Chemical identification and indexing in full-text articles: an overview of the NLM-Chem track at BioCreative VII.

The BioCreative National Library of Medicine (NLM)-Chem track calls for a community effort to fine-tune automated recognition of chemical names in the biomedical literature. Chemicals are one of the most searched biomedical entities in PubMed, and-as highlighted during the coronavirus disease 2019 pandemic-their identification may significantly advance research in multiple biomedical subfields. While previous community challenges focused on identifying chemical names mentioned in titles and abstracts, the full text contains valuable additional detail. We, therefore, organized the BioCreative NLM-Chem track as a community effort to address automated chemical entity recognition in full-text articles. The track consisted of two tasks: (i) chemical identification and (ii) chemical indexing. The chemical identification task required predicting all chemicals mentioned in recently published full-text articles, both span [i.e. named entity recognition (NER)] and normalization (i.e. entity linking), using Medical Subject Headings (MeSH). The chemical indexing task required identifying which chemicals reflect topics for each article and should therefore appear in the listing of MeSH terms for the document in the MEDLINE article indexing. This manuscript summarizes the BioCreative NLM-Chem track and post-challenge experiments. We received a total of 85 submissions from 17 teams worldwide. The highest performance achieved for the chemical identification task was 0.8672 F-score (0.8759 precision and 0.8587 recall) for strict NER performance and 0.8136 F-score (0.8621 precision and 0.7702 recall) for strict normalization performance. The highest performance achieved for the chemical indexing task was 0.6073 F-score (0.7417 precision and 0.5141 recall). This community challenge demonstrated that (i) the current substantial achievements in deep learning technologies can be utilized to improve automated prediction accuracy further and (ii) the chemical indexing task is substantially more challenging. We look forward to further developing biomedical text-mining methods to respond to the rapid growth of biomedical literature. The NLM-Chem track dataset and other challenge materials are publicly available at https://ftp.ncbi.nlm.nih.gov/pub/lu/BC7-NLM-Chem-track/. Database URL https://ftp.ncbi.nlm.nih.gov/pub/lu/BC7-NLM-Chem-track/.

Delays in the assessment and management of primary lung cancers in South Auckland.

AIM: To determine the patient characteristics, referral patterns and delays in assessment and treatment of patients with primary lung cancer in South Auckland, New Zealand and compare with international standards. METHODS: Retrospective review of the clinical records of 80 patients referred to a secondary care respiratory service and diagnosed with primary lung cancer in 2004. RESULTS: Eighty-five percent of inpatient referrals and 48.5% of outpatient referrals were for advanced stage lung cancers. The median interval from receipt of outpatient referral to first chest physician assessment was 18 days, with median interval from the first chest physician assessment to bronchoscopy of 17 days and for staging CT chest of 16 days. For patients requiring a CT-guided percutaneous needle aspiration for diagnosis, there was a further median delay of 37 days after the initial CT scan. The median interval from the date of receipt of initial outpatient referral to diagnosis was 38 days, but for early stage lung cancers it was 54 days. The median interval to diagnosis for inpatient admissions was 6 days after the first respiratory assessment. CONCLUSION: The intervals for initial assessment, diagnosis and treatment of lung cancer in South Auckland do not meet the recommendations of international guidelines, especially for early stage lung cancers. Organisational and resource changes are required at each point in the diagnostic and management pathway to reduce delays.