PASBADIA - Patient-centred smartphone-based diagnostics with local and central AI platform for primary care in rural areas

Background
The PASBADIA joint project on the Lübeck campus with the Technical University and the University of Lübeck is developing and researching smartphone-based, patient-oriented diagnostic procedures with local and decentralised AI. Engineers, scientists and practising physicians are working together to create new diagnostic options.

In medicine, a quick, patient-centred diagnosis is often necessary. For example, the use of widely available diagnostic devices is a promising approach for monitoring the curative course of patients in rural areas, with limited mobility, in poorly accessible or underserved areas. Current smartphones lend themselves to this task due to their widespread use and the sensors and computing capacity already built in, but are currently only used in isolated and rudimentary cases.

The high-quality cameras together with the light sources (LED flash) built into smartphones allow the implementation of optical diagnostic procedures from the field of classic devices, if appropriate attachments and applications are adapted to the smartphone and measurement data is analysed on site.

Objective
The aim of the CoSA sub-project is the distributed collection, storage and processing of data with limited resources in the area of conflict between the methods of AI, the available database and, in some cases, low or no internet connection in rural areas.

Methodology
The Laboratory for Ophthalmic Technology (LfO) develops robust and safe-to-use optical attachments for smartphones as a combination of spectral, fluorescence or polarisation-based methods to generate and analyse raw diagnostic data from the fundus of the eye, for example.

The Institute of Electrical Engineering in Medicine (IME) is researching the efficient data-based evaluation of this raw data using modern methods of statistical learning theory, in the field of probabilistic graphical models and efficient Gaussian process analysis with the integration of prior knowledge as well as stochastic uncertainty information.

At the Institute of Family Medicine the needs of general practitioners in the field of ophthalmotechnology are being assessed by specifically analysing processes in primary care and exploring the determinants for successful implementation of the technical applications to be developed in general healthcare.

The aim of the interdisciplinary collaboration is to solve the task with the following overarching central medical question:
"How efficiently can an AI-based diagnostic tool based on a smartphone support a GP in carrying out the ophthalmological diagnostics required in local (primary) care on site (and thus relieve the burden on specialists, e.g. ophthalmologists)?"