Medical Visual Question Answering (MedVQA) enhances diagnostic accuracy and healthcare delivery by leveraging artificial intelligence to interpret medical images. This study aims to redefine MedVQA as a generation task that mirrors human–machine interaction and to develop a model capable of integrating complex visual and textual information. We constructed a large-scale medical visual-question answering dataset, PMC-VQA, containing 227,000 VQA pairs across 149,000 images that span various modalities and diseases. We introduced a generative model that aligns visual information from a pre-trained vision encoder with a large language model. This model was initially trained on PMC-VQA and subsequently fine-tuned on multiple public benchmarks. Here, we show that our model significantly outperforms existing MedVQA models in generating relevant, accurate free-form answers. We also propose a manually verified test set that presents a greater challenge and serves as a robust measure to monitor the advancement of generative MedVQA methods. The PMC-VQA dataset proves to be an essential resource for the research community, and our model marks a significant breakthrough in MedVQA. We maintain a leaderboard to facilitate comprehensive evaluation and comparison, providing a centralized resource for benchmarking state-of-the-art approaches. Medical images play a crucial role in healthcare, but interpreting them accurately can be challenging. This study developed an artificial intelligence system that can answer questions about medical images, similar to how a medical expert would explain findings to patients. We created a large collection of medical images paired with questions and answers to train our AI system, covering various types of medical scans and conditions. Our system can generate detailed, accurate responses to questions about medical images, performing better than existing approaches. The system and dataset we developed are freely available to researchers, which should help advance the field of medical image interpretation and ultimately improve healthcare delivery. Zhang et al. investigate how the large body of publicly available images from the biomedical domain can be used to generate a new medical visual question-answering dataset. Along with the resulting benchmark dataset, the authors propose a novel visual-language model and compare its performance against existing approaches.
{"title":"Development of a large-scale medical visual question-answering dataset","authors":"Xiaoman Zhang, Chaoyi Wu, Ziheng Zhao, Weixiong Lin, Ya Zhang, Yanfeng Wang, Weidi Xie","doi":"10.1038/s43856-024-00709-2","DOIUrl":"10.1038/s43856-024-00709-2","url":null,"abstract":"Medical Visual Question Answering (MedVQA) enhances diagnostic accuracy and healthcare delivery by leveraging artificial intelligence to interpret medical images. This study aims to redefine MedVQA as a generation task that mirrors human–machine interaction and to develop a model capable of integrating complex visual and textual information. We constructed a large-scale medical visual-question answering dataset, PMC-VQA, containing 227,000 VQA pairs across 149,000 images that span various modalities and diseases. We introduced a generative model that aligns visual information from a pre-trained vision encoder with a large language model. This model was initially trained on PMC-VQA and subsequently fine-tuned on multiple public benchmarks. Here, we show that our model significantly outperforms existing MedVQA models in generating relevant, accurate free-form answers. We also propose a manually verified test set that presents a greater challenge and serves as a robust measure to monitor the advancement of generative MedVQA methods. The PMC-VQA dataset proves to be an essential resource for the research community, and our model marks a significant breakthrough in MedVQA. We maintain a leaderboard to facilitate comprehensive evaluation and comparison, providing a centralized resource for benchmarking state-of-the-art approaches. Medical images play a crucial role in healthcare, but interpreting them accurately can be challenging. This study developed an artificial intelligence system that can answer questions about medical images, similar to how a medical expert would explain findings to patients. We created a large collection of medical images paired with questions and answers to train our AI system, covering various types of medical scans and conditions. Our system can generate detailed, accurate responses to questions about medical images, performing better than existing approaches. The system and dataset we developed are freely available to researchers, which should help advance the field of medical image interpretation and ultimately improve healthcare delivery. Zhang et al. investigate how the large body of publicly available images from the biomedical domain can be used to generate a new medical visual question-answering dataset. Along with the resulting benchmark dataset, the authors propose a novel visual-language model and compare its performance against existing approaches.","PeriodicalId":72646,"journal":{"name":"Communications medicine","volume":" ","pages":"1-13"},"PeriodicalIF":5.4,"publicationDate":"2024-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s43856-024-00709-2.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142862451","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-20DOI: 10.1038/s43856-024-00697-3
Ngozi F. Anachebe, Leila Amiri, Kristen Goodell, Demondes Haynes, Remo Panaccione, Aaron Saguil, Carol A. Terregino, Mike Woodson, Kenneth Royal
There has been considerable discussion of how best to address racial and ethnic disparities in health outcomes, both globally and specifically in the United States. Increasing diversity among future clinicians and physician-scientists has been identified as a key strategy for addressing and correcting health disparities among underrepresented populations. Increasingly, medical schools, the institutions that train clinicians, have embraced the practice of holistic review for evaluating applicants and virtually all medical schools have reported contributing to a diverse physician workforce as an important aspect of their educational mission. Yet despite these goals and practices, relatively little progress has been made in diversifying the workforce and achieving equitable health outcomes. Here we present a framework for centering equity in medical school admissions that focuses on equity-based recruiting, admissions standards, selection and support and present a number of promising examples and universally applicable strategies that medical schools can potentially implement given their unique missions, goals, priorities, and resources. Anachebe et al. discuss how to center equity in medical school admissions by presenting an equity-based framework that focuses on recruiting, standards, selection and support. Their recommended strategies are universally applicable across training programs and are accompanied by a number of promising examples.
{"title":"Approaches to ensure an equitable and fair admissions process for medical training","authors":"Ngozi F. Anachebe, Leila Amiri, Kristen Goodell, Demondes Haynes, Remo Panaccione, Aaron Saguil, Carol A. Terregino, Mike Woodson, Kenneth Royal","doi":"10.1038/s43856-024-00697-3","DOIUrl":"10.1038/s43856-024-00697-3","url":null,"abstract":"There has been considerable discussion of how best to address racial and ethnic disparities in health outcomes, both globally and specifically in the United States. Increasing diversity among future clinicians and physician-scientists has been identified as a key strategy for addressing and correcting health disparities among underrepresented populations. Increasingly, medical schools, the institutions that train clinicians, have embraced the practice of holistic review for evaluating applicants and virtually all medical schools have reported contributing to a diverse physician workforce as an important aspect of their educational mission. Yet despite these goals and practices, relatively little progress has been made in diversifying the workforce and achieving equitable health outcomes. Here we present a framework for centering equity in medical school admissions that focuses on equity-based recruiting, admissions standards, selection and support and present a number of promising examples and universally applicable strategies that medical schools can potentially implement given their unique missions, goals, priorities, and resources. Anachebe et al. discuss how to center equity in medical school admissions by presenting an equity-based framework that focuses on recruiting, standards, selection and support. Their recommended strategies are universally applicable across training programs and are accompanied by a number of promising examples.","PeriodicalId":72646,"journal":{"name":"Communications medicine","volume":" ","pages":"1-5"},"PeriodicalIF":5.4,"publicationDate":"2024-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s43856-024-00697-3.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142862474","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-20DOI: 10.1038/s43856-024-00695-5
Gil Shamai, Ran Schley, Alexandra Cretu, Tal Neoran, Edmond Sabo, Yoav Binenbaum, Shachar Cohen, Tal Goldman, António Polónia, Keren Drumea, Karin Stoliar, Ron Kimmel
Molecular profiling of estrogen receptor (ER), progesterone receptor (PR), and ERBB2 (also known as Her2) is essential for breast cancer diagnosis and treatment planning. Nevertheless, current methods rely on the qualitative interpretation of immunohistochemistry and fluorescence in situ hybridization (FISH), which can be costly, time-consuming, and inconsistent. Here we explore the clinical utility of predicting receptor status from digitized hematoxylin and eosin-stained (H&E) slides using machine learning trained and evaluated on a multi-institutional dataset. We developed a deep learning system to predict ER, PR, and ERBB2 statuses from digitized H&E slides and evaluated its utility in three clinical applications: identifying hormone receptor-positive patients, serving as a second-read tool for quality assurance, and addressing intratumor heterogeneity. For development and validation, we collected 19,845 slides from 7,950 patients across six independent cohorts representative of diverse clinical settings. Here we show that the system identifies 30.5% of patients as hormone receptor-positive, achieving a specificity of 0.9982 and a positive predictive value of 0.9992, demonstrating its ability to determine eligibility for hormone therapy without immunohistochemistry. By restaining and reassessing samples flagged as potential false negatives, we discover 31 cases of misdiagnosed ER, PR, and ERBB2 statuses. These findings demonstrate the utility of the system in diverse clinical settings and its potential to improve breast cancer diagnosis. Given the substantial focus of current guidelines on reducing false negative diagnoses, this study supports the integration of H&E-based machine learning tools into workflows for quality assurance. Breast cancer diagnosis involves identifying three important proteins: estrogen receptor (ER), progesterone receptor (PR), and ERBB2. Profiling these proteins helps oncologists determine which treatments are most likely to benefit patients. However, current testing methods can be expensive, time-consuming, and sometimes inaccurate. This study introduces and validates an artificial intelligence system that predicts the presence of these proteins using routine tissue slides. The system is tested on data from multiple medical centers and accurately identifies patients with ER and PR proteins who could benefit from hormone therapy. It also detects cases where the original diagnosis was incorrect. This tool may improve diagnostic accuracy, reduce errors, and enhance the efficiency of breast cancer care by integrating artificial intelligence into clinical workflows. Shamai et al. develop and validate a deep learning system for predicting receptor status from H&E images in breast cancer. The system accurately identifies hormone receptor-positive patients and detects false negative diagnoses, supporting its integration into clinical workflows to improve diagnostic accuracy, patient care, and quality assuran
{"title":"Clinical utility of receptor status prediction in breast cancer and misdiagnosis identification using deep learning on hematoxylin and eosin-stained slides","authors":"Gil Shamai, Ran Schley, Alexandra Cretu, Tal Neoran, Edmond Sabo, Yoav Binenbaum, Shachar Cohen, Tal Goldman, António Polónia, Keren Drumea, Karin Stoliar, Ron Kimmel","doi":"10.1038/s43856-024-00695-5","DOIUrl":"10.1038/s43856-024-00695-5","url":null,"abstract":"Molecular profiling of estrogen receptor (ER), progesterone receptor (PR), and ERBB2 (also known as Her2) is essential for breast cancer diagnosis and treatment planning. Nevertheless, current methods rely on the qualitative interpretation of immunohistochemistry and fluorescence in situ hybridization (FISH), which can be costly, time-consuming, and inconsistent. Here we explore the clinical utility of predicting receptor status from digitized hematoxylin and eosin-stained (H&E) slides using machine learning trained and evaluated on a multi-institutional dataset. We developed a deep learning system to predict ER, PR, and ERBB2 statuses from digitized H&E slides and evaluated its utility in three clinical applications: identifying hormone receptor-positive patients, serving as a second-read tool for quality assurance, and addressing intratumor heterogeneity. For development and validation, we collected 19,845 slides from 7,950 patients across six independent cohorts representative of diverse clinical settings. Here we show that the system identifies 30.5% of patients as hormone receptor-positive, achieving a specificity of 0.9982 and a positive predictive value of 0.9992, demonstrating its ability to determine eligibility for hormone therapy without immunohistochemistry. By restaining and reassessing samples flagged as potential false negatives, we discover 31 cases of misdiagnosed ER, PR, and ERBB2 statuses. These findings demonstrate the utility of the system in diverse clinical settings and its potential to improve breast cancer diagnosis. Given the substantial focus of current guidelines on reducing false negative diagnoses, this study supports the integration of H&E-based machine learning tools into workflows for quality assurance. Breast cancer diagnosis involves identifying three important proteins: estrogen receptor (ER), progesterone receptor (PR), and ERBB2. Profiling these proteins helps oncologists determine which treatments are most likely to benefit patients. However, current testing methods can be expensive, time-consuming, and sometimes inaccurate. This study introduces and validates an artificial intelligence system that predicts the presence of these proteins using routine tissue slides. The system is tested on data from multiple medical centers and accurately identifies patients with ER and PR proteins who could benefit from hormone therapy. It also detects cases where the original diagnosis was incorrect. This tool may improve diagnostic accuracy, reduce errors, and enhance the efficiency of breast cancer care by integrating artificial intelligence into clinical workflows. Shamai et al. develop and validate a deep learning system for predicting receptor status from H&E images in breast cancer. The system accurately identifies hormone receptor-positive patients and detects false negative diagnoses, supporting its integration into clinical workflows to improve diagnostic accuracy, patient care, and quality assuran","PeriodicalId":72646,"journal":{"name":"Communications medicine","volume":" ","pages":"1-16"},"PeriodicalIF":5.4,"publicationDate":"2024-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s43856-024-00695-5.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142862466","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-19DOI: 10.1038/s43856-024-00686-6
Alexander W. Harris, Liriye Kurtovic, Jeane Nogueira, Isabel Bouzas, D. Herbert Opi, Bruce D. Wines, Wen Shi Lee, P. Mark Hogarth, Pantelis Poumbourios, Heidi E. Drummer, Clarissa Valim, Luís Cristóvão Porto, James G. Beeson
SARS-CoV-2 transmission and COVID-19 disease severity is influenced by immunity from natural infection and/or vaccination. Population-level immunity is complicated by the emergence of viral variants. Antibody Fc-dependent effector functions are as important mediators in immunity. However, their induction in populations with diverse infection and/or vaccination histories and against variants remains poorly defined. We evaluated Fc-dependent functional antibodies following vaccination with two widely used vaccines, AstraZeneca (AZ) and Sinovac (SV), including antibody binding of Fcγ-receptors and complement-fixation in vaccinated Brazilian adults (n = 222), some of who were previously infected with SARS-CoV-2, as well as adults with natural infection only (n = 200). IgG, IgM, IgA, and IgG subclasses were also quantified. AZ induces greater Fcγ-receptor-binding (types I, IIa, and IIIa/b) antibodies than SV or natural infection. Previously infected individuals have significantly greater vaccine-induced responses compared to naïve counterparts. Fcγ-receptor-binding is highest among AZ vaccinated individuals with a prior infection, for all receptor types, and substantial complement-fixing activity is only seen among this group. SV induces higher IgM than AZ, but this does not drive better complement-fixing activity. Some SV responses are associated with subject age, whereas AZ responses are not. Importantly, functional antibody responses are well retained against the Omicron BA.1 S protein, being best retained for Fcγ-receptor-1 binding, and are higher for AZ than SV. Hybrid immunity, from combined natural exposure and vaccination, generates strong Fc-mediated antibody functions which may contribute to immunity against evolving SARS-CoV-2 variants. Understanding determinants of Fc-mediated functions may enable future vaccines with greater efficacy against different variants. Antibodies are proteins produced as part of the immune response that identify and prevent the negative consequences of infections. We studied antibody responses produced following vaccination with two different COVID-19 vaccines in adults, some of whom previously had COVID-19. Differences were seen in the antibodies produced, with more active antibodies produced in people who had previously had COVID-19. There were also differences in how effective the antibodies were against different viral variants. This improved understanding of antibody responses could inform the development of future vaccines to improve their impact against infection with viral variants. Harris et al. evaluate Fc-dependent functional antibodies with two widely used COVID vaccines in vaccinated Brazilian adults. Vaccine and natural immunity underlie the differences observed in Fcγ-receptor-binding (types I, IIa, and IIIa/b), IgG, IgM, and IgA production, and complement-fixing antibodies.
{"title":"Induction of Fc-dependent functional antibodies against different variants of SARS-CoV-2 varies by vaccine type and prior infection","authors":"Alexander W. Harris, Liriye Kurtovic, Jeane Nogueira, Isabel Bouzas, D. Herbert Opi, Bruce D. Wines, Wen Shi Lee, P. Mark Hogarth, Pantelis Poumbourios, Heidi E. Drummer, Clarissa Valim, Luís Cristóvão Porto, James G. Beeson","doi":"10.1038/s43856-024-00686-6","DOIUrl":"10.1038/s43856-024-00686-6","url":null,"abstract":"SARS-CoV-2 transmission and COVID-19 disease severity is influenced by immunity from natural infection and/or vaccination. Population-level immunity is complicated by the emergence of viral variants. Antibody Fc-dependent effector functions are as important mediators in immunity. However, their induction in populations with diverse infection and/or vaccination histories and against variants remains poorly defined. We evaluated Fc-dependent functional antibodies following vaccination with two widely used vaccines, AstraZeneca (AZ) and Sinovac (SV), including antibody binding of Fcγ-receptors and complement-fixation in vaccinated Brazilian adults (n = 222), some of who were previously infected with SARS-CoV-2, as well as adults with natural infection only (n = 200). IgG, IgM, IgA, and IgG subclasses were also quantified. AZ induces greater Fcγ-receptor-binding (types I, IIa, and IIIa/b) antibodies than SV or natural infection. Previously infected individuals have significantly greater vaccine-induced responses compared to naïve counterparts. Fcγ-receptor-binding is highest among AZ vaccinated individuals with a prior infection, for all receptor types, and substantial complement-fixing activity is only seen among this group. SV induces higher IgM than AZ, but this does not drive better complement-fixing activity. Some SV responses are associated with subject age, whereas AZ responses are not. Importantly, functional antibody responses are well retained against the Omicron BA.1 S protein, being best retained for Fcγ-receptor-1 binding, and are higher for AZ than SV. Hybrid immunity, from combined natural exposure and vaccination, generates strong Fc-mediated antibody functions which may contribute to immunity against evolving SARS-CoV-2 variants. Understanding determinants of Fc-mediated functions may enable future vaccines with greater efficacy against different variants. Antibodies are proteins produced as part of the immune response that identify and prevent the negative consequences of infections. We studied antibody responses produced following vaccination with two different COVID-19 vaccines in adults, some of whom previously had COVID-19. Differences were seen in the antibodies produced, with more active antibodies produced in people who had previously had COVID-19. There were also differences in how effective the antibodies were against different viral variants. This improved understanding of antibody responses could inform the development of future vaccines to improve their impact against infection with viral variants. Harris et al. evaluate Fc-dependent functional antibodies with two widely used COVID vaccines in vaccinated Brazilian adults. Vaccine and natural immunity underlie the differences observed in Fcγ-receptor-binding (types I, IIa, and IIIa/b), IgG, IgM, and IgA production, and complement-fixing antibodies.","PeriodicalId":72646,"journal":{"name":"Communications medicine","volume":" ","pages":"1-13"},"PeriodicalIF":5.4,"publicationDate":"2024-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s43856-024-00686-6.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142862456","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-19DOI: 10.1038/s43856-024-00700-x
Tim R. Mocking, Angèle Kelder, Tom Reuvekamp, Lok Lam Ngai, Philip Rutten, Patrycja Gradowska, Arjan A. van de Loosdrecht, Jacqueline Cloos, Costa Bachas
The proportion of residual leukemic blasts after chemotherapy assessed by multiparameter flow cytometry, is an important prognostic factor for the risk of relapse and overall survival in acute myeloid leukemia (AML). This measurable residual disease (MRD) is used in clinical trials to stratify patients for more or less intensive consolidation therapy. However, an objective and reproducible analysis method to assess MRD status from flow cytometry data is lacking, yet is highly anticipated for broader implementation of MRD testing. We propose a computational pipeline based on Gaussian mixture modeling that allows a fully automated assessment of MRD status while remaining completely interpretable for clinical diagnostic experts. Our pipeline requires limited training data, which makes it easily transferable to other medical centers and cytometry platforms. We identify all healthy and leukemic immature myeloid cells in with high concordance (Spearman’s Rho = 0.974) and classification performance (median F-score = 0.861) compared to manual analysis. Using control samples (n = 18), we calculate a computational MRD percentage with high concordance to expert gating (Spearman’s rho = 0.823) and predict MRD status in a cohort of 35 AML follow-up measurements with high accuracy (97%). We demonstrate that our pipeline provides a powerful tool for fast (~3 s) and objective automated MRD assessment in AML. Cancer cells can be targeted with intensive chemotherapy in patients with acute myeloid leukemia (a type of blood cell cancer). However, disease can return after treatment due to the survival of cancer cells in the bone marrow. Identifying these cells is relevant to decide on future treatment options. However, this analysis is still performed manually by looking at a series of graphs to identify cancer and healthy cells. This process is labor-intensive, and results can differ based on the person performing the analysis. In this study, we demonstrate that this process can be automated using a computer algorithm (calculations), cutting the analysis time down from thirty minutes to three seconds. We anticipate that this can improve the accessibility and accuracy of diagnosing acute myeloid leukemia. Mocking et al. address the need for enhanced detection of measurable residual disease (MRD) in leukemia utilizing flow cytometry and computational methods. Their fully automated assessment of MRD status produces interpretable results for clinical diagnostic experts.
{"title":"Computational assessment of measurable residual disease in acute myeloid leukemia using mixture models","authors":"Tim R. Mocking, Angèle Kelder, Tom Reuvekamp, Lok Lam Ngai, Philip Rutten, Patrycja Gradowska, Arjan A. van de Loosdrecht, Jacqueline Cloos, Costa Bachas","doi":"10.1038/s43856-024-00700-x","DOIUrl":"10.1038/s43856-024-00700-x","url":null,"abstract":"The proportion of residual leukemic blasts after chemotherapy assessed by multiparameter flow cytometry, is an important prognostic factor for the risk of relapse and overall survival in acute myeloid leukemia (AML). This measurable residual disease (MRD) is used in clinical trials to stratify patients for more or less intensive consolidation therapy. However, an objective and reproducible analysis method to assess MRD status from flow cytometry data is lacking, yet is highly anticipated for broader implementation of MRD testing. We propose a computational pipeline based on Gaussian mixture modeling that allows a fully automated assessment of MRD status while remaining completely interpretable for clinical diagnostic experts. Our pipeline requires limited training data, which makes it easily transferable to other medical centers and cytometry platforms. We identify all healthy and leukemic immature myeloid cells in with high concordance (Spearman’s Rho = 0.974) and classification performance (median F-score = 0.861) compared to manual analysis. Using control samples (n = 18), we calculate a computational MRD percentage with high concordance to expert gating (Spearman’s rho = 0.823) and predict MRD status in a cohort of 35 AML follow-up measurements with high accuracy (97%). We demonstrate that our pipeline provides a powerful tool for fast (~3 s) and objective automated MRD assessment in AML. Cancer cells can be targeted with intensive chemotherapy in patients with acute myeloid leukemia (a type of blood cell cancer). However, disease can return after treatment due to the survival of cancer cells in the bone marrow. Identifying these cells is relevant to decide on future treatment options. However, this analysis is still performed manually by looking at a series of graphs to identify cancer and healthy cells. This process is labor-intensive, and results can differ based on the person performing the analysis. In this study, we demonstrate that this process can be automated using a computer algorithm (calculations), cutting the analysis time down from thirty minutes to three seconds. We anticipate that this can improve the accessibility and accuracy of diagnosing acute myeloid leukemia. Mocking et al. address the need for enhanced detection of measurable residual disease (MRD) in leukemia utilizing flow cytometry and computational methods. Their fully automated assessment of MRD status produces interpretable results for clinical diagnostic experts.","PeriodicalId":72646,"journal":{"name":"Communications medicine","volume":" ","pages":"1-9"},"PeriodicalIF":5.4,"publicationDate":"2024-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s43856-024-00700-x.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142862458","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-19DOI: 10.1038/s43856-024-00688-4
Hugo F. Posada–Quintero, Bruce J. Derrick, M. Claire Ellis, Michael J. Natoli, Christopher Winstead-Derlega, Sara I. Gonzalez, Christopher M. Allen, Matthew S. Makowski, Brian M. Keuski, Richard E. Moon, John J. Freiberger, Ki H. Chon
Oxygen-rich breathing mixtures up to 100% are used in some underwater diving operations for several reasons. Breathing elevated oxygen partial pressures (PO2) increases the risk of developing central nervous system oxygen toxicity (CNS-OT) which could impair performance or result in a seizure and subsequent drowning. We aimed to study the dynamics of the electrodermal activity (EDA) and heart rate (HR) while breathing elevated PO2 in the hyperbaric environment (HBO2) as a possible means to predict impending CNS-OT. EDA is recorded during 50 subject exposures (26 subjects) to evaluate CNS-OT in immersed (head out of water) exercising divers in a hyperbaric chamber breathing 100% O2 at 35 feet of seawater (FSW), (PO2 = 2.06 ATA) for up to 120 min. 32 subject exposures exhibit symptoms “definitely” or “probably” due to CNS-OT before the end of the exposure, whereas 18 do not. We obtain traditional and time-varying spectral indices (TVSymp) of EDA to determine its utility as predictive physio markers. Variations in EDA and heart rate (HR) for the last 5 min of the experiment are compared to baseline values prior to breathing O2. In the subset of experiments where “definite” CNS-OT symptoms developed, we find a significant elevation in the mean ± standard deviation TVSymp value 57 ± 79 s and median of 10 s, prior to symptoms. In this retrospective analysis, TVSymp may have predictive value for CNS-OT with high sensitivity (1.0) but lower specificity (0.48). Additional work is being undertaken to improve the detection algorithm. This study looked at the effects of breathing high levels of oxygen during underwater diving and the risk of central nervous system oxygen toxicity. This toxicity can cause problems with movement, seizures or even drowning. We wanted to see if changes in skin and heart activity could help predict the symptoms of toxicity. We tested 26 divers (50 dives) in a special chamber. They breathed pure oxygen at increased pressure (equivalent to being underwater at 35 feet). 32 dives showed signs of toxicity, while 18 did not. We looked at the electrodermal activity (a measurement of the skin conductance) and heart rate data to see if they could warn of an issue. We found that in dives where toxicity symptoms definitely developed, there were significant changes in electrodermal activity around 57 s before symptoms appeared. While this method was very sensitive, it wasn’t always specific. We are working on improving this prediction method. This may be used to warn divers of dangerous gases so they can switch breathing gases or move to a shallower depth, and can improve the chances of escaping a disabled submarine. Posada-Quintero et al. study the dynamics of the electrodermal activity and heart rate while breathing at elevated oxygen partial pressures in a hyperbaric environment. Electrodermal activitycan be used to predict the onset of central nervous system oxygen toxicity symptoms in divers resulting from prolonged exposure to a hyperb
{"title":"Elevation of spectral components of electrodermal activity precedes central nervous system oxygen toxicity symptoms in divers","authors":"Hugo F. Posada–Quintero, Bruce J. Derrick, M. Claire Ellis, Michael J. Natoli, Christopher Winstead-Derlega, Sara I. Gonzalez, Christopher M. Allen, Matthew S. Makowski, Brian M. Keuski, Richard E. Moon, John J. Freiberger, Ki H. Chon","doi":"10.1038/s43856-024-00688-4","DOIUrl":"10.1038/s43856-024-00688-4","url":null,"abstract":"Oxygen-rich breathing mixtures up to 100% are used in some underwater diving operations for several reasons. Breathing elevated oxygen partial pressures (PO2) increases the risk of developing central nervous system oxygen toxicity (CNS-OT) which could impair performance or result in a seizure and subsequent drowning. We aimed to study the dynamics of the electrodermal activity (EDA) and heart rate (HR) while breathing elevated PO2 in the hyperbaric environment (HBO2) as a possible means to predict impending CNS-OT. EDA is recorded during 50 subject exposures (26 subjects) to evaluate CNS-OT in immersed (head out of water) exercising divers in a hyperbaric chamber breathing 100% O2 at 35 feet of seawater (FSW), (PO2 = 2.06 ATA) for up to 120 min. 32 subject exposures exhibit symptoms “definitely” or “probably” due to CNS-OT before the end of the exposure, whereas 18 do not. We obtain traditional and time-varying spectral indices (TVSymp) of EDA to determine its utility as predictive physio markers. Variations in EDA and heart rate (HR) for the last 5 min of the experiment are compared to baseline values prior to breathing O2. In the subset of experiments where “definite” CNS-OT symptoms developed, we find a significant elevation in the mean ± standard deviation TVSymp value 57 ± 79 s and median of 10 s, prior to symptoms. In this retrospective analysis, TVSymp may have predictive value for CNS-OT with high sensitivity (1.0) but lower specificity (0.48). Additional work is being undertaken to improve the detection algorithm. This study looked at the effects of breathing high levels of oxygen during underwater diving and the risk of central nervous system oxygen toxicity. This toxicity can cause problems with movement, seizures or even drowning. We wanted to see if changes in skin and heart activity could help predict the symptoms of toxicity. We tested 26 divers (50 dives) in a special chamber. They breathed pure oxygen at increased pressure (equivalent to being underwater at 35 feet). 32 dives showed signs of toxicity, while 18 did not. We looked at the electrodermal activity (a measurement of the skin conductance) and heart rate data to see if they could warn of an issue. We found that in dives where toxicity symptoms definitely developed, there were significant changes in electrodermal activity around 57 s before symptoms appeared. While this method was very sensitive, it wasn’t always specific. We are working on improving this prediction method. This may be used to warn divers of dangerous gases so they can switch breathing gases or move to a shallower depth, and can improve the chances of escaping a disabled submarine. Posada-Quintero et al. study the dynamics of the electrodermal activity and heart rate while breathing at elevated oxygen partial pressures in a hyperbaric environment. Electrodermal activitycan be used to predict the onset of central nervous system oxygen toxicity symptoms in divers resulting from prolonged exposure to a hyperb","PeriodicalId":72646,"journal":{"name":"Communications medicine","volume":" ","pages":"1-11"},"PeriodicalIF":5.4,"publicationDate":"2024-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s43856-024-00688-4.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142862461","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-19DOI: 10.1038/s43856-024-00692-8
Qian Wang, Michelle R. Kapolowicz, Jia-Nan Li, Fei Ji, Wei-Dong Shen, Fang-Yuan Wang, Wei Chen, Wei-Wei Guo, Chi Zhang, Ri-Yuan Liu, Miao Zhang, Meng-Di Hong, Ai-Ting Chen, Fan-Gang Zeng, Shi-Ming Yang
Cochlear implants have helped over one million individuals restore functional hearing globally, but their clinical utility in suppressing tinnitus has not been firmly established. In a decade-long study, we examined longitudinal effects of cochlear implants on tinnitus in 323 post-lingually deafened individuals including 211 with pre-existing tinnitus and 112 without tinnitus. The primary endpoints were tinnitus loudness and tinnitus handicap inventory. The secondary endpoints were speech recognition, anxiety and sleep quality. Here we show that after 24 month implant usage, the tinnitus cohort experience 58% reduction in tinnitus loudness (on a 0–10 scale from 4.3 baseline to 1.8 = −2.5, 95% CI: −2.7 to −2.2, p = 3 x 10−6; effect size d’ = −1.4,) and 44% in tinnitus handicap inventory (=−21.2, 95% CI: −24.5 to −17.9, p = 1 x 10−15; d’=−1.0). Conversely, only 3.6% of those without pre-existing tinnitus develop it post-implantation. Prior to implantation, the tinnitus cohort have lower speech recognition, higher anxiety and poorer sleep quality than the non-tinnitus cohort, measured by Mandarin monosyllabic words, Zung Self-rating Anxiety Scale and Pittsburgh Sleep Quality Index, respectively. Although the 24 month implant usage eliminate the group difference in speech and anxiety measures, the tinnitus cohort still face significant sleep difficulties likely due to the tinnitus coming back when the device was inactive at night. The present result shows that cochlear implantation can offer an alternative effective treatment for tinnitus. The present result also identifies a critical need in developing always-on and atraumatic devices for tinnitus patients, including potentially those with normal hearing. Tinnitus is the perception that there is sound when it is not present. Cochlear implants are placed in the ears and can suppress tinnitus. However, the FDA do not yet recommend them as a tinnitus treatment. We evaluated 323 individuals with or without tinnitus before cochlear implantation and for over 2 years after implantation surgery. We investigated whether cochlear implantation is safe and effective for treating tinnitus and whether it causes tinnitus in people who did not have tinnitus previously. We found that cochlear implantation reduces tinnitus in 90% of those with pre-surgical tinnitus whilst causing tinnitus in only 3.4% of those without pre-surgical tinnitus. This finding confirms that cochlear implants are a safe and effective treatment for tinnitus. Wang, Kapolowicz, Li et al. investigate the effect of cochlear implantation on tinnitus in postlingually deafened individuals with or without pre-surgical tinnitus. There is a low risk of cochlear implants causing tinnitus but a high chance of them suppressing tinnitus, with a fast tinnitus suppression mechanism relating to device activation and a slow one that relates to brain plasticity.
{"title":"A prospective cohort study of cochlear implantation as a treatment for tinnitus in post-lingually deafened individuals","authors":"Qian Wang, Michelle R. Kapolowicz, Jia-Nan Li, Fei Ji, Wei-Dong Shen, Fang-Yuan Wang, Wei Chen, Wei-Wei Guo, Chi Zhang, Ri-Yuan Liu, Miao Zhang, Meng-Di Hong, Ai-Ting Chen, Fan-Gang Zeng, Shi-Ming Yang","doi":"10.1038/s43856-024-00692-8","DOIUrl":"10.1038/s43856-024-00692-8","url":null,"abstract":"Cochlear implants have helped over one million individuals restore functional hearing globally, but their clinical utility in suppressing tinnitus has not been firmly established. In a decade-long study, we examined longitudinal effects of cochlear implants on tinnitus in 323 post-lingually deafened individuals including 211 with pre-existing tinnitus and 112 without tinnitus. The primary endpoints were tinnitus loudness and tinnitus handicap inventory. The secondary endpoints were speech recognition, anxiety and sleep quality. Here we show that after 24 month implant usage, the tinnitus cohort experience 58% reduction in tinnitus loudness (on a 0–10 scale from 4.3 baseline to 1.8 = −2.5, 95% CI: −2.7 to −2.2, p = 3 x 10−6; effect size d’ = −1.4,) and 44% in tinnitus handicap inventory (=−21.2, 95% CI: −24.5 to −17.9, p = 1 x 10−15; d’=−1.0). Conversely, only 3.6% of those without pre-existing tinnitus develop it post-implantation. Prior to implantation, the tinnitus cohort have lower speech recognition, higher anxiety and poorer sleep quality than the non-tinnitus cohort, measured by Mandarin monosyllabic words, Zung Self-rating Anxiety Scale and Pittsburgh Sleep Quality Index, respectively. Although the 24 month implant usage eliminate the group difference in speech and anxiety measures, the tinnitus cohort still face significant sleep difficulties likely due to the tinnitus coming back when the device was inactive at night. The present result shows that cochlear implantation can offer an alternative effective treatment for tinnitus. The present result also identifies a critical need in developing always-on and atraumatic devices for tinnitus patients, including potentially those with normal hearing. Tinnitus is the perception that there is sound when it is not present. Cochlear implants are placed in the ears and can suppress tinnitus. However, the FDA do not yet recommend them as a tinnitus treatment. We evaluated 323 individuals with or without tinnitus before cochlear implantation and for over 2 years after implantation surgery. We investigated whether cochlear implantation is safe and effective for treating tinnitus and whether it causes tinnitus in people who did not have tinnitus previously. We found that cochlear implantation reduces tinnitus in 90% of those with pre-surgical tinnitus whilst causing tinnitus in only 3.4% of those without pre-surgical tinnitus. This finding confirms that cochlear implants are a safe and effective treatment for tinnitus. Wang, Kapolowicz, Li et al. investigate the effect of cochlear implantation on tinnitus in postlingually deafened individuals with or without pre-surgical tinnitus. There is a low risk of cochlear implants causing tinnitus but a high chance of them suppressing tinnitus, with a fast tinnitus suppression mechanism relating to device activation and a slow one that relates to brain plasticity.","PeriodicalId":72646,"journal":{"name":"Communications medicine","volume":" ","pages":"1-9"},"PeriodicalIF":5.4,"publicationDate":"2024-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s43856-024-00692-8.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142862462","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-19DOI: 10.1038/s43856-024-00674-w
Francesco Ria, Anru R. Zhang, Reginald Lerebours, Alaattin Erkanli, Ehsan Abadi, Daniele Marin, Ehsan Samei
Risk-versus-benefit optimization required a quantitative comparison of the two. The latter, directly related to effective diagnosis, can be associated to clinical risk. While many strategies have been developed to ascertain radiation risk, there has been a paucity of studies assessing clinical risk, thus limiting the optimization reach to achieve a minimum total risk to patients undergoing imaging examinations. In this study, we developed a mathematical framework for an imaging procedure total risk index considering both radiation and clinical risks based on specific tasks and investigated diseases. The proposed model characterized total risk as the sum of radiation and clinical risks defined as functions of radiation burden, disease prevalence, false-positive rate, expected life-expectancy loss for misdiagnosis, and radiologist interpretative performance (i.e., AUC). The proposed total risk model was applied to a population of one million cases simulating a liver cancer scenario. For all demographics, the clinical risk outweighs radiation risk by at least 400%. The optimization application indicates that optimizing typical abdominal CT exams should involve a radiation dose increase in over 90% of the cases, with the highest risk optimization potential in Asian population (24% total risk reduction; 306% $${{CTDI}}_{{vol}}$$ increase) and lowest in Hispanic population (5% total risk reduction; 89% $${{CTDI}}_{{vol}}$$ increase). Framing risk-to-benefit assessment as a risk-versus-risk question, calculating both clinical and radiation risk using comparable units, allows a quantitative optimization of total risks in CT. The results highlight the dominance of clinical risk at typical CT examination dose levels, and that exaggerated dose reductions can even harm patients. The proper practice of radiology (using imaging technology to diagnose and treat diseases) should take into consideration both the risk and benefit to a patient. Such a comparison can be hard because risk and benefit are measured in different ways. The risk includes some amount of radiation exposure to patients which can cause harm, but the benefit could be identifying a medical problem that needs attention. To overcome this obstacle, we developed a mathematical model describing the risk-to-benefit of a medical imaging study. Our modeling exercise found that the clinical benefit outweighs the radiation risk. The finding that benefit of detecting a problem is worth the risk of imaging is contrary to common belief. This study shows that so much emphasis could be put on radiation safety in imaging that avoiding imaging could negatively impact patients’ path of care. Ria et al. develop a mathematical framework for estimating total risk of an imaging procedure that accounts for both radiation and clinical risks. The authors propose a model that accounts for a variety of factors including disease prevalence, false positive rate, and expected life-expectancy loss.
风险与收益优化需要对两者进行定量比较。后者与有效诊断直接相关，可能与临床风险相关。虽然已经开发了许多策略来确定辐射风险，但缺乏评估临床风险的研究，从而限制了优化范围，以实现对接受影像学检查的患者的最小总风险。在这项研究中，我们开发了一个数学框架，用于考虑基于特定任务和调查疾病的放射和临床风险的成像程序总风险指数。提出的模型将总风险描述为辐射和临床风险的总和，定义为辐射负担、疾病患病率、假阳性率、误诊预期寿命损失和放射科医生解释能力（即AUC）的函数。提出的总风险模型应用于100万例人群中，模拟肝癌的情景。对所有人来说，临床风险至少比辐射风险高出400倍%. The optimization application indicates that optimizing typical abdominal CT exams should involve a radiation dose increase in over 90% of the cases, with the highest risk optimization potential in Asian population (24% total risk reduction; 306% $${{CTDI}}_{{vol}}$$ increase) and lowest in Hispanic population (5% total risk reduction; 89% $${{CTDI}}_{{vol}}$$ increase). Framing risk-to-benefit assessment as a risk-versus-risk question, calculating both clinical and radiation risk using comparable units, allows a quantitative optimization of total risks in CT. The results highlight the dominance of clinical risk at typical CT examination dose levels, and that exaggerated dose reductions can even harm patients. The proper practice of radiology (using imaging technology to diagnose and treat diseases) should take into consideration both the risk and benefit to a patient. Such a comparison can be hard because risk and benefit are measured in different ways. The risk includes some amount of radiation exposure to patients which can cause harm, but the benefit could be identifying a medical problem that needs attention. To overcome this obstacle, we developed a mathematical model describing the risk-to-benefit of a medical imaging study. Our modeling exercise found that the clinical benefit outweighs the radiation risk. The finding that benefit of detecting a problem is worth the risk of imaging is contrary to common belief. This study shows that so much emphasis could be put on radiation safety in imaging that avoiding imaging could negatively impact patients’ path of care. Ria et al. develop a mathematical framework for estimating total risk of an imaging procedure that accounts for both radiation and clinical risks. The authors propose a model that accounts for a variety of factors including disease prevalence, false positive rate, and expected life-expectancy loss.
{"title":"Optimization of abdominal CT based on a model of total risk minimization by putting radiation risk in perspective with imaging benefit","authors":"Francesco Ria, Anru R. Zhang, Reginald Lerebours, Alaattin Erkanli, Ehsan Abadi, Daniele Marin, Ehsan Samei","doi":"10.1038/s43856-024-00674-w","DOIUrl":"10.1038/s43856-024-00674-w","url":null,"abstract":"Risk-versus-benefit optimization required a quantitative comparison of the two. The latter, directly related to effective diagnosis, can be associated to clinical risk. While many strategies have been developed to ascertain radiation risk, there has been a paucity of studies assessing clinical risk, thus limiting the optimization reach to achieve a minimum total risk to patients undergoing imaging examinations. In this study, we developed a mathematical framework for an imaging procedure total risk index considering both radiation and clinical risks based on specific tasks and investigated diseases. The proposed model characterized total risk as the sum of radiation and clinical risks defined as functions of radiation burden, disease prevalence, false-positive rate, expected life-expectancy loss for misdiagnosis, and radiologist interpretative performance (i.e., AUC). The proposed total risk model was applied to a population of one million cases simulating a liver cancer scenario. For all demographics, the clinical risk outweighs radiation risk by at least 400%. The optimization application indicates that optimizing typical abdominal CT exams should involve a radiation dose increase in over 90% of the cases, with the highest risk optimization potential in Asian population (24% total risk reduction; 306% $${{CTDI}}_{{vol}}$$ increase) and lowest in Hispanic population (5% total risk reduction; 89% $${{CTDI}}_{{vol}}$$ increase). Framing risk-to-benefit assessment as a risk-versus-risk question, calculating both clinical and radiation risk using comparable units, allows a quantitative optimization of total risks in CT. The results highlight the dominance of clinical risk at typical CT examination dose levels, and that exaggerated dose reductions can even harm patients. The proper practice of radiology (using imaging technology to diagnose and treat diseases) should take into consideration both the risk and benefit to a patient. Such a comparison can be hard because risk and benefit are measured in different ways. The risk includes some amount of radiation exposure to patients which can cause harm, but the benefit could be identifying a medical problem that needs attention. To overcome this obstacle, we developed a mathematical model describing the risk-to-benefit of a medical imaging study. Our modeling exercise found that the clinical benefit outweighs the radiation risk. The finding that benefit of detecting a problem is worth the risk of imaging is contrary to common belief. This study shows that so much emphasis could be put on radiation safety in imaging that avoiding imaging could negatively impact patients’ path of care. Ria et al. develop a mathematical framework for estimating total risk of an imaging procedure that accounts for both radiation and clinical risks. The authors propose a model that accounts for a variety of factors including disease prevalence, false positive rate, and expected life-expectancy loss.","PeriodicalId":72646,"journal":{"name":"Communications medicine","volume":" ","pages":"1-9"},"PeriodicalIF":5.4,"publicationDate":"2024-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s43856-024-00674-w.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142862473","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-19DOI: 10.1038/s43856-024-00694-6
Pauliina Auvinen, Jussi Vehviläinen, Karita Rämö, Ida Laukkanen, Heidi Marjonen-Lindblad, Essi Wallén, Viveca Söderström-Anttila, Hanna Kahila, Christel Hydén-Granskog, Timo Tuuri, Aila Tiitinen, Nina Kaminen-Ahola
Assisted reproductive technology (ART) has been associated with increased risks for growth disturbance, disrupted imprinting as well as cardiovascular and metabolic disorders. However, the molecular mechanisms and whether they are a result of the ART procedures or the underlying subfertility are unknown. We performed genome-wide DNA methylation (EPIC Illumina microarrays) and gene expression (mRNA sequencing) analyses for a total of 80 ART and 77 control placentas. The separate analyses for placentas from different ART procedures and sexes were performed. To separate the effects of ART procedures and subfertility, 11 placentas from natural conception of subfertile couples and 12 from intrauterine insemination treatments were included. Here we show that ART-associated changes in the placenta enriche in the pathways of hormonal regulation, insulin secretion, neuronal development, and vascularization. Observed decreased number of stromal cells as well as downregulated TRIM28 and NOTCH3 expressions in ART placentas indicate impaired angiogenesis and growth. DNA methylation changes in the imprinted regions and downregulation of TRIM28 suggest defective stabilization of the imprinting. Furthermore, downregulated expression of imprinted endocrine signaling molecule DLK1 associates with both ART and subfertility. Decreased expressions of TRIM28, NOTCH3, and DLK1 bring forth potential mechanisms for several phenotypic features associated with ART. Our results support previous procedure specific findings: the changes associated with growth and metabolism link more prominently to the fresh embryo transfer with smaller placentas and newborns, than to the frozen embryo transfer with larger placentas and newborns. Furthermore, since the observed changes associate also with subfertility, they offer a precious insight to the molecular background of infertility. For those that struggle with conception, medical and scientific methods called Assisted Reproductive Technology (ART) may help. However, ART have been associated with increased risks for negative medical outcomes for babies. Whether these risks are caused by ART use or the underlying condition of subfertility (less than ideal natural conception outcomes) are not known. Here we looked at the effects of ART and subfertility by studying specific genetics in placenta and newborn’s characteristics. We show that changes in genetics in the placenta from ART use are linked to hormonal control, insulin secretion, and brain and blood vessel development. Although the observed changes are subtle, they can contribute to risks for metabolic and heart disorders as well as growth disturbances in newborns. Our results provide important evidence for the effect of medical outcomes associated with both ART and subfertility. Auvinen et al. examine genome-wide DNA methylation, imprinting, and gene expression in human placentas. Placentas from assisted reproductive technologies experience a variety of altered signaling pathways
{"title":"Genome-wide DNA methylation and gene expression in human placentas derived from assisted reproductive technology","authors":"Pauliina Auvinen, Jussi Vehviläinen, Karita Rämö, Ida Laukkanen, Heidi Marjonen-Lindblad, Essi Wallén, Viveca Söderström-Anttila, Hanna Kahila, Christel Hydén-Granskog, Timo Tuuri, Aila Tiitinen, Nina Kaminen-Ahola","doi":"10.1038/s43856-024-00694-6","DOIUrl":"10.1038/s43856-024-00694-6","url":null,"abstract":"Assisted reproductive technology (ART) has been associated with increased risks for growth disturbance, disrupted imprinting as well as cardiovascular and metabolic disorders. However, the molecular mechanisms and whether they are a result of the ART procedures or the underlying subfertility are unknown. We performed genome-wide DNA methylation (EPIC Illumina microarrays) and gene expression (mRNA sequencing) analyses for a total of 80 ART and 77 control placentas. The separate analyses for placentas from different ART procedures and sexes were performed. To separate the effects of ART procedures and subfertility, 11 placentas from natural conception of subfertile couples and 12 from intrauterine insemination treatments were included. Here we show that ART-associated changes in the placenta enriche in the pathways of hormonal regulation, insulin secretion, neuronal development, and vascularization. Observed decreased number of stromal cells as well as downregulated TRIM28 and NOTCH3 expressions in ART placentas indicate impaired angiogenesis and growth. DNA methylation changes in the imprinted regions and downregulation of TRIM28 suggest defective stabilization of the imprinting. Furthermore, downregulated expression of imprinted endocrine signaling molecule DLK1 associates with both ART and subfertility. Decreased expressions of TRIM28, NOTCH3, and DLK1 bring forth potential mechanisms for several phenotypic features associated with ART. Our results support previous procedure specific findings: the changes associated with growth and metabolism link more prominently to the fresh embryo transfer with smaller placentas and newborns, than to the frozen embryo transfer with larger placentas and newborns. Furthermore, since the observed changes associate also with subfertility, they offer a precious insight to the molecular background of infertility. For those that struggle with conception, medical and scientific methods called Assisted Reproductive Technology (ART) may help. However, ART have been associated with increased risks for negative medical outcomes for babies. Whether these risks are caused by ART use or the underlying condition of subfertility (less than ideal natural conception outcomes) are not known. Here we looked at the effects of ART and subfertility by studying specific genetics in placenta and newborn’s characteristics. We show that changes in genetics in the placenta from ART use are linked to hormonal control, insulin secretion, and brain and blood vessel development. Although the observed changes are subtle, they can contribute to risks for metabolic and heart disorders as well as growth disturbances in newborns. Our results provide important evidence for the effect of medical outcomes associated with both ART and subfertility. Auvinen et al. examine genome-wide DNA methylation, imprinting, and gene expression in human placentas. Placentas from assisted reproductive technologies experience a variety of altered signaling pathways","PeriodicalId":72646,"journal":{"name":"Communications medicine","volume":" ","pages":"1-15"},"PeriodicalIF":5.4,"publicationDate":"2024-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s43856-024-00694-6.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142862425","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-18DOI: 10.1038/s43856-024-00705-6
Shuang Chang, Greyson A. Wintergerst, Camella Carlson, Haoli Yin, Kristen R. Scarpato, Amy N. Luckenbaugh, Sam S. Chang, Soheil Kolouri, Audrey K. Bowden
Bladder cancer is the 10th most common malignancy and carries the highest treatment cost among all cancers. The elevated cost stems from its high recurrence rate, which necessitates frequent surveillance. White light cystoscopy (WLC), the standard of care surveillance tool to examine the bladder for lesions, has limited sensitivity for early-stage bladder cancer. Blue light cystoscopy (BLC) utilizes a fluorescent dye to induce contrast in cancerous regions, improving the sensitivity of detection by 43%. Nevertheless, the added equipment cost and lengthy dwell time of the dye limits the availability of BLC. Here, we report the first demonstration of digital staining as a promising strategy to convert WLC images collected with standard-of-care clinical equipment into accurate BLC-like images, providing enhanced sensitivity for WLC without the associated labor or equipment cost. By introducing key pre-processing steps to circumvent color and brightness variations in clinical datasets needed for successful model performance, the results achieve a staining accuracy of 80.58% and show excellent qualitative and quantitative agreement of the digitally stained WLC (dsWLC) images with ground truth BLC images, including color consistency. In short, dsWLC can affordably provide the fluorescent contrast needed to improve the detection sensitivity of bladder cancer, thereby increasing the accessibility of BLC contrast for bladder cancer surveillance. The broader implications of this work suggest digital staining is a cost-effective alternative to contrast-based endoscopy for other clinical scenarios outside of urology that can democratize access to better healthcare. Bladder cancer is one of the most common and costly cancers to treat. Traditional white light imaging of the bladder is not very effective at detecting early-stage cancer. Blue light imaging is better able to detect these cancers but requires administration of a dye. In this study, we use a computational process to transform white light bladder images into fluorescent, blue light versions, which improves detection of early-stage cancers. Our approach may be applicable to other clinical uses and could potentially be used to improve diagnosis of cancer. Chang et al. convert white light cystoscopy (WLC) images collected with standard-of-care clinical equipment into accurate blue light cystoscopy (BLC)-like images. By introducing key pre-processing steps to circumvent color and brightness variations in clinical datasets, they provide enhanced sensitivity without labor or equipment cost.
背景：膀胱癌是第十大最常见的恶性肿瘤，也是所有癌症中治疗费用最高的。高昂的费用源于其高复发率，需要经常监测。白光膀胱镜检查（WLC）是检查膀胱病变的标准护理监测工具，但对早期膀胱癌的敏感性有限。蓝光膀胱镜检查（BLC）利用荧光染料在癌变区域诱导造影剂，将检测灵敏度提高43%。然而，设备成本的增加和染料停留时间的延长限制了BLC的可用性。方法：在这里，我们首次报告了数字染色作为一种有前途的策略，将标准临床设备收集的WLC图像转换为准确的blc样图像，提高WLC的灵敏度，而无需相关的人工或设备成本。结果：通过引入关键的预处理步骤，以避免成功的模型性能所需的临床数据集中的颜色和亮度变化，结果实现了80.58%的染色精度，并且显示了数字染色WLC （dsWLC）图像与ground truth BLC图像的极好的定性和定量一致性，包括颜色一致性。结论：总之，dsWLC能够经济实惠地提供提高膀胱癌检测灵敏度所需的荧光造影剂，从而增加了BLC造影剂在膀胱癌监测中的可及性。这项工作的广泛意义表明，对于泌尿外科以外的其他临床情况，数字染色是一种具有成本效益的替代基于造影剂的内窥镜检查，可以使人们获得更好的医疗保健。
{"title":"Low-cost and label-free blue light cystoscopy through digital staining of white light cystoscopy videos","authors":"Shuang Chang, Greyson A. Wintergerst, Camella Carlson, Haoli Yin, Kristen R. Scarpato, Amy N. Luckenbaugh, Sam S. Chang, Soheil Kolouri, Audrey K. Bowden","doi":"10.1038/s43856-024-00705-6","DOIUrl":"10.1038/s43856-024-00705-6","url":null,"abstract":"Bladder cancer is the 10th most common malignancy and carries the highest treatment cost among all cancers. The elevated cost stems from its high recurrence rate, which necessitates frequent surveillance. White light cystoscopy (WLC), the standard of care surveillance tool to examine the bladder for lesions, has limited sensitivity for early-stage bladder cancer. Blue light cystoscopy (BLC) utilizes a fluorescent dye to induce contrast in cancerous regions, improving the sensitivity of detection by 43%. Nevertheless, the added equipment cost and lengthy dwell time of the dye limits the availability of BLC. Here, we report the first demonstration of digital staining as a promising strategy to convert WLC images collected with standard-of-care clinical equipment into accurate BLC-like images, providing enhanced sensitivity for WLC without the associated labor or equipment cost. By introducing key pre-processing steps to circumvent color and brightness variations in clinical datasets needed for successful model performance, the results achieve a staining accuracy of 80.58% and show excellent qualitative and quantitative agreement of the digitally stained WLC (dsWLC) images with ground truth BLC images, including color consistency. In short, dsWLC can affordably provide the fluorescent contrast needed to improve the detection sensitivity of bladder cancer, thereby increasing the accessibility of BLC contrast for bladder cancer surveillance. The broader implications of this work suggest digital staining is a cost-effective alternative to contrast-based endoscopy for other clinical scenarios outside of urology that can democratize access to better healthcare. Bladder cancer is one of the most common and costly cancers to treat. Traditional white light imaging of the bladder is not very effective at detecting early-stage cancer. Blue light imaging is better able to detect these cancers but requires administration of a dye. In this study, we use a computational process to transform white light bladder images into fluorescent, blue light versions, which improves detection of early-stage cancers. Our approach may be applicable to other clinical uses and could potentially be used to improve diagnosis of cancer. Chang et al. convert white light cystoscopy (WLC) images collected with standard-of-care clinical equipment into accurate blue light cystoscopy (BLC)-like images. By introducing key pre-processing steps to circumvent color and brightness variations in clinical datasets, they provide enhanced sensitivity without labor or equipment cost.","PeriodicalId":72646,"journal":{"name":"Communications medicine","volume":" ","pages":"1-10"},"PeriodicalIF":5.4,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s43856-024-00705-6.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142856889","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：