Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
258
result(s) for
"Paul Gamble"
Sort by:
Large language models encode clinical knowledge
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
1
(PaLM, a 540-billion parameter LLM) and its instruction-tuned variant, Flan-PaLM
2
on MultiMedQA. Using a combination of prompting strategies, Flan-PaLM achieves state-of-the-art accuracy on every MultiMedQA multiple-choice dataset (MedQA
3
, MedMCQA
4
, PubMedQA
5
and Measuring Massive Multitask Language Understanding (MMLU) clinical topics
6
), 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.
Med-PaLM, a state-of-the-art large language model for medicine, is introduced and evaluated across several medical question answering tasks, demonstrating the promise of these models in this domain.
Journal Article
The Ministry of SUITs
Jack Pearse and Trudy Emerson are the newest recruits to SUIT--the Strange, Unusual, and Impossible Things ministry--and must investigate unconfirmed signs of pirates as well as the disappearance of oddball kids in Belfast.
BOOK
Current and future applications of artificial intelligence in pathology: a clinical perspective
During the last decade, a dramatic rise in the development and application of artificial intelligence (AI) tools for use in pathology services has occurred. This trend is often expected to continue and reshape the field of pathology in the coming years. The deployment of computational pathology and applications of AI tools can be considered as a paradigm shift that will change pathology services, making them more efficient and capable of meeting the needs of this era of precision medicine. Despite the success of AI models, the translational process from discovery to clinical applications has been slow. The gap between self-contained research and clinical environment may be too wide and has been largely neglected. In this review, we cover the current and prospective applications of AI in pathology. We examine its applications in diagnosis and prognosis, and we offer insights for considerations that could improve clinical applicability of these tools. Then, we discuss its potential to improve workflow efficiency, and its benefits in pathologist education. Finally, we review the factors that could influence adoption in clinical practices and the associated regulatory processes.
Journal Article
Strength and Conditioning for Team Sports
Strength and Conditioning for Team Sports is designed to help trainers and coaches to devise more effective high-performance training programs for team sports. This remains the only evidence-based study of sport-specific practice to focus on team sports and features all-new chapters covering neuromuscular training, injury prevention and specific injury risks for different team sports. Fully revised and updated throughout, the new edition also includes over two hundred new references from the current research literature.
The book introduces the core science underpinning different facets of physical preparation, covering all aspects of training prescription and the key components of any degree-level strength and conditioning course, including:
physiological and performance testing
strength training
metabolic conditioning
power training
agility and speed development
training for core stability
training periodisation
training for injury prevention
Bridging the traditional gap between sports science research and practice, each chapter features guidelines for evidence-based best practice as well as recommendations for approaches to physical preparation to meet the specific needs of team sports players. This new edition also includes an appendix that provides detailed examples of training programmes for a range of team sports. Fully illustrated throughout, it is essential reading for all serious students of strength and conditioning, and for any practitioner seeking to extend their professional practice.
Paul Gamble has worked in high performance sport for over a decade, during which time he has coached elite athletes in an array of sports and at all ages and stages of development. Paul began his career working in professional rugby with English Premiership side London Irish, and has since worked in a range of sports, most recently serving as National Strength & Conditioning Lead for Scottish Squash. He has published a number of articles in peer-reviewed journals, chapters in edited textbooks and has previously written two textbooks as sole author.
1. Principles of Specificity and Transfer of Training Effects 2. Assessing Physiological and Physical Performance Parameters 3. Neuromuscular Training 4. Metabolic Conditioning 5. Strength Training 6. Power Development and Plyometric Training 7. Sports Speed and Agility Development 8. Lumbopelvic ‘Core’ Stability 9. Training for Injury Prevention – Identifying Risk Factors 10. Injury Prevention – Specific Training Interventions 11. Planning and Scheduling – Periodisation of Training 12. Physical Preparation for Youth Sports
eBook
SIG-DB: Leveraging homomorphic encryption to securely interrogate privately held genomic databases
Genomic data are becoming increasingly valuable as we develop methods to utilize the information at scale and gain a greater understanding of how genetic information relates to biological function. Advances in synthetic biology and the decreased cost of sequencing are increasing the amount of privately held genomic data. As the quantity and value of private genomic data grows, so does the incentive to acquire and protect such data, which creates a need to store and process these data securely. We present an algorithm for the Secure Interrogation of Genomic DataBases (SIG-DB). The SIG-DB algorithm enables databases of genomic sequences to be searched with an encrypted query sequence without revealing the query sequence to the Database Owner or any of the database sequences to the Querier. SIG-DB is the first application of its kind to take advantage of locality-sensitive hashing and homomorphic encryption to allow generalized sequence-to-sequence comparisons of genomic data.
Journal Article
Adoption of microfluidic MEA technology for electrophysiology of 3D neuronal networks exposed to suborbital conditions
Studying neuronal cells in space reveals how microgravity affects brain function, gene expression, and cellular processes. This study details the preparation and validation of a 3D neuronal electrophysiology (EPHYS) sensing microfluidic biodevice used during a suborbital space flight. Initially, the device’s function was tested with rat hippocampal neurons using EPHYS data collected via a microelectrode array (MEA). This system was later applied to human glutamatergic (Glu) neurons for eight days preceding a suborbital flight. A live-dead assay confirmed cell viability, and the system was integrated into a CubeLab to maintain a controlled environment. Two biological samples were flown, along with two control samples, to validate the EPHYS system. Results showed that human Glu-neurons exposed to microgravity exhibited altered expression of vesicular glutamate transporters (VGLUTs) while maintaining neuronal differentiation markers. The findings contribute to understanding neurological disorders, neuro-inflammation, and cognitive impacts of space travel, with broader applications for brain health research on Earth.
Journal Article
Development and characterization of a low intensity vibrational system for microgravity studies
Extended-duration human spaceflight necessitates a better understanding of the physiological impacts of microgravity. While the ground-based microgravity simulations identified low intensity vibration (LIV) as a possible countermeasure, how cells may respond to LIV under real microgravity remain unexplored. In this way, adaptation of LIV bioreactors for space remains limited, resulting in a significant gap in microgravity research. In this study, we introduce an LIV bioreactor designed specifically for the usage in the International Space Station. Our research covers the bioreactor’s design process and evaluation of the short-term viability of cells encapsulated in hydrogel-laden 3D printed scaffolds under 0.7 g, 90 Hz LIV. An LIV bioreactor compatible with the operation requirements of space missions provides a robust platform to study cellular effects of LIV under real microgravity conditions.
Journal Article
User-centred design for machine learning in health care: a case study from care management
ObjectivesFew machine learning (ML) models are successfully deployed in clinical practice. One of the common pitfalls across the field is inappropriate problem formulation: designing ML to fit the data rather than to address a real-world clinical pain point.MethodsWe introduce a practical toolkit for user-centred design consisting of four questions covering: (1) solvable pain points, (2) the unique value of ML (eg, automation and augmentation), (3) the actionability pathway and (4) the model’s reward function. This toolkit was implemented in a series of six participatory design workshops with care managers in an academic medical centre.ResultsPain points amenable to ML solutions included outpatient risk stratification and risk factor identification. The endpoint definitions, triggering frequency and evaluation metrics of the proposed risk scoring model were directly influenced by care manager workflows and real-world constraints.ConclusionsIntegrating user-centred design early in the ML life cycle is key for configuring models in a clinically actionable way. This toolkit can guide problem selection and influence choices about the technical setup of the ML problem.
Journal Article
Periodization of Training for Team Sports Athletes
Training variation and periodization is widely acknowledged as crucial to optimizing training responses. Applying periodized planning to team sports poses unique challenges due to the variety of training goals, volume of concurrent training and practices, and extended season of competition. Practical suggestions are offered in this article to address these considerations and apply periodization in training design for different phases of physical preparation for team sports athletes. [PUBLICATION ABSTRACT]
Journal Article