Ai idea to implementation : Use cases in Healthcare
Download as PPTX, PDF0 likes123 views
The document discusses the use of artificial intelligence (AI) in healthcare, outlining its definition, sub-fields like machine learning, and the steps necessary for implementation from identifying a business case to deploying models. It also mentions various use cases such as predictive analytics, text analysis, and image analysis while highlighting challenges like bias and ethics. The author emphasizes the importance of transparency and building trust in AI applications in the healthcare sector.
Ai idea to implementation : Use cases in Healthcare
- 1. AI Use cases in Healthcare: From Idea to Implementation Swathi Young CTO, Integrity Management Services, Inc. IntegrityM.com @swathiyoung
- 2. 2 What is AI? The term was coined by John McCarthy in 1956 and it means “is intelligence demonstrated by machines, in contrast to the natural intelligence displayed by humans. It is an umbrella term whose sub-fields range from robotics to machine learning.” Artificial Intelligence
- 3. 3
- 4. 4 Machine Learning AI that uses algorithms that automatically “learns” without being explicitly programmed. Machine learning is the application of AI techniques using statistical methods Genre Award x y Sci-Fi Drama Golden Globes Oscars x x x x x x x x x x x x x x x x x x x x x x o ?
- 5. 5 Supervised and Unsupervised learning
- 6. 6 TO GET STARTED 1. BUSINESS CASE 2. DATA 3. ML MODELS
- 7. 7 KEY ACTIVITIES FOR ENTERPRISE AI ADOPTION
- 8. 8 Key steps of implementation of a use case Business Objective Data Sources Data Analysis/ Feature Engg. Training DataSet Validation/ Test Dataset Evaluation Model Deploy Visualize Output Pre-Processing Modeling Outcomes Business rules
- 9. 9 USE CASES
- 11. 11 CELL-BASED DISEASED MODELS Source: Insitro.com
- 12. 12 TEXT ANALYSIS
- 17. 17 THANK YOU
- 18. 18 Connect with me on LinkedIn and Twitter @Swathiyoung YouTube channel – Trendy Techie THANK YOU!
Editor's Notes
- #4: Dubai robo cop
- #13: Machine Learning to learn to tell fraudsters from legitimate users without explicitly telling it what designates to look for. Let’s dive deeper… The idea is that there are certain characteristics of fraudulent transactions that differentiate them from legitimate ones. Machine Learning algorithms recognize patterns in the data that allow them to discern fraudsters from legitimate clients, based on thousands of pieces of information, that sometimes may seem completely unrelated to a human being. The algorithm is searching for patterns in fraudsters’ behavior, their hardware characteristics etc.