Abstract：
The International Federation of Gynecology and Obstetrics (FIGO) scoring system uses the sum of eight risk-factors to predict single-agent chemotherapy resistance in Gestational Trophoblastic Neoplasia (GTN). To improve ease of use, this study aimed to generate: (i) streamlined models that match FIGO performance and; (ii) visual-decision aids (nomograms) for guiding management.
Using training (n = 4191) and validation datasets (n = 144) of GTN patients from two UK specialist centres, logistic regression analysis generated two-factor models for cross-validation and exploration. Performance was assessed using true and false positive rate, positive and negative predictive values, Bland-Altman calibration plots, receiver operating characteristic (ROC) curves, decision-curve analysis (DCA) and contingency tables. Nomograms were developed from estimated model parameters and performance cross-checked upon the training and validation dataset.
Three streamlined, two-factor models were selected for analysis: (i) M1, pre-treatment hCG + history of failed chemotherapy; (ii) M2, pre-treatment hCG + site of metastases and; (iii) M3, pre-treatment hCG + number of metastases. Using both training and validation datasets, these models showed no evidence of significant discordance from FIGO (McNemar\'s test p > 0.78) or across a range of performance parameters. This behaviour was maintained when applying algorithms simulating the logic of the nomograms.
Our streamlined models could be used to assess GTN patients and replace FIGO, statistically matching performance. Given the importance of imaging parameters in guiding treatment, M2 and M3 are favoured for ongoing validation. In resource-poor countries, where access to specialist centres is problematic, M1 could be pragmatically implemented. Further prospective validation on a larger cohort is recommended.
Using training (n = 4191) and validation datasets (n = 144) of GTN patients from two UK specialist centres, logistic regression analysis generated two-factor models for cross-validation and exploration. Performance was assessed using true and false positive rate, positive and negative predictive values, Bland-Altman calibration plots, receiver operating characteristic (ROC) curves, decision-curve analysis (DCA) and contingency tables. Nomograms were developed from estimated model parameters and performance cross-checked upon the training and validation dataset.
Three streamlined, two-factor models were selected for analysis: (i) M1, pre-treatment hCG + history of failed chemotherapy; (ii) M2, pre-treatment hCG + site of metastases and; (iii) M3, pre-treatment hCG + number of metastases. Using both training and validation datasets, these models showed no evidence of significant discordance from FIGO (McNemar\'s test p > 0.78) or across a range of performance parameters. This behaviour was maintained when applying algorithms simulating the logic of the nomograms.
Our streamlined models could be used to assess GTN patients and replace FIGO, statistically matching performance. Given the importance of imaging parameters in guiding treatment, M2 and M3 are favoured for ongoing validation. In resource-poor countries, where access to specialist centres is problematic, M1 could be pragmatically implemented. Further prospective validation on a larger cohort is recommended.
摘要：
目的：国际妇产科联合会（FIGO）评分系统使用八个危险因素的总和来预测妊娠滋养细胞肿瘤（GTN）的单药化疗耐药性。为了提高易用性，这项研究旨在生成：（i）符合FIGO性能的简化模型；（ii）用于指导管理的视觉决策辅助工具（列线图）。
方法：使用来自两个英国专科中心的GTN患者的培训（n=4191）和验证数据集（n=144），逻辑回归分析产生了用于交叉验证和探索的双因素模型。使用真阳性率和假阳性率评估性能，阳性和阴性预测值，Bland-Altman校准图,接收机工作特性(ROC)曲线，决策曲线分析(DCA)和列联表。根据估计的模型参数和对训练和验证数据集的性能交叉检查来开发列线图。
结果：三个流线型，选择双因素模型进行分析:(i)M1,治疗前hCG+化疗失败史;(ii)M2,治疗前hCG+转移部位;(iii)M3,治疗前hCG+转移数量.使用训练和验证数据集，这些模型没有显示出与FIGO(McNemar检验p>0.78)或一系列性能参数的显著不一致的证据。当应用模拟列线图的逻辑的算法时,保持这种行为。
结论：我们简化的模型可用于评估GTN患者并取代FIGO，统计匹配性能。鉴于影像学参数在指导治疗中的重要性，M2和M3有利于进行验证。在资源匮乏的国家,进入专家中心是有问题的，M1可以务实地实施。建议对更大的队列进行进一步的前瞻性验证。
方法：使用来自两个英国专科中心的GTN患者的培训（n=4191）和验证数据集（n=144），逻辑回归分析产生了用于交叉验证和探索的双因素模型。使用真阳性率和假阳性率评估性能，阳性和阴性预测值，Bland-Altman校准图,接收机工作特性(ROC)曲线，决策曲线分析(DCA)和列联表。根据估计的模型参数和对训练和验证数据集的性能交叉检查来开发列线图。
结果：三个流线型，选择双因素模型进行分析:(i)M1,治疗前hCG+化疗失败史;(ii)M2,治疗前hCG+转移部位;(iii)M3,治疗前hCG+转移数量.使用训练和验证数据集，这些模型没有显示出与FIGO(McNemar检验p>0.78)或一系列性能参数的显著不一致的证据。当应用模拟列线图的逻辑的算法时,保持这种行为。
结论：我们简化的模型可用于评估GTN患者并取代FIGO，统计匹配性能。鉴于影像学参数在指导治疗中的重要性，M2和M3有利于进行验证。在资源匮乏的国家,进入专家中心是有问题的，M1可以务实地实施。建议对更大的队列进行进一步的前瞻性验证。
