Your browser doesn't support javascript.
loading
Banff scoring of kidney allograft biopsies: "Manual" application vs software-assisted sign-out.
Demetris, Anthony J; Lesniak, Andrew J; Popp, Benjamin A; Frencho, Ronald J; Minervini, Marta I; Nalesnik, Michael A; El Hag, Mohamed I; Hariharan, Sundaram; Randhawa, Parmjeet S.
Afiliación
  • Demetris AJ; Department of Pathology, Division of Transplantation, University of Pittsburgh, Pittsburgh, PA, US.
  • Lesniak AJ; Department of Pathology, Division of Transplantation, University of Pittsburgh, Pittsburgh, PA, US.
  • Popp BA; Department of Pathology, Division of Transplantation, University of Pittsburgh, Pittsburgh, PA, US.
  • Frencho RJ; Scalable Solutions, Ingomar, PA, US.
  • Minervini MI; Department of Pathology, Division of Transplantation, University of Pittsburgh, Pittsburgh, PA, US.
  • Nalesnik MA; Department of Pathology, Division of Transplantation, University of Pittsburgh, Pittsburgh, PA, US.
  • El Hag MI; Department of Pathology, Division of Transplantation, University of Pittsburgh, Pittsburgh, PA, US.
  • Hariharan S; Division of Transplant Nephrology, University of Pittsburgh Medical Center, Pittsburgh, PA, US.
  • Randhawa PS; Department of Pathology, Division of Transplantation, University of Pittsburgh, Pittsburgh, PA, US.
Am J Clin Pathol ; 161(6): 543-552, 2024 Jun 03.
Article en En | MEDLINE | ID: mdl-38340346
ABSTRACT

OBJECTIVES:

Pathologists interpreting kidney allograft biopsies using the Banff system usually start by recording component scores (eg, i, t, cg) using histopathologic criteria committed to memory. Component scores are then melded into diagnoses using the same manual/mental processes. This approach to complex Banff rules during routine sign-out produces a lack of fidelity and needs improvement.

METHODS:

We constructed a web-based "smart template" (software-assisted sign-out) system that uniquely starts with upstream Banff-defined additional diagnostic parameters (eg, infection) and histopathologic criteria (eg, percent interstitial inflammation) collectively referred to as feeder data that is then translated into component scores and integrated into final diagnoses using software-encoded decision trees.

RESULTS:

Software-assisted sign-out enables pathologists to (1) accurately and uniformly apply Banff rules, thereby eliminating human inconsistencies (present in 25% of the cohort); (2) document areas of improvement; (3) show improved correlation with function; (4) examine t-Distributed Stochastic Neighbor Embedding clustering for diagnosis stratification; and (5) ready upstream incorporation of artificial intelligence-assisted scoring of biopsies.

CONCLUSIONS:

Compared with the legacy approach, software-assisted sign-out improves Banff accuracy and fidelity, more closely correlates with kidney function, is practical for routine clinical work and translational research studies, facilitates downstream integration with nonpathology data, and readies biopsy scoring for artificial intelligence algorithms.
Asunto(s)
Palabras clave
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Programas Informáticos / Trasplante de Riñón Tipo de estudio: Guideline / Prognostic_studies Límite: Humans Idioma: En Revista: Am J Clin Pathol Año: 2024 Tipo del documento: Article País de afiliación: Estados Unidos Pais de publicación: Reino Unido
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Programas Informáticos / Trasplante de Riñón Tipo de estudio: Guideline / Prognostic_studies Límite: Humans Idioma: En Revista: Am J Clin Pathol Año: 2024 Tipo del documento: Article País de afiliación: Estados Unidos Pais de publicación: Reino Unido