Nature Medicine最新文献

{"title":"Evaluating generalizability of oncology trial results to real-world patients using machine learning-based trial emulations","authors":"Xavier Orcutt, Kan Chen, Ronac Mamtani, Qi Long, Ravi B. Parikh","doi":"10.1038/s41591-024-03352-5","DOIUrl":"https://doi.org/10.1038/s41591-024-03352-5","url":null,"abstract":"<p>Randomized controlled trials (RCTs) evaluating anti-cancer agents often lack generalizability to real-world oncology patients. Although restrictive eligibility criteria contribute to this issue, the role of selection bias related to prognostic risk remains unclear. In this study, we developed TrialTranslator, a framework designed to systematically evaluate the generalizability of RCTs for oncology therapies. Using a nationwide database of electronic health records from Flatiron Health, this framework emulates RCTs across three prognostic phenotypes identified through machine learning models. We applied this approach to 11 landmark RCTs that investigated anti-cancer regimens considered standard of care for the four most prevalent advanced solid malignancies. Our analyses reveal that patients in low-risk and medium-risk phenotypes exhibit survival times and treatment-associated survival benefits similar to those observed in RCTs. In contrast, high-risk phenotypes show significantly lower survival times and treatment-associated survival benefits compared to RCTs. Our results were corroborated by a comprehensive robustness assessment, including examinations of specific patient subgroups, holdout validation and semi-synthetic data simulation. These findings suggest that the prognostic heterogeneity among real-world oncology patients plays a substantial role in the limited generalizability of RCT results. Machine learning frameworks may facilitate individual patient-level decision support and estimation of real-world treatment benefits to guide trial design.</p>","PeriodicalId":19037,"journal":{"name":"Nature Medicine","volume":"208 1","pages":""},"PeriodicalIF":82.9,"publicationDate":"2025-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142916975","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}

{"title":"Singing for health: a participatory process to design a song-based intervention for hypertension","authors":"Ifedola I. Olojo,&nbsp;Chidi Okafor,&nbsp;Ihediwa F. Chimchetaram,&nbsp;Olajide Williams,&nbsp;Folahanmi Akinsolu,&nbsp;Juliet Iwelunmor,&nbsp;Oliver Ezechi,&nbsp;Joseph D. Tucker","doi":"10.1038/s41591-024-03377-w","DOIUrl":"10.1038/s41591-024-03377-w","url":null,"abstract":"","PeriodicalId":19037,"journal":{"name":"Nature Medicine","volume":"31 1","pages":"16-17"},"PeriodicalIF":58.7,"publicationDate":"2025-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142916967","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}

{"title":"Preparedness and priority research to tackle the mpox outbreak response","authors":"Ali Azizi,&nbsp;Kristine Rose,&nbsp;Gathoni Kamuyu,&nbsp;Deborah Ogbeni,&nbsp;Valentina Bernasconi","doi":"10.1038/s41591-024-03367-y","DOIUrl":"10.1038/s41591-024-03367-y","url":null,"abstract":"","PeriodicalId":19037,"journal":{"name":"Nature Medicine","volume":"31 1","pages":"14-15"},"PeriodicalIF":58.7,"publicationDate":"2025-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142916970","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}

{"title":"How a medical mystery led to a cure for viral hepatitis","authors":"T. Jake Liang","doi":"10.1038/s41591-024-03368-x","DOIUrl":"10.1038/s41591-024-03368-x","url":null,"abstract":"T. Jake Liang describes how meeting a patient with fulminant hepatitis led to a collaboration that resulted in the first infectious clone of hepatitis C virus.","PeriodicalId":19037,"journal":{"name":"Nature Medicine","volume":"31 1","pages":"8-8"},"PeriodicalIF":58.7,"publicationDate":"2025-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142916968","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}

{"title":"Gene therapy targets the retina to treat eye disease","authors":"Carrie Arnold","doi":"10.1038/s41591-024-03454-0","DOIUrl":"10.1038/s41591-024-03454-0","url":null,"abstract":"Several gene therapies are hoped to cure blindness and other eye diseases.","PeriodicalId":19037,"journal":{"name":"Nature Medicine","volume":"31 1","pages":"2-3"},"PeriodicalIF":58.7,"publicationDate":"2025-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142911750","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}

{"title":"Genetic insights into global heterogeneity of type 2 diabetes","authors":"Miriam S. Udler","doi":"10.1038/s41591-024-03413-9","DOIUrl":"10.1038/s41591-024-03413-9","url":null,"abstract":"In people of South Asia ancestry, specific genetic mechanisms may drive diabetes development, as revealed by a new study offering insights into global diabetes heterogeneity and potential avenues toward precision medicine.","PeriodicalId":19037,"journal":{"name":"Nature Medicine","volume":"31 1","pages":"35-36"},"PeriodicalIF":58.7,"publicationDate":"2025-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142911749","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}

{"title":"Can quantum computing crack the biggest challenges in health?","authors":"Marianne Guenot","doi":"10.1038/s41591-024-03369-w","DOIUrl":"10.1038/s41591-024-03369-w","url":null,"abstract":"Quantum computing can model molecular interactions for drug discovery and analyze complex health datasets, but better hardware is needed.","PeriodicalId":19037,"journal":{"name":"Nature Medicine","volume":"31 1","pages":"4-7"},"PeriodicalIF":58.7,"publicationDate":"2025-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142911751","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}

{"title":"Structured programs to train the next generation of clinician scientists","authors":"Anette Melk,&nbsp;Carl Grabitz,&nbsp;Johanna Ernst,&nbsp;Thorsten Saenger,&nbsp;Eva Degraeuwe,&nbsp;Beatrice Beck Schimmer,&nbsp;Johan Vande Walle,&nbsp;Karolis Ažukaitis,&nbsp;Berent Prakken,&nbsp;Elias Campo,&nbsp;Michela Giulia Bertero","doi":"10.1038/s41591-024-03339-2","DOIUrl":"10.1038/s41591-024-03339-2","url":null,"abstract":"Structured programs for training clinician scientists have been implemented in several European countries, but these must include adequate resourcing and mentoring and foster career opportunities.","PeriodicalId":19037,"journal":{"name":"Nature Medicine","volume":"31 1","pages":"24-27"},"PeriodicalIF":58.7,"publicationDate":"2025-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142911752","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}

{"title":"Combined endurance and resistance exercise training in heart failure with preserved ejection fraction: a randomized controlled trial","authors":"Frank Edelmann,&nbsp;Rolf Wachter,&nbsp;André Duvinage,&nbsp;Stephan Mueller,&nbsp;Isabel Fegers-Wustrow,&nbsp;Silja Schwarz,&nbsp;Jeffrey W. Christle,&nbsp;Elisabeth Pieske-Kraigher,&nbsp;Melchior Seyfarth,&nbsp;Markus Knapp,&nbsp;Marcus Dörr,&nbsp;Kathleen Nolte,&nbsp;Hans-Dirk Düngen,&nbsp;Christoph Herrmann-Lingen,&nbsp;Katrin Esefeld,&nbsp;Andreas Hagendorff,&nbsp;Mark J. Haykowsky,&nbsp;Gerd Hasenfuss,&nbsp;Volker Holzendorf,&nbsp;Christiane Prettin,&nbsp;Meinhard Mende,&nbsp;Burkert Pieske,&nbsp;Martin Halle","doi":"10.1038/s41591-024-03342-7","DOIUrl":"10.1038/s41591-024-03342-7","url":null,"abstract":"Endurance exercise training (ET) is an effective treatment in heart failure with preserved ejection fraction (HFpEF), but the efficacy of resistance training in this patient population has been only scarcely evaluated. In this multicenter, randomized trial, we evaluated the effects of combined endurance and resistance training over 12 months in patients with HFpEF. The primary endpoint was a modified Packer score, including all-cause mortality, hospitalizations classified as potentially related to heart failure or exercise and changes in peak oxygen consumption ( $${dot{rm{V}}}{rm{O}}_2$$ ), diastolic function (E/e′), New York Heart Association (NYHA) class and global self-assessment (GSA). In total, 322 patients (mean age, 70 years; 192 females (59.6%) and 130 males (40.4%)) were randomized (1:1) to ET or usual care (UC). At 12 months, the modified Packer score showed an improvement in 33 ET patients (20.5%) and in 13 UC patients (8.1%) and showed a worsening in 69 ET patients (42.9%) and in 71 UC patients (44.1%) (Kendall’s tau-b = −0.073, P = 0.17). Although the primary endpoint was not met, clinically relevant differences favoring the ET group as compared to the UC group were observed for the following secondary endpoints: changes in peak $${dot{rm{V}}}{rm{O}}_2$$ (mean difference, 1.3 ml kg−1 min−1 (95% confidence interval (CI): 0.4–2.1)) and NYHA class (odds ratio = 7.77 (95% CI: 3.73–16.21)). No significant between-group differences were observed for other secondary endpoints, including change in E/e′, change in GSA, time to cardiovascular hospitalization or all-cause mortality. In conclusion, 1 year of combined endurance and resistance ET did not result in a significantly better modified Packer score, but it did result in improvements in important clinical parameters, such as peak $${dot{rm{V}}}{rm{O}}_2$$ and NYHA class, as compared to UC. ISRCTN registration: ISRCTN86879094 . In a multicenter, randomized trial, patients with heart failure with preserved ejection fraction who underwent a regimen of combined endurance and resistance exercise training over the course of 1 year did not show a statistically significant improvement in the modified Packer score—the primary efficacy endpoint—as compared to patients who received usual care, but they did show improvements in secondary endpoints for maximal oxygen consumption and NYHA heart failure class.","PeriodicalId":19037,"journal":{"name":"Nature Medicine","volume":"31 1","pages":"306-314"},"PeriodicalIF":58.7,"publicationDate":"2025-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s41591-024-03342-7.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142911757","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"International multicenter validation of AI-driven ultrasound detection of ovarian cancer","authors":"Filip Christiansen,&nbsp;Emir Konuk,&nbsp;Adithya Raju Ganeshan,&nbsp;Robert Welch,&nbsp;Joana Palés Huix,&nbsp;Artur Czekierdowski,&nbsp;Francesco Paolo Giuseppe Leone,&nbsp;Lucia Anna Haak,&nbsp;Robert Fruscio,&nbsp;Adrius Gaurilcikas,&nbsp;Dorella Franchi,&nbsp;Daniela Fischerova,&nbsp;Elisa Mor,&nbsp;Luca Savelli,&nbsp;Maria Àngela Pascual,&nbsp;Marek Jerzy Kudla,&nbsp;Stefano Guerriero,&nbsp;Francesca Buonomo,&nbsp;Karina Liuba,&nbsp;Nina Montik,&nbsp;Juan Luis Alcázar,&nbsp;Ekaterini Domali,&nbsp;Nelinda Catherine P. Pangilinan,&nbsp;Chiara Carella,&nbsp;Maria Munaretto,&nbsp;Petra Saskova,&nbsp;Debora Verri,&nbsp;Chiara Visenzi,&nbsp;Pawel Herman,&nbsp;Kevin Smith,&nbsp;Elisabeth Epstein","doi":"10.1038/s41591-024-03329-4","DOIUrl":"10.1038/s41591-024-03329-4","url":null,"abstract":"Ovarian lesions are common and often incidentally detected. A critical shortage of expert ultrasound examiners has raised concerns of unnecessary interventions and delayed cancer diagnoses. Deep learning has shown promising results in the detection of ovarian cancer in ultrasound images; however, external validation is lacking. In this international multicenter retrospective study, we developed and validated transformer-based neural network models using a comprehensive dataset of 17,119 ultrasound images from 3,652 patients across 20 centers in eight countries. Using a leave-one-center-out cross-validation scheme, for each center in turn, we trained a model using data from the remaining centers. The models demonstrated robust performance across centers, ultrasound systems, histological diagnoses and patient age groups, significantly outperforming both expert and non-expert examiners on all evaluated metrics, namely F1 score, sensitivity, specificity, accuracy, Cohen’s kappa, Matthew’s correlation coefficient, diagnostic odds ratio and Youden’s J statistic. Furthermore, in a retrospective triage simulation, artificial intelligence (AI)-driven diagnostic support reduced referrals to experts by 63% while significantly surpassing the diagnostic performance of the current practice. These results show that transformer-based models exhibit strong generalization and above human expert-level diagnostic accuracy, with the potential to alleviate the shortage of expert ultrasound examiners and improve patient outcomes. In a comprehensive dataset from 3,652 patients across 20 centers in eight countries, an ultrasound-based AI model shows robust performance across centers, ultrasound systems, 58 histological diagnoses and patient age groups and reduced referral to experts by 63% in a retrospective triage simulation.","PeriodicalId":19037,"journal":{"name":"Nature Medicine","volume":"31 1","pages":"189-196"},"PeriodicalIF":58.7,"publicationDate":"2025-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s41591-024-03329-4.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142911758","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}