Clinical Decision Support Systems (CDSS) utilizing machine learning (ML) classifiers have demonstrated substantial potential for improving diagnostic accuracy across various medical domains. However, concerns regarding automation bias, diminished sense of agency, and over-reliance on these systems remain, particularly in clinical settings where decision-making autonomy is critical.To address these challenges, we propose "Judicial AI,"an innovative interaction protocol aimed at reducing automation bias and preserving a sense of agency. This system presents contrasting explanations to medical professionals rather than definitive recommendations, encouraging user engagement and critical evaluation.Before adopting interaction protocols that avoid definitive recommendations, it is important to assess whether such an approach impacts diagnostic accuracy, and if so, how. This paper reports an exploratory study investigating the efficacy of a Judicial CDSS in the diagnosis of vertebral fractures from X-ray images. Sixteen medical professionals, comprising spine surgeons and radiologists, participated in the diagnosis of 18 X-ray images, which were carefully selected to represent particularly difficult and complex cases. Diagnosticians first recorded their decisions independently and then with support from the Judicial AI, which provided activation maps for opposing diagnoses.Our findings show a significant improvement in diagnostic accuracy for complex cases among experienced users (p =.045), with an overall accuracy increase of 0.24. Confidence levels also rose, particularly in the case of complex diagnoses (p =.034). However, the protocol was less beneficial for less experienced users, suggesting that cognitive load might be a limiting factor.These results suggest that Judicial AI, which frames decision-makers as the ultimate authority in the decision-making process, may be an effective tool for mitigating automation bias and preserving a sense of agency in clinical environments.

BACKGROUND: The COVID-19 pandemic has caused over 776 million infections and 7 million deaths globally between December 2019 and November 2024. Since the emergence of the original Wuhan strain, SARS-CoV-2 has evolved into multiple variants-including Alpha, Delta, and Omicron-primarily through mutations in the Spike glycoprotein. The S1 subunit, which binds the human angiotensin-converting enzyme 2 (ACE2) receptor, mutates frequently and plays a key role in infectivity and immune escape, while the more conserved S2 subunit mediates membrane fusion. Anticipating future mutations is essential for guiding vaccine design and therapeutic strategies. Generative Large Language Models (LLMs) have shown promise in protein sequence modeling due to their capacity to produce realistic and functional synthetic sequences. Here, we introduce SARITA, a GPT-3-based LLM with up to 1.2 billion parameters, fine-tuned via continual learning on the protein model RITA trained on 107 017 high-quality SARS-CoV-2 Spike sequences (up to March 1st 2021) to generate high-quality synthetic SARS-CoV-2 Spike S1 subunits. RESULTS: SARITA is able to generate realistic, full-length synthetic S1 subunits starting from a 14-amino-acid prompt. When evaluated on unseen sequences collected between March 2021 and November 2023-including major Variants of Concern (VOCs) such as Delta and Omicron, and Variants of Interest such as Iota-SARITA outperforms baseline and state-of-the-art LLMs in terms of sequence quality, biological plausibility, and similarity to real-world viral evolution. SARITA generates high-quality sequences in over 97% of cases, with markedly lower False Mutation Rate and higher similarity scores (PAM30, Levenshtein distance) compared to alternative approaches. It also accurately reproduces key mutations characteristic of future variants-such as L212I, R158L, T95P, and E406K-which were not present in the training data but emerged later in VOCs like Omicron and Delta. Structure-based analysis confirms the functional plausibility of these substitutions, with ΔΔG values within experimentally supported thresholds for ACE2 and antibody binding. Furthermore, SARITA anticipates immune-evasive mutations and accurately captures the positional and statistical distribution of mutations found in post- March 1st 2021 variants, highlighting its potential as a predictive tool for viral evolution. CONCLUSION: These results indicate the potential of SARITA to predict future SARS-CoV-2 S1 evolution, potentially aiding in the development of adaptable vaccines and treatments.

BACKGROUND: Radiology reports are typically written in a free-text format, making clinical information difficult to extract and use. Recently, the adoption of structured reporting (SR) has been recommended by various medical societies thanks to the advantages it offers, e.g. standardization, completeness, and information retrieval. We propose a pipeline to extract information from Italian free-text radiology reports that fits with the items of the reference SR registry proposed by a national society of interventional and medical radiology, focusing on CT staging of patients with lymphoma. METHODS: Our work aims to leverage the potential of Natural Language Processing and Transformer-based models to deal with automatic SR registry filling. With the availability of 174 Italian radiology reports, we investigate a rule-free generative Question Answering approach based on the Italian-specific version of T5: IT5. To address information content discrepancies, we focus on the six most frequently filled items in the annotations made on the reports: three categorical (multichoice), one free-text (free-text), and two continuous numerical (factual). In the preprocessing phase, we encode also information that is not supposed to be entered. Two strategies (batch-truncation and ex-post combination) are implemented to comply with the IT5 context length limitations. Performance is evaluated in terms of strict accuracy, f1, and format accuracy, and compared with the widely used GPT-3.5 Large Language Model. Unlike multichoice and factual, free-text answers do not have 1-to-1 correspondence with their reference annotations. For this reason, we collect human-expert feedback on the similarity between medical annotations and generated free-text answers, using a 5-point Likert scale questionnaire (evaluating the criteria of correctness and completeness). RESULTS: The combination of fine-tuning and batch splitting allows IT5 ex-post combination to achieve notable results in terms of information extraction of different types of structured data, performing on par with GPT-3.5. Human-based assessment scores of free-text answers show a high correlation with the AI performance metrics f1 (Spearman's correlation coefficients>0.5, p-values<0.001) for both IT5 ex-post combination and GPT-3.5. The latter is better at generating plausible human-like statements, even if it systematically provides answers even when they are not supposed to be given. CONCLUSIONS: In our experimental setting, a fine-tuned Transformer-based model with a modest number of parameters (i.e., IT5, 220 M) performs well as a clinical information extraction system for automatic SR registry filling task. It can extract information from more than one place in the report, elaborating it in a manner that complies with the response specifications provided by the SR registry (for multichoice and factual items), or that closely approximates the work of a human-expert (free-text items); with the ability to discern when an answer is supposed to be given or not to a user query.

Increasingly complex learning methods such as boosting, bagging and deep learning have made ML models more accurate, but harder to interpret and explain, culminating in black-box machine learning models. Model developers and users alike are often presented with a trade-off between performance and intelligibility, especially in high-stakes applications like medicine. In the present article we propose a novel methodological approach for generating explanations for the predictions of a generic machine learning model, given a specific instance for which the prediction has been made. The method, named AraucanaXAI, is based on surrogate, locally-fitted classification and regression trees that are used to provide post-hoc explanations of the prediction of a generic machine learning model. Advantages of the proposed XAI approach include superior fidelity to the original model, ability to deal with non-linear decision boundaries, and native support to both classification and regression problems. We provide a packaged, open-source implementation of the AraucanaXAI method and evaluate its behaviour in a number of different settings that are commonly encountered in medical applications of AI. These include potential disagreement between the model prediction and physician's expert opinion and low reliability of the prediction due to data scarcity.

In the era of digital healthcare, the huge volumes of textual information generated every day in hospitals constitute an essential but underused asset that could be exploited with task-specific, fine-tuned biomedical language representation models, improving patient care and management. For such specialized domains, previous research has shown that fine-tuning models stemming from broad-coverage checkpoints can largely benefit additional training rounds over large-scale in-domain resources. However, these resources are often unreachable for less-resourced languages like Italian, preventing local medical institutions to employ in-domain adaptation. In order to reduce this gap, our work investigates two accessible approaches to derive biomedical language models in languages other than English, taking Italian as a concrete use-case: one based on neural machine translation of English resources, favoring quantity over quality; the other based on a high-grade, narrow-scoped corpus natively written in Italian, thus preferring quality over quantity. Our study shows that data quantity is a harder constraint than data quality for biomedical adaptation, but the concatenation of high-quality data can improve model performance even when dealing with relatively size-limited corpora. The models published from our investigations have the potential to unlock important research opportunities for Italian hospitals and academia. Finally, the set of lessons learned from the study constitutes valuable insights towards a solution to build biomedical language models that are generalizable to other less-resourced languages and different domain settings.

The introduction of computerized medical records in hospitals has reduced burdensome activities like manual writing and information fetching. However, the data contained in medical records are still far underutilized, primarily because extracting data from unstructured textual medical records takes time and effort. Information Extraction, a subfield of Natural Language Processing, can help clinical practitioners overcome this limitation by using automated text-mining pipelines. In this work, we created the first Italian neuropsychiatric Named Entity Recognition dataset, PsyNIT, and used it to develop a Transformers-based model. Moreover, we collected and leveraged three external independent datasets to implement an effective multicenter model, with overall F1-score 84.77 %, Precision 83.16 %, Recall 86.44 %. The lessons learned are: (i) the crucial role of a consistent annotation process and (ii) a fine-tuning strategy that combines classical methods with a "low-resource" approach. This allowed us to establish methodological guidelines that pave the way for Natural Language Processing studies in less-resourced languages.

INTRODUCTION: Thanks to improvement of care, cancer has become a chronic condition. But due to the toxicity of treatment, the importance of supporting the quality of life (QoL) of cancer patients increases. Monitoring and managing QoL relies on data collected by the patient in his/her home environment, its integration, and its analysis, which supports personalization of cancer management recommendations. We review the state-of-the-art of computerized systems that employ AI and Data Science methods to monitor the health status and provide support to cancer patients managed at home. OBJECTIVE: Our main objective is to analyze the literature to identify open research challenges that a novel decision support system for cancer patients and clinicians will need to address, point to potential solutions, and provide a list of established best-practices to adopt. METHODS: We designed a review study, in compliance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, analyzing studies retrieved from PubMed related to monitoring cancer patients in their home environments via sensors and self-reporting: what data is collected, what are the techniques used to collect data, semantically integrate it, infer the patient's state from it and deliver coaching/behavior change interventions. RESULTS: Starting from an initial corpus of 819 unique articles, a total of 180 papers were considered in the full-text analysis and 109 were finally included in the review. Our findings are organized and presented in four main sub-topics consisting of data collection, data integration, predictive modeling and patient coaching. CONCLUSION: Development of modern decision support systems for cancer needs to utilize best practices like the use of validated electronic questionnaires for quality-of-life assessment, adoption of appropriate information modeling standards supplemented by terminologies/ontologies, adherence to FAIR data principles, external validation, stratification of patients in subgroups for better predictive modeling, and adoption of formal behavior change theories. Open research challenges include supporting emotional and social dimensions of well-being, including PROs in predictive modeling, and providing better customization of behavioral interventions for the specific population of cancer patients.