clinical medicine


Will artificial intelligence revolutionize medicine or amplify its deepest problems?

#artificialintelligence

The American Medical Association (AMA) recently released its first policy recommendations for augmented intelligence. It highlights some of the most serious challenges in artificial intelligence, including the need for transparency, bias avoidance, reproducibility, and privacy. Those working in medicine may find this list familiar. Medicine has long struggled with similar problems. The similarities are not a coincidence. There are deep philosophical and methodological intersections across AI and clinical medicine. Both professions recently experienced a pendulum swing in their prevailing approaches. And in the zeitgeist of big data, powerful interests in medicine and AI are presently aligned on the same side of a centuries-long ideological struggle. People are understandably excited about a digital convergence in health tech. But ideological alignment and entrenchment may reinforce these shared challenges in a perverse codependency. The philosophical intersections between AI and medicine are not well known within their respective communities, let alone across them. Yet a positive and productive collaboration may unfold.


AHA Precision Medicine Platform Offers Up Data for Machine Learning

#artificialintelligence

"There is great potential in machine learning and other artificial intelligence methods to discover new insights. There are new findings showing that retina scans are an early predictor of heart disease, for example, and we never would have had that information before had we not been able to pool all this data together and bring artificial intelligence and machine learning to the table," Hall said.


Second annual Women in Data Science conference showcases research, explores challenges

MIT News

Two hundred students, industry professionals, and academic leaders convened at the Microsoft NERD Center in Cambridge, Massachusetts for the second annual Women in Data Science (WiDS) conference on March 5. The conference grew from 150 participants last year, and highlighted local strength in academics and health care. "The WiDS conference highlighted female leadership in data science in the Boston area," said Caroline Uhler, a member of the WiDS steering committee who is an IDSS core faculty member and assistant professor of electrical engineering and computer science (EECS) at MIT. "This event is particularly important to encourage more female scientists in related areas to join this emerging area that has such broad societal impact." Regina Barzilay, Delta Electronics Professor of EECS, gave the first presentation on how data science and machine learning approaches are improving cancer research. Barzilay said her experiences as a breast cancer survivor motivates her work.


See How This Robotic Arm Brace Uses Neurological Signals To Restore Movement

Forbes Europe

Air Force veteran (1968-1975) Angel Camareno is fitted with a MyoPro device. Angel suffered a brachial plexus injury 40 years ago which led to reduced motion in his arm. Myomo, a spinout from Massachusetts Institute of Technology (MIT) has created a robotic arm brace for people with limb paralysis from neurological disorders such as Amyotrophic Lateral Sclerosis (ALS), Multiple Sclerosis (MS) or stroke to help them regain movement with their hands and arms. The robotic arm brace, MyoPro, senses the patient's electromyography (EMG) signals through non-invasive sensors and restores function to their paralyzed arms. Patients who use the device are able to do things they were unable to do or found difficult to do before such as feeding themselves, doing laundry, carrying objects or even returning to work.


5 Innovative Uses for Machine Learning

#artificialintelligence

Though its time horizon can't be predicted, artificial intelligence (AI) promises to foundationally influence modern society, for better or worse. A sub-genre of AI -- machine learning -- has garnered particular attention from the pundits for its potential impact on the world's most important industries. Due to the resulting hype, massive amounts of talent and resources are entering this space. But what is machine learning and why should we care about it in the first place? The answer is that, in the broadest sense, machine learning models are an application of AI in which algorithms independently predict outcomes.


Multi-Task Pharmacovigilance Mining from Social Media Posts

arXiv.org Artificial Intelligence

Social media has grown to be a crucial information source for pharmacovigilance studies where an increasing number of people post adverse reactions to medical drugs that are previously unreported. Aiming to effectively monitor various aspects of Adverse Drug Reactions (ADRs) from diversely expressed social medical posts, we propose a multi-task neural network framework that learns several tasks associated with ADR monitoring with different levels of supervisions collectively. Besides being able to correctly classify ADR posts and accurately extract ADR mentions from online posts, the proposed framework is also able to further understand reasons for which the drug is being taken, known as 'indication', from the given social media post. A coverage-based attention mechanism is adopted in our framework to help the model properly identify 'phrasal' ADRs and Indications that are attentive to multiple words in a post. Our framework is applicable in situations where limited parallel data for different pharmacovigilance tasks are available.We evaluate the proposed framework on real-world Twitter datasets, where the proposed model outperforms the state-of-the-art alternatives of each individual task consistently.


Not to Cry Wolf: Distantly Supervised Multitask Learning in Critical Care

arXiv.org Artificial Intelligence

Patients in the intensive care unit (ICU) require constant and close supervision. To assist clinical staff in this task, hospitals use monitoring systems that trigger audiovisual alarms if their algorithms indicate that a patient's condition may be worsening. However, current monitoring systems are extremely sensitive to movement artefacts and technical errors. As a result, they typically trigger hundreds to thousands of false alarms per patient per day - drowning the important alarms in noise and adding to the exhaustion of clinical staff. In this setting, data is abundantly available, but obtaining trustworthy annotations by experts is laborious and expensive. We frame the problem of false alarm reduction from multivariate time series as a machine-learning task and address it with a novel multitask network architecture that utilises distant supervision through multiple related auxiliary tasks in order to reduce the number of expensive labels required for training. We show that our approach leads to significant improvements over several state-of-the-art baselines on real-world ICU data and provide new insights on the importance of task selection and architectural choices in distantly supervised multitask learning.


Medical Exam Question Answering with Large-scale Reading Comprehension

AAAI Conferences

Reading and understanding text is one important component in computer aided diagnosis in clinical medicine, also being a major research problem in the field of NLP.  In this work, we introduce a question-answering task called MedQA to study answering questions in clinical medicine using knowledge in a large-scale document collection. The aim of MedQA is to answer real-world questions with large-scale reading comprehension. We propose our solution SeaReader---a modular end-to-end reading comprehension model based on LSTM networks and dual-path attention architecture. The novel dual-path attention models information flow from two perspectives and has the ability to simultaneously read individual documents and integrate information across multiple documents. In experiments our SeaReader achieved a large increase in accuracy on MedQA over competing models.  Additionally, we develop a series of novel techniques to demonstrate the interpretation of the question answering process in SeaReader.


The wilder shores of brain boosting

Nature

Transcranial direct current stimulation has been claimed to enhance learning.Credit: Liz Hafalia/Polaris/eyevine Is there a common element that binds diverse mental abilities, from language to mental arithmetic? Or do these skills compete for our brains' limited resources? In The Genius Within, Dav...


Reliable Decision Support using Counterfactual Models

arXiv.org Artificial Intelligence

Decision-makers are faced with the challenge of estimating what is likely to happen when they take an action. For instance, if I choose not to treat this patient, are they likely to die? Practitioners commonly use supervised learning algorithms to fit predictive models that help decision-makers reason about likely future outcomes, but we show that this approach is unreliable, and sometimes even dangerous. The key issue is that supervised learning algorithms are highly sensitive to the policy used to choose actions in the training data, which causes the model to capture relationships that do not generalize. We propose using a different learning objective that predicts counterfactuals instead of predicting outcomes under an existing action policy as in supervised learning. To support decision-making in temporal settings, we introduce the Counterfactual Gaussian Process (CGP) to predict the counterfactual future progression of continuous-time trajectories under sequences of future actions. We demonstrate the benefits of the CGP on two important decision-support tasks: risk prediction and "what if?" reasoning for individualized treatment planning.