Innovations in AI Applications for Group-Based Medical Investigation
Exploring the diverse applications of artificial intelligence (AI) in the field of medicine, this presentation delves into topics such as AI in disease diagnosis/prognosis, molecular data analysis, disease treatment/drug development, and utilizing Watson from IBM. It also discusses the role of AI in combating COVID-19 and emphasizes the importance of AI-human interaction skills, ethics, patient privacy, and other key factors in deploying AI systems. Additionally, the presentation sheds light on AI's significance in drug development stages and provides useful sources for further exploration in the field of AI in healthcare.
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. Download presentation by click this link. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
E N D
Presentation Transcript
AI in Medicine Topics for Group-Based Investigation, Presentation and Discussion To download these slides: 1. Go to folk.idi.ntnu.no/keithd/downloads 2. Click on file ai-medicine.pptx
AI Application Areas in Medicine Diagnosis / Prognosis based on: Group 1: Imaging (CT, EKG, MRI, whole-slide, etc.) Group 2: Molecular (Genomic) data Groups 3 & 4: Disease Treatment and/or Drug Development Group 5: Watson (from IBM) Overview of the AI involved Claims vs- Actual results Group 6: Fighting Covid-19 with AI Overview of tactics and uses of AI therein.
Basic Task for Groups 1-4 Choose 2-3 Systems / Technologies that are new and promising (IYHO). Describe each w.r.t. basic I/O behavior + any other easily-conveyed technical details about what s inside the black box. E.g. Input = (patient genome + online oncology literature) Output = cancer risks Technical = A deep network + WATSON Address Key Factors (next slide) for each.
Key Factors in deploying the AI system AI-Human Interaction Skills required of the humans Skills taken over by the AI Interface between Human and AI Ethics Patient information s privacy and security Job loss (or creation) Patient s Experience and Reaction Comfort, cost, convenience Time Frame How quickly (or slowly) to achieve in Trondheim? Why? Other pertinent factors (e.g. pros + cons) - optional
Drug Development Four Main Stages 1. Find molecular targets 2. Find drug candidates 3. Testing Trials (speed up w/o increased risk) 4. Find biomarkers a. Diagnostic Does patient (P) have the disease (D)? b. Risk Is P at risk of getting D? c. Prognostic How has D progressed in P? d. Therapeutic Predictive How will P respond to Drug X? AI can be useful in all of these stages.
Sources VPN login at NTNU is probably necessary to access some (many?) of these. General builtin.com/artificial-intelligence/artificial-intelligence-healthcare (AI in healthcare) ncbi.nlm.nih.gov/pmc/articles/PMC7226189 (AI in oncology) datarevenue.com/en-blog/artificial-intelligence-in-medicine (overview of application areas) Diagnosis nature.com/articles/d41586-020-00847-2 (AI in cancer diagnosis) genomemedicine.biomedcentral.com/articles/10.1186/s13073-019-0689-8 (AI in genomic diagnostics) Treatment and Drug Discovery nature.com/articles/d41586-018-05267-x (AI in drug discovery) ddw-online.com/informatics/p323284-how-artificial-intelligence-is-transforming-drug-design.html Pubmed.ncbi.nlm.nih.gov/31209850 (AI in personalized medicine) Watson aaai.org/Magazine/Watson/watson.php (tech details) ibm.com/cloud/watson-discovery (pure promotion from IBM) Spectrum.ieee.org/biomedical/diagnostics/how-ibm-watson-overpromised-and-underdelivered-on-ai- health-care (reality check) Covid-19 datarevenue.com/en-blog/machine-learning-covid-19 sciencedirect.com/science/article/pii/S1871402120300771
