We focus on furthering the application of technology and artificial intelligence to improve healthcare and other diverse application areas.
Our aim is to bolster the urgent and critical nature of making decisions in diverse applications. Our methods include improving the gathering, availability, security, and use of information throughout the organization and beyond. Some of our recent work includes establishing a scalable informatics framework and implementing tools and techniques to "understand" text from data.
Our focus is using computational tools to summarize health-related data to help clinicians focus on decision-making rather than just keeping up with the data.
Using adversarial signals and a cycle-consistency based regularization, we can supplement paired regression tasks with unpaired data to improve regression performance.
Our team uses accelerometers and machine learning to help detect vocal disorders. We capture data about the motions of patient's vocal folds to determine if their vocal behavior is normal or abnormal.
In an analysis of over 160,000 transplant candidates, researchers found that race is linked to how likely an organ offer is to be accepted on behalf of a patient.
In a new paper, researchers from Microsoft and MIT CSAIL propose a novel method for measuring how accurately an LLM's explanations represent the reasoning process behind the model’s answer.
Researchers at MIT, NYU, and UCLA develop an approach to help evaluate whether large language models like GPT-4 are equitable enough to be clinically viable for mental health support.
In a recent commentary, a team from MIT, Equality AI, and Boston University highlights the gaps in regulation for AI models and non-AI algorithms in health care.
An interdisciplinary team of researchers thinks health AI could benefit from some of the aviation industry’s long history of hard-won lessons that have created one of the safest activities today.
Inspired by unintended negative consequences of NLP models found to reflect societal biases such as gender and racial biases, an MIT researcher created a decision-making framework to help scientists align their NLP research with social good
MIT’s new system TextFooler can trick the types of natural-language-processing systems that Google uses to help power its search results, including audio for Google Home
In the last 10 years, it’s become far more common for physicians to keep records electronically. Those records could contain a wealth of medically useful data: hidden correlations between symptoms, treatments and outcomes, for instance, or indications that patients are promising candidates for trials of new drugs.
