The intersection podcast is an outreach initiative to discuss recent research in artificial intelligence and healthcare. In a series of casual conversations, we dissect the essence of the methods used, their clinical applications and limits. Subscribe for
The Intersection Podcast: AI & Healthcare
In this episode, we discuss how AI can be used to screen for depression on Facebook, as shown in this 2018 PNAS article " Facebook language predicts depression in medical records", by Eichstaedt et al. Links: The article: https://www.pnas.org/content/115/44/11203 American Psychiatric Association: https://www.psychiatry.org/patients-families/depression/what-is-depression National Institute of Health Mental: https://www.nimh.nih.gov/health/statistics/major-depression.shtml
Geoffrey Hinton recently posted this provocative question on twitter: "Suppose you have cancer and you have to choose between a black box AI surgeon that cannot explain how it works but has a 90% cure rate and a human surgeon with an 80% cure rate. Do you want the AI surgeon to be illegal?" We try to analyze the subtext to that question and provide our own personal answer.
In this episode we discuss the recent Science Paper - Dissecting racial bias in an algorithm used to manage the health of populations. ------- Link: The article: https://science.sciencemag.org/content/366/6464/447
Precision Medicine and Artificial Intelligence: A Pilot Study on Deep Learning for Hypoglycemic Events Detection based on ECG Links: The article: https://www.nature.com/articles/s41598-019-56927-5 Blood sugar testing: Why, when and how: https://www.mayoclinic.org/diseases-conditions/diabetes/in-depth/blood-sugar/art-20046628 What is an EKG: https://www.heart.org/en/health-topics/heart-attack/diagnosing-a-heart-attack/electrocardiogram-ecg-or-ekg
#Pathology is an essential step for cancer diagnosis. It is currently being revolutionized by #ArtificialIntelligence. We discuss the promises and challenges in digital pathology in our latest episode, available on SoundCloud, Apple Podcasts and Spotify. --------------------- Links to go further: The article: https://www.nature.com/articles/s41591-019-0508-1 What happens after a biopsy: https://www.cancer.net/navigating-cancer-care/diagnosing-cancer/reports-and-results/after-biopsy-making-diagnosis
Special report: Can AI help us manage the coronavirus 2019-nCov outbreak? _______ LINKS: Methods Using Social Media and Search Queries to Predict Infectious Disease Outbreaks: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5688036/ Harnessing wearable device data to improve state-level real-time surveillance of influenza-like illness in the USA: a population-based study: https://www.sciencedirect.com/science/article/pii/S2589750019302225?via%3Dihub Predicting Infectious Disease Using Deep Learning and Big Data: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6121625/ Prediction of infectious disease epidemics via weighted density ensembles: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5834190/
Episode about the Nature article by SM McKinney et al. "International evaluation of an AI system for breast cancer screening". ___________ LINKS: The article: https://www.nature.com/articles/s41586-019-1799-6 Breast cancer screening: https://www.nhs.uk/conditions/breast-cancer-screening/why-its-offered/ Understanding mammogram reports: https://www.cancer.org/cancer/breast-cancer/screening-tests-and-early-detection/mammograms/understanding-your-mammogram-report.html Breast Cancer Classifier (NYU - GitHub): https://github.com/nyukat/breast_cancer_classifier
Introduction to the intersection, a podcast to discuss recent research in artificial intelligence and healthcare.