Explore the vast range of titles available.

Artificial intelligence (AI) is being increasingly integrated into scientific discovery to augment and accelerate research, helping scientists to generate hypotheses, design experiments, collect and interpret large datasets, and gain insights that might not have been possible using traditional scientific methods alone. Here we examine breakthroughs over the past decade that include self-supervised learning, which allows models to be trained on vast amounts of unlabelled data, and geometric deep learning, which leverages knowledge about the structure of scientific data to enhance model accuracy and efficiency. Generative AI methods can create designs, such as small-molecule drugs and proteins, by analysing diverse data modalities, including images and sequences. We discuss how these methods can help scientists throughout the scientific process and the central issues that remain despite such advances. Both developers and users of AI tools need a better understanding of when such approaches need improvement, and challenges posed by poor data quality and stewardship remain. These issues cut across scientific disciplines and require developing foundational algorithmic approaches that can contribute to scientific understanding or acquire it autonomously, making them critical areas of focus for AI innovation. The advances in artificial intelligence over the past decade are examined, with a discussion on how artificial intelligence systems can aid the scientific process and the central issues that remain despite advances.

AbstractObjectiveTo examine the accuracy of artificial intelligence (AI) for the detection of breast cancer in mammography screening practice.DesignSystematic review of test accuracy studies.Data sourcesMedline, Embase, Web of Science, and Cochrane Database of Systematic Reviews from 1 January 2010 to 17 May 2021.Eligibility criteriaStudies reporting test accuracy of AI algorithms, alone or in combination with radiologists, to detect cancer in women’s digital mammograms in screening practice, or in test sets. Reference standard was biopsy with histology or follow-up (for screen negative women). Outcomes included test accuracy and cancer type detected.Study selection and synthesisTwo reviewers independently assessed articles for inclusion and assessed the methodological quality of included studies using the QUality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool. A single reviewer extracted data, which were checked by a second reviewer. Narrative data synthesis was performed.ResultsTwelve studies totalling 131 822 screened women were included. No prospective studies measuring test accuracy of AI in screening practice were found. Studies were of poor methodological quality. Three retrospective studies compared AI systems with the clinical decisions of the original radiologist, including 79 910 women, of whom 1878 had screen detected cancer or interval cancer within 12 months of screening. Thirty four (94%) of 36 AI systems evaluated in these studies were less accurate than a single radiologist, and all were less accurate than consensus of two or more radiologists. Five smaller studies (1086 women, 520 cancers) at high risk of bias and low generalisability to the clinical context reported that all five evaluated AI systems (as standalone to replace radiologist or as a reader aid) were more accurate than a single radiologist reading a test set in the laboratory. In three studies, AI used for triage screened out 53%, 45%, and 50% of women at low risk but also 10%, 4%, and 0% of cancers detected by radiologists.ConclusionsCurrent evidence for AI does not yet allow judgement of its accuracy in breast cancer screening programmes, and it is unclear where on the clinical pathway AI might be of most benefit. AI systems are not sufficiently specific to replace radiologist double reading in screening programmes. Promising results in smaller studies are not replicated in larger studies. Prospective studies are required to measure the effect of AI in clinical practice. Such studies will require clear stopping rules to ensure that AI does not reduce programme specificity.Study registrationProtocol registered as PROSPERO CRD42020213590.

The successful use of artificial intelligence (AI) for diagnostic purposes has prompted the application of AI-based cancer imaging analysis to address other, more complex, clinical needs. In this Perspective, we discuss the next generation of challenges in clinical decision-making that AI tools can solve using radiology images, such as prognostication of outcome across multiple cancers, prediction of response to various treatment modalities, discrimination of benign treatment confounders from true progression, identification of unusual response patterns and prediction of the mutational and molecular profile of tumours. We describe the evolution of and opportunities for AI in oncology imaging, focusing on hand-crafted radiomic approaches and deep learning-derived representations, with examples of their application for decision support. We also address the challenges faced on the path to clinical adoption, including data curation and annotation, interpretability, and regulatory and reimbursement issues. We hope to demystify AI in radiology for clinicians by helping them to understand its limitations and challenges, as well as the opportunities it provides as a decision-support tool in cancer management.Prognostication of outcome across multiple cancers and prediction of response to various treatment modalities are among the next generation of challenges that artificial intelligence (AI) tools can solve using radiology images. The authors of this Perspective describe the evolution of AI-based approaches in oncology imaging and address the path to their adoption as decision-support tools in the clinic.

In the high-stakes realm of critical care, where daily decisions are crucial and clear communication is paramount, comprehending the rationale behind Artificial Intelligence (AI)-driven decisions appears essential. While AI has the potential to improve decision-making, its complexity can hinder comprehension and adherence to its recommendations. “Explainable AI” (XAI) aims to bridge this gap, enhancing confidence among patients and doctors. It also helps to meet regulatory transparency requirements, offers actionable insights, and promotes fairness and safety. Yet, defining explainability and standardising assessments are ongoing challenges and balancing performance and explainability can be needed, even if XAI is a growing field.

Screening mammography aims to identify breast cancer at earlier stages of the disease, when treatment can be more successful 1 . Despite the existence of screening programmes worldwide, the interpretation of mammograms is affected by high rates of false positives and false negatives 2 . Here we present an artificial intelligence (AI) system that is capable of surpassing human experts in breast cancer prediction. To assess its performance in the clinical setting, we curated a large representative dataset from the UK and a large enriched dataset from the USA. We show an absolute reduction of 5.7% and 1.2% (USA and UK) in false positives and 9.4% and 2.7% in false negatives. We provide evidence of the ability of the system to generalize from the UK to the USA. In an independent study of six radiologists, the AI system outperformed all of the human readers: the area under the receiver operating characteristic curve (AUC-ROC) for the AI system was greater than the AUC-ROC for the average radiologist by an absolute margin of 11.5%. We ran a simulation in which the AI system participated in the double-reading process that is used in the UK, and found that the AI system maintained non-inferior performance and reduced the workload of the second reader by 88%. This robust assessment of the AI system paves the way for clinical trials to improve the accuracy and efficiency of breast cancer screening. An artificial intelligence (AI) system performs as well as or better than radiologists at detecting breast cancer from mammograms, and using a combination of AI and human inputs could help to improve screening efficiency.

Sepsis is the third leading cause of death worldwide and the main cause of mortality in hospitals 1 – 3 , but the best treatment strategy remains uncertain. In particular, evidence suggests that current practices in the administration of intravenous fluids and vasopressors are suboptimal and likely induce harm in a proportion of patients 1 , 4 – 6 . To tackle this sequential decision-making problem, we developed a reinforcement learning agent, the Artificial Intelligence (AI) Clinician, which extracted implicit knowledge from an amount of patient data that exceeds by many-fold the life-time experience of human clinicians and learned optimal treatment by analyzing a myriad of (mostly suboptimal) treatment decisions. We demonstrate that the value of the AI Clinician’s selected treatment is on average reliably higher than human clinicians. In a large validation cohort independent of the training data, mortality was lowest in patients for whom clinicians’ actual doses matched the AI decisions. Our model provides individualized and clinically interpretable treatment decisions for sepsis that could improve patient outcomes. A reinforcement learning agent, the AI Clinician, can assist physicians by providing individualized and clinically interpretable treatment decisions to improve patient outcomes.

Training algorithms to computationally plan multistep organic syntheses has been a challenge for more than 50 years 1 – 7 . However, the field has progressed greatly since the development of early programs such as LHASA 1 , 7 , for which reaction choices at each step were made by human operators. Multiple software platforms 6 , 8 – 14 are now capable of completely autonomous planning. But these programs ‘think’ only one step at a time and have so far been limited to relatively simple targets, the syntheses of which could arguably be designed by human chemists within minutes, without the help of a computer. Furthermore, no algorithm has yet been able to design plausible routes to complex natural products, for which much more far-sighted, multistep planning is necessary 15 , 16 and closely related literature precedents cannot be relied on. Here we demonstrate that such computational synthesis planning is possible, provided that the program’s knowledge of organic chemistry and data-based artificial intelligence routines are augmented with causal relationships 17 , 18 , allowing it to ‘strategize’ over multiple synthetic steps. Using a Turing-like test administered to synthesis experts, we show that the routes designed by such a program are largely indistinguishable from those designed by humans. We also successfully validated three computer-designed syntheses of natural products in the laboratory. Taken together, these results indicate that expert-level automated synthetic planning is feasible, pending continued improvements to the reaction knowledge base and further code optimization. A synthetic route-planning algorithm, augmented with causal relationships that allow it to strategize over multiple steps, can design complex natural-product syntheses that are indistinguishable from those designed by human experts.

Artificial intelligence (AI) has been developed for echocardiography 1 – 3 , although it has not yet been tested with blinding and randomization. Here we designed a blinded, randomized non-inferiority clinical trial (ClinicalTrials.gov ID: NCT05140642; no outside funding) of AI versus sonographer initial assessment of left ventricular ejection fraction (LVEF) to evaluate the impact of AI in the interpretation workflow. The primary end point was the change in the LVEF between initial AI or sonographer assessment and final cardiologist assessment, evaluated by the proportion of studies with substantial change (more than 5% change). From 3,769 echocardiographic studies screened, 274 studies were excluded owing to poor image quality. The proportion of studies substantially changed was 16.8% in the AI group and 27.2% in the sonographer group (difference of −10.4%, 95% confidence interval: −13.2% to −7.7%, P  < 0.001 for non-inferiority, P  < 0.001 for superiority). The mean absolute difference between final cardiologist assessment and independent previous cardiologist assessment was 6.29% in the AI group and 7.23% in the sonographer group (difference of −0.96%, 95% confidence interval: −1.34% to −0.54%, P  < 0.001 for superiority). The AI-guided workflow saved time for both sonographers and cardiologists, and cardiologists were not able to distinguish between the initial assessments by AI versus the sonographer (blinding index of 0.088). For patients undergoing echocardiographic quantification of cardiac function, initial assessment of LVEF by AI was non-inferior to assessment by sonographers. The impact of artificial intelligence in cardiac function assessment is evaluated by a blinded, randomized non-inferiority trial of artificial intelligence versus sonographer initial assessment of the left ventricular ejection fraction.

Artificial intelligence (AI) can transform health care practices with its increasing ability to translate the uncertainty and complexity in data into actionable—though imperfect—clinical decisions or suggestions. In the evolving relationship between humans and AI, trust is the one mechanism that shapes clinicians’ use and adoption of AI. Trust is a psychological mechanism to deal with the uncertainty between what is known and unknown. Several research studies have highlighted the need for improving AI-based systems and enhancing their capabilities to help clinicians. However, assessing the magnitude and impact of human trust on AI technology demands substantial attention. Will a clinician trust an AI-based system? What are the factors that influence human trust in AI? Can trust in AI be optimized to improve decision-making processes? In this paper, we focus on clinicians as the primary users of AI systems in health care and present factors shaping trust between clinicians and AI. We highlight critical challenges related to trust that should be considered during the development of any AI system for clinical use.

The high demand for health care services and the growing capability of artificial intelligence have led to the development of conversational agents designed to support a variety of health-related activities, including behavior change, treatment support, health monitoring, training, triage, and screening support. Automation of these tasks could free clinicians to focus on more complex work and increase the accessibility to health care services for the public. An overarching assessment of the acceptability, usability, and effectiveness of these agents in health care is needed to collate the evidence so that future development can target areas for improvement and potential for sustainable adoption. This systematic review aims to assess the effectiveness and usability of conversational agents in health care and identify the elements that users like and dislike to inform future research and development of these agents. PubMed, Medline (Ovid), EMBASE (Excerpta Medica dataBASE), CINAHL (Cumulative Index to Nursing and Allied Health Literature), Web of Science, and the Association for Computing Machinery Digital Library were systematically searched for articles published since 2008 that evaluated unconstrained natural language processing conversational agents used in health care. EndNote (version X9, Clarivate Analytics) reference management software was used for initial screening, and full-text screening was conducted by 1 reviewer. Data were extracted, and the risk of bias was assessed by one reviewer and validated by another. A total of 31 studies were selected and included a variety of conversational agents, including 14 chatbots (2 of which were voice chatbots), 6 embodied conversational agents (3 of which were interactive voice response calls, virtual patients, and speech recognition screening systems), 1 contextual question-answering agent, and 1 voice recognition triage system. Overall, the evidence reported was mostly positive or mixed. Usability and satisfaction performed well (27/30 and 26/31), and positive or mixed effectiveness was found in three-quarters of the studies (23/30). However, there were several limitations of the agents highlighted in specific qualitative feedback. The studies generally reported positive or mixed evidence for the effectiveness, usability, and satisfactoriness of the conversational agents investigated, but qualitative user perceptions were more mixed. The quality of many of the studies was limited, and improved study design and reporting are necessary to more accurately evaluate the usefulness of the agents in health care and identify key areas for improvement. Further research should also analyze the cost-effectiveness, privacy, and security of the agents. RR2-10.2196/16934.