CANCER SURVIVAL STATUS OVERVIEW

CANCER STATUS OVERVIEW

?

INTRODUCTION

?I analyzed the Cancer Survival Dataset as requested by my client for the period from December 2016 to December 2019. The goal was to determine the total number of cases for the period and note the survival status of each variable related to survival. During the data validation and analysis, we found that the survival status in the dataset was categorized into three elements: Alive, Dead, and Unspecified cases.

?

To fulfil this task, the client provided the following objectives:

1.???? Identify the total number of cases and the sex distribution.

2.???? Calculate the total and average insurance paid.

3.???? Determine the total insurance paid by patients based on their status.

4.???? Analyze the age distribution.

5.???? Identify different surgery types.

6.???? State the tumor stage by patient status.

The dataset was obtained from Kaggle.com with the permission of the Hospital. Note that this is a fictitious dataset.

?

IMPLEMENTATION

To implement this analysis, I utilized the Prepare, Model, Analyze, Visualize, and Manage Resources Process (PMAVM) framework. The tools used were:

?

1.???? SQL (Structured Query Language): for data preparation and modelling.

2.???? Tableau: for data analysis and visualization.

?

STEP ONE(1): DATA PREPARATION

In the data preparation process, the major aim is to define the objectives, confirm the objects (table) verify the fields(columns) and records(rows), get, clean, and transform the data set.

?

1.1 MEASURES

The dataset required should contain information basically about the patient status, the insurance amount paid, and other variables mentioned as part of the objectives. In this case, the hospital made available its patient record for 2016 to 2019, which is the period covered for this study.

?

1.2 Get Data

The data was obtained as a soft copy from the hospital and stored as a CSV (Comma-Separated Values) file. To do this, first, we create database_name, use the database_name and show tables, as shown in the picture below. Then on the schemas panel, click on the database_name>right click>click on table import wizard>browse>locate the file and click open> click on next till finish.

?

?

?

?

1.3 Clean and Transform Data

The dataset wasn't very dirty, but we did the following:

·?????? used the drop command to remove the unwanted columns based on our objectives

·?????? used the update and replace statement to remove the Dollar $, dot, and comma signs on the insurance paid column, and also input N/A to the date of surgery and patient status columns.

?

?

STEP TWO(2): DATA ANALYSIS AND VISUALISATION

For this purpose, I will use Tableau as my visualization tool, Tableau is a powerful data analysis and visualization tool that allows users to explore, analyze, and present data in a visually appealing and interactive manner.

To call up the data from SQL to the Tableau environment, export the table from SQL and save it in a desired location.

Open Tableau Desktop>Text file>Locate the document > click on Open

?

?

?

ANALYSIS AND VISUALIZATION

To analyze and visualize, we click on new sheet 1 to go to a worksheet and start sorting out the objectives on separate sheets in no particular order.

Objective 1:?Sex distribution.

?

Objective 2:?Total insurance paid by patients with respect to patient status.

?

Objective 3:?Ascertain the age distribution.

Using calculated fields, I created a group for the age range and groupings.

Objective 4:?Surgery types by patient status.

?

?

?

?

Objective 5:?Tumour stage by patient status.

?

?Objective 6:?Date trend by patient status.

STEP THREE(3): DASHBOARD AND RECOMMENDATIONS

Click on the sheet below for a new dashboard.

Below is the Dashboard I created for Cancer Status Overview using Tableau.

Because I don’t want the dashboard to be overcrowded, I created another dashboard for recommendations, as shown below:

?

Based on the analysis presented on the dashboard, the following recommendations apply:

?

1. Enhancing Affordability: Reforming Insurance Payment for Cancer Treatment.

2. Promoting Awareness: Conducting Sensitization and Awareness Campaigns.

3. Prioritizing Patient Care: Monitoring and Attending to Stage II Tumor Cases.

4. Age-related Concerns: Increasing Awareness of Cancer Progression from Stage I to II.

5. Exploring Surgical Alternatives: Evaluating Other Surgical Options for Improved Survival Rates.

?

Feel free to contact me and my team for further assistance in implementing these strategies effectively.

?

Thank You.

Queen Ibim Gabriel

Gimo HMO Consults

?

?

??

?

?

?

?

?