Leapfrogging cancer diagnostics with AI: a mixed-methods assessment of implementation determinants in low- and middle-income countries
- 1Department of Radiation Oncology, Leiden University Medical Center, Leiden, The Netherlands
Abstract
IntroductionCancer incidence is rising rapidly in low- and middle-income countries (LMICs), where diagnostic pathology capacity is constrained. AI applied to routine histopathology could strengthen diagnostic capacity and offer leapfrogging potential by embedding AI into diagnostic systems as they are built up. However, without empirically identifying implementation determinants in LMIC cancer-diagnostic settings, AI solutions risk being poorly aligned with local constraints, limiting impact or exacerbating existing disparities.
MethodsWe conducted an exploratory mixed-methods pilot study across three phases: 1) a structured survey characterising the diagnostic and technical landscape and AI priorities; 2) focus group discussions (FGDs) to inductively identify implementation determinants and 3) a second survey quantifying FGD-derived themes. Twelve physicians were purposively recruited (10 from LMIC, 2 from high-income countries for reference) and findings integrated through narrative triangulation.
ResultsThere was substantial heterogeneity in diagnostic and AI infrastructure that did not track consistently with country income classification. H&E staining was universally available, immunohistochemistry capacity was rudimentary at 7 of 10 sites and molecular testing absent or minimal at 6 of 10 sites. Whole-slide-imaging scanners were available at 8 of 10 sites, while graphical processing units, required for efficient AI inference, were available at only 4 of 10 sites. The participants would prioritise use of AI for cancer screening, cancer diagnosis, and biomarker prediction from H&E slides. Six implementation determinants were identified: AI literacy, governance frameworks, funding, evidence generation, clinical deployment, and collaboration. Financial constraints emerged as the dominant barrier across all determinants, and collaboration as an important enabling mechanism.
ConclusionAI implementation readiness in LMIC cancer-diagnostic settings is highly heterogeneous and cannot be inferred from income classification, underscoring the need for institution-level assessment. Realising the leapfrogging potential of AI in this context requires coordinated progress across all determinants, with sustainable financing, and collaboration enabling the remaining determinants.
Key messagesO_ST_ABSWhat is already known on this topic?C_ST_ABSCancer incidence is rising rapidly in LMICs, where diagnostic capacity and molecular testing capabilities are severely constrained. AI could alleviate gaps, yet evidence on implementation determinants for integrating AI into cancer diagnostics in these settings remains limited.
What this study adds?AI implementation readiness varies substantially within LMIC settings and does not track with country income classification. Readiness is shaped by six implementation determinants: AI literacy, governance frameworks, funding, evidence generation, clinical deployment, and collaboration, with financial constraints as the dominant cross-cutting barrier.
How this study might affect research, practice or policy?These findings support institution-level feasibility assessment over income-classification proxies and highlight the need for sustainable financing and collaboration as foundational prerequisites for AI implementation in cancer diagnostics in LMICs.
Related
- Azithromycin in crisis: antimicrobial resistance, diagnostics gaps, and vaccine-linked stewardship for enteric infections in low- and middle-income countries
- Cancer-Associated Parasitic Neglected Tropical Diseases: Precision Diagnostics, Risk Stratification, and Implementation Priorities
- Implementation strategies, outcomes and determinants of integrated care for cardiometabolic conditions and mental, neurological and substance use disorders: protocol for a mixed-methods systematic review
- Building Bridges: A framework for redefining and decolonizing implementation science in low- and middle-income countries
- Severity and Determinants of Anemia Among Adolescent Girls in Africa: A Multicountry and Multilevel Analysis of 25 Countries.
BibTeX
@misc{schoenpflug2026leapfrogging,
title = {{Leapfrogging cancer diagnostics with AI: a mixed-methods assessment of implementation determinants in low- and middle-income countries}},
author = {L. A. Schoenpflug and N. J. van den Berg and S. V. Chhut and E. Y. L. Leung and L.-M. Looi and R. Lukande and S. J. Meja and R. Parra-Medina and T. B. Pathak and J. J. Pyuza and R. Razack and A. Tawiah and M. W. Waithaka and P. Zoroquiain and J. Barkey Wolf and G. Jundt and M. W. Lafarge and T. Bosse and V. H. Koelzer and N. Horeweg},
howpublished = {medRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.19.26365881},
url = {https://www.medrxiv.org/content/10.64898/2026.10.19.26365881v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Leapfrogging cancer diagnostics with AI: a mixed-methods assessment of implementation determinants in low- and middle-income countries
AU - L. A. Schoenpflug
AU - N. J. van den Berg
AU - S. V. Chhut
AU - E. Y. L. Leung
AU - L.-M. Looi
AU - R. Lukande
AU - S. J. Meja
AU - R. Parra-Medina
AU - T. B. Pathak
AU - J. J. Pyuza
AU - R. Razack
AU - A. Tawiah
AU - M. W. Waithaka
AU - P. Zoroquiain
AU - J. Barkey Wolf
AU - G. Jundt
AU - M. W. Lafarge
AU - T. Bosse
AU - V. H. Koelzer
AU - N. Horeweg
PY - 2026
DA - 2026/10/19
PB - medRxiv
DO - 10.64898/2026.10.19.26365881
UR - https://www.medrxiv.org/content/10.64898/2026.10.19.26365881v1
AB - IntroductionCancer incidence is rising rapidly in low- and middle-income countries (LMICs), where diagnostic pathology capacity is constrained. AI applied to routine histopathology could strengthen diagnostic capacity and offer leapfrogging potential by embedding AI into diagnostic systems as they are built up. However, without empirically identifying implementation determinants in LMIC cancer-diagnostic settings, AI solutions risk being poorly aligned with local constraints, limiting impact or exacerbating existing disparities. MethodsWe conducted an exploratory mixed-methods pilot study across three phases: 1) a structured survey characterising the diagnostic and technical landscape and AI priorities; 2) focus group discussions (FGDs) to inductively identify implementation determinants and 3) a second survey quantifying FGD-derived themes. Twelve physicians were purposively recruited (10 from LMIC, 2 from high-income countries for reference) and findings integrated through narrative triangulation. ResultsThere was substantial heterogeneity in diagnostic and AI infrastructure that did not track consistently with country income classification. H&E staining was universally available, immunohistochemistry capacity was rudimentary at 7 of 10 sites and molecular testing absent or minimal at 6 of 10 sites. Whole-slide-imaging scanners were available at 8 of 10 sites, while graphical processing units, required for efficient AI inference, were available at only 4 of 10 sites. The participants would prioritise use of AI for cancer screening, cancer diagnosis, and biomarker prediction from H&E slides. Six implementation determinants were identified: AI literacy, governance frameworks, funding, evidence generation, clinical deployment, and collaboration. Financial constraints emerged as the dominant barrier across all determinants, and collaboration as an important enabling mechanism. ConclusionAI implementation readiness in LMIC cancer-diagnostic settings is highly heterogeneous and cannot be inferred from income classification, underscoring the need for institution-level assessment. Realising the leapfrogging potential of AI in this context requires coordinated progress across all determinants, with sustainable financing, and collaboration enabling the remaining determinants. Key messagesO_ST_ABSWhat is already known on this topic?C_ST_ABSCancer incidence is rising rapidly in LMICs, where diagnostic capacity and molecular testing capabilities are severely constrained. AI could alleviate gaps, yet evidence on implementation determinants for integrating AI into cancer diagnostics in these settings remains limited. What this study adds?AI implementation readiness varies substantially within LMIC settings and does not track with country income classification. Readiness is shaped by six implementation determinants: AI literacy, governance frameworks, funding, evidence generation, clinical deployment, and collaboration, with financial constraints as the dominant cross-cutting barrier. How this study might affect research, practice or policy?These findings support institution-level feasibility assessment over income-classification proxies and highlight the need for sustainable financing and collaboration as foundational prerequisites for AI implementation in cancer diagnostics in LMICs.
ER -