Goto

Collaborating Authors

Results


Bowel cancer: Artificial intelligence can reduce overtreatment and wrong treatment

#artificialintelligence

In 2018, more than 4,500 people in Norway were treated for colon cancer. This is the most common cancer in Norway with a rapid increase over the past 50 years, according to the Norwegian Cancer Society (NCS). A new method, based on artificial intelligence, can now make sure many of these patients don't get overtreated or wrongly treated. "For many people, there is no effect of the treatment and it is just a nuisance," said Håvard Danielsen, professor at the University of Oxford and the Department of informatics at the University of Oslo. "We want to stop treating or give another treatment to these patients."


How is AI and machine learning benefiting the healthcare industry?

#artificialintelligence

In order to help build increasingly effective care pathways in healthcare, modern artificial intelligence technologies must be adopted and embraced. Events such as the AI & Machine Learning Convention are essential in providing medical experts around the UK access to the latest technologies, products and services that are revolutionising the future of care pathways in the healthcare industry. AI has the potential to save the lives of current and future patients and is something that is starting to be seen across healthcare services across the UK. Looking at diagnostics alone, there have been large scale developments in rapid image recognition, symptom checking and risk stratification. AI can also be used to personalise health screening and treatments for cancer, not only benefiting the patient but clinicians too – enabling them to make the best use of their skills, informing decisions and saving time.


Estimating the Effects of Continuous-valued Interventions using Generative Adversarial Networks

arXiv.org Machine Learning

While much attention has been given to the problem of estimating the effect of discrete interventions from observational data, relatively little work has been done in the setting of continuous-valued interventions, such as treatments associated with a dosage parameter. In this paper, we tackle this problem by building on a modification of the generative adversarial networks (GANs) framework. Our model, SCIGAN, is flexible and capable of simultaneously estimating counterfactual outcomes for several different continuous interventions. The key idea is to use a significantly modified GAN model to learn to generate counterfactual outcomes, which can then be used to learn an inference model, using standard supervised methods, capable of estimating these counterfactuals for a new sample. To address the challenges presented by shifting to continuous interventions, we propose a novel architecture for our discriminator - we build a hierarchical discriminator that leverages the structure of the continuous intervention setting. Moreover, we provide theoretical results to support our use of the GAN framework and of the hierarchical discriminator. In the experiments section, we introduce a new semi-synthetic data simulation for use in the continuous intervention setting and demonstrate improvements over the existing benchmark models.


Google AI tool bests clinicians in breast cancer detection study

#artificialintelligence

Roughly one in eight women in the U.S. will develop invasive breast cancer over the course of her lifetime, according to the American Cancer Society. Early detection of abnormal tissue or tumor is critically important for treatment, but mammograms -- the best screening tools currently available for doctors -- have their limitations. Clinicians fail to catch about a fifth of all breast cancer cases, and half of U.S. women receiving annual mammograms in a given decade will be incorrectly told they have breast cancer when they actually don't, the cancer group says. Google Health's new tool, developed in tandem with its British subsidiary DeepMind, Northwestern Medicine and Imperial College London and the University of Cambridge, improved mistakes in both areas. False positives were reduced by 5.7% and 1.2%, and false negatives were reduced by 9.4% and 2.7% in the U.S. and U.K., respectively.


Google's AI system can beat doctors at detecting breast cancer

#artificialintelligence

London (CNN Business)Google (GOOGL) says it has developed an artificial intelligence system that can detect the presence of breast cancer more accurately than doctors. A study that tested the accuracy of the system, which was developed through a collaboration between the tech giant and cancer researchers, was published Wednesday in the scientific journal Nature. The program was trained to detect cancer using tens of thousands of mammograms from women in the United Kingdom and the United States, and early research shows it can produce more accurate detection than human radiologists. According to the study, using the AI technology resulted in fewer false positives, where test results suggest cancer is present when it isn't, and false negatives, where an existing cancer goes undetected. Compared to human experts, the program reduced false positives by 5.7% for US subjects and 1.2% for UK subjects.


AutoDiscern: Rating the Quality of Online Health Information with Hierarchical Encoder Attention-based Neural Networks

arXiv.org Machine Learning

Patients increasingly turn to search engines and online content before, or in place of, talking with a health professional. Low quality health information, which is common on the internet, presents risks to the patient in the form of misinformation and a possibly poorer relationship to their physician. To address this, the DISCERN criteria (developed at University of Oxford) are used to evaluate the quality of online health information. However, patients are unlikely to take the time to apply these criteria to the health websites they visit. We built an automated implementation of the DISCERN instrument (Brief version) using machine learning models. We compared the use of a traditional model (Random Forest) with a hierarchical encoder attention-based neural network (HEA) model using two language embeddings based on BERT and BioBERT. The HEA BERT and BioBERT models achieved F1-macro scores averaging 0.75 and 0.74, respectively, on all criteria outperforming the Random Forest model (F1-macro = 0.69). Similarly, HEA BERT and BioBERT scored on average 0.8 and 0.81 (F1-micro) vs. 0.76 for the Random Forest model. Overall, the neural network based models achieved 81% and 86% average accuracy at 100% and 80% coverage, respectively, compared to 94% manual rating accuracy. The attention mechanism implemented in the HEA architectures provided 'model explainability' by identifying reasonable supporting sentences for the documents fulfilling the Brief DISCERN criteria. Our research suggests that it is feasible to automate online health information quality assessment, which is an important step towards empowering patients to become informed partners in the healthcare process.


Large expert-curated database for benchmarking document similarity detection in biomedical literature search

#artificialintelligence

Document recommendation systems for locating relevant literature have mostly relied on methods developed a decade ago. This is largely due to the lack of a large offline gold-standard benchmark of relevant documents that cover a variety of research fields such that newly developed literature search techniques can be compared, improved and translated into practice. To overcome this bottleneck, we have established the RElevant LIterature SearcH consortium consisting of more than 1500 scientists from 84 countries, who have collectively annotated the relevance of over 180 000 PubMed-listed articles with regard to their respective seed (input) article/s. The majority of annotations were contributed by highly experienced, original authors of the seed articles. The collected data cover 76% of all unique PubMed Medical Subject Headings descriptors. No systematic biases were observed across different experience levels, research fields or time spent on annotations.


AI Tool Helps Radiologists More Accurately Identify Breast Cancer

#artificialintelligence

Authors from the Center for Data Science at New York University were Nan Wu, Jason Phang, Jungkyu Park, Yiqiu Shen, Zhe Huang, Thibault Févry, and Kyunghyun Cho, who is also on the faculty of NYU's Courant Institute of Mathematical Sciences. Also authors were Kara Ho at SUNY Downstate College of Medicine; Masha Zorin in the Department of Computer Science and Technology at the University of Cambridge in the United Kingdom; and Stanisław Jastrzębski from Jagiellonian University in Poland, and Joe Katsnelson in the Department of Information Technology, NYU Langone Health.


BlackThorn Therapeutics Raises $76M to Personalise Medicine for Mental Disorders

#artificialintelligence

The National Health Service reported that over 70 million prescriptions for antidepressants alone were prescribed in England last year. According to a Scientific American study from 2016, more than one in six US adults takes a psychiatric drug. However, most mental disorders are treated based on symptoms instead of the patient's underlying biology. BlackThorn Therapeutics wants to change that. The AI-based neurobehavioural health startup is using machine learning and artificial intelligence to personalise psychiatric medication.


Reinforcement Learning in Healthcare: A Survey

arXiv.org Artificial Intelligence

As a subfield of machine learning, \emph{reinforcement learning} (RL) aims at empowering one's capabilities in behavioural decision making by using interaction experience with the world and an evaluative feedback. Unlike traditional supervised learning methods that usually rely on one-shot, exhaustive and supervised reward signals, RL tackles with sequential decision making problems with sampled, evaluative and delayed feedback simultaneously. Such distinctive features make RL technique a suitable candidate for developing powerful solutions in a variety of healthcare domains, where diagnosing decisions or treatment regimes are usually characterized by a prolonged and sequential procedure. This survey will discuss the broad applications of RL techniques in healthcare domains, in order to provide the research community with systematic understanding of theoretical foundations, enabling methods and techniques, existing challenges, and new insights of this emerging paradigm. By first briefly examining theoretical foundations and key techniques in RL research from efficient and representational directions, we then provide an overview of RL applications in a variety of healthcare domains, ranging from dynamic treatment regimes in chronic diseases and critical care, automated medical diagnosis from both unstructured and structured clinical data, as well as many other control or scheduling domains that have infiltrated many aspects of a healthcare system. Finally, we summarize the challenges and open issues in current research, and point out some potential solutions and directions for future research.