Quadrivalent live attenuated influenza vaccines (LAIV-4) offer an alternative to inactivated influenza vaccines (IIV) for children aged 2-17 years, but data on their comparative effectiveness are limited. This study assessed vaccination rates and real-world effectiveness of LAIV-4 and IIV in preventing influenza and influenza-like illness (ILI) in Italian children during the 2022-2023 and 2023-2024 seasons. We conducted a population-based cohort study of children aged 2-14 years from September 2022 to April 2024, using data from Pedianet, a pediatric primary care database of anonymized records from family pediatricians. Children vaccinated with LAIV-4 or IIV were compared to unvaccinated children. The primary outcome was any first influenza or ILI episode. Monthly vaccination incidence rates per 1000 person-months were calculated for each vaccine type. Hazard ratios (HRs) and their 95 % confidence intervals (CIs) for vaccine effectiveness (VE) were estimated using adjusted mixed-effects Cox models. A total of 65,545 (472,173 person-months) and 72,377 (527,348 person-months) children were included for the 2022-2023 and 2023-2024 seasons, respectively. Vaccination rates were 12.71 and 12.85 per 1000 person-months, respectively. Compared to unvaccinated children, LAIV-4 had an overall effectiveness of 43 % (95 % CI, 32 %-53 %), while IIV effectiveness was 54 % (95 % CI, 46 %-61 %). In 2022-2023, LAIV-4 (38 % [95 % CI, 12 %-56 %]) and IIV (49 % [95 % CI, 37 %-58 %]) had comparable effectiveness. In 2023-2024, LAIV-4 (40 % [95 % CI, 25 %-52 %]) was slightly less effective than IIV (58 % [95 % CI, 44 %-68 %])(p = 0.048). An overall moderate, comparable effectiveness of LAIV-4 and IIV in preventing influenza/ILI among Italian children was observed.

Background: This study aims to propose a semi-automatic method for monitoring the waiting times of follow-up examinations within the National Health System (NHS) in Italy, which is currently not possible to due the absence of the necessary structured information in the official databases. Methods: A Natural Language Processing (NLP) based pipeline has been developed to extract the waiting time information from the text of referrals for follow-up examinations in the Lombardy Region. A manually annotated dataset of 10 000 referrals has been used to develop the pipeline and another manually annotated dataset of 10 000 referrals has been used to test its performance. Subsequently, the pipeline has been used to analyze all 12 million referrals prescribed in 2021 and performed by May 2022 in the Lombardy Region. Results: The NLP-based pipeline exhibited high precision (0.999) and recall (0.973) in identifying waiting time information from referrals’ texts, with high accuracy in normalization (0.948-0.998). The overall reporting of timing indications in referrals’ texts for follow-up examinations was low (2%), showing notable variations across medical disciplines and types of prescribing physicians. Among the referrals reporting waiting times, 16% experienced delays (average delay = 19 days, standard deviation = 34 days), with significant differences observed across medical disciplines and geographical areas. Conclusions: The use of NLP proved to be a valuable tool for assessing waiting times in follow-up examinations, which are particularly critical for the NHS due to the significant impact of chronic diseases, where follow-up exams are pivotal. Health authorities can exploit this tool to monitor the quality of NHS services and optimize resource allocation.

Identifying patient diagnoses from hospital discharge letters is essential for large-scale cohort selection and epidemiological research, but traditional supervised approaches require extensive manual annotation, which is often impractical for large textual datasets. We present a weakly supervised Natural Language Processing (NLP) pipeline for classifying Italian discharge letters without document-level manual annotation. The method extracts diagnosis-related sentences, generates semantic embeddings using a transformer model further pre-trained on Italian medical documents, and applies a two-level clustering procedure to derive weak labels that are then used to train a document-level classifier. The approach was evaluated in a case study on bronchiolitis using 33,176 discharge letters of children admitted to 44 emergency rooms or hospitals in the Veneto Region, Italy, between 2017 and 2020. The best weakly supervised model achieved an AUROC of 77.68% ( $$\pm 4.30\%$$ ), an AUPRC of 73.13% ( $$\pm 4.93\%$$ ), and an F1-score of 78.14% ( $$\pm 4.89\%$$ ) against manually annotated data. Performance surpassed unsupervised baselines and approached fully supervised models, while reducing the need for manual annotation by more than 1,500 hours for a dataset of this size. Similar model rankings were observed in a secondary validation on a smaller bronchitis dataset (3,188 discharge letters, 2020-2025), where the best weakly supervised model achieved an AUPRC of 76.72% ( $$\pm 5.02\%$$ ). These results suggest the potential of weakly supervised NLP methods for scalable disease identification from clinical discharge letters.

Objective: Heart failure (HF) patients present with diverse phenotypes affecting treatment and prognosis. This study evaluates models for phenotyping HF patients based on left ventricular ejection fraction (LVEF) classes, using structured and unstructured data, assessing performance and interpretability. Materials and Methods: The study analyzes all HF hospitalizations at both Amsterdam UMC hospitals (AMC and VUmc) from 2015 to 2023 (33,105 hospitalizations, 16,334 patients). Data from AMC were used for model training, and from VUmc for external validation. The dataset was unlabelled and included tabular clinical measurements and discharge letters. Silver labels for LVEF classes were generated by combining diagnosis codes, echocardiography results, and textual mentions. Gold labels were manually annotated for 300 patients for testing. Multiple Transformer-based (black-box) and Aug-Linear (white-box) models were trained and compared with baselines on structured and unstructured data. To evaluate interpretability, two clinicians annotated 20 discharge letters by highlighting information they considered relevant for LVEF classification. These were compared to SHAP and LIME explanations from black-box models and the inherent explanations of Aug-Linear models. Results: BERT-based and Aug-Linear models, using discharge letters alone, achieved the highest classification results (AUC=0.84 for BERT, 0.81 for Aug-Linear on external validation), outperforming baselines. Aug-Linear explanations aligned more closely with clinicians' explanations than post-hoc explanations on black-box models. Conclusions: Discharge letters emerged as the most informative source for phenotyping HF patients. Aug-Linear models matched black-box performance while providing clinician-aligned interpretability, supporting their use in transparent clinical decision-making.

Background: Influenza vaccination prevents influenza and influenza-like illness (ILI) in children, but its potential influence on susceptibility to other respiratory viruses remains unclear. We aimd to evaluate the relationships between influenza/ILI, non-influenza respiratory virus (NIRV) infections, and influenza vaccination in children. Methods: We conducted a retrospective cohort study using real-world data from the Italian Pedianet pediatric network, including children aged 6 months to 14 years followed during two influenza seasons (September 2022/April 2023 and September 2023/April 2024). Multistate models were used to describe transitions over time between vaccination and infection states (influenza/ILI and NIRV), allowing events to occur in any order and enabling estimation of transition probabilities and timing. A Self-Controlled Case Series (SCCS) analysis using Poisson regression estimated the incidence rate ratio (IRR) of NIRV infection associated with vaccination, accounting for influenza/ILI and seasonality. Results: Among 91,695 children (median age 8 years; IQR 4 to 11; 51% male), vaccinated children showed delayed progression to NIRV infection and fewer early infections. Multistate models showed a substantially lower probability of transitioning to NIRV infection, by approximately 9- to > 60fold, in vaccinated vs unvaccinated children. In the SCCS analysis, influenza vaccination was associated with a reduced risk of NIRV infection (2022/2023:IRR 0.54; 95%CI,0.51 to 0.58; 2023/2024:IRR 0.60; 95%CI,0.56 to 0.64). Conclusions: Influenza vaccination was associated with reduced NIRV infection risk in children, beyond its expected protection against influenza/ILI. These findings support virus interactions as a plausible mechanism shaping infection dynamics and reinforce the value of influenza vaccination in pediatric respiratory disease.