Abstract: BACKGROUND: The study aimed to determine the optimal pool size of ABO matched buffy coat pooled platelets (BCPP) to achieve a typical adult dose (TAD) of platelets comparable to single donor platelet concentrates (SDPC), following recent regulatory changes allowing random donor platelet concentrate (and/or buffy coat [BC]) pooling, in India. MATERIALS AND METHODS: This prospective study, done in 2024 at a tertiary hospital, included donors who met whole blood (WB) or SDPC donation criteria. WB was collected in quadruple bags and separated into red cells, plasma, and BC. BC units were pooled into groups of 4, 5, or 6 with 300 mL of ABO-matched plasma. SDPC was collected with automatic separators. The study examined four groups: BCPP, prepared from pools of four, five, or six BC units, and SDPC; 10 pools of BCPP (from three pool sizes of BC), and 10 units (SDPC) were assessed for in vitro parameters. Subsequently, conducted pilot in vivo study looked at the corrected count increment (CCI) and percentage platelet recovery (PPR) of the “optimal pool,” identified on the basis of in vitro analysis. RESULTS: The study used 150 WB and 10 SDPC donors, having no significant variations in physical, biochemical, or hematological markers across four groups. Pool-of-5 BC units met TAD standards with fewer units than pool-of-6 and produced comparable quality to SDPC. Transfusion of BCPP (pool-of-5) resulted in a CCI of 9.7 ± 4 × 10 9 /L and a PPR of 25 ± 11%. CONCLUSION: BCPP (pool-of-five BC units) provides an effective TAD, making it viable option to SDPC, with comparable quality and effectiveness.
Artificial intelligence (AI) applied to the standard 12-lead electrocardiogram (AI-ECG) is being developed as a scalable approach to screen for left ventricular systolic dysfunction (LVSD) and support triage for confirmatory testing. Supervised models trained on paired ECG–echocardiography data show high discrimination for reduced ejection fraction across thresholds and can identify individuals at higher risk of subsequent LV dysfunction despite a normal baseline echocardiogram. External validation of an FDA-cleared ECG-AI device across four geographically diverse U.S. health systems confirmed strong diagnostic accuracy, though signal-format compatibility and quality gating meaningfully affect real-world yield. Two pragmatic randomized trials demonstrate practice-level impact. In primary care, AI-ECG increased the number of new low-ejection-fraction diagnoses and directed echocardiography preferentially to screen-positive patients. In non-cardiology inpatient wards, AI alerts improved diagnostic yield through increased cardiology consultation rather than increased imaging volume. In emergency-department patients with dyspnea, AI-ECG supports a prioritization role with high negative predictive value, outperforming NT-proBNP, but requires confirmatory imaging given prevalence-dependent positive predictive value. In population cohorts, adding AI-ECG signals to PREVENT-HF improves near-term heart-failure risk discrimination and reclassification, though without demonstrated benefit on clinical outcomes such as heart-failure hospitalization or mortality. Foundation models pretrained on large ECG datasets reduce labeled-data requirements and improve transportability, but prospective echocardiography-anchored validation is required before broader deployment. FDA-cleared software is available for left ventricular ejection fraction ≤40% screening from 12-lead ECGs as clinician decision support. This review summarizes performance across thresholds and care settings, outlines threshold selection and calibration, and defines priorities for outcome-oriented trials, equitable deployment, and implementation governance.
Early identification or rule-out of left ventricular systolic dysfunction (LVSD) is critical for optimizing clinical care pathways. AI-enabled analysis of 12-lead resting ECGs offers a low-cost and scalable solution, but direct comparisons between foundation models and conventional deep learning architectures remain limited. To evaluate the performance of a novel time-series foundation model (TSFM) for detecting LVSD from ECGs and compare it with a standard ResNet-18 deep learning (DL) model. Both models were trained and tested using 31,832 Heart Center Leipzig ECG–echocardiogram pairs, split into training (n = 20,372), validation (n = 5,093), and test (n = 6,367) cohorts. TSFM was additionally pre-trained on 33K unlabeled ECGs using masked pre-training. LVSD was defined as LVEF ≤ 40%, with a prevalence of 15% across all sets. Model performance was evaluated using AUROC, AUPRC, and standard classification metrics. On the test dataset, TSFM achieved a higher AUROC (0.924 [95% CI: 0.918–0.928]) than ResNet-18 (0.912 [95% CI: 0.904–0.916], p < 0.001), and a slightly higher but not statistically significant AUPRC (0.695 [0.663–0.723] vs. 0.646 [0.612–0.683]). TSFM also demonstrated improved sensitivity (0.89 vs. 0.87) and negative predictive value (0.98 vs. 0.97), with identical specificity (0.81) and positive predictive value (0.44). The transformer-based ECG model outperforms a conventional DL model in detecting LVSD. Its high negative predictive value supports further evaluation in triage, emergency, and preoperative settings where rapid rule-out of LVSD can inform downstream clinical decision-making.
Pharmacovigilance in Latin America has witnessed notable progress in recent years, marked by advancements in regulatory frameworks, regional cooperation, and increased academic involvement. However, heterogeneity among countries, uneven institutional development, and limited resources still hinder its full impact on public health. In this context, the Latin American Chapter of the International Society of Pharmacovigilance (ISoP LATAM) has played a key role in organizing two regional symposia: Cartagena, Colombia (2023), and Merida, Mexico (2025). Through multidisciplinary roundtables and open forums, ISoP LATAM has brought together regulators, academia, healthcare professionals, researchers, patient organizations, and industry representatives to promote dialogue, identify opportunities, and propose measures to improve pharmacovigilance in the region. Discussion included regulatory harmonization and convergence, the adoption of international standards for risk management and safety reporting, and the integration of artificial intelligence and real-world evidence into pharmacovigilance systems. Participants emphasized the importance of addressing medication errors through a Human Factors/Ergonomics approach, strengthening the monitoring and regulation of biosimilars, and creating differentiated frameworks for recognizing therapeutic failures. The expansion of pharmaceutical care and the systematic inclusion of pharmacovigilance education across the health sciences’ curriculum were highlighted as priorities. The reflections from these symposia emphasize the crucial role of ISoP LATAM in providing a platform for open and multidisciplinary discussions. Shifting the focus from solely regulatory topics to a broader public health perspective and expanding the agenda to include emerging fields such as pharmacogenomics, ecopharmacovigilance, and patient engagement—while ensuring fair access to technological innovations—will be vital for enhancing drug safety in Latin America.
Systematic reviews are essential for evidence synthesis but often require extensive time and resources, especially during data extraction. This proof-of-concept study evaluates the performance of Elicit, an AI tool specifically developed to support systematic reviews, in the context of a systematic review on psychological factors in dermatological conditions. We compared Elicit's automated data extraction with manually extracted data across 43 studies and 602 data points. Both were assessed against a consensus-based ground truth. Elicit achieved an overall accuracy of 81.4%, compared to 86.7% for human reviewers-a difference that was not statistically significant. In cases where Elicit and the human reviewer extracted the same information, this information was correct in 100% of instances, suggesting that agreement between human and machine may serve as a reliable proxy for validity. Based on these results, we propose a semi-automated workflow in which Elicit functions as a second reviewer, reducing workload while maintaining high data quality. Our results demonstrate that domain-specific AI tools can effectively augment data extraction in systematic reviews, especially in settings with limited time or personnel.
