A Natural Language Processing Approach Towards Harmonized Communication of Uncertainties Identified During the European Medicine Authorization Process.

Within the European Union, the European Medicines Agency's (EMA's) European Public Assessment Report (EPAR) is an important source of information for healthcare professionals and patients that allows them to understand important risks and uncertainties associated with the use of a medicine. However, the EPAR sections describing such important uncertainties can differ substantially in wording, length, and detail, thereby potentially limiting understanding. In this study, we therefore present a natural language processing approach to cluster sentences extracted from the sections on uncertainties in EPARs of centrally authorized medicines, as a steppingstone to harmonization of text describing uncertainties. We used a BERT language model together with dimensionality reduction (Uniform Manifold Approximation and Projection (UMAP)) and clustering (Density-Based Spatial Clustering of Applications with Noise (DBSCAN)) to identify semantic similarities between sentences. Clusters were labeled according to an overarching topic by reviewing the semantically similar sentences. Each cluster was also characterized according to medicine-related characteristics, such as efficacy or side effects. In total, 1,648 medicines were included in this study. For 573 of these medicines (authorized July 27, 2010 to December 31, 2022), we identified an EPAR that described a complete regulatory dossier and contained sections on uncertainties. Of these, 553 EPARs could be attributed to unique active substance-indication combinations. In these 553 EPARs, we identified 13,105 sentences in sections on uncertainties, leading to 26 clusters of which 2 were labeled as noise. The clusters and associated topics provided in this article can be used by regulators and medicine developers as a steppingstone toward a unified way of communicating uncertainties identified during the EMA process to the broader public.

BERT based natural language processing for triage of adverse drug reaction reports shows close to human-level performance.

Post-marketing reports of suspected adverse drug reactions are important for establishing the safety profile of a medicinal product. However, a high influx of reports poses a challenge for regulatory authorities as a delay in identification of previously unknown adverse drug reactions can potentially be harmful to patients. In this study, we use natural language processing (NLP) to predict whether a report is of serious nature based solely on the free-text fields and adverse event terms in the report, potentially allowing reports mislabelled at time of reporting to be detected and prioritized for assessment. We consider four different NLP models at various levels of complexity, bootstrap their train-validation data split to eliminate random effects in the performance estimates and conduct prospective testing to avoid the risk of data leakage. Using a Swedish BERT based language model, continued language pre-training and final classification training, we achieve close to human-level performance in this task. Model architectures based on less complex technical foundation such as bag-of-words approaches and LSTM neural networks trained with random initiation of weights appear to perform less well, likely due to the lack of robustness that a base of general language training provides.

A full-document analysis of the semantic relation between European Public Assessment Reports and EMA guidelines using a BERT language model.

In the European Union, the Committee for Medicinal Products for Human Use of the European Medicines Agency (EMA) develop guidelines to guide drug development, supporting development of efficacious and safe medicines. A European Public Assessment Report (EPAR) is published for every medicine application that has been granted or refused marketing authorisation within the EU. In this work, we study the use of text embeddings and similarity metrics to investigate the semantic similarity between EPARs and EMA guidelines. All 1024 EPARs for initial marketing authorisations from 2008 to 2022 was compared to the 669 current EMA scientific guidelines. Documents were converted to plain text and split into overlapping chunks, generating 265,757 EPAR and 27,649 guideline text chunks. Using a Sentence BERT language model, the chunks were transformed into embeddings and fed into an in-house piecewise matching algorithm to estimate the full-document semantic distance. In an analysis of the document distance scores and product characteristics using a linear regression model, EPARs of anti-virals for systemic use (ATC code J05) and antihemorrhagic medicines (B02) present with statistically significant lower overall semantic distance to guidelines compared to other therapeutic areas, also when adjusting for product age and EPAR length. In conclusion, we believe our approach provides meaningful insight into the interplay between EMA scientific guidelines and the assessment made during regulatory review, and could potentially be used to answer more specific questions such as which therapeutic areas could benefit from additional regulatory guidance.

A natural language processing approach towards harmonisation of European medicinal product information.

Product information (PI) is a vital part of any medicinal product approved for use within the European Union and consists of a summary of products characteristics (SmPC) for healthcare professionals and package leaflet (PL) for patients, together with the product packaging. In this study, based on the English corpus of the EMA product information documents for all centrally approved medicinal products within the EU, a BERT sentence embedding model was used together with clustering and dimensional reduction techniques to identify sentence similarity clusters that could be candidates for standardization. A total of 1258 medicinal products were included in the study. From these, a total of 783 K sentences were extracted from SmPC and PL documents which were aggregated into a total of 284 and 129 semantic similarity clusters, respectively. The spread distribution among clusters shows separation into different cluster types. Examples of clusters with low spread include those with identical word embeddings due to current standardization, such as section headings and standard phrases. Others show minor linguistic variations, while the group with the largest variability contains variable wording but with significant semantic overlap. The sentence clusters identified could serve as candidates for further standardization of the PI. Moving from free text human wording to auto-generated text elements based on multiple-choice input for appropriate parts of the package leaflet and summary of product characteristics, could reduce both time and complexity for applicants as well as regulators, and ultimately provide patients and prescribers with documents that are easier to understand and better adapted for search availabilities.

Intra-arterial versus intra venous contrast-enhanced computed tomography of the equine head.

BACKGROUND: The anatomical complexity of the horse's head limits the abilities of radiography. Computed tomography (CT) in combination with contrast enhanced CT is used more often for diagnosing various head pathology in horses. The objective of this study was to compare intravenous and intra-arterial contrast-enhancement techniques and describe normal and abnormal contrast enhancement in the horse's head. RESULTS: All 24 horses included in the study recovered without complication from the procedures. Compared to the pre-contrast studies, post-contrast studies showed significant contrast enhancement in the pituitary gland (IA: p < 0.0001; IV: p < 0.0001), IA nose septum (p = 0.002), nose mucosa (IA: p < 0.0001; IV: p = 0.02), parotid salivary gland (IA: p < 0.0001; IV p < 0.0001), cerebrum (IA: p < 0.0001; IV: p < 0.0001), rectus capitis muscle (IA: p < 0.0001; IV p = 0.001), IA temporal muscle (p < 0.0001), IA masseter muscle (p <0.0001) and IV brainstem (p = 0.01). No significant contrast enhancement was seen in the eye (IA: p = 0.23; IV p = 0.33), tongue (IA p = 0.2; IV p = 0.57), IA brainstem (p = 0.88), IV nose septum (p = 0.26), IV temporal muscle (p = 0.09) and IV masseter muscle (p = 0.46). Three different categories of abnormal enhancement were detected: a strong vascularised mass, an enhanced rim surrounding an unenhanced structure and an inflamed anatomical structure with abnormal contrast enhancement. CONCLUSION: Using the intra-arterial technique, similar contrast enhancement is achieved using less contrast medium compared to the intravenous technique. And a potential major advantage of the IA technique is the ability to evaluate lesions that are characterized by increased blood flow. Using the intravenous technique, a symmetrical and homogenous enhancement is achieved, however timing is more crucial and the contrast dosage is more of influence in the IV protocol. And a potential major advantage of the IV technique is the ability to evaluate lesions that are characterized by increased vascular permeability. Knowing the different normal contrast enhancement patterns will facilitate the recognition of abnormal contrast enhancements.

Computed tomographic anatomy of the equine stifle joint.

OBJECTIVE: To provide a detailed computed tomography (CT) reference of the anatomically normal equine stifle joint. Sample-16 hind limbs from 8 equine cadavers; no horses had evidence of orthopedic disease of the stifle joints. PROCEDURES: CT of the stifle joint was performed on 8 hind limbs. In all limbs, CT was also performed after intra-articular injection of 60 mL of contrast material (150 mg of iodine/mL) in the lateral and medial compartments of the femorotibial joint and 80 mL of contrast material in the femoropatellar joint (CT arthrography). Reformatted CT images in the transverse, parasagittal, and dorsal plane were matched with corresponding anatomic slices of the 8 remaining limbs. RESULTS: The femur, tibia, and patella were clearly visible. The patellar ligaments, common origin of the tendinous portions of the long digital extensor muscle and peroneus tertius muscle, collateral ligaments, tendinous portion of the popliteus muscle, and cranial and caudal cruciate ligaments could also be consistently evaluated. The cruciate ligaments and the meniscotibial ligaments could be completely assessed in the arthrogram sequences. Margins of the meniscofemoral ligament and the lateral and medial femoropatellar ligaments were difficult to visualize on the precontrast and postcontrast images. CONCLUSIONS AND CLINICAL RELEVANCE: CT and CT arthrography were used to accurately identify and characterize osseous and soft tissue structures of the equine stifle joint. This technique may be of value when results from other diagnostic imaging techniques are inconclusive. The images provided will serve as a CT reference for the equine stifle joint.