Anthony J Guidi, Barbara J Blond, Thomas A Long, Suzanne N Coulter, Richard W Brown
{"title":"Turnaround Time for Image-Guided Breast Core Biopsies: A College of American Pathologists Survey Q-Probes Study.","authors":"Anthony J Guidi, Barbara J Blond, Thomas A Long, Suzanne N Coulter, Richard W Brown","doi":"10.5858/arpa.2024-0316-CP","DOIUrl":"https://doi.org/10.5858/arpa.2024-0316-CP","url":null,"abstract":"<p><strong>Context.—: </strong>Timely breast core biopsy results help expedite appropriate treatment for patients. Many institutions track turnaround times from biopsy to report; however, there are no established benchmarks to evaluate performance and identify potential improvement opportunities.</p><p><strong>Objective.—: </strong>To determine benchmark turnaround times for breast core biopsy reports and identify key drivers impacting turnaround time.</p><p><strong>Design.—: </strong>Participants enrolled in the College of American Pathologists Q-Probes study entitled Turnaround Time for Image-Guided Breast Needle Biopsy Specimens provided intervals for processing steps through report completion, and details regarding potential influencing variables.</p><p><strong>Results.—: </strong>Nineteen participants submitted data for 876 cases. The median turnaround time from accession to report completion was 31.0 hours, with a median time of 19.2 hours from accessioning to slide delivery to pathologists. The median time from biopsy to accessioning (3.4 hours) and slide delivery to report completion (7.5 hours) was notably shorter. Cases with malignant diagnoses were associated with longer median turnaround times than those with benign/atypical/borderline diagnoses (44.1 versus 29.4 hours; P = .04). Cases requiring additional testing or consultation were associated with longer median turnaround times than straightforward cases (45.3 versus 27.4 hours; P < .001). Fixation time variability was noted between laboratories (median, 11.0 hours; 10th and 90th percentile times: 7.1 and 31.3 hours, respectively). Variability was seen in the total processing times among laboratories (mean, 9.1 hours; range, 4.5-12.5 hours).</p><p><strong>Conclusions.—: </strong>Participating laboratories provided timely breast core biopsy results. Benchmark data presented may be useful for laboratories to assess performance and develop strategies for improvement.</p>","PeriodicalId":93883,"journal":{"name":"Archives of pathology & laboratory medicine","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143434585","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Alexander D Borowsky, Dylan V Miller, Thomas W Bauer, Richard M Feddersen, Dorina Gui, Brian J Hall, James E Albro, Isaac E Lloyd, John W Bishop, Morgan A Darrow, James H Spigel, David R Martin, Samuel J Reynolds, Thomas G McConnell, Eric F Glassy, Jonathan Zuckerman, Nathash S Kallichanda, Xiaozhi Zhou, Jenny V Lewis, Shubham Dayal, Joseph Chiweshe, Aysegul Ergin Sutcu, Michael White
{"title":"A Multicenter Study to Evaluate Diagnostic Accuracy by Pathologists Using the Aperio GT 450 DX in Local and Remote Viewing Stations.","authors":"Alexander D Borowsky, Dylan V Miller, Thomas W Bauer, Richard M Feddersen, Dorina Gui, Brian J Hall, James E Albro, Isaac E Lloyd, John W Bishop, Morgan A Darrow, James H Spigel, David R Martin, Samuel J Reynolds, Thomas G McConnell, Eric F Glassy, Jonathan Zuckerman, Nathash S Kallichanda, Xiaozhi Zhou, Jenny V Lewis, Shubham Dayal, Joseph Chiweshe, Aysegul Ergin Sutcu, Michael White","doi":"10.5858/arpa.2024-0204-OA","DOIUrl":"https://doi.org/10.5858/arpa.2024-0204-OA","url":null,"abstract":"<p><strong>Context.—: </strong>The adoption of digital pathology may enable pathologists to perform primary diagnosis in both local and remote whole slide image viewing settings, improving logistics and convenience.</p><p><strong>Objective.—: </strong>To test the performance of a new whole slide imaging system (Aperio GT 450 DX), both local intranet-based and remote internet-based viewing were compared with manual glass slide light microscopy.</p><p><strong>Design.—: </strong>A total of 1161 curated cases, enriched with difficult clinical diagnoses, were enrolled in this accuracy study and digitally scanned on 3 Aperio GT 450 DX instruments at 3 clinical sites. Ten reading pathologists across the 3 study sites viewed images either locally (directly connected to the image server) or remotely (viewed over an internet connection). Each diagnosis was scored (concordant, minor, or major discrepancy) by a separate team of 3 adjudication pathologists. The diagnostic accuracy of the Aperio GT 450 DX was tested by comparing the whole slide image review diagnosis with the conventional light microscope manual slide review diagnosis.</p><p><strong>Results.—: </strong>The difference in the major discrepancy rate between whole slide image review diagnosis and manual slide review diagnosis was 2.40% (95% CI, 1.40%-3.39%), meeting the predefined acceptance criterion of the 95% CI upper bound of 4% or less. Secondary end points were also met, including an upper bound of 7% or less and both local-only and remote-only upper-bound discrepancy rates of 4% or less. Major discrepancies were slightly lower for the remotely viewed cases (2.17%) compared with local direct server connection (2.61%), and time per read was not different.</p><p><strong>Conclusions.—: </strong>The diagnoses made using the Aperio GT 450 DX, using both local and remote access image data, are noninferior to the diagnoses made using conventional light microscopy.</p>","PeriodicalId":93883,"journal":{"name":"Archives of pathology & laboratory medicine","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143411665","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Henry D Tazelaar, Marie-Christine Aubry, Anja C Roden, Cynthia Heltne, Carolyn Mead-Harvey, Matthew J Cecchini, Donald Guinee, Jeffrey L Myers
{"title":"Twenty-Four Years' Experience With a Pulmonary Pathology Journal Club: What Have We Learned?","authors":"Henry D Tazelaar, Marie-Christine Aubry, Anja C Roden, Cynthia Heltne, Carolyn Mead-Harvey, Matthew J Cecchini, Donald Guinee, Jeffrey L Myers","doi":"10.5858/arpa.2024-0331-OA","DOIUrl":"https://doi.org/10.5858/arpa.2024-0331-OA","url":null,"abstract":"<p><strong>Context.—: </strong>A monthly pathology journal club has met for 24 years. It was established to help members stay apprised of the literature relevant to diagnostic pulmonary pathology.</p><p><strong>Objective.—: </strong>To assess whether the journal club met its goal and to report on opportunities identified for improvement.</p><p><strong>Design.—: </strong>To determine whether articles chosen for discussion as opposed to notation were more significant, Scopus citation indices for article types reviewed from January 2007 to November 2023 were compared. A survey of current faculty was undertaken to determine if the club was meeting expectations and to identify improvement opportunities.</p><p><strong>Results.—: </strong>Articles from January 2007 to November 2023 included 858 discussed and 3385 noted. Mean (SD) citation count was 103.0 (409.80) for discussion and 64.9 (259.77) for notation articles (P < .001). The citation count was noticeably right skewed, as articles with high citation counts inflated the mean. Members were mostly satisfied with the way the journal club was structured and managed. Members most valued the summary of the articles, followed by the live discussion. Opportunities for improvement included decreasing the number of journals scanned, decreasing detail in summaries, and using generative artificial intelligence (AI) to facilitate summary generation. A pilot using AI anecdotally reduced preparatory time, but the human-edited summary included more specific context, critical commentary, and enhanced take-home messages, providing a more nuanced analysis.</p><p><strong>Conclusions.—: </strong>The journal club met its initial goal. Opportunities for improvement have been identified including the use of generative AI to facilitate article summarization.</p>","PeriodicalId":93883,"journal":{"name":"Archives of pathology & laboratory medicine","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143411854","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Benjamin L Coiner, Hernán Correa, Joyce E Johnson, Jiancong Liang, Huiying Wang
{"title":"Intraoperative Evaluation of Pediatric Bone and Soft Tissue Lesions: Retrospective Analysis of 595 Frozen Sections With Emphasis on Discrepancy and Diagnostic Pitfalls.","authors":"Benjamin L Coiner, Hernán Correa, Joyce E Johnson, Jiancong Liang, Huiying Wang","doi":"10.5858/arpa.2024-0329-OA","DOIUrl":"https://doi.org/10.5858/arpa.2024-0329-OA","url":null,"abstract":"<p><strong>Context.—: </strong>Frozen section (FS) evaluation of pediatric bone and soft tissue (BST) lesions is infrequently encountered and may pose considerable diagnostic challenges. Limited data exist about the accuracy and related diagnostic difficulties.</p><p><strong>Objective.—: </strong>To identify and analyze discrepancy between the FS diagnosis and final diagnosis in order to increase the awareness of common diagnostic pitfalls in FS evaluation of pediatric BST lesions.</p><p><strong>Design.—: </strong>We retrospectively reviewed 595 consecutive FSs of pediatric BST lesions from 373 patients and analyzed the accuracy and causes for interpretation errors.</p><p><strong>Results.—: </strong>Discrepant diagnoses were found in 23 of 595 FSs (3.9%). Discrepancy rates were slightly higher in benign, soft tissue lesions and FSs requested for diagnosis/adequacy, although no statistically significant difference was observed. Pathologist misinterpretation contributed to discrepancy in 17 of 23 FSs (73.9%), which were classified into 6 patterns of error. For margin, 3 patterns were found: normal hematopoietic elements versus malignant cells in Ewing sarcoma bone marrow margin (n = 3), prominent sinonasal vasculature and stroma versus sinonasal tract angiofibroma (n = 3), and atrophic skeletal muscles versus malignant cells in rhabdomyosarcoma and Ewing sarcoma (n = 2). For diagnosis, another 3 patterns were identified: misclassification of benign bone tumors (n = 5), misclassification of benign spindle neoplasms (n = 2), and vascular malformation versus normal tissue (n = 2).</p><p><strong>Conclusions.—: </strong>FS is a valuable tool for guiding surgical management of pediatric BST lesions, which can be challenging entities and represent significant diagnostic pitfalls. Awareness of these FS pitfalls may help in further increasing diagnostic accuracy.</p>","PeriodicalId":93883,"journal":{"name":"Archives of pathology & laboratory medicine","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143191422","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Oleksandr Yanko, Andrew G Lytle, Pedro Farinha, Merrill Boyle, Graham W Slack, David W Scott, Jeffrey W Craig
{"title":"The Impact of Scoring Method on Accuracy and Reproducibility of Hans Cell-of-Origin Prediction in Excisional Biopsies of Diffuse Large B-Cell Lymphoma, Not Otherwise Specified.","authors":"Oleksandr Yanko, Andrew G Lytle, Pedro Farinha, Merrill Boyle, Graham W Slack, David W Scott, Jeffrey W Craig","doi":"10.5858/arpa.2024-0366-OA","DOIUrl":"https://doi.org/10.5858/arpa.2024-0366-OA","url":null,"abstract":"<p><strong>Context.—: </strong>Aided by tissue microarray (TMA) technology, several RNA-correlated immunohistochemistry-based algorithms have been developed for cell-of-origin (COO) prediction in diffuse large B-cell lymphoma, not otherwise specified (DLBCL-NOS). However, there is currently no empirical evidence to guide the optimal application of these algorithms to whole tissue sections (WTSs).</p><p><strong>Objective.—: </strong>To assess the impact of various scoring methods on the accuracy and reproducibility of the popular Hans algorithm.</p><p><strong>Design.—: </strong>We compared 3 different WTS-based scoring methods, designated as global, selective, and hotspot scoring, to a matched TMA evaluation and gold standard RNA analysis (Lymph2Cx; germinal center B cell n = 64; activated B cell/unclassified n = 68) using a representative series of 132 excisional biopsies of de novo DLBCL-NOS. Positivity scores (10% increments) were submitted by 3 expert lymphoma pathologists, with 30% or more defining positivity.</p><p><strong>Results.—: </strong>Sixty-eight of the 132 cases of DLBCL-NOS (52%) exhibited variation in Hans immunohistochemistry marker phenotype as a consequence of scoring method and/or interscorer discordance. Although this led to changes in Hans COO assignment in 27 of 132 cases (20%), none of the WTS-based scoring methods were statistically inferior to one another in terms of raw accuracy. Hotspot scoring yielded the lowest proportion of borderline scores (20%-40% range) for BCL6 transcription repressor (BCL6) and IRF4 transcription factor (MUM1) but negatively impacted the balance between sensitivity and specificity for these markers. Selective scoring was associated with significantly worse interscorer concordance compared to TMA evaluation, which it was designed to replicate.</p><p><strong>Conclusions.—: </strong>Overall, our data favor the use of global scoring for its noninferior accuracy, solid interscorer concordance, nonnegative influence on individual Hans markers, and current widespread use.</p>","PeriodicalId":93883,"journal":{"name":"Archives of pathology & laboratory medicine","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143082618","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Brian R Jackson, Hooman H Rashidi, Jochen K Lennerz, M E de Baca
{"title":"Ethical and Regulatory Perspectives on Generative Artificial Intelligence in Pathology.","authors":"Brian R Jackson, Hooman H Rashidi, Jochen K Lennerz, M E de Baca","doi":"10.5858/arpa.2024-0205-RA","DOIUrl":"10.5858/arpa.2024-0205-RA","url":null,"abstract":"<p><strong>Context.—: </strong>Technology companies and research groups are increasingly exploring applications of generative artificial intelligence (GenAI) in pathology and laboratory medicine. Although GenAI holds considerable promise, it also introduces novel risks for patients, communities, professionals, and the scientific process.</p><p><strong>Objective.—: </strong>To summarize the current frameworks for the ethical development and management of GenAI within health care settings.</p><p><strong>Data sources.—: </strong>The analysis draws from scientific journals, organizational websites, and recent guidelines on artificial intelligence ethics and regulation.</p><p><strong>Conclusions.—: </strong>The literature on the ethical management of artificial intelligence in medicine is extensive but is still in its nascent stages because of the evolving nature of the technology. Effective and ethical integration of GenAI requires robust processes and shared accountability among technology vendors, health care organizations, regulatory bodies, medical professionals, and professional societies. As the technology continues to develop, a multifaceted ecosystem of safety mechanisms and ethical oversight is crucial to maximize benefits and mitigate risks.</p>","PeriodicalId":93883,"journal":{"name":"Archives of pathology & laboratory medicine","volume":" ","pages":"123-129"},"PeriodicalIF":0.0,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142303214","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Dylan Wang, Hong Fang, Chi Young Ok, Jeffrey L Jorgensen, L Jeffrey Medeiros, Wei Wang, Sa A Wang
{"title":"Advancing Diagnostic Accuracy and Quality of Patient Care Through the Implementation of a Flow Cytometry Quality Assurance Program.","authors":"Dylan Wang, Hong Fang, Chi Young Ok, Jeffrey L Jorgensen, L Jeffrey Medeiros, Wei Wang, Sa A Wang","doi":"10.5858/arpa.2024-0020-OA","DOIUrl":"10.5858/arpa.2024-0020-OA","url":null,"abstract":"<p><strong>Context.—: </strong>Flow cytometry immunophenotypic analysis plays an important role in the diagnosis, classification, and disease monitoring of hematologic neoplasms. The interpretation of flow cytometry testing can be challenging.</p><p><strong>Objective.—: </strong>To explore ways to improve diagnostic accuracy and in turn enhance the quality of patient care.</p><p><strong>Design.—: </strong>A flow cytometry quality assurance (QA) program was developed. Cases from various complex flow cytometry panels were randomly selected and cross-reviewed. The outcomes of the QA review were categorized into 3 groups: complete agreement, minor discrepancy, and major discrepancy. Each discrepancy underwent a process of documentation, discussion, and resolution. Here we summarize our 3 years of experience with this program.</p><p><strong>Results.—: </strong>In total, 6166 cases were evaluated; 6028 cases (97.7%) showed complete concordance, 120 cases (2.0%) showed minor discrepancies, and 18 cases (0.3%) showed major discrepancies. Among the top 5 panels evaluated, the panel evaluating mature T-cell abnormalities showed the highest rate of discrepancy, whereas the panel for evaluation of myelodysplastic syndromes showed the lowest discrepancy rate. When analyzing the trends of concordance and discrepancy over time, we observed a statistically significant decrease in discrepancy rate over time, from 4% at the beginning of the 6-month period to 1.5% in the final 6-month period.</p><p><strong>Conclusions.—: </strong>The overall concordance rate was 97.7%. The remaining 2.3% of cases showed discrepancies that required a correction, underscoring the value and necessity of having a QA program. The overall discrepancy rates exhibited a gradual decline over time, indicative of the positive impact of the QA program on enhancing diagnostic competency and accuracy over time.</p>","PeriodicalId":93883,"journal":{"name":"Archives of pathology & laboratory medicine","volume":" ","pages":"e26-e30"},"PeriodicalIF":0.0,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141319252","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Matthew J Cecchini, Michael J Borowitz, Eric F Glassy, Rama R Gullapalli, Steven N Hart, Lewis A Hassell, Robert J Homer, Ronald Jackups, Jeffrey L McNeal, Scott R Anderson
{"title":"Harnessing the Power of Generative Artificial Intelligence in Pathology Education: Opportunities, Challenges, and Future Directions.","authors":"Matthew J Cecchini, Michael J Borowitz, Eric F Glassy, Rama R Gullapalli, Steven N Hart, Lewis A Hassell, Robert J Homer, Ronald Jackups, Jeffrey L McNeal, Scott R Anderson","doi":"10.5858/arpa.2024-0187-RA","DOIUrl":"10.5858/arpa.2024-0187-RA","url":null,"abstract":"<p><strong>Context.—: </strong>Generative artificial intelligence (AI) technologies are rapidly transforming numerous fields, including pathology, and hold significant potential to revolutionize educational approaches.</p><p><strong>Objective.—: </strong>To explore the application of generative AI, particularly large language models and multimodal tools, for enhancing pathology education. We describe their potential to create personalized learning experiences, streamline content development, expand access to educational resources, and support both learners and educators throughout the training and practice continuum.</p><p><strong>Data sources.—: </strong>We draw on insights from existing literature on AI in education and the collective expertise of the coauthors within this rapidly evolving field. Case studies highlight practical applications of large language models, demonstrating both the potential benefits and unique challenges associated with implementing these technologies in pathology education.</p><p><strong>Conclusions.—: </strong>Generative AI presents a powerful tool kit for enriching pathology education, offering opportunities for greater engagement, accessibility, and personalization. Careful consideration of ethical implications, potential risks, and appropriate mitigation strategies is essential for the responsible and effective integration of these technologies. Future success lies in fostering collaborative development between AI experts and medical educators, prioritizing ongoing human oversight and transparency to ensure that generative AI augments, rather than supplants, the vital role of educators in pathology training and practice.</p>","PeriodicalId":93883,"journal":{"name":"Archives of pathology & laboratory medicine","volume":" ","pages":"142-151"},"PeriodicalIF":0.0,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142334228","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Peter McCaffrey, Ronald Jackups, Jansen Seheult, Mark A Zaydman, Ulysses Balis, Harshwardhan M Thaker, Hooman Rashidi, Rama R Gullapalli
{"title":"Evaluating Use of Generative Artificial Intelligence in Clinical Pathology Practice: Opportunities and the Way Forward.","authors":"Peter McCaffrey, Ronald Jackups, Jansen Seheult, Mark A Zaydman, Ulysses Balis, Harshwardhan M Thaker, Hooman Rashidi, Rama R Gullapalli","doi":"10.5858/arpa.2024-0208-RA","DOIUrl":"10.5858/arpa.2024-0208-RA","url":null,"abstract":"<p><strong>Context.—: </strong>Generative artificial intelligence (GAI) technologies are likely to dramatically impact health care workflows in clinical pathology (CP). Applications in CP include education, data mining, decision support, result summaries, and patient trend assessments.</p><p><strong>Objective.—: </strong>To review use cases of GAI in CP, with a particular focus on large language models. Specific examples are provided for the applications of GAI in the subspecialties of clinical chemistry, microbiology, hematopathology, and molecular diagnostics. Additionally, the review addresses potential pitfalls of GAI paradigms.</p><p><strong>Data sources.—: </strong>Current literature on GAI in health care was reviewed broadly. The use case scenarios for each CP subspecialty review common data sources generated in each subspecialty. The potential for utilization of CP data in the GAI context was subsequently assessed, focusing on issues such as future reporting paradigms, impact on quality metrics, and potential for translational research activities.</p><p><strong>Conclusions.—: </strong>GAI is a powerful tool with the potential to revolutionize health care for patients and practitioners alike. However, GAI must be implemented with much caution considering various shortcomings of the technology such as biases, hallucinations, practical challenges of implementing GAI in existing CP workflows, and end-user acceptance. Human-in-the-loop models of GAI implementation have the potential to revolutionize CP by delivering deeper, meaningful insights into patient outcomes both at an individual and a population level.</p>","PeriodicalId":93883,"journal":{"name":"Archives of pathology & laboratory medicine","volume":" ","pages":"130-141"},"PeriodicalIF":0.0,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142395873","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Rajendra Singh, Ji Yeon Kim, Eric F Glassy, Rajesh C Dash, Victor Brodsky, Jansen Seheult, M E de Baca, Qiangqiang Gu, Shannon Hoekstra, Bobbi S Pritt
{"title":"Introduction to Generative Artificial Intelligence: Contextualizing the Future.","authors":"Rajendra Singh, Ji Yeon Kim, Eric F Glassy, Rajesh C Dash, Victor Brodsky, Jansen Seheult, M E de Baca, Qiangqiang Gu, Shannon Hoekstra, Bobbi S Pritt","doi":"10.5858/arpa.2024-0221-RA","DOIUrl":"10.5858/arpa.2024-0221-RA","url":null,"abstract":"<p><strong>Context.—: </strong>Generative artificial intelligence (GAI) is a promising new technology with the potential to transform communication and workflows in health care and pathology. Although new technologies offer advantages, they also come with risks that users, particularly early adopters, must recognize. Given the fast pace of GAI developments, pathologists may find it challenging to stay current with the terminology, technical underpinnings, and latest advancements. Building this knowledge base will enable pathologists to grasp the potential risks and impacts that GAI may have on the future practice of pathology.</p><p><strong>Objective.—: </strong>To present key elements of GAI development, evaluation, and implementation in a way that is accessible to pathologists and relevant to laboratory applications.</p><p><strong>Data sources.—: </strong>Information was gathered from recent studies and reviews from PubMed and arXiv.</p><p><strong>Conclusions.—: </strong>GAI offers many potential benefits for practicing pathologists. However, the use of GAI in clinical practice requires rigorous oversight and continuous refinement to fully realize its potential and mitigate inherent risks. The performance of GAI is highly dependent on the quality and diversity of the training and fine-tuning data, which can also propagate biases if not carefully managed. Ethical concerns, particularly regarding patient privacy and autonomy, must be addressed to ensure responsible use. By harnessing these emergent technologies, pathologists will be well placed to continue forward as leaders in diagnostic medicine.</p>","PeriodicalId":93883,"journal":{"name":"Archives of pathology & laboratory medicine","volume":" ","pages":"112-122"},"PeriodicalIF":0.0,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142781258","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}