-
Cancer Discovery Dec 2023This article presents a review of recent major advances in precision oncology and the future implications of these advances, specifying the iterative progress achieved... (Review)
Review
This article presents a review of recent major advances in precision oncology and the future implications of these advances, specifying the iterative progress achieved from the end of 2022 through 2023. We discuss the different classes of precision oncology drugs and associated biomarkers as well as the improvements in clinical trial design that have enabled the efficient testing of these drugs.
Topics: Humans; Neoplasms; Precision Medicine; Medical Oncology; Biomarkers, Tumor
PubMed: 38084089
DOI: 10.1158/2159-8290.CD-23-1194 -
Nature Aug 2023Large language models (LLMs) have demonstrated impressive capabilities, but the bar for clinical applications is high. Attempts to assess the clinical knowledge of... (Comparative Study)
Comparative Study
Large language models (LLMs) have demonstrated impressive capabilities, but the bar for clinical applications is high. Attempts to assess the clinical knowledge of models typically rely on automated evaluations based on limited benchmarks. Here, to address these limitations, we present MultiMedQA, a benchmark combining six existing medical question answering datasets spanning professional medicine, research and consumer queries and a new dataset of medical questions searched online, HealthSearchQA. We propose a human evaluation framework for model answers along multiple axes including factuality, comprehension, reasoning, possible harm and bias. In addition, we evaluate Pathways Language Model (PaLM, a 540-billion parameter LLM) and its instruction-tuned variant, Flan-PaLM on MultiMedQA. Using a combination of prompting strategies, Flan-PaLM achieves state-of-the-art accuracy on every MultiMedQA multiple-choice dataset (MedQA, MedMCQA, PubMedQA and Measuring Massive Multitask Language Understanding (MMLU) clinical topics), including 67.6% accuracy on MedQA (US Medical Licensing Exam-style questions), surpassing the prior state of the art by more than 17%. However, human evaluation reveals key gaps. To resolve this, we introduce instruction prompt tuning, a parameter-efficient approach for aligning LLMs to new domains using a few exemplars. The resulting model, Med-PaLM, performs encouragingly, but remains inferior to clinicians. We show that comprehension, knowledge recall and reasoning improve with model scale and instruction prompt tuning, suggesting the potential utility of LLMs in medicine. Our human evaluations reveal limitations of today's models, reinforcing the importance of both evaluation frameworks and method development in creating safe, helpful LLMs for clinical applications.
Topics: Benchmarking; Bias; Clinical Competence; Comprehension; Computer Simulation; Datasets as Topic; Knowledge; Licensure; Medicine; Natural Language Processing; Patient Safety; Physicians
PubMed: 37438534
DOI: 10.1038/s41586-023-06291-2 -
Journal of Cancer Research and Clinical... Aug 2023Artificial intelligence (AI) is influencing our society on many levels and has broad implications for the future practice of hematology and oncology. However, for many... (Review)
Review
BACKGROUND
Artificial intelligence (AI) is influencing our society on many levels and has broad implications for the future practice of hematology and oncology. However, for many medical professionals and researchers, it often remains unclear what AI can and cannot do, and what are promising areas for a sensible application of AI in hematology and oncology. Finally, the limits and perils of using AI in oncology are not obvious to many healthcare professionals.
METHODS
In this article, we provide an expert-based consensus statement by the joint Working Group on "Artificial Intelligence in Hematology and Oncology" by the German Society of Hematology and Oncology (DGHO), the German Association for Medical Informatics, Biometry and Epidemiology (GMDS), and the Special Interest Group Digital Health of the German Informatics Society (GI). We provide a conceptual framework for AI in hematology and oncology.
RESULTS
First, we propose a technological definition, which we deliberately set in a narrow frame to mainly include the technical developments of the last ten years. Second, we present a taxonomy of clinically relevant AI systems, structured according to the type of clinical data they are used to analyze. Third, we show an overview of potential applications, including clinical, research, and educational environments with a focus on hematology and oncology.
CONCLUSION
Thus, this article provides a point of reference for hematologists and oncologists, and at the same time sets forth a framework for the further development and clinical deployment of AI in hematology and oncology in the future.
Topics: Humans; Artificial Intelligence; Medical Oncology; Hematology; Forecasting
PubMed: 36920563
DOI: 10.1007/s00432-023-04667-5 -
Advanced Science (Weinheim,... Jul 2023Unveiling biomedical functions of tumor-resident microbiota is challenging for developing advanced anticancer medicines. This study demonstrates that isolated...
Unveiling biomedical functions of tumor-resident microbiota is challenging for developing advanced anticancer medicines. This study demonstrates that isolated intratumoral bacteria, associated with natural purple photosynthetic bacteria, have inherent biocompatibility and strong immunogenic anticancer efficacies. They preferentially grow and proliferate within a targeted tumor milieu, which effectively causes immune cells to infiltrate the tumor and provoke strong anticancer responses in various syngeneic mouse models, including colorectal cancer, sarcoma, metastatic lung cancer, and extensive drug-resistant breast cancer. Furthermore, these functional bacteria-treated mice exhibit excellent anticancerous responses and have significantly prolonged survival rates with effective immunological memory. Light-harvesting nanocomplexes of microbial consortia of intratumoral bacteria and purple photosynthetic bacteria can diagnose tumors using bio-optical-window near-infrared light, making them useful theranostic agents for highly targeted immunological elimination of the tumor and for precisely marking tumor location.
Topics: Mice; Animals; Precision Medicine; Antineoplastic Agents; Disease Models, Animal; Lung Neoplasms; Bacteria
PubMed: 37150857
DOI: 10.1002/advs.202301679 -
Journal of Hematology & Oncology Nov 2023Research into the potential benefits of artificial intelligence for comprehending the intricate biology of cancer has grown as a result of the widespread use of deep... (Review)
Review
Research into the potential benefits of artificial intelligence for comprehending the intricate biology of cancer has grown as a result of the widespread use of deep learning and machine learning in the healthcare sector and the availability of highly specialized cancer datasets. Here, we review new artificial intelligence approaches and how they are being used in oncology. We describe how artificial intelligence might be used in the detection, prognosis, and administration of cancer treatments and introduce the use of the latest large language models such as ChatGPT in oncology clinics. We highlight artificial intelligence applications for omics data types, and we offer perspectives on how the various data types might be combined to create decision-support tools. We also evaluate the present constraints and challenges to applying artificial intelligence in precision oncology. Finally, we discuss how current challenges may be surmounted to make artificial intelligence useful in clinical settings in the future.
Topics: Humans; Artificial Intelligence; Neoplasms; Precision Medicine; Machine Learning; Medical Oncology
PubMed: 38012673
DOI: 10.1186/s13045-023-01514-5 -
Ugeskrift For Laeger Sep 2023Polygenic risk scores (PRS) identify at-risk individuals for many common diseases. A discussion of strengths and limitations is carried out in this review. PRS... (Review)
Review
Polygenic risk scores (PRS) identify at-risk individuals for many common diseases. A discussion of strengths and limitations is carried out in this review. PRS complement traditional genetic testing and have shown utility in establishing a proper diagnosis and guiding primary and secondary prevention. Some individuals with high PRS have risks similar to those with monogenic predisposition. Limitations include potential misinterpretations, problems with application across ancestries, and limited usefulness in low-heritability traits. Despite its shortcomings PRS are predicted to play major roles in the future of personal medicine and genetic testing.
Topics: Humans; Risk Factors; Genetic Testing; Medicine; Secondary Prevention; Genetic Predisposition to Disease; Genome-Wide Association Study
PubMed: 37873989
DOI: No ID Found -
Cell Mar 2024The integration of cancer biomarkers into oncology has revolutionized cancer treatment, yielding remarkable advancements in cancer therapeutics and the prognosis of... (Review)
Review
The integration of cancer biomarkers into oncology has revolutionized cancer treatment, yielding remarkable advancements in cancer therapeutics and the prognosis of cancer patients. The development of personalized medicine represents a turning point and a new paradigm in cancer management, as biomarkers enable oncologists to tailor treatments based on the unique molecular profile of each patient's tumor. In this review, we discuss the scientific milestones of cancer biomarkers and explore future possibilities to improve the management of patients with solid tumors. This progress is primarily attributed to the biological characterization of cancers, advancements in testing methodologies, elucidation of the immune microenvironment, and the ability to profile circulating tumor fractions. Integrating these insights promises to continually advance the precision oncology field, fostering better patient outcomes.
Topics: Humans; Biomarkers, Tumor; Medical Oncology; Neoplasms; Precision Medicine; Tumor Microenvironment
PubMed: 38552610
DOI: 10.1016/j.cell.2024.02.041 -
Ugeskrift For Laeger Dec 2023Introduction The use and consumption of "products", such as cosmetic procedures and confectionery, is on a rise in the Danish population. However, it has never been...
Introduction The use and consumption of "products", such as cosmetic procedures and confectionery, is on a rise in the Danish population. However, it has never been evaluated if the same tendency can be observed among the providers of these products. In view of the upcoming Christmas, we decided to investigate this delicate matter. Methods This study was a survey-based cross-sectional study examining demographics, professional backgrounds, as well as frequency and preferences regarding confectionery and cosmetic procedures among confectioners and plastic surgeons. Results A total of 90 persons answered the questionnaire. Results showed that consumption of confectionery was high among both confectioners and plastic surgeons, and that the use of cosmetic procedures was higher among both confectioners and plastic surgeons than among the background population. Both groups preferred to know the person who provided "the product" within their respective area. Conclusion Most plastic surgeons do not need to know their confectioner but would like to know their cosmetic procedure provider. So, if you, as part of the department management, or simply as a well-meaning colleague, want to treat your staff/colleagues, you can safely order cake from a random confectioner but not cosmetic procedures from a random surgeon! Funding none. Trial registration not relevant.
Topics: Humans; Surgery, Plastic; Cross-Sectional Studies; Operating Rooms; Surveys and Questionnaires; Surgeons
PubMed: 38084615
DOI: No ID Found -
International Journal of Molecular... Aug 2023Our understanding of the molecular mechanisms underlying cancer development and evolution have evolved rapidly over recent years, and the variation from one patient to... (Review)
Review
Our understanding of the molecular mechanisms underlying cancer development and evolution have evolved rapidly over recent years, and the variation from one patient to another is now widely recognized. Consequently, one-size-fits-all approaches to the treatment of cancer have been superseded by precision medicines that target specific disease characteristics, promising maximum clinical efficacy, minimal safety concerns, and reduced economic burden. While precision oncology has been very successful in the treatment of some tumors with specific characteristics, a large number of patients do not yet have access to precision medicines for their disease. The success of next-generation precision oncology depends on the discovery of new actionable disease characteristics, rapid, accurate, and comprehensive diagnosis of complex phenotypes within each patient, novel clinical trial designs with improved response rates, and worldwide access to novel targeted anticancer therapies for all patients. This review outlines some of the current technological trends, and highlights some of the complex multidisciplinary efforts that are underway to ensure that many more patients with cancer will be able to benefit from precision oncology in the near future.
Topics: Humans; Neoplasms; Precision Medicine; Medical Oncology; Interdisciplinary Studies; Phenotype
PubMed: 37628794
DOI: 10.3390/ijms241612613 -
British Journal of Hospital Medicine... Jan 2024The acute locked knee is an orthopaedic emergency requiring prompt diagnosis and treatment. It can be classified as acute or chronic. The term 'locked knee' refers to a...
The acute locked knee is an orthopaedic emergency requiring prompt diagnosis and treatment. It can be classified as acute or chronic. The term 'locked knee' refers to a knee that demonstrates fixed flexion or which has a 'block' to complete extension. Some degree of active or passive extension may be achievable, but not full extension. The most frequent causes of a locked knee are a meniscal tear, rupture of the anterior cruciate ligament or loose bodies. Magnetic resonance imaging is the gold standard in diagnostic imaging. Knee arthroscopy is considered the gold standard in management. This article gives an overview of the presentation, assessment and management of the locked knee for core surgical, acute care common stem and emergency medicine trainees.
Topics: Humans; Knee Joint; Critical Care; Emergency Medicine; Knee Injuries; Orthopedics
PubMed: 38300674
DOI: 10.12968/hmed.2022.0215