The integration of (NLP) and transformers, such as BERT, in the medical field has revolutionized text processing and analysis, offering remarkable opportunities for advancements in research and clinical practice. This article presents a comprehensive exploration of the application of NLP and transformers in the medical domain, specifically focusing on their utilization in cancer-related radiological reports' classification by priority. The study employs BERT, a bidirectional transformer-based language model, to convert radiological reports into embedding vectors, capturing contextual relationships between words. An attention technique is employed to aggregate word-embedding vectors, emphasizing important words within the report. next, an analysis using the gated rectified unit (GRU) is performed on a collection of radiological reports pertaining to an individual patient. This analysis aims to derive a patient embedding vector, which encapsulates the essential information from the multiple reports and represents the overall condition of the patient. Finally, a classifier is implemented to classify the reports based on their priority levels, enabling doctors to treat patients in an ordered and timely manner. Experimental results on a dataset consisting of 1,000 cancer-related radiological reports demonstrate the efficacy of the proposed approach. The dataset includes reports with varying degrees of severity, allowing for the classification of reports into priority categories. Evaluation metrics such as precision, recall, and F1 score showcase the model's accuracy and robustness, achieving high performance across different priority levels.

We are presently living in the age of intelligent machines, machines are rapidly imitating humans as a result of technological breakthroughs and advances in machine learning, deep learning, and artificial intelligence. In our work, we based our approach on the idea of utilizing a specialized corpus to enhance the performance of a pre-trained language model. We utilized the following approach: (V = vocabulary domain, C1 = initial corpus, C2 = specialization corpus). We applied this approach with different combinations such as (V = general, C1 = general, C2 = ∅), (V = general, C1 = general, C2 = medical), (V = medical, C1 = medical, C2 = ∅), and (V = medical, C1 = medical, C2 = medical) to compare the performance of a general bidirectional encoder representations from transformers model and specialized BERT models for the medical domain. In addition, we evaluated the model’s using informatics for integrating biology and the bedside, and drug-drug interaction datasets to measure their effectiveness in medical tasks.

Breast cancer, a leading cause of cancer mortality among women, necessitates early detection to improve survival rates. Traditional diagnostics face accuracy and speed limitations, prompting this study to explore machine learning for enhanced diagnostics. We applied bidirectional encoder representations from transformers (BERT), long short-term memory (LSTM), naive Bayes, support vector machine (SVM), and random forest to the Breast Cancer Wisconsin dataset, implementing a thorough methodology involving data preprocessing, feature extraction, and model validation. BERT led in accuracy at 92.5%, showcasing advanced algorithms' potential in medical diagnostics, with random forest 90.6%, SVM 89.3%, LSTM 88.7%, and naive Bayes 85.2%; also showing promising results. The study underscores the importance of incorporating machine learning, especially BERT, into clinical decision-making, potentially revolutionizing breast cancer diagnostics by improving accuracy and efficiency. We recommend healthcare practitioners integrate these algorithms into their diagnostic processes. Future research should reeefine these algorithms and extend their application to enhance patient care further.