# Applications of Artificial Intelligence in Science and Medicine | Hamzeh Ghorbani | TEDxUTMA

Source: https://www.youtube.com/watch?v=K4imntESj4Y
Recap page: https://rapidrecap.app/video/K4imntESj4Y
Generated: 2026-01-14T18:04:20.314+00:00

---
## Quick Overview

Hamzeh Ghorbani details the application of Artificial Intelligence (AI) across scientific, medical, and industrial sectors, emphasizing its role in prediction and anomaly detection, which leads to optimizing processes, decreasing time, and reducing costs, as illustrated by examples like predicting supply chain distribution costs and detecting anomalies in well logging data.

**Key Points:**
- The idea of Artificial Intelligence was introduced by the British computer pioneer Alan Mathison in 1935, describing a computing machine that could move back and forth, read symbols, and write symbols.
- AI is defined as a computer system associated with human intelligence, involving learning, problem-solving, and decision-making, fundamentally differing from traditional programming where the program dictates the output based on data.
- An example application in management involves predicting Supply Chain Management Distribution Cost (SCMD), where AI helps optimize the best way to decrease distribution costs and find the best way quickly, decreasing analysis time.
- In industry (energy), AI is used for anomaly detection in well logging data, concluding that AI enables detection of abnormality, decreases time and cost for well logging, and reduces energy consumption.
- In medicine, AI, specifically using Convolutional Neural Networks (CNNs) in Computer Vision, predicts tumor delivery efficiency (DE) by nanoparticles, leading to the detection of breast cancer, and decreasing the time and cost associated with lab tests.
- The AI data pre-processing pipeline involves collection, cleaning, feature selection/reduction, handling outliers/imbalanced data, splitting data (train/test/validation), building the machine, evaluation, and final outcome prediction.

![Screenshot at 00:13: The speaker, Hamzeh Ghorbani, stands on stage next to a large screen displaying the title slide for his talk: "Application of Artificial Intelligence in the Scientific Sphere and Medicine."](https://ss.rapidrecap.app/screens/K4imntESj4Y/00-00-13.jpg)

**Context:** This TEDxUTMA presentation by Hamzeh Ghorbani, a Researcher at ML, explores the practical applications of Artificial Intelligence (AI) across various fields: science (historical context), management (supply chain), industry (energy/well logging), and medicine (tumor delivery efficiency and cancer detection). The presentation contrasts AI methods with traditional programming and outlines the necessary steps for developing and applying AI models in these domains.

## Detailed Analysis

Hamzeh Ghorbani begins by establishing the historical foundation of AI, noting that the concept of Artificial Intelligence was introduced by Alan Mathison in 1935, describing a machine capable of computation involving memory, movement, reading, and writing symbols. He then defines AI as a computer system associated with human intelligence, highlighting key functions like learning, problem-solving, and decision-making. Ghorbani contrasts this with traditional programming, where the program explicitly dictates the output for given data, whereas AI systems learn the program from data and output. The presentation transitions to specific applications. In management, AI is used for prediction, specifically predicting Supply Chain Management Distribution Cost (SCMD). The conclusion for this example is that AI can 'optimize the best way' to decrease distribution costs and find the best way 'fast' (decreasing analysis time). In industry (energy), an example shows AI performing anomaly detection on well logging data, leading to conclusions that AI improves detection of abnormality, decreases time and cost for well logging, and reduces energy consumption. In medicine, AI is applied via Computer Vision (CNNs) to predict tumor delivery efficiency (DE) by nanoparticles, which leads to early detection of breast cancer, and consequently decreases the time and cost associated with lab tests. Ghorbani details the general data pre-processing steps for AI machines: Data Collection, Data Cleaning, Feature Selection & Reduction, Outliers & Imbalanced Data handling, Data Splitting (Train, Test, Validation), Building the AI machine, Evaluating it, and finally, Prediction of the Outcome. He emphasizes that the AI machine finds features to solve complex problems where human experts might not reach the solution.

### Introduction to AI History

- Idea of Artificial Intelligence introduced by British computer pioneer Alan Mathison in 1935
- Mathison described a computing machine with limited memory that could move back and forth, read, and write symbols.

### Definition and Contrast with Traditional Methods

- AI involves learning, problem-solving, and decision-making, unlike traditional programming where data and program lead to a fixed output.

### AI Classification Diagram

- Shows AI as the largest set, containing Machine Learning, which contains Deep Learning; intersections include NLP and Computer Vision, with Generative AI & Large Language Models at the core.

### Application in Management (Prediction)

- Example predicts Supply Chain Management Distribution Cost (SCMD); AI optimizes the best way to decrease cost and finds the best way quickly.

### Application in Industry (Energy)

- AI performs anomaly detection on well logging data, leading to improved detection, decreased time/cost/energy consumption for logging.

### Application in Medicine (Computer Vision)

- AI (CNN) predicts tumor delivery efficiency (DE) by nanoparticles, resulting in breast cancer detection, decreased time, and decreased cost for lab tests.

### AI Data Pre-process Flow

- Steps include Data Collection, Cleaning, Feature Selection & Reduction, Outliers handling, Data Splitting (Train/Test/Validation), Model Building, Evaluation, and Prediction.

![Screenshot at 0:00: Introduction slide showing the TEDxUTMA event is shared by the University of Traditional Medicine of Armenia \(UTMA\).](https://ss.rapidrecap.app/screens/K4imntESj4Y/00-00-00.jpg)
![Screenshot at 0:13: The speaker, Hamzeh Ghorbani, stands on stage, presenting the title slide: "Application of Artificial Intelligence in the Scientific Sphere and Medicine."](https://ss.rapidrecap.app/screens/K4imntESj4Y/00-00-13.jpg)
![Screenshot at 0:27: Slide introducing the core questions: "Why do we need AI? Is it helpful for us?"](https://ss.rapidrecap.app/screens/K4imntESj4Y/00-00-27.jpg)
![Screenshot at 0:38: Slide detailing the History of AI, crediting Alan Mathison for introducing the idea in 1935.](https://ss.rapidrecap.app/screens/K4imntESj4Y/00-00-38.jpg)
![Screenshot at 1:32: Slide defining AI and contrasting it with traditional programming methods using flow diagrams.](https://ss.rapidrecap.app/screens/K4imntESj4Y/00-01-32.jpg)
![Screenshot at 2:47: Slide showing the Classification of AI Systems via nested circles: AI contains Machine Learning, which contains Deep Learning, with intersections for NLP, Computer Vision, and Generative AI.](https://ss.rapidrecap.app/screens/K4imntESj4Y/00-02-47.jpg)
![Screenshot at 3:11: Slide detailing the Classification of Supervised Machine Learning, distinguishing between Classification \(discrete data like yes/no\) and Regression \(continuous data like pressure/temperature\).](https://ss.rapidrecap.app/screens/K4imntESj4Y/00-03-11.jpg)
![Screenshot at 4:08: Slide illustrating the Data Pre-Process for AI Machine workflow in seven sequential steps.](https://ss.rapidrecap.app/screens/K4imntESj4Y/00-04-08.jpg)
![Screenshot at 5:11: Slide showing the Application of AI in Management for predicting supply chain distribution cost \(SCMD\), with a prediction scatter plot and conclusion points.](https://ss.rapidrecap.app/screens/K4imntESj4Y/00-05-11.jpg)
![Screenshot at 6:26: Slide detailing the Application of AI in Industry \(Energy\) for determining abnormal detection of well logging data, showing input tables, output graph, and key conclusions.](https://ss.rapidrecap.app/screens/K4imntESj4Y/00-06-26.jpg)
![Screenshot at 7:13: Slide detailing the Application of AI in Medicine \(Prediction\) for tumor delivery efficiency \(DE\) by nanoparticles, showing a flow diagram and conclusion points.](https://ss.rapidrecap.app/screens/K4imntESj4Y/00-07-13.jpg)
![Screenshot at 8:24: Detailed diagram showing the CNN process flow for breast cancer prediction using image data.](https://ss.rapidrecap.app/screens/K4imntESj4Y/00-08-24.jpg)
![Screenshot at 9:44: Final slide showing the References used in the presentation.](https://ss.rapidrecap.app/screens/K4imntESj4Y/00-09-44.jpg)