of COVID-19 (3). The large amount of social computational data generated by the pandemic may lead to breakthroughs in AI that can greatly alter human behavior. Newer COVID-19 variants and behavioral changes are causing resurgence of the pandemic. AI can use social computational data to devise novel non-pharmaceutical interventions to prevent newer outbreaks. “How we feel” a web and mobile application that longitudinally tracks COVID-19 symptoms, behavior and testing, can predict likely COVID-19 positive individuals and outbreaks (4). Genomic, structural data and outcomes can be used to make COVID-19 simulations, predict mutations, outbreaks and guide therapy leading to drug discovery, drug repurposing and precision medicine (5). Multiple applications for predicting severity using imaging and lab data in real time have been developed and have been externally validated (6). These applications have played a pivotal role in the management of the pandemic.
{"title":"COVID-19 in the era of artificial intelligence: a black swan event?","authors":"Fahad S Mohammed, Hisham Qadri, S. Mohammed","doi":"10.21037/jmai-21-23","DOIUrl":"https://doi.org/10.21037/jmai-21-23","url":null,"abstract":"of COVID-19 (3). The large amount of social computational data generated by the pandemic may lead to breakthroughs in AI that can greatly alter human behavior. Newer COVID-19 variants and behavioral changes are causing resurgence of the pandemic. AI can use social computational data to devise novel non-pharmaceutical interventions to prevent newer outbreaks. “How we feel” a web and mobile application that longitudinally tracks COVID-19 symptoms, behavior and testing, can predict likely COVID-19 positive individuals and outbreaks (4). Genomic, structural data and outcomes can be used to make COVID-19 simulations, predict mutations, outbreaks and guide therapy leading to drug discovery, drug repurposing and precision medicine (5). Multiple applications for predicting severity using imaging and lab data in real time have been developed and have been externally validated (6). These applications have played a pivotal role in the management of the pandemic.","PeriodicalId":73815,"journal":{"name":"Journal of medical artificial intelligence","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44755234","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}
: This note presents an analysis of the medico-legal and bioethical risks posed by the incorporation of artificial intelligence (AI) and machine learning into clinical radiology practice, with specific focus on the field of mammography. The analysis presents an overview of the current medical malpractice framework relative to mammography; examines the fitness of current legal frameworks for apportioning liability in cases of injury resulting from errors by machine learning tools; evaluates various options for addressing the malpractice model’s gaps as AI is incorporated into clinical patient care; and provides means by which the healthcare industry may both minimize short-term liability for machine learning error, while ensuring that neither the public nor the regulatory framework are unnecessarily biased against the use of AI in medicine.
{"title":"Intersection of artificial intelligence and medicine: tort liability in the technological age","authors":"Kyle T. Jorstad","doi":"10.21037/jmai-20-57","DOIUrl":"https://doi.org/10.21037/jmai-20-57","url":null,"abstract":": This note presents an analysis of the medico-legal and bioethical risks posed by the incorporation of artificial intelligence (AI) and machine learning into clinical radiology practice, with specific focus on the field of mammography. The analysis presents an overview of the current medical malpractice framework relative to mammography; examines the fitness of current legal frameworks for apportioning liability in cases of injury resulting from errors by machine learning tools; evaluates various options for addressing the malpractice model’s gaps as AI is incorporated into clinical patient care; and provides means by which the healthcare industry may both minimize short-term liability for machine learning error, while ensuring that neither the public nor the regulatory framework are unnecessarily biased against the use of AI in medicine.","PeriodicalId":73815,"journal":{"name":"Journal of medical artificial intelligence","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47130813","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}
Teresa T. Martin-Carreras, Hongming Li, Po-Hao Chen
: Artificial intelligence (AI) promises wide-reaching impacts on the field of radiology, and has the potential to influence every aspect of image interpretation. In recent decades, significant advancements in computing power, combined with the availability of large data stores or “Big Data” and algorithm democratization have revolutionized AI and machine learning (ML). Research applications utilizing these technological advancements are booming, and their adoption is expected to continue to rise at a rapid pace. While AI and ML have impacted many components of the imaging value chain, the purpose of this article is to discuss interpretative uses of the technology as it relates to musculoskeletal (MSK) radiology. This review provides a general introduction to AI and ML concepts, and highlights the major promises, challenges, and anticipated future applications of these developments in MSK radiology. AI and ML advances for image interpretation can increase the value that MSK radiologists provide to their patients, referring clinicians, and organizations by increasing diagnostic accuracy while decreasing turnaround times, enhancing image processing and quantitative analysis, and by potentially improving patient outcomes. Familiarity with these processes among MSK clinicians and researchers will be paramount to the improvement and implementation of these new techniques into the clinical practice. Radiology departments, practices and practitioners who embrace these technologies now will be well-suited to lead this influential change in our field in the near future.
{"title":"Interpretative applications of artificial intelligence in musculoskeletal imaging: concepts, current practice, and future directions","authors":"Teresa T. Martin-Carreras, Hongming Li, Po-Hao Chen","doi":"10.21037/jmai-20-30","DOIUrl":"https://doi.org/10.21037/jmai-20-30","url":null,"abstract":": Artificial intelligence (AI) promises wide-reaching impacts on the field of radiology, and has the potential to influence every aspect of image interpretation. In recent decades, significant advancements in computing power, combined with the availability of large data stores or “Big Data” and algorithm democratization have revolutionized AI and machine learning (ML). Research applications utilizing these technological advancements are booming, and their adoption is expected to continue to rise at a rapid pace. While AI and ML have impacted many components of the imaging value chain, the purpose of this article is to discuss interpretative uses of the technology as it relates to musculoskeletal (MSK) radiology. This review provides a general introduction to AI and ML concepts, and highlights the major promises, challenges, and anticipated future applications of these developments in MSK radiology. AI and ML advances for image interpretation can increase the value that MSK radiologists provide to their patients, referring clinicians, and organizations by increasing diagnostic accuracy while decreasing turnaround times, enhancing image processing and quantitative analysis, and by potentially improving patient outcomes. Familiarity with these processes among MSK clinicians and researchers will be paramount to the improvement and implementation of these new techniques into the clinical practice. Radiology departments, practices and practitioners who embrace these technologies now will be well-suited to lead this influential change in our field in the near future.","PeriodicalId":73815,"journal":{"name":"Journal of medical artificial intelligence","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48288816","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}
This survey summarizes the state of the art for type 2 diabetes mellitus (T2DM) prediction and compares the prediction accuracies obtained by conventional statistical regression and machine learning methods, including deep learning. The impact of feature selection and inclusion of clinical and genomic data on T2DM risk prediction accuracy is also reviewed. The results show that there is a tendency that machine learning algorithms outperform logistic regression in the accuracy of T2DM prediction. Inclusion of clinical data and biomarkers to the core feature set improves accuracy, while incorporating genetic markers in the prediction model is still challenging, due to dimensionality problem and the genetic heterogeneity of T2DM.
{"title":"Impact of machine learning and feature selection on type 2 diabetes risk prediction","authors":"Päivi Riihimaa","doi":"10.21037/jmai-20-4","DOIUrl":"https://doi.org/10.21037/jmai-20-4","url":null,"abstract":"This survey summarizes the state of the art for type 2 diabetes mellitus (T2DM) prediction and compares the prediction accuracies obtained by conventional statistical regression and machine learning methods, including deep learning. The impact of feature selection and inclusion of clinical and genomic data on T2DM risk prediction accuracy is also reviewed. The results show that there is a tendency that machine learning algorithms outperform logistic regression in the accuracy of T2DM prediction. Inclusion of clinical data and biomarkers to the core feature set improves accuracy, while incorporating genetic markers in the prediction model is still challenging, due to dimensionality problem and the genetic heterogeneity of T2DM.","PeriodicalId":73815,"journal":{"name":"Journal of medical artificial intelligence","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.21037/jmai-20-4","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48483365","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}
Pub Date : 2020-03-25DOI: 10.21037/jmai.2019.10.03
James P Howard, Jeremy Tan, Matthew J Shun-Shin, Dina Mahdi, Alexandra N Nowbar, Ahran D Arnold, Yousif Ahmad, Peter McCartney, Massoud Zolgharni, Nick W F Linton, Nilesh Sutaria, Bushra Rana, Jamil Mayet, Daniel Rueckert, Graham D Cole, Darrel P Francis
Echocardiography is the commonest medical ultrasound examination, but automated interpretation is challenging and hinges on correct recognition of the 'view' (imaging plane and orientation). Current state-of-the-art methods for identifying the view computationally involve 2-dimensional convolutional neural networks (CNNs), but these merely classify individual frames of a video in isolation, and ignore information describing the movement of structures throughout the cardiac cycle. Here we explore the efficacy of novel CNN architectures, including time-distributed networks and two-stream networks, which are inspired by advances in human action recognition. We demonstrate that these new architectures more than halve the error rate of traditional CNNs from 8.1% to 3.9%. These advances in accuracy may be due to these networks' ability to track the movement of specific structures such as heart valves throughout the cardiac cycle. Finally, we show the accuracies of these new state-of-the-art networks are approaching expert agreement (3.6% discordance), with a similar pattern of discordance between views.
{"title":"Improving ultrasound video classification: an evaluation of novel deep learning methods in echocardiography.","authors":"James P Howard, Jeremy Tan, Matthew J Shun-Shin, Dina Mahdi, Alexandra N Nowbar, Ahran D Arnold, Yousif Ahmad, Peter McCartney, Massoud Zolgharni, Nick W F Linton, Nilesh Sutaria, Bushra Rana, Jamil Mayet, Daniel Rueckert, Graham D Cole, Darrel P Francis","doi":"10.21037/jmai.2019.10.03","DOIUrl":"https://doi.org/10.21037/jmai.2019.10.03","url":null,"abstract":"<p><p>Echocardiography is the commonest medical ultrasound examination, but automated interpretation is challenging and hinges on correct recognition of the 'view' (imaging plane and orientation). Current state-of-the-art methods for identifying the view computationally involve 2-dimensional convolutional neural networks (CNNs), but these merely classify individual frames of a video in isolation, and ignore information describing the movement of structures throughout the cardiac cycle. Here we explore the efficacy of novel CNN architectures, including time-distributed networks and two-stream networks, which are inspired by advances in human action recognition. We demonstrate that these new architectures more than halve the error rate of traditional CNNs from 8.1% to 3.9%. These advances in accuracy may be due to these networks' ability to track the movement of specific structures such as heart valves throughout the cardiac cycle. Finally, we show the accuracies of these new state-of-the-art networks are approaching expert agreement (3.6% discordance), with a similar pattern of discordance between views.</p>","PeriodicalId":73815,"journal":{"name":"Journal of medical artificial intelligence","volume":"3 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.21037/jmai.2019.10.03","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"37784427","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 : 2020-03-01DOI: 10.21037/jmai.2019.10.04
Qingqing Xu, Li-ye Wang, S. Sansgiry
Background: Diabetic retinopathy, nephropathy and neuropathy in patients with type 1 diabetes (T1D) are microvascular complications that can adversely impact disease prognosis and incur greater healthcare costs. Early identification of patients at risk of these microvascular complications using predictive models through machine learning (ML) can be helpful in T1D management. The objective of current review was to systematically identify and summarize published predictive models that used ML to assess the risk of diabetic nephropathy, retinopathy and neuropathy in T1D patients. Methods: A targeted review of English literature was undertaken in PubMed (http://www.ncbi.nlm.nih. gov/pubmed) and Google Scholar (http://scholar.google.com/) from January 1, 2016 to May 31, 2019. Eligible articles were also identified from cross-references. Following concepts were used in combination to conduct the search queries: diabetes, retinopathy, nephropathy, neuropathy, microvascular complication, risk/predictive model, and ML/artificial intelligence/data mining. Results: A total of 3,769 hits were found from all sources combined, duplicates were removed, titles and abstracts were screened, 61 studies underwent full-text review and a total of six studies met the eligibility criteria. Among them, four studies had developed risk models using data obtained from T1D patients alone, whereas two used data from both T1D and type 2 diabetes (T2D) patients. There was only one study that evaluated all three types of microvascular complications while the other five focused on one individual complication, i.e., either diabetic retinopathy, nephropathy or neuropathy. Only two studies evaluated time to developing a complication. The other four studies assessed complications as either binary (yes/no) or categorical (multiple levels). Prediction models were built using cross-sectional data from survey questionnaire (n=1, Iran) and longitudinal data (n=5) which were further classified as sources of electronic medical records (EMR) (n=3, US: 1, Europe: 2), clinical trial (n=1, US) and prospective study (n=1, Europe). Common predictors across studies as well as across types of microvascular complications included age, gender, diabetes duration, BMI, blood pressure, lipid level, and mean or a single HbA1C value. Commonly used ML algorithms included classification and regression tree (CART) and random forest (RF) (CART/RF, n=3), support vector machines (SVMs, n=2), logistic regression (LR, n=2) and neural networks (NNs, n=1). Model performance was evaluated using area under curve (AUC, n=4) and accuracy (n=2). Only half (n=3) of the included studies tested their developed models in an external dataset of patients with T1D. Conclusions: Overall, very few studies reported predictive models for diabetic retinopathy, nephropathy and neuropathy using ML specifically for T1D patients. Future research that utilizes contemporary clinical data from T1D patients to predict the three types o
{"title":"A systematic literature review of predicting diabetic retinopathy, nephropathy and neuropathy in patients with type 1 diabetes using machine learning","authors":"Qingqing Xu, Li-ye Wang, S. Sansgiry","doi":"10.21037/jmai.2019.10.04","DOIUrl":"https://doi.org/10.21037/jmai.2019.10.04","url":null,"abstract":"Background: Diabetic retinopathy, nephropathy and neuropathy in patients with type 1 diabetes (T1D) are microvascular complications that can adversely impact disease prognosis and incur greater healthcare costs. Early identification of patients at risk of these microvascular complications using predictive models through machine learning (ML) can be helpful in T1D management. The objective of current review was to systematically identify and summarize published predictive models that used ML to assess the risk of diabetic nephropathy, retinopathy and neuropathy in T1D patients. \u0000 Methods: A targeted review of English literature was undertaken in PubMed (http://www.ncbi.nlm.nih. gov/pubmed) and Google Scholar (http://scholar.google.com/) from January 1, 2016 to May 31, 2019. Eligible articles were also identified from cross-references. Following concepts were used in combination to conduct the search queries: diabetes, retinopathy, nephropathy, neuropathy, microvascular complication, risk/predictive model, and ML/artificial intelligence/data mining. \u0000 Results: A total of 3,769 hits were found from all sources combined, duplicates were removed, titles and abstracts were screened, 61 studies underwent full-text review and a total of six studies met the eligibility criteria. Among them, four studies had developed risk models using data obtained from T1D patients alone, whereas two used data from both T1D and type 2 diabetes (T2D) patients. There was only one study that evaluated all three types of microvascular complications while the other five focused on one individual complication, i.e., either diabetic retinopathy, nephropathy or neuropathy. Only two studies evaluated time to developing a complication. The other four studies assessed complications as either binary (yes/no) or categorical (multiple levels). Prediction models were built using cross-sectional data from survey questionnaire (n=1, Iran) and longitudinal data (n=5) which were further classified as sources of electronic medical records (EMR) (n=3, US: 1, Europe: 2), clinical trial (n=1, US) and prospective study (n=1, Europe). Common predictors across studies as well as across types of microvascular complications included age, gender, diabetes duration, BMI, blood pressure, lipid level, and mean or a single HbA1C value. Commonly used ML algorithms included classification and regression tree (CART) and random forest (RF) (CART/RF, n=3), support vector machines (SVMs, n=2), logistic regression (LR, n=2) and neural networks (NNs, n=1). Model performance was evaluated using area under curve (AUC, n=4) and accuracy (n=2). Only half (n=3) of the included studies tested their developed models in an external dataset of patients with T1D. Conclusions: Overall, very few studies reported predictive models for diabetic retinopathy, nephropathy and neuropathy using ML specifically for T1D patients. Future research that utilizes contemporary clinical data from T1D patients to predict the three types o","PeriodicalId":73815,"journal":{"name":"Journal of medical artificial intelligence","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.21037/jmai.2019.10.04","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43339506","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}
Pub Date : 2019-12-03DOI: 10.21037/JMAI.2019.02.03
R. Dietz, L. Pantanowitz
This editorial is in response to the article on digital pathology published by Van Es (1), which is in turn a response to the articles published by Eric F. Glassy (2) and Thomas James Flotte (3). Our goal is to add what we feel are pertinent historical details and offer our perspective concerning the emerging role of digital pathology in anatomic pathology.
这篇社论是对Van Es(1)发表的关于数字病理学的文章的回应，这篇文章反过来是对Eric F. Glassy(2)和Thomas James Flotte(3)发表的文章的回应。我们的目标是添加我们认为相关的历史细节，并提供我们对数字病理学在解剖病理学中的新兴作用的看法。
{"title":"The future of anatomic pathology: deus ex machina?","authors":"R. Dietz, L. Pantanowitz","doi":"10.21037/JMAI.2019.02.03","DOIUrl":"https://doi.org/10.21037/JMAI.2019.02.03","url":null,"abstract":"This editorial is in response to the article on digital pathology published by Van Es (1), which is in turn a response to the articles published by Eric F. Glassy (2) and Thomas James Flotte (3). Our goal is to add what we feel are pertinent historical details and offer our perspective concerning the emerging role of digital pathology in anatomic pathology.","PeriodicalId":73815,"journal":{"name":"Journal of medical artificial intelligence","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.21037/JMAI.2019.02.03","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45070692","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}
Pub Date : 2019-12-01DOI: 10.21037/jmai.2019.10.02
{"title":"Application of the CARE guideline as reporting standard in the Journal of Medical Artificial Intelligence","authors":"","doi":"10.21037/jmai.2019.10.02","DOIUrl":"https://doi.org/10.21037/jmai.2019.10.02","url":null,"abstract":"","PeriodicalId":73815,"journal":{"name":"Journal of medical artificial intelligence","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.21037/jmai.2019.10.02","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43671637","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}
Pub Date : 2019-10-12DOI: 10.21037/jmai.2019.09.05
M. Montorsi, G. Capretti
The title of the work we are here presenting “ Diagnostic ability of artificial intelligence using deep learning analysis of cyst fluid in differentiating malignant from benign pancreatic cystic lesions ” immediately strikes the interest of readers, especially of the ones performing pancreatic surgery (1). This article debates a theme of major concern for surgeons, the correct identification of a pancreatic cystic lesion, and a theme of major concern for the medical society and the society in general, the application of artificial intelligence (AI).
{"title":"The prospect of artificial intelligence in the differential diagnosis of pancreatic cysts","authors":"M. Montorsi, G. Capretti","doi":"10.21037/jmai.2019.09.05","DOIUrl":"https://doi.org/10.21037/jmai.2019.09.05","url":null,"abstract":"The title of the work we are here presenting “ Diagnostic ability of artificial intelligence using deep learning analysis of cyst fluid in differentiating malignant from benign pancreatic cystic lesions ” immediately strikes the interest of readers, especially of the ones performing pancreatic surgery (1). This article debates a theme of major concern for surgeons, the correct identification of a pancreatic cystic lesion, and a theme of major concern for the medical society and the society in general, the application of artificial intelligence (AI).","PeriodicalId":73815,"journal":{"name":"Journal of medical artificial intelligence","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47930955","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}
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：