Explainable AI for Infection Prevention and Control: Modeling CPE Acquisition and Patient Outcomes in an Irish Hospital with Transformers

Carbapenemase-Producing Enterobacteriace poses a critical concern for infection prevention and control in hospitals. However, predictive modeling of previously highlighted CPE-associated risks such as readmission, mortality, and extended length of stay (LOS) remains underexplored, particularly with modern deep learning approaches. This study introduces an eXplainable AI modeling framework to investigate CPE impact on patient outcomes from Electronic Medical Records data of an Irish hospital. We analyzed an inpatient dataset from an Irish acute hospital, incorporating diagnostic codes, ward transitions, patient demographics, infection-related variables and contact network features. Several Transformer-based architectures were benchmarked alongside traditional machine learning models. Clinical outcomes were predicted, and XAI techniques were applied to interpret model decisions. Our framework successfully demonstrated the utility of Transformer-based models, with TabTransformer consistently outperforming baselines across multiple clinical prediction tasks, especially for CPE acquisition (AUROC and sensitivity). We found infection-related features, including historical hospital exposure, admission context, and network centrality measures, to be highly influential in predicting patient outcomes and CPE acquisition risk. Explainability analyses revealed that features like "Area of Residence", "Admission Ward" and prior admissions are key risk factors. Network variables like "Ward PageRank" also ranked highly, reflecting the potential value of structural exposure information. This study presents a robust and explainable AI framework for analyzing complex EMR data to identify key risk factors and predict CPE-related outcomes. Our findings underscore the superior performance of the Transformer models and highlight the importance of diverse clinical and network features.

Blockchain Transaction Fee Forecasting: A Comparison of Machine Learning Methods

Gas is the transaction-fee metering system of the Ethereum network. Users of the network are required to select a gas price for submission with their transaction, creating a risk of overpaying or delayed/unprocessed transactions in this selection. In this work, we investigate data in the aftermath of the London Hard Fork and shed insight into the transaction dynamics of the net-work after this major fork. As such, this paper provides an update on work previous to 2019 on the link between EthUSD BitUSD and gas price. For forecasting, we compare a novel combination of machine learning methods such as Direct Recursive Hybrid LSTM, CNNLSTM, and Attention LSTM. These are combined with wavelet threshold denoising and matrix profile data processing toward the forecasting of block minimum gas price, on a 5-min timescale, over multiple lookaheads. As the first application of the matrix profile being applied to gas price data and forecasting we are aware of, this study demonstrates that matrix profile data can enhance attention-based models however, given the hardware constraints, hybrid models outperformed attention and CNNLSTM models. The wavelet coherence of inputs demonstrates correlation in multiple variables on a 1 day timescale, which is a deviation of base free from gas price. A Direct-Recursive Hybrid LSTM strategy outperforms other models. Hybrid models have favourable performance up to a 20 min lookahead with performance being comparable to attention models when forecasting 25/50-min ahead. Forecasts over a range of lookaheads allow users to make an informed decision on gas price selection and the optimal window to submit their transaction in without fear of their transaction being rejected. This, in turn, gives more detailed insight into gas price dynamics than existing recommenders, oracles and forecasting approaches, which provide simple heuristics or limited lookahead horizons.