Search

Patient-focused drug development (PFDD) represents a transformative approach that is reshaping the pharmaceutical landscape by centering on patients throughout the drug development process. Recent advancements in Artificial Intelligence (AI), especially in Natural Language Processing (NLP), have enabled the analysis of vast social media datasets, also called Social Media Listening (SML), providing insights not only into patient perspectives but also into those of other interest groups such as caregivers. In this method study, we propose an NLP framework that-given a particular disease-is designed to extract pertinent information related to three primary research topics: identification of interest groups, understanding of challenges, and assessing treatments and support systems. Leveraging external resources like ontologies and employing various NLP techniques, particularly zero-shot text classification, the presented framework yields initial meaningful insights into these research topics with minimal annotation effort., Competing Interests: VM was an Independent Researcher. MK, MJ, MR, VS, and ES were employed by the Know Center Research GmbH. MV, GM, SN, RG, and RM were employed by the Chiesi Farmaceutici SpA., (Copyright © 2025 Matoshi, De Vuono, Gaspari, Kröll, Jantscher, Nicolardi, Mazzola, Rauch, Sabol, Salhofer and Mariani.)

We sincerely appreciate the authors' comments [...].

Objectives: Cardiac arrest patients with a shockable rhythm are more likely to survive an out-of-hospital cardiac arrest (OHCA) compared with a nonshockable rhythm. An electrocardiogram (ECG) is the most common way to identify a shockable rhythm, but it can miss patients with clinically significant ventricular fibrillation (vfib). We sought to determine the percentage of nonshockable OHCA patients that demonstrated vfib on echo., Methods: Secondary analysis of echo images recorded from a prior study from our group, Real-Time Evaluation and Assessment for Sonography-Outcomes Network (REASON), a multicenter, observational study of OHCA patients presenting to the emergency department with nonshockable rhythms. Using ECG and echocardiogram images recorded during the initial cardiopulmonary resuscitation (CPR) pause, 2 independent emergency physicians determined the presence of vfib. Two experienced emergency physicians (R.G. and T.G.) reviewed echo images with adjudication by a third if necessary. ECG interpretation was unblinded to patient information. The primary outcome was the proportion of patients in occult vfib., Results: During the first CPR pause, reviewers noted occult vfib in 22/685 (3.2%; 95% CI, 2.1%-4.8%) subjects. Patients with ECG vfib (n = 55) were defibrillated immediately during the first pause in CPR, but no patients with occult vfib during the first pause in CPR were defibrillated. Subsequently, 50% (11 of 22) of occult vfib patients were defibrillated when ECG vfib was recognized during an ensuing pause in CPR., Conclusion: One in 33 OHCAs with a nonshockable ECG rhythm exhibits VF on echocardiogram. Patients presenting to the emergency department in a presumed nonshockable rhythm following OHCA may benefit from prompt defibrillation if personnel recognize occult vfib on echo., Competing Interests: S.A. has book royalties from Springer and is a paid consultant for General Electric and EXO ultrasound. R.G. was a paid consultant to Butterfly Ultrasound Inc. The other authors have affirmed they have no conflicts of interest to declare., (© 2024 The Authors.)