Artificial Intelligence —
Training activity: 5

Details

Critically appraise common tools used in machine learning

Type

Developmental training activity (DTA)

Evidence requirements

Evidence the activity has been undertaken by the trainee​.

Reflection on the activity at one or more time points after the event including learning from the activity and/or areas of the trainees practice for development.

An action plan to implement learning and/or to address skills or knowledge gaps identified.

Considerations

• Programming languages
• IDE
• Libraries

Reflective practice guidance

The guidance below is provided to support reflection at different time points, providing you with questions to aid you to reflect for this training activity. They are provided for guidance and should not be considered as a mandatory checklist. Trainees should not be expected to provide answers to each of the guidance questions listed.

Before action

• Consider what constitutes a ‘tool’ in the context of machine learning (e.g., programming languages, libraries, platforms).
• What are some common machine learning tools that are relevant to healthcare applications that you need to research?
• What specific insights do you hope to gain about the strengths, weaknesses, and suitability of different machine learning tools for various healthcare tasks?
• How will this activity enhance your ability to select appropriate tools for future machine learning projects?
• What is your current familiarity with common machine learning tools?
• Discuss with your training officer which common machine learning tools you should focus on.
• Research popular machine learning libraries (e.g., scikit-learn, TensorFlow, PyTorch) and platforms (e.g., cloud-based ML services).
• Consider the criteria for critical appraisal (e.g., ease of use, functionality, performance, cost, community support).
• How do you feel about evaluating and comparing technical software tools?

In action

• How are you approaching the critical appraisal of the machine learning tools? What features or capabilities are you currently comparing and why?
• What decisions are you making about which tools to focus on in more detail as you conduct your appraisal?
• Which aspects of the tool appraisal (e.g., ease of use, functionality, performance, cost) come more naturally to you, and which require more deliberate consideration?
• How effectively are you identifying the key strengths and limitations of the different machine learning tools?
• What challenges are you facing in understanding the specific applications and requirements for each tool?
• What new information are you gaining about the practical utility and suitability of different machine learning tools as the appraisal unfolds?
• How does this appraisal relate to your existing knowledge of software and platforms used in data science and machine learning?
• If you find that your initial appraisal criteria are not effectively differentiating the tools, what alternative criteria could you consider?
• Do you need to explore any of the tools hands-on or consult user reviews to gain a better understanding?
• Are you ensuring that your critical appraisal is balanced and within your level of expertise with these types of tools?

On action

• List the common machine learning tools you appraised and summarise their key features and functionalities. What were the main strengths and weaknesses of each tool you considered? For what types of machine learning tasks or problems did each tool seem most suitable?
• What new knowledge did you gain about the capabilities and limitations of different machine learning tools? Were there any tools that surprised you in terms of their features or ease of use? What did you learn from these? How did this activity enhance your ability to select appropriate tools for machine learning tasks? How will your understanding of these tools inform your approach to future machine learning projects?
• Which machine learning tools do you want to gain more hands-on experience with? How will you apply your appraisal skills when considering new machine learning tools in the future? What actions will you take to become more proficient in using various machine learning tools? What resources or support might you need to further develop your skills in using machine learning tools?

Beyond action

• Have you reviewed your appraisal of the machine learning tools? Have new or updated machine learning tools become available since you completed this training activity? How do they compare to the ones you appraised?
• Has your knowledge of machine learning tools influenced your understanding of research papers or technical discussions involving AI? Has this training activity helped you to better understand the capabilities and limitations of different machine learning approaches?
• What transferable skills (e.g., critical evaluation of technical resources, understanding of machine learning workflows) did you develop that will be valuable if you are involved in using or selecting machine learning tools in the future? Are there any specific machine learning tools you are now interested in learning more about in detail?

Relevant learning outcomes

#	Outcome
# 2	Outcome Critically appraise the application of AI and machine learning in healthcare.