The development of an artificial intelligence-based digital pathology for neglected tropical diseases: A platform specific analysis of the World Health Organization diagnostic target product profile for soil-transmitted helminthiasis

Abstract

The World Health Organization (WHO) recently published target product profiles (TPPs) for neglected tropical diseases (NTDs) to inform and accelerate the development of diagnostics tools necessary to achieve targets in the decade ahead. These TPPs describe the minimal and ideal requirements for various diagnostic needs related to NTD specific use-cases. An early step towards the manufacture and implementation of new diagnostics is to critically review the TPPs and translate these into an initial design and ultimately into user requirement specifications (URS). Artificial intelligence-based digital pathology (AI-DP) may overcome critical shortcomings of current standards for most NTDs reliant on microscopy, such as poor reproducibility and error-prone manual read-out. Furthermore, a digitalised workflow can create opportunities to reduce operational costs via increased throughput and automated data capture, analysis, and reporting. Despite these promising benefits, a critical review of the NTD TPPs with consideration to an AI-DP diagnostic solution is lacking. We present a systematic analysis of one of the WHO TPPs with the aim to inform the development of a URS for an AI-DP solution for NTDs. As a case study we focused on monitoring and evaluation (M&E) of programs designed to control soil-transmitted helminths (STHs). To this end, we start by outlining a brief overview of diagnostic needs for STHs, after which we systematically analyse the recently published WHO TPPs, highlighting the technical considerations for an AI-DP diagnostic solution to meet the minimal requirements for this TPP. Finally, we further reflect on the feasibility of an AI-DP informing STH programs towards the WHO 2030 targets in due time.