Medical Data Analysis: Dashboard Edition

PROJECT PURPOSE

The major aim of the project is to gain understanding of the healthcare landscape within the dataset and identify factors influencing patient quality of life and provide actionable insights for enhanced patient care.

ANALYSIS LIST

Exploratory and Descriptive Analytics

1. Disease Prevalence Analysis (Including identifying Top 5 Conditions and Procedures)

• Identify the most prevalent medical conditions and within the patient population to prioritize resource allocation and targeted interventions.

2. Patient Risk Profiling

• Develop profiles of patients at higher risk based on their demographic information and medical history to enable proactive care management.

3. Health Trends Analysis

• Analyze trends in key health metrics such as BMI, Blood Pressure and Cholesterol to monitor population health and identify areas of concern

4. Medication Effectiveness Analysis

• Evaluate the effectiveness of medications in managing specific health conditions and their impact on patient outcomes.

5. Mortality Rate Analysis

• Understanding mortality rates at this hospital and conditions associated with the highest mortality rates.

Prescriptive and Predictive Analytics

1. Clinical Decision Support:

• Provide actionable insights to healthcare providers to support clinical decision-making and enhance personalized care delivery.

2. Quality of Life Assessment

• Build predictive models to estimate Quality Adjusted Life Years (QALY) based on factors influencing health-related quality of life (HRQL).

3. Optimizing Healthcare Resource Allocation

• Inform resource allocation strategies based on prevalent conditions, patient demographics, and healthcare utilization patterns.

APPROACH USED

SQL Analysis

1. Data Wrangling: The inspection of data to make sure NULL values and missing values are detected and data replacement methods are used to replace, missing or NULL values.
2. Feature Engineering: This will help use generate some new columns from existing ones and drop some columns that will not be used for the analysis and edit some records

Power BI Analysis

1. Data Modeling
2. Building relevant visualizations
3. DAX Calculations

Python Analysis

1. Data Preparation
2. Model Selection and Training
3. Exporting to Power BI

The Python Notebook can be found under Medical Data Analysis: Python Edition

All details can be found on github.