Using Virtual Patients to Train Clinical Interviewing Skills

AAAI Conferences

Virtual patients are viewed as a cost-effective alternative to standardized patients for role-play training of clinical interviewing skills. However, training studies produce mixed results. Students give high ratings to practice with virtual patients and feel more self-confident, but they show little improvement in objective skills. This confidence-competence gap matches a common cognitive illusion, in which students overestimate the effectiveness of training that is too easy. We hypothesize that cost-effective training requires virtual patients that emphasize functional and psychological fidelity over physical fidelity. We discuss 12 design decisions aimed at cost-effective training and their application in virtual patients for practicing brief intervention in alcohol abuse. Our STAR Workshop includes 3 such patients and a virtual coach. A controlled experiment evaluated STAR and compared it to an easier E-Book and no-training Control. E-Book subjects displayed the illusion, giving high ratings to their training and self-confidence, but performing no better than Control subjects on skills. STAR subjects gave high ratings to their training and self-confidence and scored better higher than E-Book or Control subjects on skills. We invite other researchers to use the underlying Imp technology to build virtual patients for their own work.


Glimpsing into the Future of AI: A Conversation with Yolanda Gil - USC Viterbi School of Engineering

#artificialintelligence

Yolanda Gil, a research director at the USC Viterbi Information Sciences Institute (ISI), co-authored a new 20-year Artificial Intelligence Roadmap. An outbreak of a highly contagious mosquito-borne virus in the U.S. has spread quickly to major cities around the world. It's all hands on deck to stop the disease from spreading–and that includes the deployment of artificial intelligence (AI) systems, which scour online news and social media for relevant data and patterns. In consultation with human scientists, AI systems could help contain infectious diseases and identify effective vaccines. Working with these results, and data gathered from numerous hospitals around the world, scientists discover an interesting link to a rare neurological condition and a treatment is developed.


Medical error third leading cause of death in U.S.: study

#artificialintelligence

Medical error is the third largest cause of death in the United States, according to an analysis published Wednesday in the medical journal BMJ. In 2013, at least 250,000 people died not from the illnesses or injuries that prompted them to seek hospital care but from preventable mistakes, according to the study. That number exceeds deaths from strokes and Alzheimer's combined, and is topped only by heart disease and cancer, which each claim about 600,000 lives per year. The death toll from medical mishaps would be even higher if nursing homes and out-patient care were included, the researchers found. "People don't just die from bacteria and heart plaque, they die from communication breakdowns, fragmented healthcare, diagnostic mistakes, and over-dosing," said Martin Makary, a professor at Johns Hopkins University School of Medicine in Baltimore and lead author of the study.


A Survey of Computational Treatments of Biomolecules by Robotics-Inspired Methods Modeling Equilibrium Structure and Dynamic

Journal of Artificial Intelligence Research

More than fifty years of research in molecular biology have demonstrated that the ability of small and large molecules to interact with one another and propagate the cellular processes in the living cell lies in the ability of these molecules to assume and switch between specific structures under physiological conditions. Elucidating biomolecular structure and dynamics at equilibrium is therefore fundamental to furthering our understanding of biological function, molecular mechanisms in the cell, our own biology, disease, and disease treatments. By now, there is a wealth of methods designed to elucidate biomolecular structure and dynamics contributed from diverse scientific communities. In this survey, we focus on recent methods contributed from the Robotics community that promise to address outstanding challenges regarding the disparate length and time scales that characterize dynamic molecular processes in the cell. In particular, we survey robotics-inspired methods designed to obtain efficient representations of structure spaces of molecules in isolation or in assemblies for the purpose of characterizing equilibrium structure and dynamics. While an exhaustive review is an impossible endeavor, this survey balances the description of important algorithmic contributions with a critical discussion of outstanding computational challenges. The objective is to spur further research to address outstanding challenges in modeling equilibrium biomolecular structure and dynamics.


Improving Mild Cognitive Impairment Prediction via Reinforcement Learning and Dialogue Simulation

arXiv.org Machine Learning

Mild cognitive impairment (MCI) is a prodromal phase in the progression from normal aging to dementia, especially Alzheimers disease. Even though there is mild cognitive decline in MCI patients, they have normal overall cognition and thus is challenging to distinguish from normal aging. Using transcribed data obtained from recorded conversational interactions between participants and trained interviewers, and applying supervised learning models to these data, a recent clinical trial has shown a promising result in differentiating MCI from normal aging. However, the substantial amount of interactions with medical staff can still incur significant medical care expenses in practice. In this paper, we propose a novel reinforcement learning (RL) framework to train an efficient dialogue agent on existing transcripts from clinical trials. Specifically, the agent is trained to sketch disease-specific lexical probability distribution, and thus to converse in a way that maximizes the diagnosis accuracy and minimizes the number of conversation turns. We evaluate the performance of the proposed reinforcement learning framework on the MCI diagnosis from a real clinical trial. The results show that while using only a few turns of conversation, our framework can significantly outperform state-of-the-art supervised learning approaches.