Postgraduate Course: Natural Language Processing (NLP) in Health and Social Care (HEIN11085)
Course Outline
| School | Deanery of Molecular, Genetic and Population Health Sciences |
College | College of Medicine and Veterinary Medicine |
| Credit level (Normal year taken) | SCQF Level 11 (Postgraduate) |
| Course type | Online Distance Learning |
Availability | Not available to visiting students |
| SCQF Credits | 10 |
ECTS Credits | 5 |
| Summary | In this course, students will explore the fundamental concepts of natural language processing (NLP) and its role in current and emerging technologies. Artificial intelligence (AI) is increasingly being adopted across the health and care industry and academia, and some of the most exciting AI applications leverage NLP. Simply put, NLP is a specialized branch of AI focused on the interpretation and manipulation of human-generated spoken and written data. This course aims to develop students technical capabilities as well as a critical understanding of the ethical and social impacts of dealing with text data, covering technical aspects of the most recent and cutting-edge Natural Language Processing (NLP) technologies (NLTK, SpaCy) used in a health and care context. |
| Course description |
This course introduces students to the field of Natural Language Processing (NLP), specifically applied to the health and social care context. NLP focuses on text data, which often lacks the structured format of conventional tabular data. It is estimated that 80% of health and social care is unstructured. In health and social care, unstructured data includes clinical notes, patient narratives, medical literature, social media posts, and even handwritten documents.
In health and social care, textual information is abundant in various sources, including electronic health records, medical literature, social media posts and online discussions and resources. Text data is a fundamental source of information in the 21st century. Natural Language Processing (NLP), the branch of AI that deals with this type of data, is in massively high demand both in academia and industry. NLP is one of the most important and useful application areas of artificial intelligence. The field of NLP is evolving rapidly as new methods and toolsets converge with an ever-expanding availability of data.
In this five-week online course, the following topics will be covered to equip learners with foundational knowledge and practical skills using NLP methods.
Week 1: Introduction to NLP in health and social care context
* Overview of NLP: Understand what NLP is and its relevance in health and social care.
* Challenges in Health Text Data: Explore unique aspects of health-related text data (e.g., clinical notes, medical literature).
* Ethical Considerations: Discuss privacy, bias, and ethical implications.
Week 2: Applications and Case Studies
* Clinical Decision Support: Real-world examples of NLP aiding clinicians.
* Disease Surveillance: Detect outbreaks using NLP.
* Resource Matching and Referrals: How NLP assists in social care.
* Hands-On Project: Introduce the assignment and how to apply NLP techniques to health or social care data.
* Challenges of working specific to health data
Week 3: Text Preprocessing and Tokenization
* Text Cleaning: Techniques for cleaning unstructured text.
* Tokenization: Break down text into meaningful units (words, phrases, tokens).
* Stop Words and Stemming: Strategies for handling common words and word variations.
* Annotation
Week 4: Information Extraction and Named Entity Recognition (NER)
* NER Basics: Identify entities (e.g., diseases, medications, symptoms) in text.
* Rule-Based and Machine Learning Approaches: Methods for NER.
* Clinical Text Mining: Apply NER to clinical narratives and health records.
Week 5: Sentiment Analysis and Opinion Mining
* Sentiment Analysis: Analyse emotions and opinions expressed in health-related text.
* Patient/Service User Feedback: Understand patient/service user sentiments from reviews, surveys, and social media.
* Applications in Social Care: How sentiment analysis informs social services.
|
Entry Requirements (not applicable to Visiting Students)
| Pre-requisites |
|
Co-requisites | |
| Prohibited Combinations | |
Other requirements | Students must have passed Foundations of Software Development in Health and Social Care (HEIN11066) or equivalent |
Course Delivery Information
|
| Academic year 2024/25, Not available to visiting students (SS1)
|
Quota: None |
| Course Start |
Flexible |
| Course Start Date |
28/10/2024 |
Timetable |
Timetable |
| Learning and Teaching activities (Further Info) |
Total Hours:
100
(
Lecture Hours 5,
Seminar/Tutorial Hours 1,
Online Activities 35,
Feedback/Feedforward Hours 5,
Formative Assessment Hours 5,
Revision Session Hours 1,
Programme Level Learning and Teaching Hours 2,
Directed Learning and Independent Learning Hours
46 )
|
| Assessment (Further Info) |
Written Exam
0 %,
Coursework
100 %,
Practical Exam
0 %
|
| Additional Information (Assessment) |
Written Exam 0 %, Coursework 100 %, Practical Exam 0 %
The assessment will be based on a programming assignment covering both theoretical and applied aspects of deep learning and its intersection with Natural Language Processing.
The assessment will include:
Discussion boards (20%)
Programming assignment (80%)
Covering a fundamental task in natural language processing (language modeling) in a health and social care context. This will involve a coding task and a written report. The coding will provide students with hands-on experience, while the report writing aims to assess their ability to describe their work supporting the technical format and ensure a critical understanding of ethical implications. This will include a theoretical explanation of the models used, laying out the experimental setups, evaluating the models performance, and assessing the ethical implications.
|
| Feedback |
Formative feedback is provided via discussion board posts, tutor support for group work and weekly Office Hours.
Feedback on summative assessed coursework is provided within fifteen working days. |
| No Exam Information |
Learning Outcomes
On completion of this course, the student will be able to:
- Design, implement and evaluate the appropriate NLP methods to solve a given task in the context of health and social care
- Critically assess how NLP methods influence the success of a given task
- Critically appraise the ethical implications and societal risks associated with the deployment of NLP methods
- Communicate complex ideas, principles, and theories clearly by oral, written and practical means, to a range of audiences
|
Reading List
| Bird, Steven, Ewan Klein, and Edward Loper. Natural language processing with Python: analyzing text with the natural language toolkit. O'Reilly Media, Inc. 2009. https://www.nltk.org/book |
Additional Information
| Graduate Attributes and Skills |
1) Mindsets
Enquiry and lifelong learning
Students on this course will be encouraged to seek out ways to develop their technical programming expertise. They will also be encouraged to strive for excellence in their professional practice and to use established and developed approaches to use NLP methods to resolve complex issues as they arise in their practice in the context of health and social care.
Aspiration and personal development
Students will be encouraged to draw on the quality, depth and breadth of their experiences to expand their potential and identify areas they wish to develop and grow. Students will also be encouraged to understand their responsibility within and contribute positively, ethically and respectfully to the academic community while acknowledging that different students and community members will have other priorities and goals.
Outlook and engagement
Students will be expected to take responsibility for their learning. Students will be asked to use their initiative and experience, often explicitly relating to their professional, educational, geographical or cultural context to engage with and enhance the learning of students from the diverse communities on the programme. Students will also be asked to reflect on the experience of their peers and identify opportunities to enhance their learning.
2) Skills
Research and enquiry
Students will use self-reflection to seek out learning opportunities. Students will also use the newly acquired knowledge and critical assessment to identify and creatively tackle problems and assimilate the findings of primary research and peer knowledge in their arguments, discussions and assessments.
Personal and intellectual autonomy
Students will be encouraged to use their personal and intellectual autonomy to critically evaluate learning materials and exercises. Students will be supported through their active participation in self-directed learning, discussion boards and collaborative activities to critically evaluate concepts, evidence and experiences of peers and superiors from an open-minded and reasoned perspective.
Personal effectiveness
Students will need to be effective and proactive learners that can articulate what they have learned, and have an awareness of their strengths and limitations, and a commitment to learning and reflection to complete this course successfully.
Communication
Effective oral and written communication, presentation and interpersonal skills. The structure of the interactive (problem-based learning examples, discussion boards and collaborative activities) and assessment elements incorporate constant reinforcement and development of these skills. |
| Keywords | Natural language processing (NLP),text analysis,artificial intelligence,health and social care |
Contacts
| Course organiser | Dr Pawel Orzechowski
Tel:
Email: porzecho@ed.ac.uk |
Course secretary | Mrs Laura Miller
Tel: (0131 6)51 5575
Email: Laura.Miller@ed.ac.uk |
|
|
University Homepage