Publications by authors named "F F Mohamad"
Rationale And Objectives: Training Convolutional Neural Networks (CNN) requires large datasets with labeled data, which can be very labor-intensive to prepare. Radiology reports contain a lot of potentially useful information for such tasks. However, they are often unstructured and cannot be directly used for training.
View Article and Find Full Text PDFArticle Synopsis
- Advances in large language models (LLMs) have led to numerous commercial and open-source models, but there has been no real-world comparison of OpenAI's GPT-4 against these models for extracting information from radiology reports.
- The study aimed to compare GPT-4 with several leading open-source LLMs in extracting relevant findings from chest radiograph reports using datasets from the ImaGenome and Massachusetts General Hospital.
- Results showed that GPT-4 slightly outperformed the best open-source model, Llama 2-70B, in terms of accuracy scores, with both showing strong performance in extracting findings from the reports.
Metabolic changes in an organism often occur much earlier than macroscopic manifestations of disease, such as invasive tumors. Therefore, noninvasive tools to monitor metabolism are fundamental as they provide insights into in vivo biochemistry. NMR represents one of the gold standards for such insights by observing metabolites.
View Article and Find Full Text PDFA cave represents a subterranean ecosystem that harbours a myriad of unique, peculiar, and secluded flora and fauna. These biotas have evolved with a wide range of ecological adaptations that allow them to thrive in harsh environments with limited light. Gua Kelam 1 constitutes part of the Gua Kelam limestone caves system in the Nakawan Range of Perlis State Park, Malaysia.
View Article and Find Full Text PDFBackground: The state of Sarawak on the island of Borneo in East Malaysia, in working towards developing and strengthening cancer services through a holistic patient-centred approach, must focus on the comprehensive needs of cancer patients by taking into account the psycho-social, cultural and spiritual aspects of Sarawak's multi-ethnic, multi-cultural population.
Methods: A 42-item survey questionnaire was developed and validated with a total of 443 patients. The perceived importance of information provided and level of patient satisfaction were assessed with a 5-point Likert scale in 10 domains (Diagnosis, Surgery, Radiotherapy, Systemic therapy, Clinical trials, Pain management, Treatment monitoring, Psychosocial support, Sexual care and fertility issues, and Financial support).