Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 6.142
Filtrar
1.
Rev Esp Patol ; 57(3): 198-210, 2024.
Artigo em Inglês | MEDLINE | ID: mdl-38971620

RESUMO

The much-hyped artificial intelligence (AI) model called ChatGPT developed by Open AI can have great benefits for physicians, especially pathologists, by saving time so that they can use their time for more significant work. Generative AI is a special class of AI model, which uses patterns and structures learned from existing data and can create new data. Utilizing ChatGPT in Pathology offers a multitude of benefits, encompassing the summarization of patient records and its promising prospects in Digital Pathology, as well as its valuable contributions to education and research in this field. However, certain roadblocks need to be dealt like integrating ChatGPT with image analysis which will act as a revolution in the field of pathology by increasing diagnostic accuracy and precision. The challenges with the use of ChatGPT encompass biases from its training data, the need for ample input data, potential risks related to bias and transparency, and the potential adverse outcomes arising from inaccurate content generation. Generation of meaningful insights from the textual information which will be efficient in processing different types of image data, such as medical images, and pathology slides. Due consideration should be given to ethical and legal issues including bias.


Assuntos
Inteligência Artificial , Humanos , Patologia , Patologia Clínica , Processamento de Imagem Assistida por Computador/métodos , Previsões
2.
Nature ; 630(8015): 181-188, 2024 Jun.
Artigo em Inglês | MEDLINE | ID: mdl-38778098

RESUMO

Digital pathology poses unique computational challenges, as a standard gigapixel slide may comprise tens of thousands of image tiles1-3. Prior models have often resorted to subsampling a small portion of tiles for each slide, thus missing the important slide-level context4. Here we present Prov-GigaPath, a whole-slide pathology foundation model pretrained on 1.3 billion 256 × 256 pathology image tiles in 171,189 whole slides from Providence, a large US health network comprising 28 cancer centres. The slides originated from more than 30,000 patients covering 31 major tissue types. To pretrain Prov-GigaPath, we propose GigaPath, a novel vision transformer architecture for pretraining gigapixel pathology slides. To scale GigaPath for slide-level learning with tens of thousands of image tiles, GigaPath adapts the newly developed LongNet5 method to digital pathology. To evaluate Prov-GigaPath, we construct a digital pathology benchmark comprising 9 cancer subtyping tasks and 17 pathomics tasks, using both Providence and TCGA data6. With large-scale pretraining and ultra-large-context modelling, Prov-GigaPath attains state-of-the-art performance on 25 out of 26 tasks, with significant improvement over the second-best method on 18 tasks. We further demonstrate the potential of Prov-GigaPath on vision-language pretraining for pathology7,8 by incorporating the pathology reports. In sum, Prov-GigaPath is an open-weight foundation model that achieves state-of-the-art performance on various digital pathology tasks, demonstrating the importance of real-world data and whole-slide modelling.


Assuntos
Conjuntos de Dados como Assunto , Processamento de Imagem Assistida por Computador , Aprendizado de Máquina , Patologia Clínica , Humanos , Benchmarking , Processamento de Imagem Assistida por Computador/métodos , Neoplasias/classificação , Neoplasias/diagnóstico , Neoplasias/patologia , Patologia Clínica/métodos , Masculino , Feminino
3.
Diagn Cytopathol ; 52(8): 433-439, 2024 Aug.
Artigo em Inglês | MEDLINE | ID: mdl-38660884

RESUMO

Over the last several years, there has been increased focus on diversity, equity, and inclusion within all areas of pathology and laboratory medicine. Many of the specialty societies within pathology have taken up the mantle of diversity. While there is little research into the diversity of cytopathologists in practice, the Accreditation Council for Graduate Medical Education (ACGME) has been collecting diversity data on pathology and laboratory medicine trainees since 2011. This data are an opportunity to explore how diverse our trainees in cytopathology are, and by extrapolation, allows us to develop some ideas as to how diverse attending level cytopathologists are. The author will also share personal observations from her own training and career regarding diversity in cytopathology.


Assuntos
Bolsas de Estudo , Humanos , Patologistas/educação , Educação de Pós-Graduação em Medicina/métodos , Patologia/educação , Patologia Clínica/educação , Diversidade Cultural , Citodiagnóstico/métodos , Citologia
5.
J Bras Nefrol ; 46(3): e20230193, 2024.
Artigo em Inglês, Português | MEDLINE | ID: mdl-38591823

RESUMO

Chronic kidney disease (CKD) represents one of today's main public health problems. Serum creatinine measurement and estimation of the glomerular filtration rate (GFR) are the main tools for evaluating renal function. There are several equations to estimate GFR, and CKD-EPI equation (Chronic Kidney Disease - Epidemiology) is the most recommended one. There are still some controversies regarding serum creatinine measurement and GFR estimation, since several factors can interfere in this process. An important recent change was the removal of the correction for race from the equations for estimating GFR, which overestimated kidney function, and consequently delayed the implementation of treatments such as dialysis and kidney transplantation. In this consensus document from the Brazilian Societies of Nephrology and Clinical Pathology and Laboratory Medicine, the main concepts related to the assessment of renal function are reviewed, as well as possible existing controversies and recommendations for estimating GFR in clinical practice.


Assuntos
Nefrologia , Patologia Clínica , Insuficiência Renal Crônica , Humanos , Taxa de Filtração Glomerular , Creatinina , Brasil , Consenso , Diálise Renal , Insuficiência Renal Crônica/diagnóstico , Insuficiência Renal Crônica/terapia
6.
Zhonghua Bing Li Xue Za Zhi ; 53(5): 424-429, 2024 May 08.
Artigo em Chinês | MEDLINE | ID: mdl-38678321

RESUMO

With the continuous development of informatization, digitalization and artificial intelligence technology, the working mode of the pathology department has gradually changed from the traditional manual check, paper circulation and physical carrier storage to the informatization process and digital storage. The traditional pathology discipline has ushered in unprecedented opportunities and challenges. Digital pathology department also emerge as the times require. Simultaneously, with the full integration of artificial intelligence technology in pathology department, the concept of "department of digital and intelligentialized pathology" was proposed. Based on information and digital technology, the digital intelligent pathology department integrates intelligent management system, optimizes the previous cumbersome management and workflow of the pathology department, develops advanced technologies such as intelligent material extraction, unmanned organization processing, artificial intelligence quality control, artificial intelligence diagnosis, and promotes the intelligent construction of the pathology department.


Assuntos
Inteligência Artificial , Saúde Digital , Serviço Hospitalar de Patologia , Patologia Clínica , Humanos , China
7.
Front Immunol ; 15: 1358511, 2024.
Artigo em Inglês | MEDLINE | ID: mdl-38596668

RESUMO

Epstein-Barr virus (EBV) is a pathogen known to cause a number of malignancies, often taking years for them to develop after primary infection. EBV-associated gastric cancer (EBVaGC) is one such malignancy, and is an immunologically, molecularly and pathologically distinct entity from EBV-negative gastric cancer (EBVnGC). In comparison with EBVnGCs, EBVaGCs overexpress a number of immune regulatory genes to help form an immunosuppressive tumor microenvironment (TME), have improved prognosis, and overall have an "immune-hot" phenotype. This review provides an overview of the histopathology, clinical features and clinical outcomes of EBVaGCs. We also summarize the differences between the TMEs of EBVaGCs and EBVnGCs, which includes significant differences in cell composition and immune infiltration. A list of available EBVaGC and EBVnGC gene expression datasets and computational tools are also provided within this review. Finally, an overview is provided of the various chemo- and immuno-therapeutics available in treating gastric cancers (GCs), with a focus on EBVaGCs.


Assuntos
Infecções por Vírus Epstein-Barr , Patologia Clínica , Neoplasias Gástricas , Humanos , Neoplasias Gástricas/terapia , Neoplasias Gástricas/genética , Herpesvirus Humano 4/fisiologia , Prognóstico , Microambiente Tumoral
8.
J Clin Pathol ; 77(6): 366-371, 2024 May 17.
Artigo em Inglês | MEDLINE | ID: mdl-38548321

RESUMO

Digital pathology (the technology whereby glass histology slides are scanned at high resolution, digitised, stored and shared with pathologists, who can view them using microscopy software on a screen) is transforming the delivery of clinical diagnostic pathology services around the world. In addition to adding value to clinical histopathology practice, digital histology slides provide a versatile medium to achieve the educational needs of a variety of learners including undergraduate students, postgraduate doctors in training and those pursuing continuing professional development portfolios. In this guide, we will review the principal use cases for digital slides in training and education and I will share tips for successful use of digital pathology to support a range of learners based on experience gathered at Leeds Teaching Hospitals National Health Service Trust and the National Pathology Imaging Co-Operative during the last 5 years of digital slide usage.


Assuntos
Microscopia , Humanos , Patologia Clínica/educação , Telepatologia , Interpretação de Imagem Assistida por Computador
12.
Arch Pathol Lab Med ; 148(6): e111-e153, 2024 Jun 01.
Artigo em Inglês | MEDLINE | ID: mdl-38391878

RESUMO

CONTEXT.­: In 2014, the College of American Pathologists developed an evidence-based guideline to address analytic validation of immunohistochemical assays. Fourteen recommendations were offered. Per the National Academy of Medicine standards for developing trustworthy guidelines, guidelines should be updated when new evidence suggests modifications. OBJECTIVE.­: To assess evidence published since the release of the original guideline and develop updated evidence-based recommendations. DESIGN.­: The College of American Pathologists convened an expert panel to perform a systematic review of the literature and update the original guideline recommendations using the Grading of Recommendations Assessment, Development and Evaluation approach. RESULTS.­: Two strong recommendations, 1 conditional recommendation, and 12 good practice statements are offered in this updated guideline. They address analytic validation or verification of predictive and nonpredictive assays, and recommended revalidation procedures following changes in assay conditions. CONCLUSIONS.­: While many of the original guideline statements remain similar, new recommendations address analytic validation of assays with distinct scoring systems, such as programmed death receptor-1 and analytic verification of US Food and Drug Administration approved/cleared assays; more specific guidance is offered for validating immunohistochemistry performed on cytology specimens.


Assuntos
Imuno-Histoquímica , Humanos , Imuno-Histoquímica/normas , Imuno-Histoquímica/métodos , Reprodutibilidade dos Testes , Estados Unidos , Medicina Baseada em Evidências/normas , Guias de Prática Clínica como Assunto/normas , Patologia Clínica/normas , Patologia Clínica/métodos
14.
Am J Clin Pathol ; 161(6): 579-585, 2024 Jun 03.
Artigo em Inglês | MEDLINE | ID: mdl-38330196

RESUMO

OBJECTIVES: We conducted the first Irish national study assessing the value of multidisciplinary team meeting review in pathology practice and its impact on error detection before treatment. METHODS: Public and private pathology laboratories across Ireland capture their quality activities using standardized codes and submit their data to a centralized database (National Quality Assurance Intelligence System) overseen by the National Histopathology Quality Improvement (NHQI) program. A total of 1,437,746 histopathology and cytopathology cases submitted to the NHQI program over a 60-month period (January 2017 to December 2021) were included in this study. Cases were analyzed with respect to multidisciplinary team meeting peer review and the presence of a revised report (amended or corrected report), a surrogate marker for error detection before treatment. RESULTS: Across all cases assessed, 13.74% (197,587) underwent multidisciplinary team meeting discussion. Cases discussed at review had a statistically significantly higher rate of revised reports (1.25% [2470]) than cases not discussed at review (0.16% [1959]) (Pearson χ2, 6619.26; P < .0001; odds ratio, 8.00 [95% CI, 7.54-8.49]). Overall, multidisciplinary team meeting review made it 8 times more likely to detect an error before treatment. Cancer resections had the highest rate of review at 55.29% (46,806), reflecting the prioritization of oncology case discussion at review meetings. CONCLUSIONS: The multidisciplinary team meeting review process plays a valuable role in pathology error detection. A pathologist's participation in the review process comes with a clinically significant workload that needs to be recognized for future workforce planning. This study highlighted the positive role pathologists play in enhancing patient safety.


Assuntos
Equipe de Assistência ao Paciente , Melhoria de Qualidade , Humanos , Irlanda , Patologia Clínica/normas , Patologia/normas , Laboratórios Clínicos
15.
Am J Clin Pathol ; 161(6): 561-569, 2024 Jun 03.
Artigo em Inglês | MEDLINE | ID: mdl-38345305

RESUMO

OBJECTIVES: Informal payments (IPs) are unofficial cash or in-kind payments for goods or services that should be covered by the health care system. They are a common but regressive method of financing health care in low- and lower-middle-income countries (LMICs). This study aims to characterize the prevalence and impact of IPs on pathology and laboratory medicine (PALM) services. METHODS: From September 2021 to September 2022, PALM staff were surveyed about the frequency, determinants, and impacts of IPs in their respective workplaces. RESULTS: In total, 268 responses were received, and 46.6% (125/268) reported experience with IPs. These 125 participants were more likely to work in the public sector and in LMICs. Approximately 65% reported accepting IPs to perform tests or release results. Obtaining faster results was the most commonly perceived reason for patients offering IPs. Overall, participants reported that IPs had more negative than positive impacts on their workplace. CONCLUSIONS: This represents a first step in characterizing IPs within PALM and how this practice may affect access to these services in LMICs. Specifically, the fact that faster turnaround time was the most frequently perceived reason for offering IPs uncovers a potential barrier to improving PALM capacity in these regions.


Assuntos
Serviços de Laboratório Clínico , Humanos , Serviços de Laboratório Clínico/economia , Serviços de Laboratório Clínico/estatística & dados numéricos , Inquéritos e Questionários , Feminino , Masculino , Adulto , Financiamento Pessoal , Países em Desenvolvimento , Atenção à Saúde/economia , Patologia Clínica/economia , Pessoa de Meia-Idade
16.
Ann Diagn Pathol ; 70: 152284, 2024 Jun.
Artigo em Inglês | MEDLINE | ID: mdl-38422806

RESUMO

OBJECTIVES: This study aimed to evaluate the accuracy and interobserver reliability of diagnosing and subtyping gastric intestinal metaplasia (IM) among general pathologists and pathology residents at a university hospital in Thailand, focusing on the challenges in the histopathologic evaluation of gastric IM for less experienced practitioners. METHODS: The study analyzed 44 non-neoplastic gastric biopsies, using a consensus diagnosis of gastrointestinal pathologists as the reference standard. Participants included 6 general pathologists and 9 pathology residents who assessed gastric IM and categorized its subtype (complete, incomplete, or mixed) on digital slides. After initial evaluations and receiving feedback, participants reviewed specific images of gastric IM, as agreed by experts. Following a one-month washout period, a reevaluation of the slides was conducted. RESULTS: Diagnostic accuracy, interobserver reliability, and time taken for diagnosis improved following training, with general pathologists showing higher accuracies than residents (median accuracy of gastric IM detection: 100 % vs. 97.7 %). Increased years of experience were associated with more IM detection accuracy (p-value<0.05). However, the overall median accuracy for diagnosing incomplete IM remained lower than for complete IM (86.4 % vs. 97.7 %). After training, diagnostic errors occurred in 6 out of 44 specimens (13.6 %), reported by over 40 % of participants. Errors involved omitting 5 slides with incomplete IM and 1 with complete IM, all showing a subtle presence of IM. CONCLUSIONS: The study highlights the diagnostic challenges in identifying incomplete gastric IM, showing notable discrepancies in accuracy and interobserver agreement. It underscores the need for better diagnostic protocols and training to enhance detection and management outcomes.


Assuntos
Metaplasia , Variações Dependentes do Observador , Patologistas , Humanos , Metaplasia/patologia , Biópsia/métodos , Reprodutibilidade dos Testes , Internato e Residência , Estômago/patologia , Tailândia , Patologia Clínica/métodos , Patologia Clínica/educação , Feminino , Erros de Diagnóstico/estatística & dados numéricos , Erros de Diagnóstico/prevenção & controle , Neoplasias Gástricas/patologia , Neoplasias Gástricas/diagnóstico , Masculino
17.
Am J Clin Pathol ; 162(1): 7-11, 2024 Jul 05.
Artigo em Inglês | MEDLINE | ID: mdl-38387037

RESUMO

OBJECTIVES: This article describes Pathologists Overseas (PO) experience supporting external quality assessment (EQA) programs in 10 clinical laboratories across 3 countries between 2009 and 2017. METHODS: Laboratories were enrolled in the condensed chemical pathology EQA program provided by the Royal College of Pathologists of Australasia Quality Assurance Program. Participants were given an initial 2- to 4-day in-person training, followed by 1 year of active feedback on performance via emails or phone calls by a PO volunteer. RESULTS: There were 2 performance metrics: percentage of reported results as a measure of compliance and percentage of acceptable reported results as a measure of accuracy. Laboratories demonstrated high compliance with result reporting, with medians of 69.9%, 71.7%, and 81.3% before, during, and after feedback, respectively. Concomitant medians for the percentage of acceptable reported results were 41.2%, 57.3%, and 53.5%, respectively. Six laboratories had low performance in terms of accuracy at baseline (<60%). Active feedback improved the percentage of acceptable reported results for these lower-performing laboratories. CONCLUSIONS: External quality assessment programs can be successfully adopted long term by laboratories in low-resource settings. Active feedback requires significant time and effort but could be especially beneficial for laboratories with poor baseline performance.


Assuntos
Garantia da Qualidade dos Cuidados de Saúde , Humanos , Uganda , Butão , Malaui , Laboratórios Clínicos/normas , Patologistas , Patologia Clínica/normas
18.
Histopathology ; 84(5): 847-862, 2024 Apr.
Artigo em Inglês | MEDLINE | ID: mdl-38233108

RESUMO

AIMS: To conduct a definitive multicentre comparison of digital pathology (DP) with light microscopy (LM) for reporting histopathology slides including breast and bowel cancer screening samples. METHODS: A total of 2024 cases (608 breast, 607 GI, 609 skin, 200 renal) were studied, including 207 breast and 250 bowel cancer screening samples. Cases were examined by four pathologists (16 study pathologists across the four speciality groups), using both LM and DP, with the order randomly assigned and 6 weeks between viewings. Reports were compared for clinical management concordance (CMC), meaning identical diagnoses plus differences which do not affect patient management. Percentage CMCs were computed using logistic regression models with crossed random-effects terms for case and pathologist. The obtained percentage CMCs were referenced to 98.3% calculated from previous studies. RESULTS: For all cases LM versus DP comparisons showed the CMC rates were 99.95% [95% confidence interval (CI) = 99.90-99.97] and 98.96 (95% CI = 98.42-99.32) for cancer screening samples. In speciality groups CMC for LM versus DP showed: breast 99.40% (99.06-99.62) overall and 96.27% (94.63-97.43) for cancer screening samples; [gastrointestinal (GI) = 99.96% (99.89-99.99)] overall and 99.93% (99.68-99.98) for bowel cancer screening samples; skin 99.99% (99.92-100.0); renal 99.99% (99.57-100.0). Analysis of clinically significant differences revealed discrepancies in areas where interobserver variability is known to be high, in reads performed with both modalities and without apparent trends to either. CONCLUSIONS: Comparing LM and DP CMC, overall rates exceed the reference 98.3%, providing compelling evidence that pathologists provide equivalent results for both routine and cancer screening samples irrespective of the modality used.


Assuntos
Neoplasias da Mama , Neoplasias Colorretais , Patologia Clínica , Humanos , Detecção Precoce de Câncer , Interpretação de Imagem Assistida por Computador/métodos , Microscopia/métodos , Patologia Clínica/métodos , Feminino , Estudos Multicêntricos como Assunto
20.
Pathol Res Pract ; 254: 155141, 2024 Feb.
Artigo em Inglês | MEDLINE | ID: mdl-38277743

RESUMO

In recent years, the integration of Artificial Intelligence (AI) into medicine has marked a transformative shift in healthcare practices. This study explores the application of ChatGPT 3.5, an AI-based natural language processing model, in the field of pathology, with a focus on Clinical Pathology, Histopathology, and Hematology. Leveraging a dataset of 30 clinical cases from an online source, the model's performance was evaluated, revealing moderate proficiency in data analysis and decision support. While ChatGPT demonstrated strengths in swift narrative comprehension and foundational insights, limitations were observed in generating detailed and comprehensive information. The study emphasizes the evolving nature of AI in pathology, highlighting the need for ongoing refinement and collaborative efforts between AI researchers and healthcare professionals.


Assuntos
Inteligência Artificial , Patologia Clínica , Humanos
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA
...