Automatic Assessment of Transcatheter Aortic Valve Implantation Results on Four-Dimensional Computed Tomography Images Using Artificial Intelligence

Transcatheter aortic valve implantation (TAVI) is a procedure to treat severe aortic stenosis. There are several clinical concerns related to potential complications after the procedure, which demand the analysis of computerized tomography (CT) scans after TAVI to assess the implant's result. This work introduces a novel, fully automatic method for the analysis of post-TAVI 4D-CT scans to characterize the prosthesis and its relationship with the patient's anatomy. The method enables measurement extraction, including prosthesis volume, center of mass, cross-sectional area (CSA) along the prosthesis axis, and CSA difference between the aortic root and prosthesis, all the variables studied throughout the cardiac cycle. The method has been implemented and evaluated with a cohort of 13 patients with five different prosthesis models, successfully extracting all the measurements from each patient in an automatic way. For Allegra patients, the mean of the obtained inner volume values ranged from 10,798.20 mm3 to 18,172.35 mm3, and CSA in the maximum diameter plane varied from 396.35 mm2 to 485.34 mm2. The implantation of this new method could provide information of the important clinical value that would contribute to the improvement of TAVI, significantly reducing the time and effort invested by clinicians in the image interpretation process.

Improving Intensive Care Unit Early Readmission Prediction Using Optimized and Explainable Machine Learning

It is of great interest to develop and introduce new techniques to automatically and efficiently analyze the enormous amount of data generated in today's hospitals, using state-of-the-art artificial intelligence methods. Patients readmitted to the ICU in the same hospital stay have a higher risk of mortality, morbidity, longer length of stay, and increased cost. The methodology proposed to predict ICU readmission could improve the patients' care. The objective of this work is to explore and evaluate the potential improvement of existing models for predicting early ICU patient readmission by using optimized artificial intelligence algorithms and explainability techniques. In this work, XGBoost is used as a predictor model, combined with Bayesian techniques to optimize it. The results obtained predicted early ICU readmission (AUROC of 0.92 ± 0.03) improves state-of-the-art consulted works (whose AUROC oscillate between 0.66 and 0.78). Moreover, we explain the internal functioning of the model by using Shapley Additive Explanation-based techniques, allowing us to understand the model internal performance and to obtain useful information, as patient-specific information, the thresholds from which a feature begins to be critical for a certain group of patients, and the feature importance ranking.

Two-Step Approach for Occupancy Estimation in Intensive Care Units Based on Bayesian Optimization Techniques

Due to the high occupational pressure suffered by intensive care units (ICUs), a correct estimation of the patients' length of stay (LoS) in the ICU is of great interest to predict possible situations of collapse, to help healthcare personnel to select appropriate treatment options and to predict patients' conditions. There has been a high amount of data collected by biomedical sensors during the continuous monitoring process of patients in the ICU, so the use of artificial intelligence techniques in automatic LoS estimation would improve patients' care and facilitate the work of healthcare personnel. In this work, a novel methodology to estimate the LoS using data of the first 24 h in the ICU is presented. To achieve this, XGBoost, one of the most popular and efficient state-of-the-art algorithms, is used as an estimator model, and its performance is optimized both from computational and precision viewpoints using Bayesian techniques. For this optimization, a novel two-step approach is presented. The methodology was carefully designed to execute codes on a high-performance computing system based on graphics processing units, which considerably reduces the execution time. The algorithm scalability is analyzed. With the proposed methodology, the best set of XGBoost hyperparameters are identified, estimating LoS with a MAE of 2.529 days, improving the results reported in the current state of the art and probing the validity and utility of the proposed approach.

Automatic Identification of Bioprostheses on X-ray Angiographic Sequences of Transcatheter Aortic Valve Implantation Procedures Using Deep Learning

Transcatheter aortic valve implantation (TAVI) has become the treatment of choice for patients with severe aortic stenosis and high surgical risk. Angiography has been established as an essential tool in TAVI, as this modality provides real-time images required to support the intervention. The automatic interpretation and parameter extraction on such images can lead to significative improvements and new applications in the procedure that, in most cases, rely on a prior identification of the transcatheter heart valve (THV). In this paper, U-Net architecture is proposed for the automatic segmentation of THV on angiographies, studying the role of its hyperparameters in the quality of the segmentations. Several experiments have been conducted, testing the methodology using multiple configurations and evaluating the results on different types of frames captured during the procedure. The evaluation has been performed in terms of conventional classification metrics, complemented with two new metrics, specifically defined for this problem. Those new metrics provide a more appropriate assessment of the quality of the results, given the class imbalance in the dataset. From an analysis of the evaluation results, it can be concluded that the method provides appropriate segmentation results for this dataset.