BASICS OF COMPUTER TECHNOLOGY AND ARTIFICIAL INTELLIGENCE IN CLINICAL SETTINGS
- Overview
- Assessment methods
- Learning objectives
- Contents
- Full programme
- Teaching methods
- Contacts/Info
None.
ADMISSION RULES:
No distinction is made between attending and non-attending students. There are no preparatory activities or other tasks required to access the exam.
TYPE OF EXAM:
The exam is written, aims to assess the knowledge acquired on the topics covered during the course, and is delivered through a web platform.
EXAM PROCEDURES:
The classroom is typically traditional (not computer-equipped). Students must bring their own device (computer or tablet) with an internet connection to take the exam. Students may only use the exam website.
ASSESSMENT CRITERIA:
The exam is graded on a 30-point scale.
A questionnaire with multiple-choice and open-ended questions is administered through a dedicated platform.
It is a timed exam lasting 45 minutes.
Students receive written confirmation of their participation via email from the instructor, with specific instructions for the exam.
The questionnaire—accessible via a link (the same for everyone) sent by email—and the access password provided at the time of the exam includes multiple-choice questions and 2 open-ended questions, for a total of 29 questions.
1 point is awarded for each correct answer.
Open-ended questions are assessed at a later stage.
Since these are open responses, students are encouraged to provide well-developed and content-rich answers.
The evaluation of the open-ended questions is at the instructor’s discretion.
The questions (and their order) are distributed automatically by the system.
The instructor does not know the questions in advance.
The environment is a web platform, and navigation follows its standard structure.
At the bottom of the page, the “submit” button sends the responses.
The results of the multiple-choice section are immediately available.
If the time expires, the exam is still submitted and evaluated by the system.
The instructor can verify in real time that the exam has been submitted, but not the responses.
Only once the system is unlocked can the instructor access and download the data for evaluation.
In this phase, it is also possible to send a report with the results of the questions, which are already visible to the student.
Once the results have been reviewed, the platform may be closed and the session ended.
It is considered that the questionnaire format, in its structure and timing, is appropriate for evaluating the learning objectives of this course. Multiple-choice questions assess specific, factual knowledge, while open-ended questions are the closest equivalent to an oral examination. In this respect, they measure broader understanding of the subject, allowing students to structure and express their reflections freely. This demonstrates their ability to identify and articulate the key elements of the topic.
The course aims to introduce students to the fundamental concepts of computer science as applied to clinical and laboratory practice.
In particular, the course aims to:
provide basic knowledge of healthcare information systems and digital workflows within hospital settings;
introduce the fundamental principles of databases and models for managing health data;
present essential notions related to big data, data quality, and data governance in the healthcare domain;
offer a clear and accessible overview of the foundations of artificial intelligence and its clinical and diagnostic applications;
illustrate the main healthcare and scientific databases used in biomedical practice;
develop awareness of the ethical, legal, and security aspects connected to the management of clinical data.
The course is in its first edition. No previous versions exist. The instructor reserves the right to make adjustments during the course as needed to achieve its objectives. Any changes will be promptly communicated to the students.
A. Healthcare Information Systems
Electronic Health Record (EHR/EMR)
Electronic Health File (Fascicolo Sanitario Elettronico)
Regional/National information flows
Security, privacy, GDPR, and traceability
B. Fundamentals of Databases and Clinical Data Management
Structured/Unstructured data
Relational model: tables, keys, relationships
Data quality and data integrity
Interoperability: HL7, FHIR
Examples of typical laboratory data structures
C. Big Data in Healthcare
Characteristics of big data (5Vs)
Sources: laboratories, imaging, genomics, devices
Data governance and anonymization
Biobanks, epidemiological networks, and clinical datasets
D. Artificial Intelligence and Clinical Applications
Definitions: AI, ML, DL
Approaches: supervised, unsupervised, neural networks
Datasets, training, testing, bias
Clinical applications: imaging, prediction, decision support
Laboratory applications: digital microscopy, hematology, microbiology
E. Healthcare and Scientific Databases
PubMed, Medline
Repositories and laboratory information systems
All study material is uploaded by the instructor to the MS Teams platform, accessible with university credentials. The group can also be identified using the alphanumeric code 083yq75.
Introduction and Healthcare Information Systems
From traditional healthcare to digital healthcare
EHR and Electronic Health Record
Laboratory information flows
Databases and clinical data management
Concept of health data
Relational model
Examples of laboratory data structures
Big Data and data governance
Definition of big data
Sources of clinical big data
Data governance, quality, anonymization
Biobanks and real clinical datasets
Foundations of AI
What is AI
Machine learning: models, datasets, training
Bias and validation
AI and reliability in the clinical domain
AI in Clinical Practice and Laboratory Settings
Applications in diagnostic imaging
AI for laboratory analysis: practical examples
Predictive algorithms and clinical decision support
Limitations, risks, and future perspectives
Healthcare Databases + Review
Scientific and clinical databases
Guided exercises for database consultation
Laboratory information flows
Didactic teaching: 20 hours
Lectures (for the theoretical component);
Interactive teaching: 4 hours
Practical exercises (to enhance the ability to relate different types of knowledge and models);
Case study analysis (to improve the ability to apply knowledge and models in analyzing the challenges and opportunities posed by digital technologies in the context of complex organizations).
Remote teaching activities may be provided in the event of specific contingencies.
Office hours:
contact via email at sergio.moriani@uninsubria.it
.
Videoconference if needed.
