Clinical Data Scientist

Datasumi; London; On-site; GBP 50,000 - 90,000; Full time

Job summary

An innovative firm is seeking a talented individual to lead the development of AI healthcare algorithms. This role combines advanced machine learning expertise with clinical understanding to enhance patient care pathways. You will work closely with healthcare practitioners and technical teams to develop, train, and validate machine learning models, deploy solutions on cloud infrastructure, and conduct data analysis. If you are passionate about improving healthcare through technology and possess strong communication skills, this is an exciting opportunity to make a significant impact in the field.

Qualifications

• PhD or MSc in Data Science, Computer Science, or Biostatistics required.
• 3+ years of experience with machine learning in healthcare data.

Responsibilities

• Develop and optimize AI algorithms for healthcare applications.
• Collaborate with clinicians to translate clinical needs into technical specifications.

Skills

Machine Learning

Python

Data Analysis

Statistical Analysis

Communication

Education

PhD in Data Science

MSc in Computer Science

Tools

Azure

Tableau

PostgreSQL

TensorFlow

GitHub

Job description

Position Overview

Lead the development and refinement of our AI HealthCare algorithms while serving as the primary bridge between our technical team and healthcare practitioners. This role combines advanced machine learning expertise with deep clinical understanding to optimise patient care pathways.

Key Responsibilities

Algorithm Development & Optimisation

• Develop, train, and validate machine learning models using healthcare datasets, including ensemble methods and large language models (LLMs)
• Deploy models on Azure cloud infrastructure to support scalable healthcare solutions
• Implement ETL processes for clinical trial data using tools like Beautiful Soup, ensuring high data integrity
• Design and implement data annotation protocols for training datasets
• Conduct hypothesis testing to evaluate model improvements and optimise workflows for better performance and efficiency
• Apply model versioning and monitoring techniques to track performance and ensure reliability throughout lifecycle
  
  

Clinical Data Analysis & Management

• Build predictive models for clinical data and mortality analysis, supporting risk assessment and healthcare research
• Process and store large-scale clinical trial records (40,000+) in PostgreSQL databases
• Conduct statistical analyses to measure model performance against clinical benchmarks
• Design and develop Tableau dashboards to visualise insights from clinical data, improving stakeholder decision-making
  
  

Collaborative & Communication

• Collaborate with NHS clinicians to understand triage workflows and translate clinical requirements into technical specifications
• Present technical concepts to clinical stakeholders in accessible language
• Lead training and knowledge-sharing sessions on statistical and computational methods
• Support the development of Trusted Research Environment and policies around data access and reuse
• Contribute to funding proposals, reporting, and publications advocating for open science research
  
  

Innovation & Automation

• Leverage OpenAI's LLMs (including ChatGPT API) to automate text summarization and information extraction
• Enhance efficiency in systematic literature reviews through automation
• Contribute to modelling efforts and tools aimed at regional priority setting and health system optimization
  
  

Requirements

Education & Experience

• PhD or MSc in Data Science, Computer Science, Biostatistics, or related field
• 3+ years' experience applying machine learning to healthcare data
• Demonstrable experience with healthcare datasets and clinical taxonomies
• Knowledge of UK healthcare systems and NHS data structures preferred
• Experience with clinical systems: PACS/RIS, EMR, HL7/DICOM
  
  

Technical Skills

• Programming: Python, JavaScript, HTML/CSS, R, MATLAB
• ML Frameworks: TensorFlow
• Database: SQL, PostgreSQL
• Data Visualisation: Tableau, Excel
• AI & Computer Vision: Model testing, image analysis, real-world evidence (RWE)
• Clinical Data Management: eCRF, SAP, GCP, LIMS, CRF Design
• API Integration: RESTNet, ChatGPT API
• Version Control: GitHub
• Cloud Computing: Azure
  
  

Soft Skills

• Excellent communication skills with ability to bridge technical and clinical domains
• Team leadership and project coordination experience
• Strong patient communication capabilities
• Academic writing, study protocols, and statistical reporting skills
• Experience with publications and research advocacy
  
  

Additional Requirements

• Experience with systematic reviews and literature analysis automation
• Proven track record of reducing manual processes through ML implementation
• Experience improving data retrieval efficiency and system optimization
• Ability to work with both structured and unstructured healthcare data
• Understanding of clinical trial data extraction and processing
• Experience with healthcare-specific ML libraries and APIs