ABSTRACT
More than 7000 rare diseases affect over 400 million people, posing significant challenges for medical research and healthcare. The integration of precision medicine with artificial intelligence offers promising solutions. This work introduces a classifier developed to discern whether research and news articles pertain to rare or non-rare diseases. Our methodology involves extracting 709 rare disease MeSH terms from Mondo and MeSH to improve rare disease categorization. We evaluate our classifier on abstracts from PubMed/MEDLINE and an expert-annotated news dataset, which includes news articles on four selected rare neurodevelopmental disorders (NDDs)-considered the largest category of rare diseases-from a total of 16 analyzed. We achieved F1 scores of 85% for abstracts and 71% for news articles, demonstrating robustness across both datasets and highlighting the potential of integrating artificial intelligence and ontologies to improve disease classification. Although the results are promising, they also indicate the need for further refinement in managing data heterogeneity. Our classifier improves the identification and categorization of medical information, essential for advancing research, enhancing information access, influencing policy, and supporting personalized treatments. Future work will focus on expanding disease classification to distinguish between attributes such as infectious and hereditary diseases, addressing data heterogeneity, and incorporating multilingual capabilities.
ABSTRACT
BACKGROUND: The term phyllodes tumours, which account for less than 1% of breast neoplasms, describes a spectrum of heterogenous tumours with different clinical behaviours. Less than 30% present as metastatic disease. Complete surgical resection is the standard of care so that recurrence rates are reduced. The role of adjuvant chemotherapy or radiation therapy is controversial. Patients with metastatic disease have a median overall survival of around 30 months. CASE DESCRIPTION: The authors present the case of a 57-year-old woman with an exuberant left malignant phyllodes tumour with bilateral involvement, as well as lung and axillar metastasis. The patient underwent haemostatic radiation therapy and started palliative chemotherapy with doxorubicin, achieving partial response with significant improvement in quality of life. A posterior simple mastectomy revealed a small residual tumour. DISCUSSION: Metastatic malignant phyllodes tumours are rare, so therapeutic strategies rely on small retrospective studies and guidelines for soft tissue sarcoma. Palliative chemotherapy protocols include anthracycline-based regimens, either as monotherapy with doxorubicin or doxorubicin together with ifosfamide. With few treatment options, management of these patients must rely on a continuum of care. LEARNING POINTS: Phyllodes tumours are a rare type of breast neoplasm.The differential diagnosis of breast cancer should include phyllodes tumours.Accurate and rapid diagnosis is required.
ABSTRACT
MOTIVATION: In the age of big data, the amount of scientific information available online dwarfs the ability of current tools to support researchers in locating and securing access to the necessary materials. Well-structured open data and the smart systems that make the appropriate use of it are invaluable and can help health researchers and professionals to find the appropriate information by, e.g., configuring the monitoring of information or refining a specific query on a disease. METHODS: We present an automated text classifier approach based on the MEDLINE/MeSH thesaurus, trained on the manual annotation of more than 26 million expert-annotated scientific abstracts. The classifier was developed tailor-fit to the public health and health research domain experts, in the light of their specific challenges and needs. We have applied the proposed methodology on three specific health domains: the Coronavirus, Mental Health and Diabetes, considering the pertinence of the first, and the known relations with the other two health topics. RESULTS: A classifier is trained on the MEDLINE dataset that can automatically annotate text, such as scientific articles, news articles or medical reports with relevant concepts from the MeSH thesaurus. CONCLUSIONS: The proposed text classifier shows promising results in the evaluation of health-related news. The application of the developed classifier enables the exploration of news and extraction of health-related insights, based on the MeSH thesaurus, through a similar workflow as in the usage of PubMed, with which most health researchers are familiar.
