Proposed
Nomenclature
change
Biomedical Instrumentation -- ?
Proposed List of
Masters course names
• Biomedical Data Science
• Artificial Intelligence in Digital Health (As it covers
medical devices)
• Artificial Intelligence in Healthcare (This is broader one)
• Health Informatics and Data Science
• Artificial Intelligence and Health informatics
• AIML in Healthcare
• Machine Intelligence in Healthcare
• Machine Learning in Healthcare
Course Universities
Biomedical Data Science NTU Singapore, Stanford, John Hopkins, Illinois,
Wisconsin, Mahindra University Hyderabad etc
Artificial Intelligence in Digital
Health
IISc Bangalore, Ohio State, IIHMR Bangalore,
Bournemouth University UK etc
Artificial Intelligence in Healthcare University of Toronto, University of Hull, Stanford
online, NUS medicine
Health Informatics and Data Science University of Alabama, University of Scranton,
Apollo university
Artificial Intelligence and Health
informatics
Apollo university, Michigan Technological
University, Aster Health academy
AIML in Healthcare, Machine
Intelligence in Healthcare, AI in
healthcare
IIHMR, Stanford, Hull, Cambridge, Aster, NTU, NUS
etc
List of MOOC courses
1. Introduction to Machine Learning
2. Introduction to Artificial Intelligence
3. Deep Learning
4. Deep Learning for Computer Vision
5. Python for Data Science
6. Advanced R programming for data analytics
7. Essentials of data science with R programming
8. Data analysis using statistical learning techniques
9. Data Science for engineers
10.Probability Theory for Data Science
11.Natural Language Processing
12.Applied Natural Language Processing
13.Human Physiology
14.Fundamentals of telehealth and virtual care
15.Health Research Fundamentals
16.Introduction to Biomedical Imaging System
17.Biomedical Signal Processing
18. Microsensors, Implantable Devices and Rodent Surgeries for Biomedical Applications
Semester I
Sr.
No.
Course
Type
Course Code Course Name Teaching Scheme Credits
L T P
1. PSMC PSMC-01 Mathematics for AI & ML 3 1 -- 4
2. PSBC PSBC-01 Anatomy & Physiology for Engineers 3 0 -- 3
3. PCC PCC-01 Medical Data Acquisition and Management 3 0 - 3
4. PCC PCC-02 Introduction to Artificial Intelligence 3 0 - 3
5. PCC PCC -03 Physiological/Biomedical Signal Processing 3 0 - 3
6. LC LC-01 Statistical Computing- with Python - - 2 1
7. LC LC-02 Statistical Computing with R - - 2 1
8. LC LC-03 Computing with MATLAB - - 2 1
9. PEC
PEC-01
Program Specific Elective –I
1. Biomedical Devices and systems
2. Introduction to Medical Software/Medical Algorithms
3 -- -- 3
10. MLC MLC-01 Research Methods in AI for Digital Health (Audit) 2 -- -- --
11. MLC MLC-02 Effective Technical Communication 1 -- -- --
21 1 6
Total Credits 22
Semester II
Sr.
No.
Course
Type
Course Code Course Name
Teaching Scheme
Credits
L T P
1. OE OE-01
Introduction to Machine Learning/Pattern recognition
and Machine Learning
3 - - 3
2.
PCC PCC-04 Deep Learning 3
0 - 3
3.
PCC PCC-05 Medical Image Analysis 3
0 - 3
4.
PCC PCC-06 Wearable Devices and Remote Monitoring 3
0 - 3
5.
LC LC-04 Health informatics and Data Analytics Lab -
- 2 1
6.
LC LC-05 Medical Image Analysis and Predictive Models
Lab/ Physiological signal analysis and predictive
models Lab
-
- 2 1
7.
LC LC-06 Wearable and Remote Monitoring Lab -
- 2 1
8. PEC
PEC-02
Program Specific Elective –II
I. Healthcare information privacy and security
II. Natural Language Processing in Healthcare
3
0 0 3
9. DEC
Program Specific t Elective –III 3 0 0 3
Semester III
Course
Type
Course
Code
Course Name
Teaching Scheme
Credits
Sr.
No. L T P S
1. VSEC VSEC-01 Dissertation Phase – I -- -- 18 12 9
2. SLC SLC-01 Massive Open Online Course -I 3 -- -- 3 3
Total Hrs. 3 -- 18 15 12
Total Credits 12
Semester IV
Sr.
No.
Course
Type
Course
Code
Course Name
Teaching Scheme
Credits
L T P
1. VSEC VSEC-02 Dissertation Phase – II -- -- 18 12 9
2. SLC SLC-02 Massive Open Online Course -II 3 -- -- 3 3
Total Hrs. 3 -- 18 15 12
Total Credits 12
Proposed list of subjects
Biomedical Vertical AIML vertical
Human biology for engineers (Bridge
course)
Statistics for Data Science
Foundation Models for Healthcare Statistical Computing with Python/ R basics
Physiological Signal Processing Artificial Intelligence
Medical Data Landscapes Machine Learning
Digital Health Deep Learning
Wearable Devices Generative AI in Healthcare
Internet of Medical Things Ethics of ML in Healthcare
Human biology for engineers (Bridge
course)
• Introduction to cell, Blood: Characteristics of blood, physiology of blood clotting, biochemical
cycle
• Heart (Circulatory System)- Anatomy of heart and blood vessels, origin and conduction of
heartbeat, cardiac cycle, electrocardiogram, blood pressure, control of cardiac cycle.
• Respiratory System- Anatomy of respiratory system, physiology of respiration in the alveolar and
tissue capillaries, control of respiration.
• Digestive system: Anatomy of digestive system, nerve and blood supply, physiology of digestion.
• Kidney and Urinary system - Anatomy of urinary system and kidney, physiology of water and
electrolyte balance, acid-base regulation.
• Muscle Tissues - Anatomy, types of muscles, physiology of muscle contraction, generation of
action potential, rhythmicity of cardiac muscle contraction, properties of skeletal and Cardiac
muscles.
• Nervous system - Neuron, anatomy and function of different parts of brain, spinal cord,
autonomic nervous system, Sensory system - Visual, auditory, Vestibular Endocrine system-
pituitary, thyroid, parathyroid, adrenal, pancreas
• Biological control and feed-back mechanism, clinical and technological implications
Foundation Models for Healthcare
• Physiological modelling: Introduction of physiological modelling, importance of physiological
modelling, Classification of models, characteristics of model, model simulation, model
validation, Time invariant and time varying systems for physiological modelling
• Electrical models: Models of neuron - Electromotive, resistive and capacitive properties of cell
membrane, change in membrane potential with distance, voltage clamp experiment and
Hodgkin and Huxley‘s model of action potential, the voltage dependent membrane constant,
model for strength- duration curve, model of the whole neuron.
• Mechanical models: Modelling neuromuscular system - modelling of skeletal muscle, mono
and polysynaptic reflexes, stretch reflex, reciprocal innervations, two control mechanism,
Golgi tendon, experimental validation, Parkinson‘s syndrome. Huxley model of isotonic
muscle contraction; Eye movement model - Four eye movements, quantitative eye movement
models, validity criteria.
• Physiological Process Models: Thermoregulatory model - Thermoregulatory mechanisms,
model of thermoregulatory system, controller model, validation and application; Modelling of
Immune response - Linearized model of the immune response: Germ, Plasma cell, Antibody,
system equation and stability criteria.
• Other models - Models of drug delivery, Modelling of insulin glucose feedback system
Physiological Signal Processing
1.Introduction to Physiological Signals
2. Signal Acquisition and Preprocessing
3. Time-Domain Signal Analysis
4. Frequency-Domain Analysis
5. Time-Frequency Analysis
6. Machine Learning for Physiological Signals
7. Signal Processing Techniques for Specific Signals
Medical Data Landscapes
• Introduction to Medical Data
• Sources of Medical Data
• Data Collection and Management
• Medical Data Standards and Privacy
• Healthcare data standards (HL7, ICD, SNOMED, LOINC)
• Privacy laws and regulations: HIPAA, GDPR, and their impact on data
management.
• De-identiication, data anonymization, and consent
• Medical Data Mining
• Big Data in Healthcare
• Applications and Case Studies
Digital Healthcare Technologies
• Introduction to Digital Healthcare
• Electronic Health Records (EHRs)
• Data Analytics in Digital Health
• Digital Health Policy and Regulation
• Patient Engagement and Empowerment
• Future Trends in Digital Healthcare
• Case Studies and Practical Applications
Wearable Devices
• Introduction to Wearable Technology: Definitions, historical context, and market trends.
• Types of Wearable Devices: Overview of fitness trackers, smartwatches, medical wearables,
and emerging technologies like AR glasses.
• Sensors and Technology: Key sensors used, communication technologies (Bluetooth, NFC),
and power management strategies.
• Data Acquisition and Processing: Methods for collecting and processing data, ensuring
accuracy and reliability.
• Health and Fitness Applications: Monitoring vital signs, tracking physical activity, and chronic
disease management.
• Data Analytics and Interpretation: Techniques for analyzing data from wearables using machine
learning and interpreting health metrics.
• User Experience and Design: Design considerations for usability, comfort, and the importance
of privacy and security.
• Regulatory and Ethical Issues: Overview of regulations governing wearables and ethical
concerns in data collection and privacy.
• Future Trends: Innovations in wearable technology, such as smart textiles and the impact of 5G.
• Case Studies and Practical Applications: Analysis of successful implementations and projects
focused on designing wearable devices.
Internet of Medical Things
1. Introduction to IoMT: Overview of IoT in healthcare, significance, and historical trends.
2. Components of IoMT: Medical devices and sensors, including wearables and communication
technologies (Bluetooth, Wi-Fi).
3. Data Management: Data acquisition, storage (cloud and edge computing), and interoperability
standards (HL7, FHIR).
4. Security and Privacy: Challenges in IoMT security, data encryption, secure transmission, and
compliance with regulations like HIPAA and GDPR.
5. Applications of IoMT: Remote patient monitoring, smart hospitals, and specific use cases
(ECG monitors, glucose monitoring).
6. Data Analytics and Machine Learning: Techniques for analyzing IoMT data, including
predictive analytics and challenges related to data volume and variety.
7. User Experience: Importance of user-centered design, enhancing patient engagement, and
ensuring accessibility.
8. Regulatory Considerations: Overview of regulatory frameworks for medical devices and
compliance with safety standards.
9. Future Trends: Emerging technologies (AI, blockchain), integration with 5G and big data, and
potential impacts on healthcare.
10.Case Studies: Analysis of successful IoMT implementations and projects focused on
developing IoMT solutions.
Statistics for data science
• Introduction to Statistics and Probability
• Descriptive statistics,
• Inferential statistics,
• Probability distributions,
• Hypothesis testing,
• Statistical modeling
Statistical Computing with Python/ R
basics R Basics
• Introduction and basics
• Variables and data types
• Inbuilt functions
• Data frames
• Plotting
• Regression analysis
• Time series data
• Statistical programming language concepts
• Writing and debugging programs
• Building and organizing software packages
• Installing and using R packages
• Importing data from external sources
• Transforming data to support analysis
• Visualizing and understanding data
• Writing basic R functions
• Conducting statistical analysis and inference
• Generating research or analytical reports
Python
• data and text
manipulation,
• regular expressions,
• data structures,
• functions
• variable scope,
• memory use,
• efficiency,
• debugging,
• testing,
• parallel processing
Artificial Intelligence
• Introduction to AI:
• Search and Problem Solving
• Knowledge Representation and Reasoning:
• Machine Learning Basics:
• Natural Language Processing (NLP):
• Computer Vision:
• Planning and Robotics:
• Ethics in AI:
Machine Learning
• Introduction to Machine Learning: Basic concepts, types of machine learning (supervised,
unsupervised, reinforcement learning), and its applications.
• Key Algorithms:
• Supervised Learning: Linear regression, logistic regression, decision trees, support vector machines (SVM), k-nearest
neighbors (KNN).
• Unsupervised Learning: Clustering (k-means, hierarchical), dimensionality reduction (PCA).
• Reinforcement Learning: Markov decision processes, Q-learning.
• Model Training and Evaluation:
• Training and testing datasets
• Model evaluation techniques: Accuracy, precision, recall, F1-score, confusion matrix, cross-validation.
• Overfitting and underfitting, bias-variance tradeoff.
• Feature Engineering: Techniques for selecting, transforming, and creating features for better model
performance.
• Optimization and Tuning:
• Hyperparameter tuning
• Regularization techniques (L1, L2)
• Gradient descent and other optimization methods.
• Applications: Examples in fields like healthcare, finance, natural language processing (NLP), and
computer vision.
• Challenges: Handling imbalanced data, interpretability of models, ethics and fairness in ML.
Deep Learning
• Introduction to Deep Learning: Overview of deep learning and how it differs from traditional machine
learning.
• Neural Networks: Basics of artificial neural networks, including perceptrons, activation functions, and
backpropagation.
• Key Architectures:
• Feedforward Neural Networks (FNNs)
• Convolutional Neural Networks (CNNs): Primarily for image data.
• Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM): For sequential data like time series.
• Generative Adversarial Networks (GANs): For generating synthetic data.
• Training Deep Networks: Concepts like optimization (gradient descent, learning rates), regularization, and
overfitting.
• Advanced Topics:
• Transfer learning
• Deep reinforcement learning
• Autoencoders and unsupervised learning
• Applications: Use cases in computer vision, natural language processing, speech recognition, and other
fields.
• Challenges: Computational demands, data requirements, model interpretability, and ethics in AI
Generative AI in Healthcare
• Learn the fundamentals of Generative AI and its role in
transforming the healthcare sector.
• Explore how Generative AI is used for analyzing and
interpreting medical imaging data.
• Discover how Generative AI can aid in more accurate and
efficient patient diagnosis.
• Learn to leverage Generative AI for tailoring healthcare
solutions to individual patient needs.
Ethics of ML in Healthcare
• Ethical Foundations: Basic ethical principles (beneficence, autonomy, fairness) and
frameworks applied in healthcare.
• ML in Healthcare: Overview of machine learning applications like diagnostics,
treatment, and disease prediction.
• Key Ethical Concerns:
• Bias and fairness in ML systems
• Transparency, explainability, and accountability
• Informed consent and privacy concerns
• Case Studies: Real-world examples highlighting successes and ethical failures in
healthcare ML.
• Legal/Regulatory Issues: Understanding healthcare laws (e.g., HIPAA, GDPR) and
AI-related legal responsibilities.
• Responsible AI Design: Best practices for ethical, human-centered ML systems in
healthcare.
• Future Challenges: Emerging issues in AI, including genomics and personalized
medicine.

Nomenclature change for M Tech Biomedical.pptx

  • 1.
  • 2.
    Proposed List of Masterscourse names • Biomedical Data Science • Artificial Intelligence in Digital Health (As it covers medical devices) • Artificial Intelligence in Healthcare (This is broader one) • Health Informatics and Data Science • Artificial Intelligence and Health informatics • AIML in Healthcare • Machine Intelligence in Healthcare • Machine Learning in Healthcare
  • 3.
    Course Universities Biomedical DataScience NTU Singapore, Stanford, John Hopkins, Illinois, Wisconsin, Mahindra University Hyderabad etc Artificial Intelligence in Digital Health IISc Bangalore, Ohio State, IIHMR Bangalore, Bournemouth University UK etc Artificial Intelligence in Healthcare University of Toronto, University of Hull, Stanford online, NUS medicine Health Informatics and Data Science University of Alabama, University of Scranton, Apollo university Artificial Intelligence and Health informatics Apollo university, Michigan Technological University, Aster Health academy AIML in Healthcare, Machine Intelligence in Healthcare, AI in healthcare IIHMR, Stanford, Hull, Cambridge, Aster, NTU, NUS etc
  • 4.
    List of MOOCcourses 1. Introduction to Machine Learning 2. Introduction to Artificial Intelligence 3. Deep Learning 4. Deep Learning for Computer Vision 5. Python for Data Science 6. Advanced R programming for data analytics 7. Essentials of data science with R programming 8. Data analysis using statistical learning techniques 9. Data Science for engineers 10.Probability Theory for Data Science 11.Natural Language Processing 12.Applied Natural Language Processing 13.Human Physiology 14.Fundamentals of telehealth and virtual care 15.Health Research Fundamentals 16.Introduction to Biomedical Imaging System 17.Biomedical Signal Processing 18. Microsensors, Implantable Devices and Rodent Surgeries for Biomedical Applications
  • 5.
    Semester I Sr. No. Course Type Course CodeCourse Name Teaching Scheme Credits L T P 1. PSMC PSMC-01 Mathematics for AI & ML 3 1 -- 4 2. PSBC PSBC-01 Anatomy & Physiology for Engineers 3 0 -- 3 3. PCC PCC-01 Medical Data Acquisition and Management 3 0 - 3 4. PCC PCC-02 Introduction to Artificial Intelligence 3 0 - 3 5. PCC PCC -03 Physiological/Biomedical Signal Processing 3 0 - 3 6. LC LC-01 Statistical Computing- with Python - - 2 1 7. LC LC-02 Statistical Computing with R - - 2 1 8. LC LC-03 Computing with MATLAB - - 2 1 9. PEC PEC-01 Program Specific Elective –I 1. Biomedical Devices and systems 2. Introduction to Medical Software/Medical Algorithms 3 -- -- 3 10. MLC MLC-01 Research Methods in AI for Digital Health (Audit) 2 -- -- -- 11. MLC MLC-02 Effective Technical Communication 1 -- -- -- 21 1 6 Total Credits 22
  • 6.
    Semester II Sr. No. Course Type Course CodeCourse Name Teaching Scheme Credits L T P 1. OE OE-01 Introduction to Machine Learning/Pattern recognition and Machine Learning 3 - - 3 2. PCC PCC-04 Deep Learning 3 0 - 3 3. PCC PCC-05 Medical Image Analysis 3 0 - 3 4. PCC PCC-06 Wearable Devices and Remote Monitoring 3 0 - 3 5. LC LC-04 Health informatics and Data Analytics Lab - - 2 1 6. LC LC-05 Medical Image Analysis and Predictive Models Lab/ Physiological signal analysis and predictive models Lab - - 2 1 7. LC LC-06 Wearable and Remote Monitoring Lab - - 2 1 8. PEC PEC-02 Program Specific Elective –II I. Healthcare information privacy and security II. Natural Language Processing in Healthcare 3 0 0 3 9. DEC Program Specific t Elective –III 3 0 0 3
  • 7.
    Semester III Course Type Course Code Course Name TeachingScheme Credits Sr. No. L T P S 1. VSEC VSEC-01 Dissertation Phase – I -- -- 18 12 9 2. SLC SLC-01 Massive Open Online Course -I 3 -- -- 3 3 Total Hrs. 3 -- 18 15 12 Total Credits 12
  • 8.
    Semester IV Sr. No. Course Type Course Code Course Name TeachingScheme Credits L T P 1. VSEC VSEC-02 Dissertation Phase – II -- -- 18 12 9 2. SLC SLC-02 Massive Open Online Course -II 3 -- -- 3 3 Total Hrs. 3 -- 18 15 12 Total Credits 12
  • 9.
    Proposed list ofsubjects Biomedical Vertical AIML vertical Human biology for engineers (Bridge course) Statistics for Data Science Foundation Models for Healthcare Statistical Computing with Python/ R basics Physiological Signal Processing Artificial Intelligence Medical Data Landscapes Machine Learning Digital Health Deep Learning Wearable Devices Generative AI in Healthcare Internet of Medical Things Ethics of ML in Healthcare
  • 10.
    Human biology forengineers (Bridge course) • Introduction to cell, Blood: Characteristics of blood, physiology of blood clotting, biochemical cycle • Heart (Circulatory System)- Anatomy of heart and blood vessels, origin and conduction of heartbeat, cardiac cycle, electrocardiogram, blood pressure, control of cardiac cycle. • Respiratory System- Anatomy of respiratory system, physiology of respiration in the alveolar and tissue capillaries, control of respiration. • Digestive system: Anatomy of digestive system, nerve and blood supply, physiology of digestion. • Kidney and Urinary system - Anatomy of urinary system and kidney, physiology of water and electrolyte balance, acid-base regulation. • Muscle Tissues - Anatomy, types of muscles, physiology of muscle contraction, generation of action potential, rhythmicity of cardiac muscle contraction, properties of skeletal and Cardiac muscles. • Nervous system - Neuron, anatomy and function of different parts of brain, spinal cord, autonomic nervous system, Sensory system - Visual, auditory, Vestibular Endocrine system- pituitary, thyroid, parathyroid, adrenal, pancreas • Biological control and feed-back mechanism, clinical and technological implications
  • 11.
    Foundation Models forHealthcare • Physiological modelling: Introduction of physiological modelling, importance of physiological modelling, Classification of models, characteristics of model, model simulation, model validation, Time invariant and time varying systems for physiological modelling • Electrical models: Models of neuron - Electromotive, resistive and capacitive properties of cell membrane, change in membrane potential with distance, voltage clamp experiment and Hodgkin and Huxley‘s model of action potential, the voltage dependent membrane constant, model for strength- duration curve, model of the whole neuron. • Mechanical models: Modelling neuromuscular system - modelling of skeletal muscle, mono and polysynaptic reflexes, stretch reflex, reciprocal innervations, two control mechanism, Golgi tendon, experimental validation, Parkinson‘s syndrome. Huxley model of isotonic muscle contraction; Eye movement model - Four eye movements, quantitative eye movement models, validity criteria. • Physiological Process Models: Thermoregulatory model - Thermoregulatory mechanisms, model of thermoregulatory system, controller model, validation and application; Modelling of Immune response - Linearized model of the immune response: Germ, Plasma cell, Antibody, system equation and stability criteria. • Other models - Models of drug delivery, Modelling of insulin glucose feedback system
  • 12.
    Physiological Signal Processing 1.Introductionto Physiological Signals 2. Signal Acquisition and Preprocessing 3. Time-Domain Signal Analysis 4. Frequency-Domain Analysis 5. Time-Frequency Analysis 6. Machine Learning for Physiological Signals 7. Signal Processing Techniques for Specific Signals
  • 13.
    Medical Data Landscapes •Introduction to Medical Data • Sources of Medical Data • Data Collection and Management • Medical Data Standards and Privacy • Healthcare data standards (HL7, ICD, SNOMED, LOINC) • Privacy laws and regulations: HIPAA, GDPR, and their impact on data management. • De-identiication, data anonymization, and consent • Medical Data Mining • Big Data in Healthcare • Applications and Case Studies
  • 14.
    Digital Healthcare Technologies •Introduction to Digital Healthcare • Electronic Health Records (EHRs) • Data Analytics in Digital Health • Digital Health Policy and Regulation • Patient Engagement and Empowerment • Future Trends in Digital Healthcare • Case Studies and Practical Applications
  • 15.
    Wearable Devices • Introductionto Wearable Technology: Definitions, historical context, and market trends. • Types of Wearable Devices: Overview of fitness trackers, smartwatches, medical wearables, and emerging technologies like AR glasses. • Sensors and Technology: Key sensors used, communication technologies (Bluetooth, NFC), and power management strategies. • Data Acquisition and Processing: Methods for collecting and processing data, ensuring accuracy and reliability. • Health and Fitness Applications: Monitoring vital signs, tracking physical activity, and chronic disease management. • Data Analytics and Interpretation: Techniques for analyzing data from wearables using machine learning and interpreting health metrics. • User Experience and Design: Design considerations for usability, comfort, and the importance of privacy and security. • Regulatory and Ethical Issues: Overview of regulations governing wearables and ethical concerns in data collection and privacy. • Future Trends: Innovations in wearable technology, such as smart textiles and the impact of 5G. • Case Studies and Practical Applications: Analysis of successful implementations and projects focused on designing wearable devices.
  • 16.
    Internet of MedicalThings 1. Introduction to IoMT: Overview of IoT in healthcare, significance, and historical trends. 2. Components of IoMT: Medical devices and sensors, including wearables and communication technologies (Bluetooth, Wi-Fi). 3. Data Management: Data acquisition, storage (cloud and edge computing), and interoperability standards (HL7, FHIR). 4. Security and Privacy: Challenges in IoMT security, data encryption, secure transmission, and compliance with regulations like HIPAA and GDPR. 5. Applications of IoMT: Remote patient monitoring, smart hospitals, and specific use cases (ECG monitors, glucose monitoring). 6. Data Analytics and Machine Learning: Techniques for analyzing IoMT data, including predictive analytics and challenges related to data volume and variety. 7. User Experience: Importance of user-centered design, enhancing patient engagement, and ensuring accessibility. 8. Regulatory Considerations: Overview of regulatory frameworks for medical devices and compliance with safety standards. 9. Future Trends: Emerging technologies (AI, blockchain), integration with 5G and big data, and potential impacts on healthcare. 10.Case Studies: Analysis of successful IoMT implementations and projects focused on developing IoMT solutions.
  • 17.
    Statistics for datascience • Introduction to Statistics and Probability • Descriptive statistics, • Inferential statistics, • Probability distributions, • Hypothesis testing, • Statistical modeling
  • 18.
    Statistical Computing withPython/ R basics R Basics • Introduction and basics • Variables and data types • Inbuilt functions • Data frames • Plotting • Regression analysis • Time series data • Statistical programming language concepts • Writing and debugging programs • Building and organizing software packages • Installing and using R packages • Importing data from external sources • Transforming data to support analysis • Visualizing and understanding data • Writing basic R functions • Conducting statistical analysis and inference • Generating research or analytical reports Python • data and text manipulation, • regular expressions, • data structures, • functions • variable scope, • memory use, • efficiency, • debugging, • testing, • parallel processing
  • 19.
    Artificial Intelligence • Introductionto AI: • Search and Problem Solving • Knowledge Representation and Reasoning: • Machine Learning Basics: • Natural Language Processing (NLP): • Computer Vision: • Planning and Robotics: • Ethics in AI:
  • 20.
    Machine Learning • Introductionto Machine Learning: Basic concepts, types of machine learning (supervised, unsupervised, reinforcement learning), and its applications. • Key Algorithms: • Supervised Learning: Linear regression, logistic regression, decision trees, support vector machines (SVM), k-nearest neighbors (KNN). • Unsupervised Learning: Clustering (k-means, hierarchical), dimensionality reduction (PCA). • Reinforcement Learning: Markov decision processes, Q-learning. • Model Training and Evaluation: • Training and testing datasets • Model evaluation techniques: Accuracy, precision, recall, F1-score, confusion matrix, cross-validation. • Overfitting and underfitting, bias-variance tradeoff. • Feature Engineering: Techniques for selecting, transforming, and creating features for better model performance. • Optimization and Tuning: • Hyperparameter tuning • Regularization techniques (L1, L2) • Gradient descent and other optimization methods. • Applications: Examples in fields like healthcare, finance, natural language processing (NLP), and computer vision. • Challenges: Handling imbalanced data, interpretability of models, ethics and fairness in ML.
  • 21.
    Deep Learning • Introductionto Deep Learning: Overview of deep learning and how it differs from traditional machine learning. • Neural Networks: Basics of artificial neural networks, including perceptrons, activation functions, and backpropagation. • Key Architectures: • Feedforward Neural Networks (FNNs) • Convolutional Neural Networks (CNNs): Primarily for image data. • Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM): For sequential data like time series. • Generative Adversarial Networks (GANs): For generating synthetic data. • Training Deep Networks: Concepts like optimization (gradient descent, learning rates), regularization, and overfitting. • Advanced Topics: • Transfer learning • Deep reinforcement learning • Autoencoders and unsupervised learning • Applications: Use cases in computer vision, natural language processing, speech recognition, and other fields. • Challenges: Computational demands, data requirements, model interpretability, and ethics in AI
  • 22.
    Generative AI inHealthcare • Learn the fundamentals of Generative AI and its role in transforming the healthcare sector. • Explore how Generative AI is used for analyzing and interpreting medical imaging data. • Discover how Generative AI can aid in more accurate and efficient patient diagnosis. • Learn to leverage Generative AI for tailoring healthcare solutions to individual patient needs.
  • 23.
    Ethics of MLin Healthcare • Ethical Foundations: Basic ethical principles (beneficence, autonomy, fairness) and frameworks applied in healthcare. • ML in Healthcare: Overview of machine learning applications like diagnostics, treatment, and disease prediction. • Key Ethical Concerns: • Bias and fairness in ML systems • Transparency, explainability, and accountability • Informed consent and privacy concerns • Case Studies: Real-world examples highlighting successes and ethical failures in healthcare ML. • Legal/Regulatory Issues: Understanding healthcare laws (e.g., HIPAA, GDPR) and AI-related legal responsibilities. • Responsible AI Design: Best practices for ethical, human-centered ML systems in healthcare. • Future Challenges: Emerging issues in AI, including genomics and personalized medicine.