論文

Background: Patients with a history of hepatitis B virus (HBV) infection who are receiving immunosuppressive therapy are at risk of HBV reactivation and disease. Therefore, HBV screening is required prior to administering antirheumatic drugs with immunosuppressive effects. This study aimed to determine the status of hepatitis B surface antigen (HBsAg), hepatitis B core antibody (HBcAb), and hepatitis B surface antibody (HBsAb) screening prior to the initiation of drug therapy, including new antirheumatic drugs, in patients with rheumatoid arthritis. Methods: This retrospective cross-sectional study used data from April 2014 to August 2022 from the Japanese hospital-based administrative claims database. The inclusion criteria were rheumatoid arthritis and first prescription date of antirheumatic drugs. Results: A total of 82,282 patients with rheumatoid arthritis who were first prescribed antirheumatic drugs between April 2016 and August 2022 were included. Of the eligible patients, 9.7% (n=7,959) were screened for all HBV (HBsAg, HBsAb, and HbcAb) within 12 months prior to the date of initial prescription. The HBsAg test was performed in 30.0% (n=24,700), HBsAb test in 11.8% (n=9,717), and HBcAb test in 13.1% (n=10,824) of patients. The proportion of patients screened for HBV infection has been increasing since 2018; however, the proportion of patients screened for rheumatoid arthritis remains low. Conclusions: Our findings suggest that HBV screening may be insufficient in patients who received antirheumatic drugs. With the increasing use of new immunosuppressive antirheumatic drugs, including biological agents, healthcare providers should understand the risk of HBV reactivation and conduct appropriate screening.

Patient-reported symptoms provide valuable insights into patient experiences and can enhance healthcare quality; however, effectively capturing them remains challenging. Although natural language processing (NLP) models have been developed to extract adverse events and symptoms from medical records written by healthcare professionals, limited studies have focused on models designed for patient-generated narratives. This study developed an NLP model to extract patient-reported symptoms from pharmaceutical care records and validated its effectiveness in analyzing diverse patient-generated narratives. The target dataset comprised “Subjective” sections of pharmaceutical care records created by community pharmacists for patients prescribed anticancer drugs. Two annotation guidelines were applied to develop robust ground-truth data, which was used to develop and evaluate a new transformer-based named entity recognition model. Model performance was compared with that of an existing tool for Japanese clinical texts and tested on external patient-generated blog data to evaluate generalizability. The newly developed BERT-CRF model significantly outperformed the existing model, achieving an F1 score > 0.8 on pharmaceutical care records and extracting > 98% of physical symptom entries from patient blogs, with a 20% improvement over the existing tool. These findings highlight the importance of fine-tuning models using patient-specific narrative data to capture nuanced and colloquial symptom expressions.

Background: Early detection of adverse events and their management are crucial to improving anticancer treatment outcomes, and listening to patients’ subjective opinions (patients’ voices) can make a major contribution to improving safety management. Recent progress in deep learning technologies has enabled various new approaches for the evaluation of safety-related events based on patient-generated text data, but few studies have focused on the improvement of real-time safety monitoring for individual patients. In addition, no study has yet been performed to validate deep learning models for screening patients’ narratives for clinically important adverse event signals that require medical intervention. In our previous work, novel deep learning models have been developed to detect adverse event signals for hand-foot syndrome or adverse events limiting patients’ daily lives from the authored narratives of patients with cancer, aiming ultimately to use them as safety monitoring support tools for individual patients. Objective: This study was designed to evaluate whether our deep learning models can screen clinically important adverse event signals that require intervention by health care professionals. The applicability of our deep learning models to data on patients’ concerns at pharmacies was also assessed. Methods: Pharmaceutical care records at community pharmacies were used for the evaluation of our deep learning models. The records followed the SOAP format, consisting of subjective (S), objective (O), assessment (A), and plan (P) columns. Because of the unique combination of patients’ concerns in the S column and the professional records of the pharmacists, this was considered a suitable data for the present purpose. Our deep learning models were applied to the S records of patients with cancer, and the extracted adverse event signals were assessed in relation to medical actions and prescribed drugs. Results: From 30,784 S records of 2479 patients with at least 1 prescription of anticancer drugs, our deep learning models extracted true adverse event signals with more than 80% accuracy for both hand-foot syndrome (n=152, 91%) and adverse events limiting patients’ daily lives (n=157, 80.1%). The deep learning models were also able to screen adverse event signals that require medical intervention by health care providers. The extracted adverse event signals could reflect the side effects of anticancer drugs used by the patients based on analysis of prescribed anticancer drugs. “Pain or numbness” (n=57, 36.3%), “fever” (n=46, 29.3%), and “nausea” (n=40, 25.5%) were common symptoms out of the true adverse event signals identified by the model for adverse events limiting patients’ daily lives. Conclusions: Our deep learning models were able to screen clinically important adverse event signals that require intervention for symptoms. It was also confirmed that these deep learning models could be applied to patients’ subjective information recorded in pharmaceutical care records accumulated during pharmacists’ daily work.

Adverse event (AE) management is important to improve anti-cancer treatment outcomes, but it is known that some AE signals can be missed during clinical visits. In particular, AEs that affect patients’ activities of daily living (ADL) need careful monitoring as they may require immediate medical intervention. This study aimed to build deep-learning (DL) models for extracting signals of AEs limiting ADL from patients’ narratives. The data source was blog posts written in Japanese by breast cancer patients. After pre-processing and annotation for AE signals, three DL models (BERT, ELECTRA, and T5) were trained and tested in three different approaches for AE signal identification. The performances of the trained models were evaluated in terms of precision, recall, and F1 scores. From 2,272 blog posts, 191 and 702 articles were identified as describing AEs limiting ADL or not limiting ADL, respectively. Among tested DL modes and approaches, T5 showed the best F1 scores to identify articles with AE limiting ADL or all AE: 0.557 and 0.811, respectively. The most frequent AE signals were “pain or numbness”, “fatigue” and “nausea”. Our results suggest that this AE monitoring scheme focusing on patients’ ADL has potential to reinforce current AE management provided by medical staff.

Intentional overdose (OD) of over-the-counter (OTC) and prescription drugs is becoming a significant social issue all over the world. While previous research has focused on drug misuse, there has been limited analysis using social networking service data. This study aims to analyze posts related to a drug overdose on Twitter® (X®) to understand the characteristics and trends of drug misuse, and to examine the applicability of social media in understanding the current situation of OD through natural language processing techniques. We collected posts in Japanese containing the term“OD”from January 10 to February 8, 2023, and analyzed 30203 posts. Using a pre-trained, fine-tuned bidirectional encoder representations from transformers (BERT) model, we classified the posts into categories, including direct mentions of OD. We examined the content for drug types and emotional context. Among the 5283 posts categorized as“Posts describing ODing,”about one-third included specific drug names or related terms. The most frequently mentioned OTC drugs included active ingredients such as codeine, dextromethorphan, ephedrine, and diphenhydramine. Prescription drugs, particularly benzodiazepines and pregabalin, were also common. Tweets peaked at midnight, suggesting a link between negative emotions and potential OD incidents. Our classifier showed high accuracy in distinguishing OD-related posts. Analyzing Twitter® posts provides valuable insights into the patterns and emotional contexts of drug misuse. Monitoring social networking services for OD-related content could help identify high-risk individuals and inform prevention strategies. Enhanced monitoring and public awareness are crucial to reducing the risks associated with both OTC and prescription drug misuse.

The purpose of this study was to identify patient outcomes after pharmacist interventions in the home health care context using pharmaceutical care records accumulated during daily operations. We focused on 591 cases at Nakajima Pharmacy from April 2020 to December 2021, where dispensing fees were charged to prevent duplication of medication and unnecessary interactions of home patients (excluding those related to adjustment of ongoing medications). The study investigated the content and background of prescription changes, the follow-up rate, and patient outcomes. The most common circumstances that led to pharmacist intervention for homebound patients were symptom occurrence (uncontrolled symptom, new symptom, drug adverse event). Of the patients for whom pharmacist intervention was provided for symptoms, 72.8% received follow-up according to the pharmaceutical care records. Furthermore, 59.2% of patients with follow-up showed an improvement of their symptoms. In addition, many patients had their medications discontinued or the dosage reduced by the pharmacist despite stable symptoms. More than 90% of these patients showed no change in symptoms. Besides interventions associated with the occurrence of symptoms, many interventions related to medication adherence were found to result from the patient’s physical condition, such as poor swallowing function. The results suggest that tracking pharmacy drug histories may help pharmacists to better understand the need for follow-up implementation and the changes in patient outcomes after interventions.

Background: Androgen receptor axis-targeting reagents (ARATs) have become key drugs for patients with castration-resistant prostate cancer (CRPC). ARATs are taken long term in outpatient settings, and effective adverse event (AE) monitoring can help prolong treatment duration for patients with CRPC. Despite the importance of monitoring, few studies have identified which AEs can be captured and assessed in community pharmacies, where pharmacists in Japan dispense medications, provide counseling, and monitor potential AEs for outpatients prescribed ARATs. Therefore, we anticipated that a named entity recognition (NER) system might be used to extract AEs recorded in pharmaceutical care records generated by community pharmacists. Objective: This study aimed to evaluate whether an NER system can effectively and systematically identify AEs in outpatients undergoing ARAT therapy by reviewing pharmaceutical care records generated by community pharmacists, focusing on assessment notes, which often contain detailed records of AEs. Additionally, the study sought to determine whether outpatient pharmacotherapy monitoring can be enhanced by using NER to systematically collect AEs from pharmaceutical care records. Methods: We used an NER system based on the widely used Japanese medical term extraction system MedNER-CR-JA, which uses Bidirectional Encoder Representations from Transformers (BERT). To evaluate its performance for pharmaceutical care records by community pharmacists, the NER system was first applied to 1008 assessment notes in records related to anticancer drug prescriptions. Three pharmaceutically proficient researchers compared the results with the annotated notes assigned symptom tags according to annotation guidelines and evaluated the performance of the NER system on the assessment notes in the pharmaceutical care records. The system was then applied to 2193 assessment notes for patients prescribed ARATs. Results: The F1-score for exact matches of all symptom tags between the NER system and annotators was 0.72, confirming the NER system has sufficient performance for application to pharmaceutical care records. The NER system automatically assigned 1900 symptom tags for the 2193 assessment notes from patients prescribed ARATs; 623 tags (32.8%) were positive symptom tags (symptoms present), while 1067 tags (56.2%) were negative symptom tags (symptoms absent). Positive symptom tags included ARAT-related AEs such as “pain,” “skin disorders,” “fatigue,” and “gastrointestinal symptoms.” Many other symptoms were classified as serious AEs. Furthermore, differences in symptom tag profiles reflecting pharmacists’ AE monitoring were observed between androgen synthesis inhibition and androgen receptor signaling inhibition. Conclusions: The NER system successfully extracted AEs from pharmaceutical care records of patients prescribed ARATs, demonstrating its potential to systematically track the presence and absence of AEs in outpatients. Based on the analysis of a large volume of pharmaceutical medical records using the NER system, community pharmacists not only detect potential AEs but also actively monitor the absence of severe AEs, offering valuable insights for the continuous improvement of patient safety management.

Background: A challenge in updating systematic reviews is the workload in screening the articles. Many screening models using natural language processing technology have been implemented to scrutinize articles based on titles and abstracts. While these approaches show promise, traditional models typically treat abstracts as uniform text. We hypothesize that selective training on specific abstract components could enhance model performance for systematic review screening. Objective: We evaluated the efficacy of a novel screening model that selects specific components from abstracts to improve performance and developed an automatic systematic review update model using an abstract component classifier to categorize abstracts based on their components. Methods: A screening model was created based on the included and excluded articles in the existing systematic review and used as the scheme for the automatic update of the systematic review. A prior publication was selected for the systematic review, and articles included or excluded in the articles screening process were used as training data. The titles and abstracts were classified into 5 categories (Title, Introduction, Methods, Results, and Conclusion). Thirty-one component-composition datasets were created by combining 5 component datasets. We implemented 31 screening models using the component-composition datasets and compared their performances. Comparisons were conducted using 3 pretrained models: Bidirectional Encoder Representations from Transformer (BERT), BioLinkBERT, and BioM- Efficiently Learning an Encoder that Classifies Token Replacements Accurately (ELECTRA). Moreover, to automate the component selection of abstracts, we developed the Abstract Component Classifier Model and created component datasets using this classifier model classification. Using the component datasets classified using the Abstract Component Classifier Model, we created 10 component-composition datasets used by the top 10 screening models with the highest performance when implementing screening models using the component datasets that were classified manually. Ten screening models were implemented using these datasets, and their performances were compared with those of models developed using manually classified component-composition datasets. The primary evaluation metric was the F10-Score weighted by the recall. Results: A total of 256 included articles and 1261 excluded articles were extracted from the selected systematic review. In the screening models implemented using manually classified datasets, the performance of some surpassed that of models trained on all components (BERT: 9 models, BioLinkBERT: 6 models, and BioM-ELECTRA: 21 models). In models implemented using datasets classified by the Abstract Component Classifier Model, the performances of some models (BERT: 7 models and BioM-ELECTRA: 9 models) surpassed that of the models trained on all components. These models achieved an 88.6% reduction in manual screening workload while maintaining high recall (0.93). Conclusions: Component selection from the title and abstract can improve the performance of screening models and substantially reduce the manual screening workload in systematic review updates. Future research should focus on validating this approach across different systematic review domains.

Abstract Background In Japan, engineering controls for preparing injectable anticancer drugs are inadequate and compliance with appropriate preparation procedures is vital. In this study, we evaluated the effects of adherence to appropriate anticancer drug formulation and packaging procedures on reducing anticancer drug dispersal in clinical practice, especially in Japan. Methods We quantitatively evaluated the effectiveness of implementing procedures that were experimentally verified to help reduce the amount of anticancer drug dispersed during preparation based on procedures described in the “Anticancer Drug Preparation Manual.” The target facilities were four regional hub hospitals in the Kanto area. Contamination of sheets and gloves with 5-fluorouracil (5-FU) and gemcitabine (GEM) in a safety cabinet during formulation was evaluated using wipe tests. Subsequently, the proper preparation procedure was shown on a video, training was provided, and the wipe tests were repeated. Results Forty-one and 39 pharmacists were engaged in drug preparation before and after intervention, respectively. 5-FU had the highest dispersal per prepared vial on the sheet before intervention. The dispersal amount per prepared vial decreased significantly (P = 0.01) after intervention. The amount of GEM dispersed before and after intervention did not differ significantly. However, the percentage of sheets below the detection limit after intervention was 62%, increasing from 46% before intervention. The amount dispersed on gloves was not significantly reduced by proper preparation technique. Although not explicitly noticeable and quantifiable, pharmacists must consider that a significant amount of anticancer drug is dispersed on gloves despite following appropriate preparation procedures. Conclusions Quantitative amounts of anticancer drugs dispersed in the preparations of 5-FU and GEM were found in our study. The difference in the amount of contamination before and after intervention was significantly reduced only for the contamination of sheets with 5-FU. There was no decrease in the amount of glove contamination. There was also no difference between medical facilities. Despite following appropriate preparation procedures, dispersed amounts cannot be maintained below the detection limit, indicating the need for a combination of education and engineering controls.