Skip to content

2026-27 Project (Kinra & Mallinson)

AI-powered digital diagnostics for non-communicable disease screening in low-resource settings

SUPERVISORY TEAM

Supervisor

Dr Sanjay Kinra at LSHTM
Faculty of Epidemiology & Population Health, Department of Non-communicable Disease Epidemiology
Email: sanjay.kinra@lshtm.ac.uk

Co-Supervisor

Dr Poppy Mallinson at LSHTM
Faculty of Epidemiology & Population Health, Department of Non-communicable Disease Epidemiology
Email: poppy.mallinson1@lshtm.ac.uk

PROJECT SUMMARY

Project Summary

This PhD project explores how artificial intelligence (AI) can transform non-communicable disease screening in low-resource settings. Using rich digital data from a large cohort study in rural India, the student will develop and evaluate AI models to detect early signs of conditions such as diabetes, frailty, or complications through images, videos, and simple low-cost measures. Techniques will include systematic reviews, machine learning model development, and performance benchmarking. With potential for stakeholder engagement and field visits, the project offers a unique opportunity to advance equitable, affordable diagnostics that could improve access to care for underserved populations worldwide. Their work will be nested within the AI in Global Health and Healthcare (GH2.AI) group at LSHTM with opportunities to join our journal clubs, retreats and broader collaborative projects.

Project Key Words

Artificial intelligence, diagnostics, NCDs, India

MRC LID Themes

  1. Health Data Science
  2. Global Health

Skills

MRC Core Skills

  1. Quantitative skills

Skills we expect a student to develop/acquire whilst pursuing this project:

  • Quantitative analysis – AI model development, computer vision, image data manipulation, coding in Python and/or R, AI model evaluation, implementation of AI-based solutions
  • International collaboration skills
  • Academic communication skills (presentation and writing)

Routes

Which route/s are available with this project?

  • 1+4 = Yes
  • +4 = Yes

Possible Master’s programme options identified by supervisory team for 1+4 applicants:

  • LSHTM – MSc Health Data Science

Full-time/Part-time Study

Is this project available for full-time study? Yes
Is this project available for part-time study? Yes

Location & Travel

Students funded through MRC LID are expected to work on site at their primary institution. At a minimum, all students must meet the institutional research degree regulations and expectations about onsite working and under this scheme they may be expected to work onsite (in-person) more frequently. Students may also be required to travel for conferences (up to 3 over the duration of the studentship), and for any required training for research degree study and training. Other travel expectations and opportunities highlighted by the supervisory team are noted below.

Day-to-day work (primary location) for the duration of this research degree project will be at: LSHTM – Bloomsbury, London

Travel requirements for this project: There will opportunity for candidate to do some stakeholder work at the project field site once the AI solutions are developed.

Eligibility/Requirements

Particular prior educational requirements for a student undertaking this project

  • Minimum standard institutional eligibility criteria for doctoral study at LSHTM
  • Either experience in or strong interest in gaining data science analytical skills such as AI and programming (to Masters level or equivalent).  Some background in health area would be beneficial.

Other useful information

  • Potential Industrial CASE (iCASE) conversion? = No

PROJECT IN MORE DETAIL

Scientific description of this research project

Project objectives:
Timely diagnosis of non-communicable diseases often requires blood tests, expert clinical assessments, and other specialist screening tools that are not widely available in rural and low-resource settings. Artificial intelligence (AI) offers an automated approach to analysing high-resolution clinical data (such as images) which could facilitate lower cost and remote evaluation of non-communicable disease risk. If accurate and affordable, these approaches could facilitate more equitable access to non-communicable disease care for underserved populations. This PhD project aims to explore the feasibility of using AI-powered digital diagnostics for non-communicable disease screening in low-resource settings, applying a range of use-cases from rural India. Specific objectives will be based around use-cases selected by the candidate but will may include use of body images and low-cost measurements to classify body mass index, body fat distribution and diabetes status, the use of videos of people walking to detect gait abnormalities, frailty and related conditions, or the use of images alongside screening questionnaires to detect diabetes complications.

Techniques to be used: 

  • Systematic review of existing evidence and AI models related to the chosen use case(s) 
  • Development of AI models (for example based on convolutional neural networks) to perform the selected classification tasks against ground-truth labels 
  • Evaluation of the performance of the AI models on held-out data samples as compared with existing alternative screening modalities 
  • If time permits and based on students interest, the above could be followed up with stakeholder consultations aiming to co-develop feasible pathways to implementation for successful AI-based solutions via a field visit to the study site.

Analysis data for this project has already been collected by the supervisory team. The Andhra Pradesh Children and Parent Study (APCAPS) is a large prospective, intergenerational cohort study in Southern India. It is situated in 29 villages near the city of Hyderabad in Ranga Reddy district, Andhra Pradesh. A range of digital image data alongside ground-truth clinical labels has been collected on 2000-4000 individuals. More information at lshtm.ac.uk/APCAPS.

Confirmed availability of any required databases or specialist materials:
This project will involve analysing a large a cohort study that has been collected by the project supervisors. All data has already been collected and access is confirmed.

Potential risks to the project and plans for their mitigation:
Minimal risks foreseen. We have already done some initial piloting of the development of similar AI models so expect that good performance will be possible. A range of use-cases are available to be explored based on students’ interests, providing additional options in case any back-up plans are needed.

Further reading

Relevant preprints and/or open access articles:
(DOI = Digital Object Identifier)

Other pre-application materials:
Information about the data source: www.lshtm.ac.uk/APCAPS

Additional information from the supervisory team

The supervisory team has provided a recording for prospective applicants who are interested in their project. This recording should be watched before any discussions begin with the supervisory team.

Kinra & Mallinson Recording

MRC LID LINKS

To apply for a studentship: MRC LID How to Apply
Full list of available projects: MRC LID Projects
For more information about the DTP: MRC LID About Us

Comments are closed.