# Machine Learning for Clinical Predictive Analytics

**Authors:** Wei-Hung Weng  
**arXiv:** [1909.09246](https://arxiv.org/abs/1909.09246)  
**Date:** 2019-09-19  
**Summary page:** https://www.summarizepaper.com/en/paper/1909.09246v1/

## Key points

- Comprehensive overview of applying machine learning techniques for clinical prediction tasks
- Introduction to concepts of machine learning and commonly used algorithms
- Objective is to enable readers to understand fundamentals of machine learning and its importance in solving clinical prediction problems
- Demonstrates how algorithms can be applied using appropriate toolkits for clinical prediction tasks
- Intuition behind various machine learning models such as regression, decision trees, and support vector machines
- Real-world case studies illustrating effective use of these models in clinical prediction problems
- Use of publicly available datasets for accessibility and reproducibility
- Equips readers with essential knowledge on algorithm selection, model interpretation, and dataset utilization

## Summary

In the chapter titled "Machine Learning for Clinical Predictive Analytics," authored by Wei-Hung Weng, a comprehensive overview of applying machine learning techniques for clinical prediction tasks is provided. The chapter begins with a concise introduction to the concepts of machine learning and highlights some of the most commonly used machine learning algorithms. The primary objective of this chapter is to enable readers to grasp the fundamentals of machine learning techniques and understand why they are instrumental in solving clinical prediction problems. To achieve this, the author demonstrates how these algorithms can be applied using appropriate toolkits to conduct machine learning experiments specifically tailored for clinical prediction tasks. Furthermore, the chapter delves into the intuition behind various machine learning models, including regression, decision trees, and support vector machines. By exploring these models in detail, readers gain a deeper understanding of their underlying principles and mechanisms. To reinforce comprehension and practical application, the author presents real-world case studies that illustrate how these models can be effectively employed in clinical prediction problems. These case studies utilize publicly available datasets, ensuring accessibility and reproducibility for readers interested in further exploration or replication. Overall, "Machine Learning for Clinical Predictive Analytics" offers an extensive examination of applying machine learning techniques within a clinical context. It equips readers with essential knowledge regarding algorithm selection, model interpretation, and dataset utilization—essential skills necessary for successfully addressing clinical prediction challenges.