AI-Augmented Diagnostic Assessment With ENLIGHT Versus Independent Pathologist Review (ENLIGHT)
This study will evaluate whether artificial intelligence (AI) can enhance clinicians' accuracy, efficiency, and confidence in distinguishing lung adenocarcinoma (LUAD) from lung squamous cell carcinoma (LUSC) and kidney renal papillary cell carcinoma (KIRP) from kidney renal clear cell carcinoma (KIRC) using digitized pathology slides. These subtype classifications are routinely performed by pathologists but can be challenging and time-consuming, particularly in difficult cases.
During the study, participating clinicians will review lung and kidney pathology slides under three different conditions:
- Unaided Review: Diagnosis without AI assistance.
- AI as Double-Check: The clinician first makes an independent diagnosis, after which the AI-generated diagnosis (prediction only or prediction with explanation) is revealed for review.
- AI as First-Look: The AI-generated diagnosis (prediction only or prediction with explanation) is presented before the clinician begins the review.
Clinicians will be randomly assigned to different review sequences to minimize potential order effects. This study design will enable us to assess the impact of AI assistance on diagnostic accuracy, interpretation time, and clinician confidence.
Visão geral do estudo
Status
Condições
Intervenção / Tratamento
- Comportamental: Unaided Review First, Then AI as Double-Check, Then AI as First-Look.
- Comportamental: Unaided Review First, Then AI as First-Look, Then AI as Double-Check.
- Comportamental: AI as Double-Check First, Then AI as First-Look, Then Unaided Review.
- Comportamental: AI as First-Look First, Then AI as Double-Check, Then Unaided Review.
Descrição detalhada
This study aims to evaluate the effect of artificial intelligence (AI) assistance on clinicians' diagnostic performance in distinguishing lung adenocarcinoma (LUAD) from lung squamous cell carcinoma (LUSC) and kidney renal papillary cell carcinoma (KIRP) from kidney renal clear cell carcinoma (KIRC) using digitized hematoxylin and eosin (H&E)-stained whole-slide images (WSIs). ENLIGHT (Explainable Neoplasm Learning In Grounded Histology Terms) will serve as the AI system under evaluation. This is a single-session, within-reader, between-case study in which each reader evaluates distinct sets of cases under all study conditions.
The study includes three diagnostic blocks: Block X, in which WSIs are reviewed without AI assistance; Block Y1, in which clinicians make an initial diagnosis before viewing the AI output as a double-check; and Block Y2, in which the AI output is displayed before clinicians begin their review as a first-look aid. Within each AI-assisted block, the prediction-only and prediction-with-explanation sub-blocks are presented in randomized order.
Each participating pathologist will review up to 400 de-identified WSIs (up to 200 lung cancer and up to 200 kidney cancer cases). Readers will be randomly assigned to one of four study arms that differ only in the order in which Blocks X, Y1, and Y2 are completed. For each reader, distinct WSIs will be randomly assigned to the diagnostic conditions so that no WSI is reviewed more than once by the same reader.
- Arm 1 (X -> Y1 -> Y2): Clinicians first complete Block X (Unaided Review), followed by Block Y1 (AI as Double-Check) and then Block Y2 (AI as First-Look).
- Arm 2 (X -> Y2 -> Y1): Clinicians first complete Block X (Unaided Review), followed by Block Y2 (AI as First-Look) and then Block Y1 (AI as Double-Check).
- Arm 3 (Y1 -> Y2 -> X): Clinicians first complete Block Y1 (AI as Double-Check), followed by Block Y2 (AI as First-Look), and then Block X (Unaided Review).
- Arm 4 (Y2 -> Y1 -> X): Clinicians first complete Block Y2 (AI as First-Look), followed by Block Y1 (AI as Double-Check), and then Block X (Unaided Review).
For each case, diagnostic accuracy, time to diagnosis, and diagnostic confidence will be recorded. No reader will review the same WSI under more than one condition, thereby eliminating within-reader recall bias. In parallel, the ENLIGHT model will independently generate diagnostic predictions for all WSIs to enable direct benchmarking of AI performance against pathologists and to evaluate the impact of different AI-assisted workflows on diagnostic performance.
Tipo de estudo
Inscrição (Estimado)
Estágio
- Não aplicável
Contactos e Locais
Locais de estudo
-
-
Massachusetts
-
Boston, Massachusetts, Estados Unidos, 02115
- Harvard Medical School,
-
-
Critérios de participação
Critérios de elegibilidade
Idades elegíveis para estudo
- Filho
- Adulto
- Adulto mais velho
Aceita Voluntários Saudáveis
Descrição
Inclusion Criteria for Pathology Slides (i.e., Cases):
- Hematoxylin and eosin (H&E)-stained pathology slides
- Final diagnosis confirmed through molecular testing in conjunction with expert pathology evaluation
Exclusion Criteria for Pathology Slides (i.e., Cases):
- Poor-quality or unreadable slides
- Cases used in AI training
Inclusion Criteria for Readers (i.e., Participants):
- Board-certified or board-eligible pathologists
- Willingness to complete both unaided and AI-assisted review sessions
Plano de estudo
Como o estudo é projetado?
Detalhes do projeto
- Finalidade Principal: Diagnóstico
- Alocação: Randomizado
- Modelo Intervencional: Atribuição cruzada
- Mascaramento: Quadruplicar
Armas e Intervenções
Grupo de Participantes / Braço |
Intervenção / Tratamento |
|---|---|
|
Comparador Ativo: Unaided Review First, Then AI as Double-Check, Then AI as First-Look.
Readers first complete Block X (Unaided) on their assigned subset SX.
They then complete Block Y1 (AI as Double-Check) on two separate subsets: SY1a (AI prediction-only as Double-Check) and SY1b (AI prediction-with-explanation as Double-Check).
Within Block Y1, the order of SY1a and SY1b is randomized.
They then complete Block Y2 (AI as First-Look) on two separate subsets: SY2a (AI prediction-only as First-Look) and SY2b (AI prediction-with-explanation as First-Look).
Within Block Y2, the order of SY2a and SY2b is randomized.
For each reader, each of the five subsets (SX, SY1a, SY1b, SY2a, and SY2b) comprises up to 80 slides: up to 40 slides from LUAD-LUSC and up to 40 slides from KIRP-KIRC.
|
Readers first complete Block X (Unaided) on their assigned subset SX.
They then complete Block Y1 (AI as Double-Check) on two separate subsets: SY1a (AI prediction-only as Double-Check) and SY1b (AI prediction-with-explanation as Double-Check).
Within Block Y1, the order of SY1a and SY1b is randomized.
They then complete Block Y2 (AI as First-Look) on two separate subsets: SY2a (AI prediction-only as First-Look) and SY2b (AI prediction-with-explanation as First-Look).
Within Block Y2, the order of SY2a and SY2b is randomized.
For each reader, SX, SY1a, SY1b, SY2a, and SY2b are disjoint.
|
|
Comparador Ativo: Unaided Review First, Then AI as First-Look, Then AI as Double-Check.
Readers first complete Block X (Unaided) on their assigned subset SX.
They then complete Block Y2 (AI as First-Look) on two separate subsets: SY2a (AI prediction-only as First-Look) and SY2b (AI prediction-with-explanation as First-Look).
Within Block Y2, the order of SY2a and SY2b is randomized.
They then complete Block Y1 (AI as Double-Check) on two separate subsets: SY1a (AI prediction-only as Double-Check) and SY1b (AI prediction-with-explanation as Double-Check).
Within Block Y1, the order of SY1a and SY1b is randomized.
For each reader, each of the five subsets (SX, SY1a, SY1b, SY2a, and SY2b) comprises up to 80 slides: up to 40 slides from LUAD-LUSC and up to 40 slides from KIRP-KIRC.
|
Readers first complete Block X (Unaided) on their assigned subset SX.
They then complete Block Y2 (AI as First-Look) on two separate subsets: SY2a (AI prediction-only as First-Look) and SY2b (AI prediction-with-explanation as First-Look).
Within Block Y2, the order of SY2a and SY2b is randomized.
They then complete Block Y1 (AI as Double-Check) on two separate subsets: SY1a (AI prediction-only as Double-Check) and SY1b (AI prediction-with-explanation as Double-Check).
Within Block Y1, the order of SY1a and SY1b is randomized.
For each reader, SX, SY1a, SY1b, SY2a, and SY2b are disjoint.
|
|
Comparador Ativo: AI as Double-Check Review First, Then AI as First-Look, Then Unaided Review.
Readers first complete Block Y1 (AI as Double-Check) on two separate subsets: SY1a (AI prediction-only as Double-Check) and SY1b (AI prediction-with-explanation as Double-Check).
Within Block Y1, the order of SY1a and SY1b is randomized.
They then complete Block Y2 (AI as First-Look) on two separate subsets: SY2a (AI prediction-only as First-Look) and SY2b (AI prediction-with-explanation as First-Look).
Within Block Y2, the order of SY2a and SY2b is randomized.
Then readers complete Block X (Unaided) on their assigned subset SX.
For each reader, each of the five subsets (SX, SY1a, SY1b, SY2a, and SY2b) comprises up to 80 slides: up to 40 slides from LUAD-LUSC and up to 40 slides from KIRP-KIRC.
|
Readers first complete Block Y1 (AI as Double-Check) on two separate subsets: SY1a (AI prediction-only as Double-Check) and SY1b (AI prediction-with-explanation as Double-Check).
Within Block Y1, the order of SY1a and SY1b is randomized.
They then complete Block Y2 (AI as First-Look) on two separate subsets: SY2a (AI prediction-only as First-Look) and SY2b (AI prediction-with-explanation as First-Look).
Within Block Y2, the order of SY2a and SY2b is randomized.
Then readers complete Block X (Unaided) on their assigned subset SX.
For each reader, SX, SY1a, SY1b, SY2a, and SY2b are disjoint.
|
|
Comparador Ativo: AI as First-Look Review First, Then AI as Double-Check, Then Unaided Review.
Readers first complete Block Y2 (AI as First-Look) on two separate subsets: SY2a (AI prediction-only as First-Look) and SY2b (AI prediction-with-explanation as First-Look).
Within Block Y2, the order of SY2a and SY2b is randomized.
They then complete Block Y1 (AI as Double-Check) on two separate subsets: SY1a (AI prediction-only as Double-Check) and SY1b (AI prediction-with-explanation as Double-Check).
Within Block Y1, the order of SY1a and SY1b is randomized.
Then readers complete Block X (Unaided) on their assigned subset SX.
For each reader, each of the five subsets (SX, SY1a, SY1b, SY2a, and SY2b) comprises up to 80 slides: up to 40 slides from LUAD-LUSC and up to 40 slides from KIRP-KIRC.
|
Readers first complete Block Y2 (AI as First-Look) on two separate subsets: SY2a (AI prediction-only as First-Look) and SY2b (AI prediction-with-explanation as First-Look).
Within Block Y2, the order of SY2a and SY2b is randomized.
They then complete Block Y1 (AI as Double-Check) on two separate subsets: SY1a (AI prediction-only as Double-Check) and SY1b (AI prediction-with-explanation as Double-Check).
Within Block Y1, the order of SY1a and SY1b is randomized.
Then readers complete Block X (Unaided) on their assigned subset SX.
For each reader, SX, SY1a, SY1b, SY2a, and SY2b are disjoint.
|
O que o estudo está medindo?
Medidas de resultados primários
Medida de resultado |
Descrição da medida |
Prazo |
|---|---|---|
|
Diagnostic performance of cancers
Prazo: Periprocedural (at the time of slide review)
|
Performance of clinicians (unaided and AI-assisted) for distinguishing LUAD- LUSC and distinguishing KIRP-KIRC, measured in accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and F1.
|
Periprocedural (at the time of slide review)
|
Medidas de resultados secundários
Medida de resultado |
Descrição da medida |
Prazo |
|---|---|---|
|
Hora de diagnóstico
Prazo: Periprocedural (no momento da revisão de slides)
|
Tempo médio (segundos por caso) necessário para finalizar um diagnóstico.
|
Periprocedural (no momento da revisão de slides)
|
|
Variabilidade entre observadores
Prazo: Periprocedural (no momento da revisão de slides)
|
Concordância entre os médicos entre as condições, medidos usando métricas de confiabilidade entre avaliadores (por exemplo, estatísticas de Kappa).
|
Periprocedural (no momento da revisão de slides)
|
|
Benefício líquido após a exposição à IA
Prazo: Periprocedural (no momento da revisão de slides)
|
A mudança geral na precisão do diagnóstico atribuível à assistência de IA.
|
Periprocedural (no momento da revisão de slides)
|
|
Clinician confidence level
Prazo: Periprocedural (at the time of slide review)
|
Self-reported diagnostic confidence recorded for each case.
Scale: 5 - Absolutely Certain; 4 - Mostly Certain; 3 - Unsure; 2 - Very Doubtful; 1 - Random Guess; With 5 being the highest confidence score and 1 being the lowest.
|
Periprocedural (at the time of slide review)
|
Colaboradores e Investigadores
Patrocinador
Datas de registro do estudo
Datas Principais do Estudo
Início do estudo (Estimado)
Conclusão Primária (Estimado)
Conclusão do estudo (Estimado)
Datas de inscrição no estudo
Enviado pela primeira vez
Enviado pela primeira vez que atendeu aos critérios de CQ
Primeira postagem (Real)
Atualizações de registro de estudo
Última Atualização Postada (Real)
Última atualização enviada que atendeu aos critérios de controle de qualidade
Última verificação
Mais Informações
Termos relacionados a este estudo
Palavras-chave
Termos MeSH relevantes adicionais
Outros números de identificação do estudo
- ENLIGHT Study
Plano para dados de participantes individuais (IPD)
Planeja compartilhar dados de participantes individuais (IPD)?
Informações sobre medicamentos e dispositivos, documentos de estudo
Estuda um medicamento regulamentado pela FDA dos EUA
Estuda um produto de dispositivo regulamentado pela FDA dos EUA
Essas informações foram obtidas diretamente do site clinicaltrials.gov sem nenhuma alteração. Se você tiver alguma solicitação para alterar, remover ou atualizar os detalhes do seu estudo, entre em contato com register@clinicaltrials.gov. Assim que uma alteração for implementada em clinicaltrials.gov, ela também será atualizada automaticamente em nosso site .