Hasso-Plattner-InstitutSDG am HPI
Hasso-Plattner-InstitutDSG am HPI
Login
 

Digital N-of-1 trials and their application (Sommersemester 2023)

Lecturer: Dr. rer. nat. Stefan Konigorski (Digital Health - Machine Learning)
Course Website: https://moodle2.uni-potsdam.de/course/view.php?id=37750

General Information

  • Weekly Hours: 2
  • Credits: 3
  • Graded: yes
  • Enrolment Deadline: 01.04.2023 - 07.05.2023
  • Teaching Form: Seminar
  • Enrolment Type: Compulsory Elective Module
  • Course Language: English
  • Maximum number of participants: 20

Programs, Module Groups & Modules

Digital Health MA
  • Digital Health
    • HPI-DH-DS Data Science for Digital Health
  • APAD: Acquisition, Processing and Analysis of Health Data
    • HPI-APAD-C Concepts and Methods
  • APAD: Acquisition, Processing and Analysis of Health Data
    • HPI-APAD-T Technologies and Tools
  • APAD: Acquisition, Processing and Analysis of Health Data
    • HPI-APAD-S Specialization
  • SCAD: Scalable Computing and Algorithms for Digital Health
    • HPI-SCAD-C Concepts and Methods
  • SCAD: Scalable Computing and Algorithms for Digital Health
    • HPI-SCAD-S Specialization
  • SCAD: Scalable Computing and Algorithms for Digital Health
    • HPI-SCAD-T Technologies and Tools
  • DICR: Digitalization of Clinical and Research Processes
    • HPI-DICR-C Concepts and Methods
  • DICR: Digitalization of Clinical and Research Processes
    • HPI-DICR-S Specialization
  • DICR: Digitalization of Clinical and Research Processes
    • HPI-DICR-T Technologies and Tools
IT-Systems Engineering MA
Data Engineering MA
Software Systems Engineering MA

Description

Perform your own N-of-1 trials!

Background

Traditionally, treatment guidelines and health intervention recommendations are developed based on results of large cohort studies or randomized controlled trials (RCTs). However, the analysis of such studies only yields estimates of average effects. Hence, these results do not allow meaningful predictions whether an intervention will help a given single individual. In the advent of digital solutions, personalized approaches have been on the rise. N-of-1 trials and other modern study designs allow to derive individual treatment effects, but also to use the data to obtain and improve the precision of population-level effect estimates of health interventions.

Content

This seminar covers N-of-1 trials and other modern study designs such as micro-randomized trials. First, we will get an overview of different study types and their characteristics, then we will give an introduction of the practical aspects for performing N-of-1 trials, and then the main focus of the class will be on methodological approaches for planning and analyzing N-of-1 trials.

Topics

  • Overview of classic and modern study designs
  • Introduction to N-of-1 trials
  • Ethics, data privacy and other requirements of digital studies
  • Standard methods for individual analysis of N-of-1 trials
  • Standard methods for aggregated analysis of N-of-1 trials
  • Bayesian regression models for N-of-1 trials
  • Meta analysis & network meta analyses
  • Sample size calculation for N-of-1 trials
  • Adaptive designs

Format

  • This seminar will be a mix of journal club and research seminar with applied data analysis
  • Introductory lectures with discussion of main concepts of N-of-1 trials and study designs
  • Introduction on technical aspects of performing digital N-of-1 trials and linking sensor data
  • From week 2-4, every student will plan and then later perform an N-of-1 trial and investigate the impact of self-determined interventions on sleep quality. The trial will be designed, implemented, and then run using the StudyU platform (studyu.health). This data will be anonymized, used throughout the course to illustrate the statistical methods, and potentially used in a joint publication afterwards.
  • Students will learn about all parts of the research process on N-of-1 trials including ethical issues, writing an ethics application, consent, data safety, and then data analysis and interpretation.
  • After the initial classes, readings of papers as homework and discussion in class. One group of students will lead the discussions
  • Joint statistical analysis of N-of-1 trial data gathered in class by applying the discussed statistical models.
  • Final project

Learning goals:

At the end of the course, the students will be able to

  • understand the main concepts of planning & conducting N-of-1 trials and selected other study designs
  • perform individual-level and aggregated analysis of N-of-1 trials using state-of-the-art methods

Class size:  max. 20 students. Eligibility is based on prerequisite courses. Slots will be given on a first-come-first-serve basis, for this please write an email to Stefan.konigorski(at)hpi.de with information about your name, study field and semester (this is independent of formal registering for the class through Studienreferat)

Requirements

1) Courses in statistics/machine learning/data science and in programming using R (e.g. "Biostatistics & Epidemiological Data Analysis using R" class)

2) Consent (forms will be provided) to record and publish data of self-designed and self-performed N-of-1 trials in class

Eligibility is based on prerequisite courses. Slots will be given on a first-come-first-serve basis, for this please write an email to Stefan.konigorski(at)hpi.de with information about your name, study field and semester (this is independent of formal registering for the class through Studienreferat)

Learning

Seminar (120 minutes weekly)

Wednesdays 15.00 - 17.00 

In presence, in Room G3.E15/16 at the HPI.

First class: April 19, 2023

Examination

  • 20% participation in class
  • 30% moderation of session
  • 50% final project

Zurück