statistically significant manner for 13 out of 15 targets, including critical events like cardiac arrest and mechanical ventilation, ICU admission as well as short- and long-term mortality. Incorporating raw waveform data significantly improves model performance, which represents one of the first robust demonstrations of this effect. Conclusions: This study highlights the uniqueness of our dataset, which encompasses a wide range of clinical tasks and utilizes a comprehensive set of features collected early during the emergency after arriving at the ED. The strong performance, as evidenced by high AUROC scores across diagnostic and deterioration targets, underscores the potential of our approach to revolutionize decision-making in acute and emergency medicine.

CardioLab: Laboratory Values Estimation from Electrocardiogram Features -- An Exploratory Study

Introduction: Laboratory value represents a cornerstone of medical diagnostics, but suffers from slow turnaround times, and high costs and only provides information about a single point in time. The continuous estimation of laboratory values from non-invasive data such as electrocardiogram (ECG) would therefore mark a significant frontier in healthcare monitoring. Despite its transformative potential, this domain remains relatively underexplored within the medical community. Methods: In this preliminary study, we used a publicly available dataset (MIMIC-IV-ECG) to investigate the feasibility of inferring laboratory values from ECG features and patient demographics using tree-based models (XGBoost). We define the prediction task as a binary prediction problem of predicting whether the lab value falls into low or high abnormalities. The model performance can then be assessed using AUROC. Results: Our findings demonstrate promising results in the estimation of laboratory values related to different organ systems based on a small yet comprehensive set of features. While further research and validation are warranted to fully assess the clinical utility and generalizability of ECG-based estimation in healthcare monitoring, our findings lay the groundwork for future investigations into approaches to laboratory value estimation using ECG data. Such advancements hold promise for revolutionizing predictive healthcare applications, offering faster, non-invasive, and more affordable means of patient monitoring.

CausalConceptTS: Causal Attributions for Time Series Classification using High Fidelity Diffusion Models

Despite the excelling performance of machine learning models, understanding the decisions of machine learning models remains a long-standing goal. While commonly used attribution methods in explainable AI attempt to address this issue, they typically rely on associational rather than causal relationships. In this study, within the context of time series classification, we introduce a novel framework to assess the causal effect of concepts, i.e., predefined segments within a time series, on specific classification outcomes. To achieve this, we leverage state-of-the-art diffusion-based generative models to estimate counterfactual outcomes. Our approach compares these causal attributions with closely related associational attributions, both theoretically and empirically. We demonstrate the insights gained by our approach for a diverse set of qualitatively different time series classification tasks. Although causal and associational attributions might often share some similarities, in all cases they differ in important details, underscoring the risks associated with drawing causal conclusions from associational data alone. We believe that the proposed approach is widely applicable also in other domains, particularly where predefined segmentations are available, to shed some light on the limits of associational attributions.

Assessing the importance of long-range correlations for deep-learning-based sleep staging

This study aims to elucidate the significance of long-range correlations for deep-learning-based sleep staging. It is centered around S4Sleep(TS), a recently proposed model for automated sleep staging. This model utilizes electroencephalography (EEG) as raw time series input and relies on structured state space sequence (S4) models as essential model component. Although the model already surpasses state-of-the-art methods for a moderate number of 15 input epochs, recent literature results suggest potential benefits from incorporating very long correlations spanning hundreds of input epochs. In this submission, we explore the possibility of achieving further enhancements by systematically scaling up the model's input size, anticipating potential improvements in prediction accuracy. In contrast to findings in literature, our results demonstrate that augmenting the input size does not yield a significant enhancement in the performance of S4Sleep(TS). These findings, coupled with the distinctive ability of S4 models to capture long-range dependencies in time series data, cast doubt on the diagnostic relevance of very long-range interactions for sleep staging.

Decoupling Pixel Flipping and Occlusion Strategy for Consistent XAI Benchmarks

Feature removal is a central building block for eXplainable AI (XAI), both for occlusion-based explanations (Shapley values) as well as their evaluation (pixel flipping, PF). However, occlusion strategies can vary significantly from simple mean replacement up to inpainting with state-of-the-art diffusion models. This ambiguity limits the usefulness of occlusion-based approaches. For example, PF benchmarks lead to contradicting rankings. This is amplified by competing PF measures: Features are either removed starting with most influential first (MIF) or least influential first (LIF). This study proposes two complementary perspectives to resolve this disagreement problem. Firstly, we address the common criticism of occlusion-based XAI, that artificial samples lead to unreliable model evaluations. We propose to measure the reliability by the R(eference)-Out-of-Model-Scope (OMS) score. The R-OMS score enables a systematic comparison of occlusion strategies and resolves the disagreement problem by grouping consistent PF rankings. Secondly, we show that the insightfulness of MIF and LIF is conversely dependent on the R-OMS score. To leverage this, we combine the MIF and LIF measures into the symmetric relevance gain (SRG) measure. This breaks the inherent connection to the underlying occlusion strategy and leads to consistent rankings. This resolves the disagreement problem, which we verify for a set of 40 different occlusion strategies.