Purpose: Recommendations to improve therapeutics (Recos) are proposals made by pharmacists during the prescription review process to address sub-optimal use of medicines. In hospitals, Recos are generated daily as text documents that are sent to prescribers. If collected Recos data were easier and less time-consuming to summarize, they could be used retrospectively to improve safeguards for better prescribing. The objective of this work was to train a deep learning algorithm for automatic Recos classification in order to value the large amount of Recos data. Methods: The study was conducted at the University Hospital of Strasbourg. Recos data were collected throughout 2017. Data from the first six months of 2017 were labeled by two pharmacists who assigned to each of the Recos one of the 29 possible classes of the French Society of Clinical Pharmacy classification. A deep neural network classifier was trained to predict the class of Recos from the raw text data. Results: 27,699 labeled Recos from the first half of 2017 were used to train and evaluate a classifier. The prediction accuracy calculated on a validation data set was 78.0%. We predicted classes for the unlabeled Recos collected during the second half of 2017. Of the 4,460 predictions reviewed, 67 required corrections. After these additional labeled data were concatenated with the original data set and the neural network re-trained, accuracy reached 81.0 %. Conclusions: We report an efficient automatic classification of Recos. Making retrospective prescription review data easier to understand should enable better anticipation of prescription-related problems in future prescriptions, thereby improving patient safety.

Objective: Medication review (MR) is the systematic assessment of a patient's medicines - a critical step in preventing of drug adverse events. MR aims to identify drug-related problems (DRP) that trigger documented pharmacist interventions (PI). The information-rich data documenting PI, produced daily, provides a unique opportunity to develop a deep learning algorithm to automatically categorize PI. Materials and Methods: The study was conducted at the University Hospital of Strasbourg. Text data documenting PI were collected over the year 2017. Data from the first six-months of 2017 were reviewed by pharmacists who manually assigned to each PI the main class of the 29 possible classes of the French Society of Clinical Pharmacy classification. A deep neural network classifier was then trained to learn to automatically predict the main PI class from processed text data. Accuracy, specificity and sensitivity metrics were used to evaluate performance. Results: 27,699 PI (first six-months of 2017) were extracted, processed and used to train and evaluate a classifier. Class prediction accuracy calculated on the validation dataset was 78.0%. Class specific sensitivities and specificities ranged from 0.31 to 0.96 and from 0.94 to 1.00, respectively. To demonstrate the classification ability of the algorithm, we predicted the PI class for documents collected during the second semester of 2017. Of the 4,460 predictions checked, only 67 required corrections. The latter data was concatenated with the original dataset to create an extended dataset to re-train the neural network. The updated global accuracy reached 81.0% showing that the prediction process can still improve with the increase in the amount of data. Conclusion: PI classification is beneficial for assessing and improving pharmaceutical care practice. Here we report a high performance automatic PI classification based on deep learning. This application could find an essential place to highlight the clinical relevance of the review of drug prescriptions performed daily by hospital pharmacists.

Objectives: The emergence of artificial intelligence (AI) is catching the interest of hospitals pharmacists. Massive collection of pharmaceutical data is now available to train AI models and hold the promise of disrupting codes and practices. The objective of this systematic review was to examine the state of the art of machine learning or deep learning models that detect inappropriate hospital medication orders. Methods: A systematic review was conducted according to the PRISMA statement. PubMed and Cochrane database were searched from inception to May 2023. Studies were included if they reported and described an AI model intended for use by clinical pharmacists in hospitals. Results: After reviewing, thirteen articles were selected. Eleven studies were published between 2020 and 2023; eight were conducted in North America and Asia. Six analyzed orders and detected inappropriate prescriptions according to patient profiles and medication orders, seven detected specific inappropriate prescriptions. Various AI models were used, mainly supervised learning techniques. Conclusions: This systematic review points out that, to date, few original research studies report AI tools based on machine or deep learning in the field of hospital clinical pharmacy. However, these original articles, while preliminary, highlighted the potential value of integrating AI into clinical hospital pharmacy practice.