Related references
Note: Only part of the references are listed.
Review
Oncology
Wiebke Roesler et al.
Summary: This article provides an expert consensus statement on the application of artificial intelligence (AI) in hematology and oncology. It proposes a technological definition and presents a taxonomy of clinically relevant AI systems. The article also highlights potential applications in clinical, research, and educational environments in the field of hematology and oncology.
JOURNAL OF CANCER RESEARCH AND CLINICAL ONCOLOGY
(2023)
Letter
Oncology
Vera Sorin et al.
Summary: Large language models like ChatGPT have attracted attention from the public and the scientific community. These models have the potential to assist oncologists in their work, but it is important for oncologists to understand their limitations and potential risks.
JOURNAL OF CANCER RESEARCH AND CLINICAL ONCOLOGY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Arya Rao et al.
Summary: This study evaluates the use of large language models for clinical decision support in radiology and finds that ChatGPT has high accuracy in breast cancer screening but lower accuracy in breast pain.
JOURNAL OF THE AMERICAN COLLEGE OF RADIOLOGY
(2023)
Article
Construction & Building Technology
Qinghe Zheng et al.
Summary: Air pollution is a serious environmental problem and a hot topic in sustainable city development. AI-based air quality sensing and prediction systems are becoming increasingly important in governance towards sustainable cities. This paper proposes a wavelet-packet transform driven deep learning model for predicting PM2.5 concentration in Qingdao, China, and demonstrates its effectiveness.
SUSTAINABLE CITIES AND SOCIETY
(2023)
Article
Computer Science, Theory & Methods
Ziwei Ji et al.
Summary: Natural Language Generation (NLG) has made significant progress in recent years, thanks to deep learning technologies like Transformer-based language models. This advancement has resulted in more fluent and coherent NLG, leading to improvements in tasks such as summarization, dialogue generation, and data-to-text conversion. However, deep learning-based generation is prone to producing unintended text, which affects system performance and fails to meet user expectations in real-world scenarios. To address this issue, researchers have conducted studies on measuring and mitigating hallucinated texts. This survey provides an overview of the research progress and challenges in the hallucination problem in NLG, covering metrics, mitigation methods, and task-specific research progress.
ACM COMPUTING SURVEYS
(2023)
Article
Public, Environmental & Occupational Health
Luigi De Angelis et al.
Summary: Large Language Models (LLMs) have gained attention due to the release of ChatGPT, a user-centered chatbot by OpenAI. This perspective article discusses the evolution of LLMs and the impact of ChatGPT in the field of artificial intelligence. LLMs offer multiple opportunities in scientific research, particularly in Natural Language Processing (NLP) tasks. However, the use of LLMs, including ChatGPT, presents ethical and practical challenges, especially in the medical field, where it has the potential to impact public health and exacerbate the spread of misinformation.
FRONTIERS IN PUBLIC HEALTH
(2023)
Editorial Material
Oncology
Vivian Weiwen Xue et al.
CLINICAL AND TRANSLATIONAL MEDICINE
(2023)
Article
Oncology
Vera Sorin et al.
Summary: This study evaluates ChatGPT as a support tool for breast tumor board decisions. Clinical information of ten patients was inserted into ChatGPT-3.5 to obtain management recommendations. The recommendations generated by ChatGPT were compared to the tumor board's decisions and independently graded by two senior radiologists. 70% of the recommendations from ChatGPT were consistent with the tumor board.
Editorial Material
Medical Informatics
Sajan B. Patel et al.
LANCET DIGITAL HEALTH
(2023)
Review
Computer Science, Artificial Intelligence
Ali Garavand et al.
Summary: This study systematically reviewed the use of artificial intelligence classification algorithms in detecting and diagnosing coronary artery disease (CAD). The findings showed that models based on different machine learning methods were successful in CAD diagnosis, providing clinical specialists with a powerful tool for quick and precise diagnosis.
INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS
(2023)
Article
Health Care Sciences & Services
Arya Rao et al.
JOURNAL OF MEDICAL INTERNET RESEARCH
(2023)
Article
Clinical Neurology
Rohaid Ali et al.
Letter
Surgery
Javier Vela Ulloa et al.
BRITISH JOURNAL OF SURGERY
(2023)
Article
Oncology
Anna D. Barker et al.
Summary: The big data revolution in cancer research is leading to progress and challenges, requiring a rebuild of an information and evidence-based learning system.
Article
Oncology
Thomas S. Tarawneh et al.
Summary: The molecular characterization of tumor tissues is essential for tumor classification, prognosis assessment, and treatment optimization. This study implemented three complementary NGS assays as a diagnostic tool in a Molecular Tumor Board and successfully provided personalized treatment recommendations for 75% of patients. These findings indicate that a combination of focused genetic diagnostics is highly informative for routine cancer care.
Article
Health Care Sciences & Services
Eric A. A. Stahlberg et al.
Summary: We are approaching a future where cancer patient digital twins can accurately predict and assist in the prevention, diagnosis, and treatment of cancer. This is made possible through advancements in high performance computing, computational modeling, and the availability of diverse observational data. The US National Cancer Institute and the US Department of Energy have launched collaborative projects to develop and implement predictive Cancer Patient Digital Twins, aiming to explore different approaches, such as deep phenotyping, personalized treatment planning, and treatment monitoring. These efforts have provided valuable insights into the opportunities and challenges of cancer patient digital twin approaches and shaped the future research direction.
FRONTIERS IN DIGITAL HEALTH
(2022)
Review
Oncology
Sameer Quazi
Summary: The advancement of precision medicine improves healthcare by enhancing diagnostics, customizing treatments, and predicting early disease risks. Scrutinizing overall patient data and broad factors helps differentiate between ill and relatively healthy individuals, leading to the most appropriate path for precision medicine.
Article
Health Care Sciences & Services
Mustafa Ghaderzadeh et al.
Summary: A highly efficient computer-aided detection (CAD) system using a neural search architecture network (NASNet)-based algorithm was designed for COVID-19 detection, achieving remarkable results in identifying patients with COVID-19 in the early stages. The performance of the CAD system demonstrated high detection sensitivity, specificity, and accuracy, showing potential to help radiologists detect COVID-19 early on and prevent the loss of healthcare resources during the pandemic.
JOURNAL OF MEDICAL INTERNET RESEARCH
(2021)
Review
Biotechnology & Applied Microbiology
Mustafa Ghaderzadeh et al.
Summary: This study systematically reviewed the application of artificial intelligence in X-ray imaging analysis for diagnosing COVID-19 cases. It found that X-rays equipped with AI algorithms had an average sensitivity and specificity of over 96% and 92% respectively, significantly higher than common X-ray methods for COVID-19 detection.
BIOMED RESEARCH INTERNATIONAL
(2021)
Article
Oncology
Xiaoyao Zhao et al.
JAPANESE JOURNAL OF CLINICAL ONCOLOGY
(2020)
Review
Oncology
Tanmoy Bhattacharya et al.
FRONTIERS IN ONCOLOGY
(2019)
Article
Oncology
S. P. Somashekhar et al.
ANNALS OF ONCOLOGY
(2018)
