Final Label Research Articles

An evaluation of linvoseltamab for treatment of relapsed/refractory multiple myeloma.

Bispecific antibody therapies, primarily targeting B-cell maturation antigen (BCMA), have shown remarkable outcomes in the treatment of heavily pretreated patients with multiple myeloma (MM). However, there are no current head-to-head trials informing practice for selection or sequencing of optimal T cell redirection strategies in later lines of therapy. Linvoseltamab is a novel BCMA-targeted bispecific antibody that was recently evaluated in the phase 1/2 LINKER-MM1 trial and is currently pending formal regulatory approval. In this drug evaluation, we review efficacy and toxicity profiles of linvoseltamab in the context of currently approved bispecific antibody therapies for MM. Specifically, we highlight differences in dosing strategy, cytokine release syndrome (CRS) kinetics, and indirect efficacy comparisons between trials of linvoseltamab and other bispecific antibodies. Linvoseltamab has a similar efficacy profile with favorable CRS incidence and time-to-onset compared to other approved bispecific antibodies. Pending final regulatory approval and labeling, further real-world analyses are needed to evaluate its final role in the evolving landscape of T cell redirection therapy for MM.

РАЗРАБОТКА ТЕХНОЛОГИИ И РЕЦЕПТУРЫ ХЛЕБА С ИСПОЛЬЗОВАНИЕМ ЗАВАРКИ ИЗ ЧЕЧЕВИЦЫ

The aim of the research is to develop a bread preparation technology and a recipe using lentil infusions to expand the range of bakery products. Tasks: to develop a recipe technology and determine the organoleptic and physico-chemical parameters of the finished product. The objects of research are lentil tea leaves, bread made from wheat flour of the 1st grade. A new method of bread production with the addition of whole grain lentil brewing is the technology of wheat bread production, which includes the following stages: preparation of raw materials, dough kneading, pre-fermentation, cutting and molding, final proofing, baking, cooling, packaging and labeling. To determine the optimal dosage of lentil flour welding, three formulations were developed with the addition of lentil welding in the amount of 5, 10 and 20 % [1]. As a result of the conducted studies, the sample with a content of 10 % of lentil tea leaves had the best organoleptic characteristics. The sample had a uniform brown color with small grain inclusions, rectangular shape without damage, well baked. The taste and smell had a nutty taste. With the addition of 20 % of the welding, the taste had a noticeable nutty taste, and the color of the product had a dark brown color, when with the addition of 5 % of the welding, the taste and smell practically did not differ from the control. During the tasting evaluation, the commission concluded that bread with the addition of 10% lentil tea leaves has the best tasting score, because it has the best taste and aroma, structure and consistency, color and appearance, shape, and this type of bread scored the highest number of points – 44. Physico-chemical indicators of the samples being developed they had no deviations from GOST, humidity 44 %, acidity 3.5 degrees, porosity 70 %, specific volume 2.8 cm3/100.

Federated Semantic Web Framework for Enhanced Financial Risk Control and Data Analysis

Recently, financial institutions have increasingly focused on risk control to protect assets and maintain trust. However, the sensitivity and privacy of data make data sharing for analysis challenging. Current systems typically rely on local data, making it difficult to handle cross-institutional data or complex fraudulent activities. To address this issue, we propose a financial risk control model based on the Federated Semantic Web (FSW). This model deploys a federated learning framework between banks, allowing data to be stored independently, thus ensuring privacy protection. The model automatically selects and scores risk features from transaction data using a multi-perspective topological graph, and assigns the final risk labels via a weighted voting mechanism. The central model updates and redistributes the global model based on parameters shared by local models through the federated averaging algorithm. Experimental results show that the proposed method effectively identifies fraudulent transactions and predicts credit risk, meets security standards, and improves accuracy.

Intramammary Labeling of Epithelial Cell Division

Thymidine analogs such as ethynyl deoxyuridine (EdU) or bromodeoxyuridine (BrdU) can be used to label mitosis of mammary epithelial cells (MEC) and to quantify their proliferation. However, labeling cells in larger animals requires considerable amounts of chemical that can be costly and hazardous. We developed a strategy to infuse EdU into the mammary glands of ewes to directly label mitotic MEC. First, each udder half of nulliparous ewes (n = 2) received an intramammary infusion of one of four different concentrations of EdU (0, 0.1, 1.0 or 10 mM) which was compared to BrdU IV (5 mg/kg) 24 h later. Tissues were analyzed by immunofluorescent histochemistry to detect EdU, BrdU, and total MEC. Of the EdU doses tested, 10 mM EdU yielded the greatest labeling index, while a proportion of MEC were labeled by both EdU and BrdU. We next sought to establish whether intramammary labeling could detect the induction of mitosis after exposure to exogenous estrogen and progesterone (E + P). We first infused EdU (10 mM) into the right udder half of ewes (n = 6) at t 0, followed by thymidine (100 mM) 24 h later to prevent further labeling. Three ewes were then administered E + P for 5 d, while n = 3 ewes served as controls. On d 5, EdU was infused into the left udder half of all mammary glands alongside BrdU IV (5 mg/kg). By the time of necropsy 24 h later an average MEC labeling index of 2.9% resulted from EdU delivered at t 0. In the left half of the udder on d 5, CON glands had a final EdU labeling index of 3.4% while glands exposed to E + P had a labeling index of 4.6% (p = 0.05). The corresponding degree of labeling with BrdU was 5.6% in CON glands, and 12% following E + P (p < 0.001). Our findings reveal that intramammary labeling is an efficient and cost-effective method for single- and dual-labeling of cell division in the mammary glands.

The unreliability of crackles: insights from a breath sound study using physicians and artificial intelligence

Background and introductionIn comparison to other physical assessment methods, the inconsistency in respiratory evaluations continues to pose a major issue and challenge.ObjectivesThis study aims to evaluate the difference in the identification ability of different breath sound.Methods/descriptionIn this prospective study, breath sounds from the Formosa Archive of Breath Sound were labeled by five physicians. Six artificial intelligence (AI) breath sound interpretation models were developed based on all labeled data and the labels from the five physicians, respectively. After labeling by AIs and physicians, labels with discrepancy were considered doubtful and relabeled by two additional physicians. The final labels were determined by a majority vote among the physicians. The capability of breath sound identification for humans and AI was evaluated using sensitivity, specificity and the area under the receiver-operating characteristic curve (AUROC).Results/outcomeA total of 11,532 breath sound files were labeled, with 579 doubtful labels identified. After relabeling and exclusion, there were 305 labels with gold standard. For wheezing, both human physicians and the AI model demonstrated good sensitivities (89.5% vs. 86.0%) and good specificities (96.4% vs. 95.2%). For crackles, both human physicians and the AI model showed good sensitivities (93.9% vs. 80.3%) but poor specificities (56.6% vs. 65.9%). Lower AUROC values were noted in crackles identification for both physicians and the AI model compared to wheezing.ConclusionEven with the assistance of artificial intelligence tools, accurately identifying crackles compared to wheezing remains challenging. Consequently, crackles are unreliable for medical decision-making, and further examination is warranted.

Local Mean Suppression Filter for Effective Background Identification in Fluorescence Images.

We present an easy-to-use, nonlinear filter for effective background identification in fluorescence microscopy images with dense and low-contrast foreground. The pixel-wise filtering is based on comparison of the pixel intensity with the mean intensity of pixels in its local neighborhood. The pixel is given a background or foreground label depending on whether its intensity is less than or greater than the mean respectively. Multiple labels are generated for the same pixel by computing mean expression values by varying neighborhood size. These labels are accumulated to decide the final pixel label. We demonstrate that the performance of our filter favorably compares with state-of-the-art image processing, machine learning, and deep learning methods. We present three use cases that demonstrate its effectiveness, and also show how it can be used in multiplexed fluorescence imaging contexts and as a denoising step in image segmentation. A fast implementation of the filter is available in Python 3 on GitHub.

Correlation mining of multimodal features based on higher-order partial least squares for emotion recognition in conversations

In fields requiring an understanding of emotions, such as digital human interaction and public opinion analysis, achieving a dependable and interpretable model for mining correlations among multimodal features remains a primary objective. However, current deep learning methods often lack transparency and suffer from low interpretability. To address these challenges, we propose a novel Correlation Mining method based on Higher-Order Partial Least Squares (HOPLS) for multimodal Emotion Recognition in conversations (CMHER) in this paper. CMHER innovatively combines HOPLS with transformers and Gated Recurrent Units (GRUs) to compute correlation matrices within unimodal data streams and between cross-modal sources. HOPLS projects source data into a latent space to predict target data via correlation matrix computations, eliminating the need for Graphical Processing Unit (GPU) acceleration and making it suitable for experimental and edge systems. The integration of HOPLS with deep neural networks involves preprocessing multimodal features into suitable dimensions and latent representations, followed by HOPLS computing correlation matrices for cross-modal latent vectors and final labels through optimal joint subspace approximation, which aims at the improvements of both interpretability and reliability. Additionally, a generalization error fitting module further refines the predicted correlation matrices to improve predictive capability and overall model performance. Experiments on two public datasets validate the superiority of our proposed method.

Weakly supervised semantic segmentation of leukocyte images based on class activation maps.

Leukocytes are an essential component of the human defense system, accurate segmentation of leukocyte images is a crucial step towards automating detection. Most existing methods for leukocyte images segmentation relied on fully supervised semantic segmentation (FSSS) with extensive pixel-level annotations, which are time-consuming and labor-intensive. To address this issue, this paper proposes a weakly supervised semantic segmentation (WSSS) approach for leukocyte images utilizing improved class activation maps (CAMs). Firstly, to alleviate ambiguous boundary problem between leukocytes and background, preprocessing technique is employed to enhance the image quality. Secondly, attention mechanism is added to refine the CAMs generated by improving the matching of local and global features. Random walks, dense conditional random fields and hole filling were leveraged to obtain final pseudo-segmentation labels. Finally, a fully supervised segmentation network is trained with pseudo-segmentation labels. The method is evaluated on BCCD and TMAMD datasets. Experimental results demonstrate that by employing the pseudo segmentation annotations generated through this method can be utilized to train UNet as close as possible to FSSS. This method effectively reduces manual annotation cost while achieving WSSS of leukocyte images.

Feature boosting with efficient attention for scene parsing

The complexity of scene parsing grows with the number of object and scene classes, which is higher in unrestricted open scenes. The biggest challenge is to model the spatial relation between scene elements while succeeding in identifying objects at smaller scales. This paper presents a novel feature-boosting network that gathers spatial context from multiple levels of feature extraction and computes the attention weights for each level of representation to generate the final class labels. A novel ‘channel attention module’ is designed to compute the attention weights, ensuring that features from the relevant extraction stages are boosted while the others are attenuated. The model also learns spatial context information at low resolution to preserve the abstract spatial relationships among scene elements and reduce computational cost. Spatial attention is subsequently concatenated into a final feature set before applying feature boosting. Low-resolution spatial attention features are trained using an auxiliary task that help to learn a coarse global scene structure. The proposed model outperforms all state-of-the-art models on both the ADE20K and the Cityscapes datasets.

Automatic labeling framework for paint loss disease of ancient murals based on hyperspectral image classification and segmentation

Ancient murals have suffered from continuous damage over time, and especially paint loss disease. Therefore, disease labeling, as the basis for ancient mural restoration, plays an important role in the protection of cultural relics. The predominant method of disease labeling is currently manual labeling, which is highly dependent on expert experience, time consuming, inefficient and results in inconsistent accuracy of the marking effect. In this paper, we propose a labeling framework for paint loss disease of ancient murals based on hyperspectral image classification and segmentation. The proposed framework involves first the extraction of features from the hyperspectral image, and then image segmentation is performed based on the spatial features to obtain more accurate region boundaries. Then, the hyperspectral image’s regions are classified based on their spatial-spectral characteristics, and the candidate areas of paint loss disease are obtained. Finally, by leveraging the true color image segmentation results, the proposed disease labeling strategy combines the results of classification and segmentation to propose the final paint loss disease labeling areas. The experimental results show that the proposed method can not only combine the hyperspectral space and spectral information effectively to obtain accurate labeling of paint loss disease, but can also mark the paint loss disease not easily observed using ordinary digital cameras. Compared with the state-of-the-art methods, the proposed framework could be promising for accurate and effective paint loss disease labeling for ancient murals.

Development and validation of a reliable DNA copy-number-based machine learning algorithm (CopyClust) for breast cancer integrative cluster classification

The Integrative Cluster subtypes (IntClusts) provide a framework for the classification of breast cancer tumors into 10 distinct groups based on copy number and gene expression, each with unique biological drivers of disease and clinical prognoses. Gene expression data is often lacking, and accurate classification of samples into IntClusts with copy number data alone is essential. Current classification methods achieve low accuracy when gene expression data are absent, warranting the development of new approaches to IntClust classification. Copy number data from 1980 breast cancer samples from METABRIC was used to train multiclass XGBoost machine learning algorithms (CopyClust). A piecewise constant fit was applied to the average copy number profile of each IntClust and unique breakpoints across the 10 profiles were identified and converted into ~ 500 genomic regions used as features for CopyClust. These models consisted of two approaches: a 10-class model with the final IntClust label predicted by a single multiclass model and a 6-class model with binary reclassification in which four pairs of IntClusts were combined for initial multiclass classification. Performance was validated on the TCGA dataset, with copy number data generated from both SNP arrays and WES platforms. CopyClust achieved 81% and 79% overall accuracy with the TCGA SNP and WES datasets, respectively, a nine-percentage point or greater improvement in overall IntClust subtype classification accuracy. CopyClust achieves a significant improvement over current methods in classification accuracy of IntClust subtypes for samples without available gene expression data and is an easily implementable algorithm for IntClust classification of breast cancer samples with copy number data.

Comprehensive Multiview Representation Learning via Deep Autoencoder-Like Nonnegative Matrix Factorization.

Learning a comprehensive representation from multiview data is crucial in many real-world applications. Multiview representation learning (MRL) based on nonnegative matrix factorization (NMF) has been widely adopted by projecting high-dimensional space into a lower order dimensional space with great interpretability. However, most prior NMF-based MRL techniques are shallow models that ignore hierarchical information. Although deep matrix factorization (DMF)-based methods have been proposed recently, most of them only focus on the consistency of multiple views and have cumbersome clustering steps. To address the above issues, in this article, we propose a novel model termed deep autoencoder-like NMF for MRL (DANMF-MRL), which obtains the representation matrix through the deep encoding stage and decodes it back to the original data. In this way, through a DANMF-based framework, we can simultaneously consider the multiview consistency and complementarity, allowing for a more comprehensive representation. We further propose a one-step DANMF-MRL, which learns the latent representation and final clustering labels matrix in a unified framework. In this approach, the two steps can negotiate with each other to fully exploit the latent clustering structure, avoid previous tedious clustering steps, and achieve optimal clustering performance. Furthermore, two efficient iterative optimization algorithms are developed to solve the proposed models both with theoretical convergence analysis. Extensive experiments on five benchmark datasets demonstrate the superiority of our approaches against other state-of-the-art MRL methods.

Structure-guided feature and cluster contrastive learning for multi-view clustering

Multi-view clustering (MVC) technology performs unsupervised clustering on data collected from multiple sources, and has received intense attention in recent years. However, most existing MVC methods fail to consider retaining view-specific information when learning multi-view consistent representations. Besides, the feature and cluster structures of multi-view data cannot be fully leveraged in clustering. In this paper, we propose a structure-guided feature and cluster contrastive learning (SGFCC) for multi-view clustering. Specifically, SGFCC utilizes autoencoders to achieve view-specific information reconstruction in feature space, and extracts high-level features for multi-view consistent representation learning to eliminate the effects of view-specific information and noise on consistent representation. To fully capture the similar clustering structure of high-level features and semantic features of samples across different views, we adopt a structure-guided feature-level and cluster-level contrastive learning strategy in our SGFCC model. Furthermore, we design a clustering layer to explore the cluster structure of high-level features. Different from most existing MVC methods, our method applies a non-fusion scheme that aggregates the semantic information of all views to obtain the final semantic labels. Extensive experiments on public datasets demonstrate that our method outperforms other competitors in clustering tasks.

An Algorithm to Assess Guideline Concordance of Antibiotic Choice in Community-Acquired Pneumonia.

This study aimed to develop and evaluate an algorithm to reduce the chart review burden of improvement efforts by automatically labeling antibiotic selection as either guideline-concordant or -discordant based on electronic health record data for patients with community-acquired pneumonia (CAP). We developed a 3-part algorithm using structured and unstructured data to assess adherence to an institutional CAP clinical practice guideline. The algorithm was applied to retrospective data for patients seen with CAP from 2017 to 2019 at a tertiary children's hospital. Performance metrics included positive predictive value (precision), sensitivity (recall), and F1 score (harmonized mean), with macro-weighted averages. Two physician reviewers independently assigned "actual" labels based on manual chart review. Of 1345 patients with CAP, 893 were included in the training cohort and 452 in the validation cohort. Overall, the model correctly labeled 435 of 452 (96%) patients. Of the 286 patients who met guideline inclusion criteria, 193 (68%) were labeled as having received guideline-concordant antibiotics, 48 (17%) were labeled as likely in a scenario in which deviation from the clinical practice guideline was appropriate, and 45 (16%) were given the final label of "possibly discordant, needs review." The sensitivity was 0.96, the positive predictive value was 0.97, and the F1 was 0.96. An automated algorithm that uses structured and unstructured electronic health record data can accurately assess the guideline concordance of antibiotic selection for CAP. This tool has the potential to improve the efficiency of improvement efforts by reducing the manual chart review needed for quality measurement.

Spatial-Temporal Knowledge-Embedded Transformer for Video Scene Graph Generation.

Video scene graph generation (VidSGG) aims to identify objects in visual scenes and infer their relationships for a given video. It requires not only a comprehensive understanding of each object scattered on the whole scene but also a deep dive into their temporal motions and interactions. Inherently, object pairs and their relationships enjoy spatial co-occurrence correlations within each image and temporal consistency/transition correlations across different images, which can serve as prior knowledge to facilitate VidSGG model learning and inference. In this work, we propose a spatial-temporal knowledge-embedded transformer (STKET) that incorporates the prior spatial-temporal knowledge into the multi-head cross-attention mechanism to learn more representative relationship representations. Specifically, we first learn spatial co-occurrence and temporal transition correlations in a statistical manner. Then, we design spatial and temporal knowledge-embedded layers that introduce the multi-head cross-attention mechanism to fully explore the interaction between visual representation and the knowledge to generate spatial- and temporal-embedded representations, respectively. Finally, we aggregate these representations for each subject-object pair to predict the final semantic labels and their relationships. Extensive experiments show that STKET outperforms current competing algorithms by a large margin, e.g., improving the mR@50 by 8.1%, 4.7%, and 2.1% on different settings over current algorithms.

Context-Aware Attentive Multilevel Feature Fusion for Named Entity Recognition.

In the era of information explosion, named entity recognition (NER) has attracted widespread attention in the field of natural language processing, as it is fundamental to information extraction. Recently, methods of NER based on representation learning, e.g., character embedding and word embedding, have demonstrated promising recognition results. However, existing models only consider partial features derived from words or characters while failing to integrate semantic and syntactic information, e.g., capitalization, inter-word relations, keywords, and lexical phrases, from multilevel perspectives. Intuitively, multilevel features can be helpful when recognizing named entities from complex sentences. In this study, we propose a novel attentive multilevel feature fusion (AMFF) model for NER, which captures the multilevel features in the current context from various perspectives. It consists of four components to, respectively, capture the local character-level (CL), global character-level (CG), local word-level (WL), and global word-level (WG) features in the current context. In addition, we further define document-level features crafted from other sentences to enhance the representation learning of the current context. To this end, we introduce a novel context-aware attentive multilevel feature fusion (CAMFF) model based on AMFF, to fully leverage document-level features from all the previous inputs. The obtained multilevel features are then fused and fed into a bidirectional long short-term memory (BiLSTM)-conditional random field (CRF) network for the final sequence labeling. Extensive experiments on four benchmark datasets demonstrate that our proposed AMFF and CAMFF models outperform a set of state-of-the-art baseline methods and the features learned from multiple levels are complementary.

Driving fatigue detection based on brain source activity and ARMA model.

Fatigue among drivers is a significant issue in society, and according to organizational reports, it substantially contributes to accidents. So accurate fatigue detection in drivers plays a crucial role in reducing the number of people fatalities or injured resulting from accidents. Several methods are proposed for fatigue driver recognition among which electroencephalography (EEG) is one. This paper proposed a method for fatigue recognition by EEG signals with extracted features from source and sensor spaces. The proposed method starts with preprocessing by applying filtering and artifact rejection. Then source localization methods are applied to EEG signals for active source extraction. A multivariate autoregressive (MVAR) model is fitted to selected sources, and a dual Kalman filter is applied to estimate the source activity and their relationships. Then multivariate autoregressive moving average (ARMA) is fitted between EEG and source activity signals. Features are extracted from model parameters, source relationship matrix, and wavelet transform of EEG and source activity signals. The novelty of this approach is the use of ARMA model between source activities (as input) and EEG signals (as output) and feature extraction from source relations. Relevant features are selected using a combination of RelifF and neighborhood component analysis (NCA) methods. Three classifiers, namely k-nearest neighbor (KNN), support vector machine (SVM), and naive Bayesian (NB) classifiers, are employed to classify drivers. To improve performance, the final label for fatigue detection is calculated by combining these classifiers using the voting method. The results demonstrate that the proposed method accurately recognizes and classifies fatigued drivers with the ensemble classifiers in comparison with other methods.

Top2Label: Explainable zero shot topic labelling using knowledge graphs

Automatic topic labelling aims to generate coherent, interpretable, and meaningful labels to facilitate the interpretation of various topics within a corpus of documents. Typically, we represent a topic as a list of terms and documents ranked according to probability. In our research, we employ Top2Vec for topic modelling. We propose a novel three-phase, zero-shot topic labelling framework leveraging the ConceptNet knowledge graph (a comprehensive semantic network of words and phrases) and pre-trained language models as external sources of information. The first phase enriches the top n words of a given topic (based on probability) by expanding their neighbourhood in ConceptNet, bridging missing connections and information gaps, and subsequently yielding a semantically enhanced set of potential labels through the generation of a sub-graph. The second phase constructs a neighbourhood graph (organized as a subgraph of ConceptNet) for each candidate label, evaluating each node’s semantic similarity to the topic and retaining the best sub-graph according to semantic similarity. In this phase, a one-word label is extracted from the final graph, concisely representing the topic. In the third phase, we use the language model to derive the final labels by taking the optimal graph as input. In the third phase, we utilize the language model to derive the sentence and summary labels using the optimal graph as input. These additional labels offer more comprehensive and contextually rich topic representations, facilitating more profound understanding and interpretation. By harnessing the power of knowledge graphs and language models, our framework expands the knowledge beyond the topic documents, optimizing the discovered topics with more representative terms while preserving the topic information. The proposed zero-shot approach (employing pre-trained language models and the ConceptNet knowledge graph without additional training) alleviates computational burdens. It reduces the cognitive and interpretative load on end-users by generating three types of labels for each topic: a one-word, sentence, and summary. Experimental results demonstrate that our model significantly surpasses unsupervised baselines and traditional topic labelling models while remaining competitive with supervised baselines in topic labelling performance.

Molecular imaging of bacterial outer membrane vesicles based on bacterial surface display

The important roles of bacterial outer membrane vesicles (OMVs) in various diseases and their emergence as a promising platform for vaccine development and targeted drug delivery necessitates the development of imaging techniques suitable for quantifying their biodistribution with high precision. To address this requirement, we aimed to develop an OMV specific radiolabeling technique for positron emission tomography (PET). A novel bacterial strain (E. coli BL21(DE3) ΔnlpI, ΔlpxM) was created for efficient OMV production, and OMVs were characterized using various methods. SpyCatcher was anchored to the OMV outer membrane using autotransporter-based surface display systems. Synthetic SpyTag-NODAGA conjugates were tested for OMV surface binding and 64Cu labeling efficiency. The final labeling protocol shows a radiochemical purity of 100% with a ~ 29% radiolabeling efficiency and excellent serum stability. The in vivo biodistribution of OMVs labeled with 64Cu was determined in mice using PET/MRI imaging which revealed that the biodistribution of radiolabeled OMVs in mice is characteristic of previously reported data with the highest organ uptakes corresponding to the liver and spleen 3, 6, and 12 h following intravenous administration. This novel method can serve as a basis for a general OMV radiolabeling scheme and could be used in vaccine- and drug-carrier development based on bioengineered OMVs.

An Evaluation of the Swissmedic Regulatory Framework for New Active Substances

BackgroundSwissmedic is a major regulatory agency that has been benchmarking its timelines for 20 years. To better understand the Swissmedic review times and to examine whether measures introduced to accelerate the process were effective, a retrospective analysis was undertaken. The objective was to provide a breakdown of where time is spent in the phases of Swissmedic’s approval process (validation, scientific assessment, authorisation) and how this compared to other major authorities.MethodsData on Swissmedic, EMA and FDA product approvals were collected from websites or through direct communication, using a standardised CIRS method and milestones previously identified, focusing on new active substances approved 2019–2021.ResultsIn 2019, 2020, and 2021, Swissmedic median approval times were 520, 470, and 392 days, respectively. The decrease over this time was mainly observed in the Authorisation Phase and can be attributed to lower proportions of applications with multiple “labelling loops”, in addition to shorter times for final label negotiation. While Swissmedic had the longest overall approval time (447 days) compared to EMA (428) and FDA (244), the timelines were more comparable when considering only the agency’s time spent on the scientific assessment, with Swissmedic at 194 days, EMA at 218 days, and FDA at 184 days.ConclusionsThese observations represent an important analysis of Swissmedic regulatory activity timelines, demonstrate the impact of process improvements, and emphasise the importance of measuring timelines. Swissmedic will continue to expedite its processes also by promoting international collaborations with like-minded authorities.