Alexander Fiedler, Mehran Dadras, Marius Drysch, Sonja Verena Schmidt, Flemming Puscz, Felix Reinkemeier, Marcus Lehnhardt, Christoph Wallner
{"title":"组织分级、肿瘤宽度和高血压预测儿童肉瘤早期复发:一项lasso正则化微队列研究。","authors":"Alexander Fiedler, Mehran Dadras, Marius Drysch, Sonja Verena Schmidt, Flemming Puscz, Felix Reinkemeier, Marcus Lehnhardt, Christoph Wallner","doi":"10.3390/children12060806","DOIUrl":null,"url":null,"abstract":"<p><p><b>Background/Objectives</b>: Pediatric sarcomas are a biologically diverse group of mesenchymal tumors associated with morbidity due to recurrence, despite aggressive multimodal treatment. Reliable predictors of early recurrence remain limited. This exploratory study aimed to identify clinical features associated with first tumor recurrence using a machine learning approach tailored to low-event settings. <b>Methods</b>: We conducted a retrospective, single-center cohort study of 23 pediatric patients with histologically confirmed sarcoma. Forty-six baseline variables were extracted per patient, including clinical, histological, and comorbidity data. Tumor recurrence was the primary binary endpoint. A LASSO-regularized logistic regression model was developed using leave-one-out cross-validation (LOOCV) to identify the most informative predictors. Dimensionality reduction (PCA) and SHAP-value analyses were used to visualize patient clustering and interpret variable contributions. <b>Results</b>: The model identified a four-variable risk signature comprising histological grade, primary tumor width, arterial hypertension, and extremity localization. Each additional tumor grade or centimeter of width approximately doubled the odds of recurrence (OR 2.18 and 2.04, respectively). Hypertension and limb location were associated with a 1.7 and 1.9 odds ratio of recurrence, respectively. The model achieved a balanced accuracy of 0.61 ± 0.08 and AUROC of 0.47 ± 0.12, reflecting limited discriminative power. PCA mapping revealed distinct outlier patterns correlating with high-risk profiles. <b>Conclusions</b>: Even in a small cohort, classical prognostic markers, such as tumor grade and size, retained predictive relevance, while hypertension emerged as a novel, potentially modifiable cofactor or indicator for recurrence. Although model performance was modest, the findings are hypothesis-generating and warrant validation in larger prospective datasets.</p>","PeriodicalId":48588,"journal":{"name":"Children-Basel","volume":"12 6","pages":""},"PeriodicalIF":2.0000,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12191661/pdf/","citationCount":"0","resultStr":"{\"title\":\"Histological Grade, Tumor Breadth, and Hypertension Predict Early Recurrence in Pediatric Sarcoma: A LASSO-Regularized Micro-Cohort Study.\",\"authors\":\"Alexander Fiedler, Mehran Dadras, Marius Drysch, Sonja Verena Schmidt, Flemming Puscz, Felix Reinkemeier, Marcus Lehnhardt, Christoph Wallner\",\"doi\":\"10.3390/children12060806\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p><b>Background/Objectives</b>: Pediatric sarcomas are a biologically diverse group of mesenchymal tumors associated with morbidity due to recurrence, despite aggressive multimodal treatment. Reliable predictors of early recurrence remain limited. This exploratory study aimed to identify clinical features associated with first tumor recurrence using a machine learning approach tailored to low-event settings. <b>Methods</b>: We conducted a retrospective, single-center cohort study of 23 pediatric patients with histologically confirmed sarcoma. Forty-six baseline variables were extracted per patient, including clinical, histological, and comorbidity data. Tumor recurrence was the primary binary endpoint. A LASSO-regularized logistic regression model was developed using leave-one-out cross-validation (LOOCV) to identify the most informative predictors. Dimensionality reduction (PCA) and SHAP-value analyses were used to visualize patient clustering and interpret variable contributions. <b>Results</b>: The model identified a four-variable risk signature comprising histological grade, primary tumor width, arterial hypertension, and extremity localization. Each additional tumor grade or centimeter of width approximately doubled the odds of recurrence (OR 2.18 and 2.04, respectively). Hypertension and limb location were associated with a 1.7 and 1.9 odds ratio of recurrence, respectively. The model achieved a balanced accuracy of 0.61 ± 0.08 and AUROC of 0.47 ± 0.12, reflecting limited discriminative power. PCA mapping revealed distinct outlier patterns correlating with high-risk profiles. <b>Conclusions</b>: Even in a small cohort, classical prognostic markers, such as tumor grade and size, retained predictive relevance, while hypertension emerged as a novel, potentially modifiable cofactor or indicator for recurrence. Although model performance was modest, the findings are hypothesis-generating and warrant validation in larger prospective datasets.</p>\",\"PeriodicalId\":48588,\"journal\":{\"name\":\"Children-Basel\",\"volume\":\"12 6\",\"pages\":\"\"},\"PeriodicalIF\":2.0000,\"publicationDate\":\"2025-06-19\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12191661/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Children-Basel\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.3390/children12060806\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"PEDIATRICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Children-Basel","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.3390/children12060806","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"PEDIATRICS","Score":null,"Total":0}
Histological Grade, Tumor Breadth, and Hypertension Predict Early Recurrence in Pediatric Sarcoma: A LASSO-Regularized Micro-Cohort Study.
Background/Objectives: Pediatric sarcomas are a biologically diverse group of mesenchymal tumors associated with morbidity due to recurrence, despite aggressive multimodal treatment. Reliable predictors of early recurrence remain limited. This exploratory study aimed to identify clinical features associated with first tumor recurrence using a machine learning approach tailored to low-event settings. Methods: We conducted a retrospective, single-center cohort study of 23 pediatric patients with histologically confirmed sarcoma. Forty-six baseline variables were extracted per patient, including clinical, histological, and comorbidity data. Tumor recurrence was the primary binary endpoint. A LASSO-regularized logistic regression model was developed using leave-one-out cross-validation (LOOCV) to identify the most informative predictors. Dimensionality reduction (PCA) and SHAP-value analyses were used to visualize patient clustering and interpret variable contributions. Results: The model identified a four-variable risk signature comprising histological grade, primary tumor width, arterial hypertension, and extremity localization. Each additional tumor grade or centimeter of width approximately doubled the odds of recurrence (OR 2.18 and 2.04, respectively). Hypertension and limb location were associated with a 1.7 and 1.9 odds ratio of recurrence, respectively. The model achieved a balanced accuracy of 0.61 ± 0.08 and AUROC of 0.47 ± 0.12, reflecting limited discriminative power. PCA mapping revealed distinct outlier patterns correlating with high-risk profiles. Conclusions: Even in a small cohort, classical prognostic markers, such as tumor grade and size, retained predictive relevance, while hypertension emerged as a novel, potentially modifiable cofactor or indicator for recurrence. Although model performance was modest, the findings are hypothesis-generating and warrant validation in larger prospective datasets.
期刊介绍:
Children is an international, open access journal dedicated to a streamlined, yet scientifically rigorous, dissemination of peer-reviewed science related to childhood health and disease in developed and developing countries.
The publication focuses on sharing clinical, epidemiological and translational science relevant to children’s health. Moreover, the primary goals of the publication are to highlight under‑represented pediatric disciplines, to emphasize interdisciplinary research and to disseminate advances in knowledge in global child health. In addition to original research, the journal publishes expert editorials and commentaries, clinical case reports, and insightful communications reflecting the latest developments in pediatric medicine. By publishing meritorious articles as soon as the editorial review process is completed, rather than at predefined intervals, Children also permits rapid open access sharing of new information, allowing us to reach the broadest audience in the most expedient fashion.