Tommaso Dolci

Chiara Criscuolo, Tommaso Dolci, Mattia Salnitri

Algorithms and technologies are essential tools that pervade all aspects of our daily lives. In the last decades, health care research benefited from new computer-based recruiting methods, the use of federated architectures for data storage, the introduction of innovative analyses of datasets, and so on. Nevertheless, health care datasets can still be affected by data bias. Due to data bias, they provide a distorted view of reality, leading to wrong analysis results and, consequently, decisions. For example, in a clinical trial that studied the risk of cardiovascular diseases, predictions were wrong due to the lack of data on ethnic minorities. It is, therefore, of paramount importance for researchers to acknowledge data bias that may be present in the datasets they use, eventually adopt techniques to mitigate them and control if and how analyses results are impacted. This paper proposes a method to address bias in datasets that: (i) defines the types of data bias that may be present in the dataset, (ii) characterizes and quantifies data bias with adequate metrics, (iii) provides guidelines to identify, measure, and mitigate data bias for different data sources. The method we propose is applicable both for prospective and retrospective clinical trials. We evaluate our proposal both through theoretical considerations and through interviews with researchers in the health care environment.

Fabio Azzalini, Tommaso Dolci, Marco Vagaggini

With the increasing availability of patient data, modern medicine is shifting towards prospective healthcare. Electronic health records offer a variety of information useful for clinical patient characterization and the development of predictive models, given that similar medical histories often lead to analogous health progressions. One application is the prediction of unplanned hospital readmissions, an essential task for reducing healthcare costs and improving patient outcomes. While predictive models demonstrate strong performances especially with deep learning approaches, they are often criticized for their lack of interpretability, a critical requirement in the medical domain where incorrect predictions may have severe consequences for patient safety. In this paper, we propose a novel and interpretable deep learning framework for predicting unplanned hospital readmissions, supported by NLP findings on word embeddings and by ConvLSTM neural networks for better handling temporal data. We validate the framework on two predictive tasks for hospital readmission within 30 and 180 days, using real-world data. Additionally, we introduce and evaluate a model-dependent technique designed to enhance result interpretability for medical professionals. Our solution outperforms traditional machine learning models in prediction accuracy while simultaneously providing more interpretable results.