*\
Welcome to the Clinical Trials Success and Dropout Analysis repository
This project is a in-depth exploration of the factors influencing the success and discontinuation of clinical trials. This work blends healthcare analytics and data visualization to uncover insights that can improve research efficiency, patient retention, and overall trial success.
This project analyzes data from ClinicalTrials.gov, focusing on oncology and immunotherapy (Pembrolizumab – Keytruda) studies conducted across the United States.
Using Python, Excel, and Power BI, it investigates trial completion rates, dropout patterns, sponsor performance, and duration trends to understand what drives successful clinical outcomes.
The main objectives of this project are:
- Assess success and dropout rates across different clinical trial phases.
- Identify major factors influencing trial completion.
- Evaluate sponsor performance and operational efficiency.
- Analyze trial duration and its impact on patient retention.
- Present insights through clear, interactive visualizations.
Upon completing this project, the following outcomes are expected:
- Insight into trends of completed vs. discontinued trials.
- Identification of sponsors and phases with the highest success rates.
- Data-driven strategies to improve trial execution and patient engagement.
- A visual dashboard summarizing all key insights.
- Phase II dominates overall activity, reflecting focus on drug efficacy and safety validation.
- Completion rates show a steady upward trend, interrupted only by short-term global disruptions.
- Mayo Clinic and Sidney Kimmel Cancer Center achieved 100% completion rates, while University of Washington had higher dropout levels.
- Trial duration typically ranges from 500–2500 days, aligning with Phase II–III cycles.
- Recruiting and completed trials make up the bulk of the dataset, suggesting a healthy research pipeline.
Data was sourced from ClinicalTrials.gov, filtered for oncology and interventional studies conducted in the U.S..
Variables analyzed include phase, study status, sponsor, intervention type, duration, and completion outcomes.
- Strengthen patient engagement and follow-up mechanisms to reduce dropouts.
- Provide operational and funding support to smaller sponsors.
- Increase Phase IV (post-marketing) trials for long-term safety data.
- Use predictive analytics to detect early signs of trial risk.
- Standardize data collection for better reliability and comparability.
This project is released under the MIT License — free for use, modification, and distribution with proper credit.
All data analyzed is publicly available from ClinicalTrials.gov.
This project is for educational and research purposes only and should not be used for regulatory or clinical decision-making.
Hi, I’m Santosh – Healthcare Data Analytics and Pharmacovigilance specialist with expertise in drug safety, data analytics, and adverse event reporting. I work at the intersection of healthcare and data, using Python, SQL, and visualization tools to generate actionable insights that improve patient safety. I’m passionate about pharmacovigilance, regulatory compliance, and building data-driven healthcare projects.