Introduction to Medical Software

This week, we will start looking at the design of software and introduce the medical software life cycle. In particular, we will introduce the international standard for medical software life cycles IEC 62304 and provide a guided tour of the process. We will also introduce our example project which we will use to anchor our discussions over the next few weeks.

In this week's segments, we will focus on user needs and the system requirements specification process. We will discuss how to identify user needs and how to communicate with medical experts. In the second half of this week's segments, we will describe the systems requirements specification document and present an example outline of such a document for our image guided neurosurgery project.

This week, we will primarily focus on the process of designing the software, i.e. the creation of a plan that will allows us to from requirements to something that now can be implemented on a computer. We will also discuss usability engineering -- the process of designing user interfaces to improve ease-of-use and to avoid user errors. Finally, we have a segment from Dr. Licholai on Digital Behavioral Health to give you an example of a use case for medical software.

In this week, we get to the most concrete components of the medical software lifecycle, coding and testing. In many ways, this is the part of the lifecycle that is most similar to any other kind of software engineering you may have had exposure to. We will present some advice on coding, especially in the medical software domain and introduce source code management. In the second half of this week's content, we will introduce software testing and discuss what a testing plan looks like.

This week, we will take a detour from the software lifecycle process to cover some mathematical background before returning to the software lifecycle next week when we talk about software validation. The goal of this week is to introduce key concept from probability and statistics. We will talk about the critical area of signal detection, and then we will present some methods that are necessary to understand how clinical trials are designed.

This week, we will cover the last steps in the medical software lifecycle. We will spend most of our time talking about validation, where we will also present a brief introduction to clinical trials. We will also have short segments discussing deployment, maintenance, and retirement.

In this week's lectures, we focus on artificial intelligence and machine learning, the use of this technology, the challenges they produce as we integrate them into software, and the challenges of regulating these technologies in order to protect patients and caregivers.

In this section of our course, we will step away from the technical aspects that you have been learning and really think about how to get your medical software or your lab prototype out into the hands of people in the real world. For those of you interested in enterpreneurship, it is just as important to get an basic overview of the business side of things so that you can launch your venture. First, we will discuss the changing models in health care. Then we will go into the nuts and bolts of starting a new health care venture, a broad overview to speak. And then we will end with when and how to raise capital.

In this optional supplementary module we will present examples of what happens when software development goes wrong. When this class is taught at Yale, the students are assigned to present these (and other) case studies in small groups. We follow this tradition for the online class as the case studies will be presented by the four Yale undergraduate students who worked as student assistants in the creation of this online course.

Throughout the creation of this course, Prof. Papademetris conducted interviews with an array of industry experts. Many of these conversations apply to multiple of the weeks' topics - please take a look and enjoy!