Osteoarthritis (OA) is a prevalent, disabling joint disease with no approved disease modifying treatments. We present a knowledge-graph based approach to discover candidate treatments for OA by integrating large-scale biomedical data. We introduce the Osteoarthritis Knowledge-graph (OKG), a comprehensive network derived from the Drug Repurposing Knowledge-graph (DRKG) and enriched with causal genetic associations from OA genome-wide association study (GWAS) involving nearly 2 million individuals. We propose CausalPathKG, a knowledge-graph embedding model built upon RotatE that integrates domain specific innovations: (i) weighted gene OA edges reflecting GWAS significance, (ii) a path based regularization term to encourage drug gene OA causal connectivity, (iii) multi hop graph attention to prioritize informative paths, and (iv) self adversarial negative sampling with type consistent corruptions for robust training. CausalPathKG was trained to predict missing links, while withholding known OA-related edges for testing. In experiments, CausalPathKG outperformed TransE and RotatE baselines in predicting held out OA treatments, achieving higher link prediction accuracy and classification performance. Case studies highlight that top ranked repurposed drugs engage key OA-associated genes and pathways identified in human genetics. These results demonstrate that incorporating genetic evidence into knowledge-graph models can improve the discovery of therapeutics, offering a computational strategy to bridge human genomic data with drug repurposing.
{"title":"Knowledge-graph embeddings for osteoarthritis candidate prediction.","authors":"Zhenggang Wang,Zhengyu Lu,Meng Li,Peiqing Zhao,Chengliang Zhang","doi":"10.1038/s41746-025-02290-x","DOIUrl":"https://doi.org/10.1038/s41746-025-02290-x","url":null,"abstract":"Osteoarthritis (OA) is a prevalent, disabling joint disease with no approved disease modifying treatments. We present a knowledge-graph based approach to discover candidate treatments for OA by integrating large-scale biomedical data. We introduce the Osteoarthritis Knowledge-graph (OKG), a comprehensive network derived from the Drug Repurposing Knowledge-graph (DRKG) and enriched with causal genetic associations from OA genome-wide association study (GWAS) involving nearly 2 million individuals. We propose CausalPathKG, a knowledge-graph embedding model built upon RotatE that integrates domain specific innovations: (i) weighted gene OA edges reflecting GWAS significance, (ii) a path based regularization term to encourage drug gene OA causal connectivity, (iii) multi hop graph attention to prioritize informative paths, and (iv) self adversarial negative sampling with type consistent corruptions for robust training. CausalPathKG was trained to predict missing links, while withholding known OA-related edges for testing. In experiments, CausalPathKG outperformed TransE and RotatE baselines in predicting held out OA treatments, achieving higher link prediction accuracy and classification performance. Case studies highlight that top ranked repurposed drugs engage key OA-associated genes and pathways identified in human genetics. These results demonstrate that incorporating genetic evidence into knowledge-graph models can improve the discovery of therapeutics, offering a computational strategy to bridge human genomic data with drug repurposing.","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"144 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2026-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145947412","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-10DOI: 10.1038/s41746-025-02312-8
Tara P Menon,Arjun Mahajan,Dylan Powell
{"title":"Foundation model embeddings for multimodal oncology data integration.","authors":"Tara P Menon,Arjun Mahajan,Dylan Powell","doi":"10.1038/s41746-025-02312-8","DOIUrl":"https://doi.org/10.1038/s41746-025-02312-8","url":null,"abstract":"","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"125 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2026-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145937742","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-10DOI: 10.1038/s41746-025-02317-3
Valentin Max Vetter, Tobias Kurth, Stefan Konigorski
Physicians face intense work-related stress, which can harm their health, increase the risk of medical errors, lower healthcare quality, and increase costs within the healthcare system. In this 4-week intervention study, individual-level and population-level effects of two short and easy-to-perform breathing exercises designed to reduce stress are evaluated among 76 physicians in residency in Germany in a series of N-of-1 trials. Levels of stress and levels of stress expected for the following day were assessed electronically every day via the StudyU App (protocol adherence: 91.9%). Average intervention effects were estimated using Bayesian linear regression models. They were overall small on the population level, but they showed large heterogeneity between individuals, with strong effects for selected individuals, with stress reduction of up to 3 points on a 1 to 10 stress scale. Thirty-one participants benefited from the anti-stress exercises. Three (mindfulness breathing) and seven participants (box breathing) had a ≥70% probability for a daily stress reduction of ≥0.5 points and thereby fulfilled our responder criteria. Of the 17 participants who completed the follow-up survey about 4.5 months after completion of the individual N-of-1 trials, 58% reported that they felt they had benefited from the intervention and 42% planned to use it in the future. The results highlight the value of personalized perspectives: while the studied interventions showed only small positive benefits for the “average person”, they may well help actual individual persons, here 10 of 76 or even 31 of 76 participants.
{"title":"Evaluation of two easy-to-implement digital breathing interventions in the context of daily stress levels in a series of N-of-1 trials: results from the Anti-Stress Intervention Among Physicians (ASIP) study","authors":"Valentin Max Vetter, Tobias Kurth, Stefan Konigorski","doi":"10.1038/s41746-025-02317-3","DOIUrl":"https://doi.org/10.1038/s41746-025-02317-3","url":null,"abstract":"Physicians face intense work-related stress, which can harm their health, increase the risk of medical errors, lower healthcare quality, and increase costs within the healthcare system. In this 4-week intervention study, individual-level and population-level effects of two short and easy-to-perform breathing exercises designed to reduce stress are evaluated among 76 physicians in residency in Germany in a series of N-of-1 trials. Levels of stress and levels of stress expected for the following day were assessed electronically every day via the StudyU App (protocol adherence: 91.9%). Average intervention effects were estimated using Bayesian linear regression models. They were overall small on the population level, but they showed large heterogeneity between individuals, with strong effects for selected individuals, with stress reduction of up to 3 points on a 1 to 10 stress scale. Thirty-one participants benefited from the anti-stress exercises. Three (mindfulness breathing) and seven participants (box breathing) had a ≥70% probability for a daily stress reduction of ≥0.5 points and thereby fulfilled our responder criteria. Of the 17 participants who completed the follow-up survey about 4.5 months after completion of the individual N-of-1 trials, 58% reported that they felt they had benefited from the intervention and 42% planned to use it in the future. The results highlight the value of personalized perspectives: while the studied interventions showed only small positive benefits for the “average person”, they may well help actual individual persons, here 10 of 76 or even 31 of 76 participants.","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"25 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2026-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145938203","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Apple Watch provides continuous monitoring of physiological and behavioural health metrics, increasingly used to support health-care delivery. Yet, evidence regarding its measurement accuracy remains limited. We aimed to assess the accuracy of measurements from Apple Watch. We searched nine databases from inception to September 24, 2025, with no restrictions on language or publication type. Eligible studies validated any Apple Watch health metric against a criterion method. The primary outcome was the agreement between Apple Watch and the criterion. We included 82 studies, which assessed 14 health metrics (430,052 participants; pooled mean age 41.3 years [SD 13.3]). Bland-Altman meta-analysis showed a small underestimation of heart rate, although limits of agreement (LoA) indicated moderate measurement variability (mean bias -0.27 bpm [95% CI -0.72-0.17]; LoA -7.19 to 6.64). For atrial fibrillation detection, Apple Watch was more specific than sensitive (specificity 0.91 [95% CI 0.81-0.96]; sensitivity 0.79 [95% CI 0.61-0.90]). For blood oxygen saturation, there was low mean bias (-0.04% [95% CI -0.42-0.35]) but wide limits of agreement (-4.00 to 3.94). Accuracy for sleep and step count was moderate, whereas error for energy expenditure was inconsistent and frequently large. Measurement accuracy varied by metric, measurement conditions, and individual physiology. Longitudinal validation of key clinical metrics, including vital signs, is needed to inform clinical practice and policy. This study was registered with PROSPERO, CRD42023481841.
Apple Watch提供对生理和行为健康指标的持续监测，越来越多地用于支持医疗保健服务。然而，关于其测量精度的证据仍然有限。我们的目的是评估Apple Watch测量的准确性。我们检索了9个数据库，从成立到2025年9月24日，没有语言和出版类型的限制。符合条件的研究根据标准方法验证了Apple Watch的任何健康指标。主要结果是Apple Watch与标准之间的一致。我们纳入了82项研究，评估了14项健康指标（430,052名参与者，合并平均年龄41.3岁[SD 13.3]）。Bland-Altman荟萃分析显示心率有轻微低估，尽管一致性限（LoA）显示中度测量变异性（平均偏差-0.27 bpm [95% CI -0.72-0.17]; LoA -7.19至6.64）。对于心房颤动的检测，Apple Watch的特异度大于敏感性（特异性0.91 [95% CI 0.81-0.96]；敏感性0.79 [95% CI 0.61-0.90]）。对于血氧饱和度，平均偏差较低（-0.04% [95% CI -0.42-0.35]），但一致性范围较广（-4.00至3.94）。睡眠和步数的准确性中等，而能量消耗的误差不一致，而且经常很大。测量精度因度量、测量条件和个体生理而异。需要对包括生命体征在内的关键临床指标进行纵向验证，以便为临床实践和政策提供信息。本研究注册号为PROSPERO， CRD42023481841。
{"title":"The accuracy of Apple Watch measurements: a living systematic review and meta-analysis.","authors":"Rory Lambe,Maximus Baldwin,Ben O'Grady,Moritz Schumann,Brian Caulfield,Cailbhe Doherty","doi":"10.1038/s41746-025-02238-1","DOIUrl":"https://doi.org/10.1038/s41746-025-02238-1","url":null,"abstract":"Apple Watch provides continuous monitoring of physiological and behavioural health metrics, increasingly used to support health-care delivery. Yet, evidence regarding its measurement accuracy remains limited. We aimed to assess the accuracy of measurements from Apple Watch. We searched nine databases from inception to September 24, 2025, with no restrictions on language or publication type. Eligible studies validated any Apple Watch health metric against a criterion method. The primary outcome was the agreement between Apple Watch and the criterion. We included 82 studies, which assessed 14 health metrics (430,052 participants; pooled mean age 41.3 years [SD 13.3]). Bland-Altman meta-analysis showed a small underestimation of heart rate, although limits of agreement (LoA) indicated moderate measurement variability (mean bias -0.27 bpm [95% CI -0.72-0.17]; LoA -7.19 to 6.64). For atrial fibrillation detection, Apple Watch was more specific than sensitive (specificity 0.91 [95% CI 0.81-0.96]; sensitivity 0.79 [95% CI 0.61-0.90]). For blood oxygen saturation, there was low mean bias (-0.04% [95% CI -0.42-0.35]) but wide limits of agreement (-4.00 to 3.94). Accuracy for sleep and step count was moderate, whereas error for energy expenditure was inconsistent and frequently large. Measurement accuracy varied by metric, measurement conditions, and individual physiology. Longitudinal validation of key clinical metrics, including vital signs, is needed to inform clinical practice and policy. This study was registered with PROSPERO, CRD42023481841.","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"3 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2026-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145937765","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Artificial intelligence has facilitated the automated selection of embryos and the prediction of pregnancy outcomes during in vitro fertilization (IVF), yet multimodal approaches remain underexplored-particularly for predicting multiple specific outcomes such as singleton pregnancy vs. multiple pregnancy, and miscarriage vs. live birth. In this study, we propose VaTEP (Video and Table model for Embryo Prediction), a multimodal embryo prediction model integrating time-lapse system (TLS) videos and tabular clinical variables. VaTEP is first pretrained on two pre-tasks (TLS video reconstruction and embryo developmental phase prediction) to fully capture the rich spatiotemporal dynamics and developmental information contained in the video, and further improved by a multiple frame sampling strategy and multitask learning framework. These designs enable VaTEP to estimate the probabilities of fetal heartbeat, singleton vs. multiple pregnancy, and miscarriage vs. live birth, promoting more informed embryo selection and outcome precognition. This helps reduce the risk of implantation failure by minimizing the chances of non-viable pregnancies, multiple gestations, and miscarriages. VaTEP offers a comprehensive and data-driven tool for personalized IVF decision-making, supporting safer and more effective reproductive treatment.
人工智能促进了体外受精（IVF）过程中胚胎的自动选择和妊娠结果的预测，但多模式方法仍未得到充分探索，特别是在预测多种特定结果方面，如单胎妊娠与多胎妊娠，流产与活产。在这项研究中，我们提出了VaTEP (Video and Table model for Embryo Prediction)，这是一种结合延时系统（TLS）视频和表格临床变量的多模态胚胎预测模型。VaTEP首先在TLS视频重构和胚胎发育阶段预测两个预任务上进行预训练，充分捕捉视频中丰富的时空动态和发育信息，并通过多帧采样策略和多任务学习框架进一步改进。这些设计使VaTEP能够估计胎儿心跳、单胎与多胎妊娠、流产与活产的概率，促进更明智的胚胎选择和结果预知。这有助于降低着床失败的风险，最大限度地减少无法存活的怀孕，多胎妊娠和流产的机会。VaTEP为个性化试管婴儿决策提供了全面和数据驱动的工具，支持更安全、更有效的生殖治疗。
{"title":"Multimodal intelligent prediction model for in vitro fertilization.","authors":"Qiang Gao,Siqiong Yao,Dan Du,Fan Yang,Ping Yu,Shouneng Quan,Renyi Hua,Lihua Zhao,Anquan Shang,Hui Lu,Chaoyan Yue","doi":"10.1038/s41746-025-02331-5","DOIUrl":"https://doi.org/10.1038/s41746-025-02331-5","url":null,"abstract":"Artificial intelligence has facilitated the automated selection of embryos and the prediction of pregnancy outcomes during in vitro fertilization (IVF), yet multimodal approaches remain underexplored-particularly for predicting multiple specific outcomes such as singleton pregnancy vs. multiple pregnancy, and miscarriage vs. live birth. In this study, we propose VaTEP (Video and Table model for Embryo Prediction), a multimodal embryo prediction model integrating time-lapse system (TLS) videos and tabular clinical variables. VaTEP is first pretrained on two pre-tasks (TLS video reconstruction and embryo developmental phase prediction) to fully capture the rich spatiotemporal dynamics and developmental information contained in the video, and further improved by a multiple frame sampling strategy and multitask learning framework. These designs enable VaTEP to estimate the probabilities of fetal heartbeat, singleton vs. multiple pregnancy, and miscarriage vs. live birth, promoting more informed embryo selection and outcome precognition. This helps reduce the risk of implantation failure by minimizing the chances of non-viable pregnancies, multiple gestations, and miscarriages. VaTEP offers a comprehensive and data-driven tool for personalized IVF decision-making, supporting safer and more effective reproductive treatment.","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"48 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2026-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145947402","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-10DOI: 10.1038/s41746-025-02271-0
Haris Smajlović,Yi Lian,Qi Long,Ibrahim Numanagić,Xiaoqian Jiang
Scattered between many healthcare providers across the US, Electronic Health Records (EHR) are extensively used for research purposes. Collaboration and sharing of EHRs between multiple institutions often provide access to more diverse datasets and a chance to conduct comprehensive studies. However, these collaboration efforts are usually hindered by privacy issues that render the pooling of such data at a centralized database impossible. Furthermore, EHRs are often incomplete and require statistical imputation prior to the study. To enable collaborative studies on top of incomplete, private EHRs, here we provide a provably secure solution built with secure multiparty computation (SMC) that provides practical runtimes and accuracy on par with the state-of-the-art, non-secure equivalents. Our solution enables the utilization of distributed datasets as a whole to impute the missing data and conduct collective studies between non-trusting private data proprietors. We demonstrate its effectiveness on various synthetic and real-world datasets, and show that our solution can significantly improve the classification of high-risk patient outcomes during ICU admission.
{"title":"Secure distributed multiple imputation enables missing data inference for private data proprietors.","authors":"Haris Smajlović,Yi Lian,Qi Long,Ibrahim Numanagić,Xiaoqian Jiang","doi":"10.1038/s41746-025-02271-0","DOIUrl":"https://doi.org/10.1038/s41746-025-02271-0","url":null,"abstract":"Scattered between many healthcare providers across the US, Electronic Health Records (EHR) are extensively used for research purposes. Collaboration and sharing of EHRs between multiple institutions often provide access to more diverse datasets and a chance to conduct comprehensive studies. However, these collaboration efforts are usually hindered by privacy issues that render the pooling of such data at a centralized database impossible. Furthermore, EHRs are often incomplete and require statistical imputation prior to the study. To enable collaborative studies on top of incomplete, private EHRs, here we provide a provably secure solution built with secure multiparty computation (SMC) that provides practical runtimes and accuracy on par with the state-of-the-art, non-secure equivalents. Our solution enables the utilization of distributed datasets as a whole to impute the missing data and conduct collective studies between non-trusting private data proprietors. We demonstrate its effectiveness on various synthetic and real-world datasets, and show that our solution can significantly improve the classification of high-risk patient outcomes during ICU admission.","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"5 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2026-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145937743","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-10DOI: 10.1038/s41746-026-02339-5
Adnan Jafar, Xun Jia
Current radiation therapy treatment planning is limited by suboptimal plan quality, inefficiency, and high costs. This perspective paper explores the complexity of treatment planning and introduces Human-Centric Intelligent Treatment Planning (HCITP), an AI-driven framework under human oversight, which integrates clinical guidelines, automates plan generation, and enables direct interaction with planners. We expect that HCITP will enhance efficiency, potentially reducing planning time to minutes, and will deliver personalized, high-quality plans. Challenges and potential solutions are discussed.
{"title":"Towards human-centric intelligent treatment planning for radiation therapy","authors":"Adnan Jafar, Xun Jia","doi":"10.1038/s41746-026-02339-5","DOIUrl":"https://doi.org/10.1038/s41746-026-02339-5","url":null,"abstract":"Current radiation therapy treatment planning is limited by suboptimal plan quality, inefficiency, and high costs. This perspective paper explores the complexity of treatment planning and introduces Human-Centric Intelligent Treatment Planning (HCITP), an AI-driven framework under human oversight, which integrates clinical guidelines, automates plan generation, and enables direct interaction with planners. We expect that HCITP will enhance efficiency, potentially reducing planning time to minutes, and will deliver personalized, high-quality plans. Challenges and potential solutions are discussed.","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"3 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2026-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145938177","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-10DOI: 10.1038/s41746-025-02262-1
David Weiss, Thomas Hager, MingDe Lin, Durga Sritharan, Khaled Bousabarah, Daniel Renninghoff, Wolfgang Holler, Kathryn Simmons, Johannes Haubold, Sarah Loh, Uwe Fischer, Julius Chapiro, Cornelius Deuschl, Mariam Aboian, Edouard Aboian, Sanjay Aneja
{"title":"Deep learning based volumetric analysis of infrarenal abdominal aortic aneurysms characterized on CTA","authors":"David Weiss, Thomas Hager, MingDe Lin, Durga Sritharan, Khaled Bousabarah, Daniel Renninghoff, Wolfgang Holler, Kathryn Simmons, Johannes Haubold, Sarah Loh, Uwe Fischer, Julius Chapiro, Cornelius Deuschl, Mariam Aboian, Edouard Aboian, Sanjay Aneja","doi":"10.1038/s41746-025-02262-1","DOIUrl":"https://doi.org/10.1038/s41746-025-02262-1","url":null,"abstract":"","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"140 1","pages":""},"PeriodicalIF":15.2,"publicationDate":"2026-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145938205","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","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：