Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/tushar2704/patient_survival_prediction
Getting a rapid understanding of the context of a patient’s overall health has been particularly important during the COVID-19 pandemic as healthcare workers around the world struggle with hospitals
https://github.com/tushar2704/patient_survival_prediction
artificial-intelligence data-science deep-learning predictive-modeling python tushar2704
Last synced: 19 days ago
JSON representation
Getting a rapid understanding of the context of a patient’s overall health has been particularly important during the COVID-19 pandemic as healthcare workers around the world struggle with hospitals
- Host: GitHub
- URL: https://github.com/tushar2704/patient_survival_prediction
- Owner: tushar2704
- License: apache-2.0
- Created: 2023-05-22T05:05:33.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2023-08-13T07:26:46.000Z (over 1 year ago)
- Last Synced: 2024-05-11T05:53:46.830Z (8 months ago)
- Topics: artificial-intelligence, data-science, deep-learning, predictive-modeling, python, tushar2704
- Language: Jupyter Notebook
- Homepage: https://tushar-aggarwal.com
- Size: 25 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Patient Survival Prediction
## Description
The **Patient Survival Prediction** project addresses the urgent need for quickly assessing a patient's overall health, a critical concern amplified during the COVID-19 pandemic when healthcare systems worldwide faced overwhelming patient loads. In many cases, Intensive Care Units (ICUs) lack access to verified medical histories for incoming patients, making it challenging to provide appropriate care. Patients arriving in distress or those unable to communicate due to confusion or unconsciousness might not be able to share information about underlying chronic conditions like heart disease, diabetes, or injuries. Additionally, transferring medical records can be time-consuming, especially when patients come from different medical providers or systems. Having insights into chronic conditions could significantly influence clinical decisions, enhance patient care, and ultimately lead to improved survival rates.
## Problem Statement
The main objective of this project is to predict the **hospital_death** binary variable. This variable serves as the target feature, and the task involves classifying it based on 84 other features. The classification process is conducted step by step, considering each day's task. The evaluation metric for this project is a combination of Accuracy and Area under the Receiver Operating Characteristic (ROC) curve, providing a comprehensive assessment of the model's performance.
## Dataset
The dataset used in this project serves as the foundation for predicting patient survival. It encompasses a wide range of features, totaling 84, along with the crucial **hospital_death** binary variable. The dataset source is provided in the accompanying files, offering valuable insights into patient characteristics and medical attributes that can aid in survival prediction.
**Data Available:** **[Here](https://journals.lww.com/ccmjournal/Citation/2019/01001/33__THE_GLOBAL_OPEN_SOURCE_SEVERITY_OF_ILLNESS.36.aspx)**
## Project Structure
The project repository is organized as follows:
```
├── LICENSE
├── README.md <- README .
├── notebooks <- Folder containing the final reports/results of this project.
│ │
│ └── patient_survival_prediction.py <- Final notebook for the project.
├── reports <- Folder containing the final reports/results of this project.
│ │
│ └── Report.pdf <- Final analysis report in PDF.
│
├── src <- Source for this project.
│ │
│ └── data <- Datasets used and collected for this project.
| └── model <- Model.
```
## License
This project is licensed under the [MIT License](LICENSE).
## Author
- ©2023 Tushar Aggarwal. All rights reserved
- [LinkedIn](https://www.linkedin.com/in/tusharaggarwalinseec/)
- [Medium](https://medium.com/@tushar_aggarwal)
- [Tushar-Aggarwal.com](https://www.tushar-aggarwal.com/)
- [New Kaggle](https://www.kaggle.com/tagg27)
## Contact me!
If you have any questions, suggestions, or just want to say hello, you can reach out to us at [Tushar Aggarwal](mailto:[email protected]). We would love to hear from you!