AI-Based Digital Health Applications with Model-Based Design

Explore the workflow for using artificial intelligence techniques such as deep learning and machine learning to build digital health applications that comply with global medical regulations. ​

The steps use MATLAB®, Simulink®, and Model-Based Design.

Introduction to Digital Health

Digital health includes mobile health (mHealth), wearable devices, telehealth and telemedicine, health information technology (IT), and personalized medicine. The use of smart phones, AI, and internet applications can provide new ways to monitor our health and provide greater access to health information. It can empower consumers and providers to make more informed decisions and enable early diagnoses.

AI-Based Software as a Medical Device (SaMD) Action Plan (FDA action plan)

Developing and Deploying AI Models on Biomedical Data Sets

There are many approaches for building predictive models on biomedical data sets such as EKG signals, medical images, and biomedical text data.

Using MATLAB, you can interactively develop and deploy predictive models on biomedical data sets by using machine or deep learning algorithms. You can deploy the models on embedded devices or on the cloud.

AI Techniques for ECG Classification (NVIDIA blog)

Interpretability and Explainability

Interpretable machine learning provides techniques and algorithms that overcome the black-box nature of AI models. By revealing how various features contribute (or do not contribute) to predictions, you can validate that the model is using the right evidence for its predictions and reveal model biases that were not apparent during training.

Model Interpretability for ECG Classification (5:49)

GPU Code Generation and Inference with Simulink

Using Simulink, you can combine powerful signal processing techniques and convolutional neural networks to classify biomedical signals.

You can also generate CUDA code automatically from Simulink models for deploying on NVIDIA® GPU devices.

Code Generation for a Deep Learning Simulink Model to Classify ECG Signals (Example)

Verification and Validation

Modeling and simulation of medical device systems is an essential component of design, development, and testing.

The MATLAB and Simulink products you use can also be validated for use in FDA/CE-regulated workflows and to meet harmonized standards such as IEC 62304.

Recommended Next Steps

MATLAB and Simulink enable engineers to speed development of medical device software and hardware by efficiently integrating and automating the phases of design, implementation, and verification.

MATLAB and Simulink for Medical Devices

Design, simulate, and build next-generation medical devices while accelerating regulatory compliance.

Learn more

AI Techniques for ECG Classification

Learn the essential aspects of developing machine learning and deep learning models for classifying ECG signals.

Watch videos (5 videos)

FDA Software Validation

Learn how to validate MATLAB products for use in FDA regulated medical device design workflow.

Learn more

Let us know how we can help you.

Contact us for a custom evaluation and get pricing based on your needs.

Get started