Nature medicine
-
Review Guideline
Guidelines for clinical trial protocols for interventions involving artificial intelligence: the SPIRIT-AI extension.
The SPIRIT 2013 statement aims to improve the completeness of clinical trial protocol reporting by providing evidence-based recommendations for the minimum set of items to be addressed. This guidance has been instrumental in promoting transparent evaluation of new interventions. More recently, there has been a growing recognition that interventions involving artificial intelligence (AI) need to undergo rigorous, prospective evaluation to demonstrate their impact on health outcomes. ⋯ SPIRIT-AI recommends that investigators provide clear descriptions of the AI intervention, including instructions and skills required for use, the setting in which the AI intervention will be integrated, considerations for the handling of input and output data, the human-AI interaction and analysis of error cases. SPIRIT-AI will help promote transparency and completeness for clinical trial protocols for AI interventions. Its use will assist editors and peer reviewers, as well as the general readership, to understand, interpret and critically appraise the design and risk of bias for a planned clinical trial.
-
The current COVID-19 pandemic challenges oncologists to profoundly re-organize oncological care in order to dramatically reduce hospital visits and admissions and therapy-induced immune-related complications without compromising cancer outcomes. Since COVID-19 is a novel disease, guidance by scientific evidence is often unavailable, and impactful decisions are inevitably made on the basis of expert opinions. ⋯ Also, we discuss how the current situation offers a unique window of opportunity for assessing the effects of de-escalating anticancer regimens, which may fast-forward the development of more-refined and less-toxic treatments. By sharing our joint experiences, we offer a roadmap for proceeding and aim to mobilize the global research community to generate the data that are critically needed to offer the best possible care to patients.
-
With the advent of next-generation sequencing, we have an unprecedented ability to study tumor and host genomes as well as those of the vast array of microorganisms that exist within living organisms. Evidence now suggests that these microbes may confer susceptibility to certain cancers and may also influence response to therapeutics. A prime example of this is seen with immunotherapy, for which gut microbes have been implicated in influencing therapeutic responses in preclinical models and patient cohorts. ⋯ Based on these influences, there is growing interest in targeting these microbes in the treatment of cancer and other diseases. Yet complexities exist, and a deeper understanding of host-microbiome interactions is critical to realization of the full potential of such approaches. These concepts and the means through which such findings may be translated into the clinic will be discussed herein.
-
Big data has become the ubiquitous watch word of medical innovation. The rapid development of machine-learning techniques and artificial intelligence in particular has promised to revolutionize medical practice from the allocation of resources to the diagnosis of complex diseases. ⋯ We discuss, among other topics, how best to conceive of health privacy; the importance of equity, consent, and patient governance in data collection; discrimination in data uses; and how to handle data breaches. We close by sketching possible ways forward for the regulatory system.
-
Here we present deep-learning techniques for healthcare, centering our discussion on deep learning in computer vision, natural language processing, reinforcement learning, and generalized methods. We describe how these computational techniques can impact a few key areas of medicine and explore how to build end-to-end systems. Our discussion of computer vision focuses largely on medical imaging, and we describe the application of natural language processing to domains such as electronic health record data. Similarly, reinforcement learning is discussed in the context of robotic-assisted surgery, and generalized deep-learning methods for genomics are reviewed.