RESUMO
PURPOSE: Electronic health records (EHRs) are valuable information repositories that offer insights for enhancing clinical research on breast cancer (BC) using real-world data. The objective of this study was to develop a natural language processing (NLP) model specifically designed to extract structured data from BC pathology reports written in natural language. METHODS: During the initial phase, the algorithm's development cohort comprised 193 pathology reports from 116 patients with BC from 2012 to 2016. A rule-based NLP algorithm was applied to extract 26 variables for analysis and was compared with the manual extraction of data performed by both a data entry specialist and an oncologist. Following the first approach, the data set was expanded to include 513 reports, and a Named Entity Recognition (NER)-NLP model was trained and evaluated using K-fold cross-validation. RESULTS: The first approach led to a concordance analysis, which revealed an 82.9% agreement between the algorithm and the oncologist, whereas the concordance between the data entry specialist and the oncologist was 90.8%. The second training approach introduced the definition of an NER-NLP model, in which the accuracy showed remarkable potential (97.8%). Notably, the model demonstrated remarkable performance, especially for parameters such as estrogen receptor, progesterone receptor, human epidermal growth factor receptor 2, and Ki-67 (F1-score 1.0). CONCLUSION: The present study aligns with the rapidly evolving field of artificial intelligence (AI) applications in oncology, seeking to expedite the development of complex cancer databases and registries. The results of the model are currently undergoing postprocessing procedures to organize the data into tabular structures, facilitating their utilization in real-world clinical and research endeavors.
Assuntos
Algoritmos , Neoplasias da Mama , Registros Eletrônicos de Saúde , Processamento de Linguagem Natural , Humanos , Neoplasias da Mama/patologia , Neoplasias da Mama/diagnóstico , Feminino , Pessoa de Meia-Idade , Idoso , Adulto , Mineração de Dados/métodosRESUMO
Secondary neoplastic lesions in lymph nodes are predominantly metastases from solid tumors, whereas primary lymph node hemangiomas are exceptionally uncommon, with only 24 well-documented cases in the literature. Histologically, they are characterized by endothelial cells that may appear flattened or enlarged, with variable vascular density, and the presence of stromal elements. Notably, the concurrent presence of a primary hemangioma and a metastasis from breast cancer - the latter being the most prevalent secondary lesion in axillary lymph nodes - represents an unprecedented observation. The unique case presented herein underscores the exceptional rarity of primary lymph node hemangiomas and demonstrates for the first time their possible coexistence with breast cancer metastasis within the same axillary lymph node. In sharing and discussing this case study, we pay homage to Professor Juan Rosai, whose work in redefining rare and complex diagnoses continues to enlighten our understanding of lymph node vascular lesions.
Assuntos
Neoplasias da Mama , Hemangioma , Linfonodos , Metástase Linfática , Humanos , Feminino , Neoplasias da Mama/patologia , Hemangioma/patologia , Linfonodos/patologia , Pessoa de Meia-IdadeRESUMO
Since the release of the DESTINY-Breast04 (DB-04) trial findings in June 2022, the field of pathology has seen a renaissance of HER2 as a predictive biomarker in breast cancer. The trial focused on patients with metastatic breast cancer who were classified as "HER2-low," i.e., those with immunohistochemistry (IHC) HER2 1 + or 2 + and negative in situ hybridization (ISH) results. The study revealed that treating these patients with trastuzumab deruxtecan (T-DXd) instead of the oncologist's chosen chemotherapy led to outstanding improvements in survival. This has challenged the existing binary HER2 pathological classification system, which categorized tumors as either positive (overexpression/amplification) or negative, as per the ASCO/CAP 2018 guideline reaffirmed by ASCO/CAP 2023 guideline update. Given that DB-04 excluded patients with HER2 IHC score 0 status, the results of the ongoing DB-06 trial may shed further light on the potential benefits of T-DXd therapy for these patients. Roughly half of all breast cancers are estimated to belong to the HER2-low category, which does not represent a distinct or specific subtype of cancer. Instead, it encompasses a diverse group of tumors that exhibit clinical, morphological, immunohistochemical, and molecular variations. However, HER2-low offers a distinctive biomarker status that identifies a specific therapeutic regimen (i.e., T-DXd) linked to a favorable prognosis in breast cancer. This unique association emphasizes the importance of accurately identifying these tumors. Differentiating between a HER2 IHC score 0 and score 1 + has not been clinically significant until now. To ensure accurate classification and avoid misdiagnosis, it is necessary to adopt standardized procedures, guidelines, and specialized training for pathologists in interpreting HER2 expression in the lower spectrum. Additionally, the utilization of artificial intelligence holds promise in supporting this endeavor. Here, we address the current state of the art and unresolved issues in assessing HER2-low status, with a particular emphasis on the score 0. We explore the dilemma surrounding the exclusion of HER2-zero patients from potentially beneficial therapy based on traditional HER2 testing. Additionally, we examine the clinical context, considering that DB-04 primarily involved heavily pretreated late-stage metastatic breast cancers. We also delve into emerging evidence suggesting that extrapolating HER2-low status from the original diagnosis may lead to misleading results. Finally, we provide recommendations for conducting high-quality testing and propose a standardized pathology report in compliance with 2023 ASCO/CAP updates and 2023 ESMO consensus statements on HER2-low breast cancer.
Assuntos
Neoplasias da Mama , Receptor ErbB-2 , Humanos , Feminino , Hibridização in Situ Fluorescente/métodos , Receptor ErbB-2/genética , Neoplasias da Mama/metabolismo , Inteligência Artificial , Hibridização In Situ , Biomarcadores TumoraisRESUMO
A gallbladder tumor is a rare condition, which usually spreads to the liver, lymph nodes, and other organs. A Krukenberg tumor, derived from the biliary tract and gallbladder cancers (GBCs), is an uncommon finding in routine clinical practice. Here, a case of a young woman with a Krukenberg tumor related to a previous diagnosis of GBC is reported. Differential diagnosis of an ovarian malignant lesion is challenging for both clinicians and pathologists. In order to provide a proper diagnosis, integrated multidisciplinary management is essential. The occurrence of Krukenberg tumors should be evaluated in the management of GBC, even if this is rare in clinical practice.
RESUMO
A black-spotted duodenal mucosa was observed during endoscopy of a man with several comorbidities including hypertension and end-stage kidney disease. Histopathological examination revealed pigment-laden macrophages in the lamina propria of the duodenal villi, which was consistent with duodenal pseudomelanosis.
RESUMO
Duodenal pseudomelanosis (also known as pseudomelanosis duodeni) is a rare endoscopic incidental finding defined by a pigmentation limited to the apex of the intestinal villi, which requires histological confirmation. While its exact pathogenesis is still poorly understood, it appears free from clinical consequences. This condition is believed to be associated with oral iron intake, antihypertensive drugs containing a sulfur moiety (i.e., hydralazine, furosemide), and several chronic diseases (i.e., hypertension, end-stage renal disease, diabetes). However, the exact prevalence of these treatments and comorbidities among patients with duodenal pseudomelanosis is not clearly defined. Several case reports and case series about duodenal pseudomelanosis have been published in recent years. In this review, we aimed to clearly define its endoscopic and microscopic presentation; its epidemiology, associated comorbidities, and drugs; the most useful special histochemical techniques used to classify the nature of the pigmentation; and the most relevant differential diagnoses. In addition, by considering our findings, we also formulated a number of hypotheses about its pathogenesis.