Speakers

attention, breathing, communication, deep learning, electronic health record, hospital, hospital medicine, hospital readmission, information, intuition, johns hopkins all children's hospital, learning, machine learning, medical record, neural network, patient, pediatrics, point of care, positive and negative predictive values, predictive modelling, risk, risk assessment, sample size determination, sensitivity and specificity, truth

attention, breathing, communication, deep learning, electronic health record, hospital, hospital medicine, hospital readmission, information, intuition, johns hopkins all children's hospital, learning, machine learning, medical record, neural network, patient, pediatrics, point of care, positive and negative predictive values, predictive modelling, risk, risk assessment, sample size determination, sensitivity and specificity, truth

attention, breathing, communication, deep learning, electronic health record, hospital, hospital medicine, hospital readmission, information, intuition, johns hopkins all children's hospital, learning, machine learning, medical record, neural network, patient, pediatrics, point of care, positive and negative predictive values, predictive modelling, risk, risk assessment, sample size determination, sensitivity and specificity, truth

analytics, anesthesia, attention, bayesian inference, breathing, census, child, communication, decision tree, deep learning, demography, disability, electronic health record, health care, hospital, hospital medicine, hospital readmission, information, intuition, johns hopkins all children's hospital, learning, machine learning, medical history, medical record, music, neural network, neurology, patient, pediatrics, perioperative, point of care, positive and negative predictive values, prediction, predictive modelling, risk, risk assessment, sample size determination, sensitivity and specificity, surgery, truth, visual analytics

analytics, anesthesia, attention, bayesian inference, breathing, census, child, communication, decision tree, deep learning, demography, disability, electronic health record, health care, hospital, hospital medicine, hospital readmission, information, intuition, johns hopkins all children's hospital, learning, machine learning, medical history, medical record, music, neural network, neurology, patient, pediatrics, perioperative, point of care, positive and negative predictive values, prediction, predictive modelling, risk, risk assessment, sample size determination, sensitivity and specificity, surgery, truth, visual analytics

analytics, anesthesia, attention, bayesian inference, breathing, census, child, communication, decision tree, deep learning, demography, disability, electronic health record, health care, hospital, hospital medicine, hospital readmission, information, intuition, johns hopkins all children's hospital, learning, machine learning, medical history, medical record, music, neural network, neurology, patient, pediatrics, perioperative, point of care, positive and negative predictive values, prediction, predictive modelling, risk, risk assessment, sample size determination, sensitivity and specificity, surgery, truth, visual analytics

analytics, anesthesia, attention, bayesian inference, breathing, census, child, communication, decision tree, deep learning, demography, disability, electronic health record, health care, hospital, hospital medicine, hospital readmission, information, intuition, johns hopkins all children's hospital, learning, machine learning, medical history, medical record, music, neural network, neurology, patient, pediatrics, perioperative, point of care, positive and negative predictive values, prediction, predictive modelling, risk, risk assessment, sample size determination, sensitivity and specificity, surgery, truth, visual analytics

adverse event, bread, child, clinician, experience, false positives and false negatives, hospital, intensive care unit, internal medicine, lyme disease, medicine, palliative care, patient, positive and negative predictive values, sensitivity and specificity, silence, subset, toronto, type i and type ii errors, university of toronto

adverse event, bread, child, clinician, experience, false positives and false negatives, hospital, intensive care unit, internal medicine, lyme disease, medicine, palliative care, patient, positive and negative predictive values, sensitivity and specificity, silence, subset, toronto, type i and type ii errors, university of toronto

adverse event, bread, child, clinician, experience, false positives and false negatives, hospital, intensive care unit, internal medicine, lyme disease, medicine, palliative care, patient, positive and negative predictive values, sensitivity and specificity, silence, subset, toronto, type i and type ii errors, university of toronto

adverse event, bread, child, clinician, experience, false positives and false negatives, hospital, intensive care unit, internal medicine, lyme disease, medicine, palliative care, patient, positive and negative predictive values, sensitivity and specificity, silence, subset, toronto, type i and type ii errors, university of toronto

adverse event, bread, child, clinician, experience, false positives and false negatives, hospital, intensive care unit, internal medicine, lyme disease, medicine, palliative care, patient, positive and negative predictive values, sensitivity and specificity, silence, subset, toronto, type i and type ii errors, university of toronto

adverse event, bread, child, clinician, experience, false positives and false negatives, hospital, intensive care unit, internal medicine, lyme disease, medicine, palliative care, patient, positive and negative predictive values, sensitivity and specificity, silence, subset, toronto, type i and type ii errors, university of toronto

adverse event, bread, child, clinician, experience, false positives and false negatives, hospital, intensive care unit, internal medicine, lyme disease, medicine, palliative care, patient, positive and negative predictive values, sensitivity and specificity, silence, subset, toronto, type i and type ii errors, university of toronto

adverse event, bread, child, clinician, experience, false positives and false negatives, hospital, intensive care unit, internal medicine, lyme disease, medicine, palliative care, patient, positive and negative predictive values, sensitivity and specificity, silence, subset, toronto, type i and type ii errors, university of toronto

accuracy and precision, active learning, adolescence, adverse event, ai, algorithmic bias, almond, arctic monkeys, artificial intelligence, artificial intelligence in healthcare, artificial neural network, asthma, automation bias, average, bias, bias of an estimator, big data, big data in precision health, brain, bread, bronchitis, child, chronic condition, chronic obstructive pulmonary disease, clinical trial, clinician, computer vision, convolutional neural network, craigslist, data mining, data quality, dialysis, disease, ecology, electronic health record, emergency department, end-of-life care, epidemiology, ethics, experience, expert, fairness (machine learning), false positives and false negatives, fei-fei li, funny people, generative model, gianni versace, gold standard (test), gregory house, hawaii, health, health care, health system, hospital, imagenet, inductive reasoning, informatics, information, informed consent, intelligence, intensive care unit, interdisciplinarity, internal medicine, learning, lexus, logistic regression, long short-term memory, lyme disease, machine learning, marzyeh ghassemi, matrix (mathematics), medical diagnosis, medical privacy, medical record, medicine, mental disorder, mental health, natural language processing, neural network, new york (state), oneonta, new york, palliative care, patient, pediatrics, positive and negative predictive values, precedent, precision health, precision medicine, prediction, privacy, property, radiology, rain, random forest, randomized controlled trial, receiver operating characteristic, recurrent neural network, refrigerant, research, respiratory disease, risk, robotics, science, self-report study, sensitivity and specificity, sepsis, silence, smartphone, stanford, stanford medicine, statistics, subset, supervised learning, surgery, synthetic data, system, technology, temecula, california, toronto, type i and type ii errors, understanding, university of toronto, use case, wheeze, youtube

adverse event, bias, bread, child, clinic, clinician, data, disease, experience, false positives and false negatives, feedback, force, goal, hospital, information, intensive care unit, internal medicine, learning, lyme disease, machine, machine learning, medicine, memory, mortality rate, orange line (cta), palliative care, parameter, patient, positive and negative predictive values, prediction, regularization (mathematics), reinforcement, risk, sensitivity and specificity, silence, subset, throughput, tire, toronto, type i and type ii errors, university of toronto

accuracy and precision, analysis, applied and computational geometry, applied mathematics, bias, causality, census, computer programming, computer science, computing, data analysis, data science, decision-making, differential privacy, economics, expected value, experiment, facebook, false positives and false negatives, intelligence analysis, internet privacy, logarithm, machine learning, math, mathematics, mind, odds, overfitting, positive and negative predictive values, prime number, probability distribution, random walk, randomness, research, sampling (statistics), simulation and modeling, standard deviation, statistical classification, statistics, student financial aid (united states), system, tax, total information awareness, total variation, truth, variance