Routine Diagnosis: 100 Percent Digital
Fully digitizing anatomic pathology results in greater staff satisfaction and lab efficiency – but is also a prerequisite for computational pathology
Granada University Hospitals, a group of two teaching and two district general hospitals integrated into the Spanish public healthcare system, have been using digital pathology for primary diagnosis of all histopathology specimens since September 2016. Since its implementation, approximately 160,000 specimens have been digitally diagnosed – around 800,000 digitized glass slides, including routine hematoxylin-eosin, special stains, and immunohistochemistry samples. Microscopes have been largely replaced by computer screens, and all our digital histology images, stored in local servers, are instantaneously available to our staff across the four hospitals.
The creation of a fully digital multi-site network has brought about several advantages, most important of which is the ability to assign caseloads according to specialty interest among our pathologists, regardless of their location. Pathologists at the peripheral hospitals can request immediate consultations from specialists located at the central hospital in Granada. Sharing cases with colleagues and requesting “curbside consultations” is straightforward, even between distant sites.
Pathologists were attracted to digital diagnosis from the start. The excellent image quality, particularly at low power; the availability of digital tools for marking, counting mitoses, and measuring lesions and their distance to surgical margins; the orderly disposition and immediate availability of digital images, including archived images; and the added ease of preparing for multidisciplinary team meetings and teaching sessions – all of these advantages made our pathologists keen to transition to digital diagnosis. Together with the rational case allocation permitted by the creation of a fully digital multi-site network, these factors have resulted in a more pleasant and productive working environment. Once our pathologists tried digital, they never looked back.
For us, digitization has paid off in many ways, from greater pathologist and lab staff satisfaction to a measurable productivity increase. Full digitization means that some lab tasks, such as slide sorting and case assembly and distribution, are now redundant. There is no shifting of glass slides across sites. For this reason, whereas some prefer a “hybrid” mode of diagnosis during the transition period (1), we decided to opt for full digitization shortly after rollout.
The adoption of digital pathology has resulted in improved efficiency. Like many public healthcare settings, our labs have experienced annual caseload increases ranging from 5 to 9 percent per annum. In addition, we have experienced staff vacancies due to non-replaced retirements. This has translated to an increase in the number of cases signed out per pathologist each year following digital implementation. The total number of cases that each pathologist signed out per year since going digital has increased, on average, 21 percent after adopting digital pathology (2).
Despite the immaterial benefits of working with digital tools in a glassless and more ergonomic environment, the investment required to implement digital pathology can only be justified if the cost incurred is outweighed by the benefits obtained. A cost-benefit model (3) proposes that improvements in productivity of at least 10 to 15 percent are required to amortize the investment after one to two years. Following this model, the fact that we were able to absorb a 21 percent increase in cases per pathologist suggests that amortization occurred even faster. In any case, the savings incurred by doing more work with fewer pathologists in the three years since the implementation of digital pathology justifies the investment from a pecuniary point of view – but it is equally important to remember that computational pathology, the so-referred third revolution in pathology (4), can only take place in digital labs.
Juan Antonio Retamero presents a webinar (hosted by The Pathologist, sponsored by Philips) on the efficiency gains experienced following the implementation of a digital pathology workflow here.
- F Fraggetta et al., “Routine digital pathology workflow: the Catania experience”, J Pathol Inform, 8, 51 (2017). PMID: 29416941.
- JA Retamero et al., “Complete digital pathology for routine histopathology diagnosis in a multicenter hospital network”, Arch Pathol Lab Med, [Epub ahead of print] (2019). PMID: 31295015.
- J Griffin, D Treanor, “Digital pathology in clinical use: where are we now and what is holding us back?”, Histopathology, 70, 134 (2017). PMID: 27960232.
- M Salto-Tellez et al., “Artificial intelligence – the third revolution in pathology”, Histopathology, 74, 372 (2019). PMID: 30270453.
Pathologist at Granada University Hospitals, Granada, Spain.