Certificates tell employers what you have been taught. Projects show them what you can do. Every dataset below is free, accessible, and paired with specific project ideas you can start this week. Pick one. Build something. Show it.

How to Turn a Dataset into a Solid Project

• Define the problem: be very clear on what you’re trying to solve.
• Understand the data: what is this data, where does it come from, what are its limits.
• Apply the right method: a well-executed simple analysis beats a poorly understood complex one.
• Evaluate: does this make clinical sense? What did you miss?
• Communicate clearly: This is a very important step, the analysis is pointless if you cannot communicate it with others. Write it up as if presenting to a non-technical manager
• Acknowledge limitations: data quality, missing values, bias. This is a sign of maturity, not weakness

The 5 Datasets

NHS England A&E Attendances Link: https://www.england.nhs.uk/statistics/statistical-work-areas/ae-waiting-times-and-activity/ae-attendances-and-emergency-admissions-2025-26/

Monthly A&E performance data for every NHS trust in England - attendances, 4-hour breaches, and 12-hour waits. Open source, no registration required.Multiple years of data available.

Project ideas

• Which trusts are struggling most and why? Are high-volume trusts always worse performers?
• How did A&E performance change across Q1 2026 (January to March)?
• Why do certain hospitals consistently outperform others?

Skills demonstrated: data cleaning, calculating rates, time-series visualisation, working with real operational health data.

Why it matters for your CV: This is government-level data describing how the NHS system performs month by month. It reflects actual patients and actual operational pressure. Working with it requires you to understand what the numbers mean in context, not just how to run the code.

NHS Referral to Treatment (RTT) Waiting Times Link: https://www.england.nhs.uk/statistics/statistical-work-areas/rtt-waiting-times/

Monthly waiting time data by trust and specialty: how many patients are waiting, and for how long. Years of data available including the full COVID-19 period, making it one of the few open datasets that captures a genuine before-and-after health system shock.

Project ideas

• Which specialties have the worst backlogs and how has it changed since COVID?
• Identify trusts that have meaningfully improved their waiting times and those that have not
• Build a simple forecast: how long will it take to clear the current backlog?

Skills demonstrated: Time-series analysis, reshaping wide data to long format, forecasting, communicating operational findings