Search

* Context.-Machine learning applications in the pathology clinical domain are emerging rapidly. As decision support systems continue to mature, laboratories will increasingly need guidance to evaluate their performance in clinical practice. Currently there are no formal guidelines to assist pathology laboratories in verification and/or validation of such systems. These recommendations are being proposed for the evaluation of machine learning systems in the clinical practice of pathology. Objective.-To propose recommendations for performance evaluation of in vitro diagnostic tests on patient samples that incorporate machine learning as part of the pre-analytical, analytical, or post-analytical phases of the laboratory workflow. Topics described include considerations for machine learning model evaluation including risk assessment, predeployment requirements, data sourcing and curation, verification and validation, change control management, human-computer interaction, practitioner training, and competency evaluation. Data Sources.-An expert panel performed a review of the literature, Clinical and Laboratory Standards Institute guidance, and laboratory and government regulatory frameworks. Conclusions.-Review of the literature and existing documents enabled the development of proposed recommendations. This white paper pertains to performance evaluation of machine learning systems intended to be implemented for clinical patient testing. Further studies with real-world clinical data are encouraged to support these proposed recommendations. Performance evaluation of machine learning models is critical to verification and/or validation of in vitro diagnostic tests using machine learning intended for clinical practice. (Arch Pathol Lab Med. 2024;148:e335-e361; doi: 10.5858/arpa.2023-0042-CP), Institution of machine learning (ML) in the pathology clinical domain has gained momentum and is rapidly advancing. As ML-based clinical decision support (CDS) systems continue to mature, laboratories will increasingly [...]

Abstract Hepatocellular carcinoma (HCC) remains a significant global health challenge with few effective treatment options. The dysregulation of endoplasmic reticulum (ER) stress responses has emerged as a pivotal factor in HCC progression and therapy resistance. Long non-coding RNAs (lncRNAs) play a crucial role as key epigenetic modifiers in this process. Recent research has explored how lncRNAs influence ER stress which in turn affects lncRNAs activity in HCC. We systematically analyze the current literature to highlight the regulatory roles of lncRNAs in modulating ER stress and vice versa in HCC. Our scrutinization highlights how dysregulated lncRNAs contribute to various facets of HCC, including apoptosis resistance, enhanced proliferation, invasion, and metastasis, all driven by ER stress. Moreover, we delve into the emerging paradigm of the lncRNA-miRNA-mRNA axis, elucidating it as the promising avenue for developing novel biomarkers and paving the way for more personalized treatment options in HCC. Nevertheless, we acknowledge the challenges and future directions in translating these insights into clinical practice. In conclusion, our review provides insights into the complex regulatory mechanisms governing ER stress modulation by lncRNAs in HCC.

The aim of this qualitative study was to explore desired ways to deliver comprehensive sexuality education (CSE) and topics, among secondary school students in a low-resource setting in Western Kenya. One school (n = 440) has received 8-9-h CSE intervention, while the other school (n = 496) served as a control. After one-year follow-up the students were asked (one open-ended question) to suggest desired topics of CSE, with a response rate of 93% (n = 867). The following topics were suggested by the students: abortion, contraception, sexual rights, abstinence and STI/HIV, and preferred CSE delivery means were school-based teaching, online resources and social media, community-based elements or trusted individuals. The students who had not received the intervention were more in favor of an abstinence-only approach and demonstrated more negative attitudes toward abortion.

PURPOSE: To characterize the recovery of diagnostic cardiovascular procedure volumes in U.S. and non-U.S. facilities in the year following the initial COVID-19 outbreak. MATERIALS AND METHODS: The International Atomic Energy Agency (IAEA) coordinated a worldwide study called the IAEA Noninvasive Cardiology Protocols Study of COVID-19 2 (INCAPS COVID 2), collecting data from 669 facilities in 107 countries, including 93 facilities in 34 U.S. states, to determine the impact of the pandemic on diagnostic cardiovascular procedure volumes. Participants reported volumes for each diagnostic imaging modality used at their facility for March 2019 (baseline), April 2020, and April 2021. This secondary analysis of INCAPS COVID 2 evaluated differences in changes in procedure volume between U.S. and non-U.S. facilities and among U.S. regions. Factors associated with return to prepandemic volumes in the United States were also analyzed in a multivariable regression analysis. RESULTS: Reduction in procedure volumes in April 2020 compared with baseline was similar for U.S. and non-U.S. facilities (-66% vs -71%, P = .27). U.S. facilities reported greater return to baseline in April 2021 than did all non-U.S. facilities (4% vs -6%, P = .008), but there was no evidence of a difference when comparing U.S. facilities with non-U.S. high-income country (NUHIC) facilities (4% vs 0%, P = .18). U.S. regional differences in return to baseline were observed between the Midwest (11%), Northeast (9%), South (1%), and West (-7%, P = .03), but no studied factors were significant predictors of 2021 change from prepandemic baseline. CONCLUSION: The reductions in cardiac testing during the early pandemic have recovered within a year to prepandemic baselines in the United States and NUHICs, while procedure volumes remain depressed in lower-income countries.Keywords: SPECT, Cardiac, Epidemiology, Angiography, CT Angiography, CT, Echocardiography, SPECT/CT, MR Imaging, Radionuclide Studies, COVID-19, Cardiovascular Imaging, Diagnostic Cardiovascular Procedure, Cardiovascular Disease, Cardiac Testing Supplemental material is available for this article. © RSNA, 2023.

BackgroundIntra-atrial shunts are associated with an elevated risk of embolic stroke of undetermined source (ESUS). Percutaneous occluder implantation is recommended as secondary prevention in younger patients. This study aims to compare the outcome after shunt occlusion between younger and older patients with a history of presumed paradox embolism and to evaluate the impact of high-volume shunting in an elderly population.MethodsWe conducted a single-center, retrospective, observational study, involving 187 patients who underwent interventional percutaneous PFO or ASD occlusion at our center between 2013 and 2023.ResultsThe mean age of participants was 51.8 ± 11.8 years, with 76 patients aged ≤50 years and 111 patients aged >50 years. Older patients presented more cardiovascular risk factors. The presence of atrial septum aneurysm or large shunting was evenly distributed (ASA 26.3% vs. 28.8%, p = 0.833, mean shunt defect size 6.67 vs. 7.23 mm, p = 0.151). There were no significant differences in procedural or intrahospital complications. The event rate during the 6-month follow-up was low. Recurrence of arterial embolism occurred in 1.6% of the younger and 3.8% of the older patients (p = 0.817). Comparison of high-volume shunts (defect size ≥10 mm or passage ≥20 bubbles during bubble study) with low-volume shunts in this elderly cohort with a mean age ≥50 years showed no significant difference in outcomes. There was a statistically non-significant trend toward a higher rate of residual shunt at the end of the procedure in the high-volume shunt group (2.9% vs. 9.8%, p = 0.0894). This difference was not observed at the 6-month follow-up anymore (14.5 vs. 12.1%, p = 0.628). Two unsuccessful implantation attempts were reported in the high-volume shunt group, while none were observed in the low-volume shunt group (p = 0.372). No intervention-related deaths occurred in this patient cohort during follow-up.ConclusionOcclusion of relevant, intra-atrial shunting is a safe and effective option for secondary prevention of cryptogenic embolism in patients over 50 years of age. The beneficial outcome was irrespective of a high-volume shunting before implantation.

This study aimed to systematically evaluate and quantify the risk of adverse maternal and neonatal outcomes in patients with pregnancy-associated cancer (PAC). This study was conducted from February 13, 2021, through July 24, 2023. A systematic search of MEDLINE, Embase, Web of Science Core Collection, Cochrane Database of Systematic Reviews, and Cochrane Central Register of Controlled Trials was conducted to identify studies reporting outcomes for patients with PAC. The study was registered on PROSPERO. Two reviewers independently conducted screening, data extraction, and quality assessment. The associations were quantified using random-effects meta-analysis. The initial search produced 29,401 titles and abstracts, after which 147 unique full-text articles were screened, of which 22 articles with 59,190 pregnancies with PAC from 70,097,167 births were included in the meta-analysis. Women with PAC were at significantly increased risk of cesarean deliveries (risk ratio [RR], 1.58; 95% CI, 1.31-1.89), preterm birth (RR, 3.07; 95% CI, 2.37-3.98), venous thromboembolism (RR, 6.76; 95% CI, 5.08-8.99), and maternal death (RR, 41.58; 95% CI, 20.38-84.83). The only outcome with reduced risk was instrumental mode of delivery (RR, 0.67; 95% CI, 0.52-0.87). Pregnancy-associated cancer increases risk of adverse outcomes, including a 7-fold risk of venous thromboembolism and a 42-fold risk of maternal death. Further research is required to better understand the mechanisms leading to these adverse outcomes, especially for women who are not diagnosed until the postpartum period. Affected women should have counseling regarding their increased risk of adverse outcomes.

BackgroundPercutaneous interventional left atrial appendage occlusion (LAAO) is a reliable, safe, and effective alternative for stroke prevention in selected patients with atrial fibrillation (AF).MethodsIn a retrospective observational study, 149 patients underwent LAAO between 2016 and 2022 at the Department of Cardiology of the Charité—Universitätsmedizin Berlin, Campus Virchow, with AF for prevention of thromboembolic complications. We compared patient characteristics, intraoperative details and postoperative outcomes between single-occlusive plug-type (SOPT) and dual-occlusive disc-type (DODT) devices.ResultsIn all patients, the device implantation was successful. 60 patients received a SOPT occluder, including Watchman (35%) and Watchman FLX Occluders (65%), while 89 patients received a DODT occluder, including Amplatzer Cardiac Plug (37.1%), the Amplatzer Amulet (25.8%), and the LAmbre occluder (37.1%) systems. Procedure duration was significantly longer for DODT occluder implantation (49 ± 33 vs. 41 ± 25 min, p = 0.018). There were no in-hospital deaths or thromboembolic events reported after LAAO in both groups. Beyond that, a low rate of bleeding or access-side-related complications and pericardial tamponades were observed. Anticoagulation at discharge varied. About 60.8% of patients received dual antiplatelet therapy at hospital discharge, and 33.1% received direct oral anticoagulants. A 6-month follow-up was obtained in 85% of the patients. All implanted devices were in the desired position. However, in 5.7% of the patients, a device-related thrombus formation was detected in the SOPT group, while no thrombus was seen in the DODT group (p = 0.11). Thromboembolic events were noticed in 3.1%, without any difference between the device types. There was a statistically non-significant trend for less residual device leaks after SOPT vs. DODT implantation (no leak in 71.7% vs. 62.2%, p = 0.07; minor leaks

Background: The American Heart Association's (AHA) Life's Essential 8 (LE8) score is a helpful tool to quantify cardiovascular health (CVH) metrics. We sought to assess sex differences in relation to LE8 and its components along with association with mortality. Methods: The National Health and Nutrition Examination Survey (NHANES) between 2009 and 2018 was utilized to evaluate the prevalence of health metrics included in LE8 among adult participants > age 18, stratified by sex. We categorized overall CVH, health factors, and health behaviors into 3 levels (low:

* Context.--Increasing implementation of whole slide imaging together with digital workflow and advances in computing capacity enable the use of artificial intelligence (AI) in pathology, including breast pathology. Breast pathologists often face a significant workload, with diagnosis complexity, tedious repetitive tasks, and semi-quantitative evaluation of biomarkers. Recent advances in developing AI algorithms have provided promising approaches to meet the demand in breast pathology. Objective.--To provide an updated review of AI in breast pathology. We examined the success and challenges of current and potential AI applications in diagnosing and grading breast carcinomas and other pathologic changes, detecting lymph node metastasis, quantifying breast cancer biomarkers, predicting prognosis and therapy response, and predicting potential molecular changes. Data Sources.--We obtained data and information by searching and reviewing literature on AI in breast pathology from PubMed and based our own experience. Conclusions.--With the increasing application in breast pathology, AI not only assists in pathology diagnosis to improve accuracy and reduce pathologists' workload, but also provides new information in predicting prognosis and therapy response., Pathology is the gold standard for disease diagnosis. Pathologists are committed to assisting clinicians in the precise treatment of various diseases, especially malignant tumors. The advance in individualized treatment requires [...]

Abstract This review discusses the profound impact of artificial intelligence (AI) on breast cancer (BC) diagnosis and management within the field of pathology. It examines the various applications of AI across diverse aspects of BC pathology, highlighting key findings from multiple studies. Integrating AI into routine pathology practice stands to improve diagnostic accuracy, thereby contributing to reducing avoidable errors. Additionally, AI has excelled in identifying invasive breast tumors and lymph node metastasis through its capacity to process large whole-slide images adeptly. Adaptive sampling techniques and powerful convolutional neural networks mark these achievements. The evaluation of hormonal status, which is imperative for BC treatment choices, has also been enhanced by AI quantitative analysis, aiding interobserver concordance and reliability. Breast cancer grading and mitotic count evaluation also benefit from AI intervention. AI-based frameworks effectively classify breast carcinomas, even for moderately graded cases that traditional methods struggle with. Moreover, AI-assisted mitotic figures quantification surpasses manual counting in precision and sensitivity, fostering improved prognosis. The assessment of tumor-infiltrating lymphocytes in triple-negative breast cancer using AI yields insights into patient survival prognosis. Furthermore, AI-powered predictions of neoadjuvant chemotherapy response demonstrate potential for streamlining treatment strategies. Addressing limitations, such as preanalytical variables, annotation demands, and differentiation challenges, is pivotal for realizing AI’s full potential in BC pathology. Despite the existing hurdles, AI’s multifaceted contributions to BC pathology hold great promise, providing enhanced accuracy, efficiency, and standardization. Continued research and innovation are crucial for overcoming obstacles and fully harnessing AI’s transformative capabilities in breast cancer diagnosis and assessment. Graphical Abstract

Abstract Background The integration of large language models (LLMs) like ChatGPT in diagnostic medicine, with a focus on digital pathology, has garnered significant attention. However, understanding the challenges and barriers associated with the use of LLMs in this context is crucial for their successful implementation. Methods A scoping review was conducted to explore the challenges and barriers of using LLMs, in diagnostic medicine with a focus on digital pathology. A comprehensive search was conducted using electronic databases, including PubMed and Google Scholar, for relevant articles published within the past four years. The selected articles were critically analyzed to identify and summarize the challenges and barriers reported in the literature. Results The scoping review identified several challenges and barriers associated with the use of LLMs in diagnostic medicine. These included limitations in contextual understanding and interpretability, biases in training data, ethical considerations, impact on healthcare professionals, and regulatory concerns. Contextual understanding and interpretability challenges arise due to the lack of true understanding of medical concepts and lack of these models being explicitly trained on medical records selected by trained professionals, and the black-box nature of LLMs. Biases in training data pose a risk of perpetuating disparities and inaccuracies in diagnoses. Ethical considerations include patient privacy, data security, and responsible AI use. The integration of LLMs may impact healthcare professionals’ autonomy and decision-making abilities. Regulatory concerns surround the need for guidelines and frameworks to ensure safe and ethical implementation. Conclusion The scoping review highlights the challenges and barriers of using LLMs in diagnostic medicine with a focus on digital pathology. Understanding these challenges is essential for addressing the limitations and developing strategies to overcome barriers. It is critical for health professionals to be involved in the selection of data and fine tuning of the models. Further research, validation, and collaboration between AI developers, healthcare professionals, and regulatory bodies are necessary to ensure the responsible and effective integration of LLMs in diagnostic medicine.

Coronary dominance describes the anatomic variation of coronary arterial supply, notably as it relates to perfusion of the inferior cardiac territories. Differences in the development and outcome in select disease states between coronary dominance patterns are increasingly recognized. In particular, observational studies have identified higher prevalence of poor outcomes in left coronary dominance in the setting of ischemic, conduction, and valvular disease. In this qualitative literature review, we summarize anatomic, physiologic, and clinical implications of differences in coronary dominance to highlight current understanding and gaps in the literature that should warrant further studies.

Abstract Digital pathology (DP) is being increasingly employed in cancer diagnostics, providing additional tools for faster, higher-quality, accurate diagnosis. The practice of diagnostic pathology has gone through a staggering transformation wherein new tools such as digital imaging, advanced artificial intelligence (AI) algorithms, and computer-aided diagnostic techniques are being used for assisting, augmenting and empowering the computational histopathology and AI-enabled diagnostics. This is paving the way for advancement in precision medicine in cancer. Automated whole slide imaging (WSI) scanners are now rendering diagnostic quality, high-resolution images of entire glass slides and combining these images with innovative digital pathology tools is making it possible to integrate imaging into all aspects of pathology reporting including anatomical, clinical, and molecular pathology. The recent approvals of WSI scanners for primary diagnosis by the FDA as well as the approval of prostate AI algorithm has paved the way for starting to incorporate this exciting technology for use in primary diagnosis. AI tools can provide a unique platform for innovations and advances in anatomical and clinical pathology workflows. In this review, we describe the milestones and landmark trials in the use of AI in clinical pathology with emphasis on future directions.