James Jones | Health Data Scientist

James Jones

Health Data Scientist

Based in Nottingham

About

Data Scientist with over a decade of experience in analytical roles within the healthcare sector. Recently completed a pre-doctoral fellowship from the National Institute for Health Research, achieving a Master of Science in Data Science with distinction. Notable achievements include establishing the EMCA data hub, recognized nationally for its data visualization and analysis in the straight-to-test pathway, resulting in a published paper in the BMJ. specializing in automating the mortality and morbidity processes and employing SQL and R programming to develop a data tool for analysing the coloFIT pathway. Proficient in leveraging machine learning techniques using Python to classify patients' cancer risk based on bio markers and other characteristics.

Skills

Projects

Visualizing Nottingham’s Busiest Roads

In this blog post, we will explore the R code that was used to create a map of Nottingham’s busiest roads. We will walk through the different steps and packages used to create this map and explain how the final visualization was created.

Visualizing Polar Bear Migration Using R

I recently got my hands on a fascinating dataset from the United States Geological Survey (USGS) that tracks polar bear sightings, and I used R to create some awesome visualizations of their migration patterns.

Midlands Cancer Alliance Data Hub

In a previous role I created the Midlands Cancer Alliance Data Hub that won Best Interactive Data Display at UKIACR Data Visualisation Competition 2018. See links to the tool and award article.

Cancer prevention – the East Midlands Approach

Previous work that projected cancer incidence and attributing factors using Power BI See links to the tool and Public Health article.

Significance Testing: Comparing Date Ranges among Groups with R

Step by step guide to comparing time intervals by groups. Includeswhich significance tests to choose based on data distribution and example code in R.

Machine Learning Classification Models Made Easy. Part 1: Simple Models in R

I have put togther a guide where I share the methodology I used in creating classification machine learning models during my MSc thesis, utilising open-source data. Here, We’ll go through the process of building these models using R. My aim here is to simplify the steps involved in building a cl

Experience

2023

Advanced Analyst in Colorectal Surgery

Building on the work on coloFIT from the NIHR fellowship. Further analysis of the pathway including variation in uptake, three year follow up review and machine learning models to classify cancer based on bio markers and patient characteristics. Other work includes automating the Trusts mortality and morbidity process.

2021-2023

Pre-Doctoral Fellow at National Institute for Health Research (NIHR)

Awarded a pre doctoral fellowship by the NIHR over two years where time was split between undertaking a Data Science MSc at the University of Aberdeen which I passed with distinction and research in the colorectal surgery department at Nottingham University Hospitals where I created the coloFIT dataset using SQL and pathway analysis tool using R.

2019- 2021

Advanced Analyst at East Midlands Academic Health Science Network

The East Midlands Cancer Alliance is being established to drive improvements in the provision of care for patients in the East Midlands who have cancer. Ensuring all patients receive high quality care in a prompt and efficient manner from diagnosis to treatment will have a significant impact for those who have cancer or a suspected cancer.

2015- 2019

Senior Cancer Information Analyst at East Midlands Academic Health Science Network

The ACE Programme is an early diagnosis programme that supports the NHS outcome of ‘preventing people from dying prematurely’. It is a unique initiative supported by Cancer Research UK and Macmillan Cancer Support and will run across England for 3 years. See www.CRUK.org/ACE . As part of this I extracted and analysed data from each of the eight Trusts in the region to evaluate whether the implementation of a straight to test pathway had any impact on early diagnosis.

2013- 2015

Information Analyst at Nottingham University Hospital

Delivering a co-ordinated high quality, relevant and timely information service, working closely with various clients. These will include the Department of Health, Care Commissioning Groups, Business Managers, Operational Service Managers, Senior Nurse Managers and all levels of Clinicians.

2011- 2013

Data Quality Officer at Nottingham University Hospital

Identifying and resolving front end issues. Training, Identifying and resolving system issues – batch tracing, interfaces, external system PMIs. Reducing the amount of data validation queries returned to the Trust by the CCG's .

Education

2021-2023

Data Science MSc at University of Aberdeen

Graduated in 2023 with Distinction. Modules included; Introduction to Programming, Introduction to Data Science, Statistics and Time Series Analysis, Introduction to Python and R, Data Visualisation, Advanced Statistics and Special Applications, Machine Learning, Image analysis and Data Science Project