Overview
Part of the ModularMaster in Data Science (Healthcare) programme
Data Science Modeling is a fundamental component of the data science workflow, encompassing a wide range of techniques and algorithms used to extract insights and make predictions from data. It involves the understanding and application of mathematical and statistical models to uncover patterns, relationships, and trends in complex datasets. Data professionals utilize various modeling approaches, such as supervised learning and unsupervised learning, depending on the nature of the problem and the available data. Through model selection, training, and evaluation, they aim to create accurate and robust models that generalize well to unseen data. Data science modeling plays a crucial role in diverse applications, including but not limited to predictive analytics, recommendation systems, fraud detection, and image recognition. By leveraging the power of modeling techniques, data professionals can harness the value of data and derive actionable insights, ultimately driving informed decision-making and generating positive impact across industries.
This course, spanning a duration of five days, is specifically designed to equips participants with skills on basic supervised and unsupervised machine learning models in healthcare settings. Participants will learn to leverage these models appropriately and evaluate various parameters based on the consequences of the predicted model. The course aims to equip individuals with the necessary skills to apply machine learning techniques in healthcare scenarios. Over the first four days, participants will gain insights into the selection and implementation of machine learning models, considering their potential impacts in healthcare decision-making. Participants will be actively involved in a healthcare-related project throughout the module. The final day, which is split into two half-days on separate weeks, will be dedicated to project consultation and project presentation.
Plan your learning path
This course can be taken as a module on its own or as part of the Graduate Certificate in Data Analytics (Healthcare) or ModularMaster in Data Science (Healthcare).
Who Should Attend
Catering to healthcare professionals and individuals aspiring to join the healthcare industry, this course is specifically designed to develop essential skills in data science models and algorithms encompassing regression, classification, clustering, and dimensionality reduction. It is highly recommended for clinicians, administrators, and managers who aim to comprehend the strengths and limitations of different models based on dataset characteristics, as well as preparing aspiring data analysts or data scientists to apply these models effectively in addressing healthcare data challenges.
Prerequisites
- Participants should preferably have passed mathematics at least ‘O’ Level or equivalent.
- Participants should preferably have basic knowledge of statistic.
- Participants should be conversant with basic IT skills such as software installation, file management and web navigation.
- Participants are encouraged to complete the Data Wrangling and Preparation with Programming and Data Validation and Statistical Analysis with Programming before enrolling in this course.
- Participants are required to pass a pre-course assessment to ensure participants have the requisite knowledge of Python programming. This assessment can be waived if participants have completed both Fundamentals in Python (Basic) and Fundamentals in Python (Intermediate).
- Participants are required to bring their laptops.