A radiomics prognostic scoring system for predicting progression-free survival in patients with stage IV non-small cell lung cancer treated with platinum-based chemotherapy

ObjectiveTo develop and validate a radiomics prognostic scoring system (RPSS) for prediction of progression-free survival (PFS) in patients with stage IV non-small cell lung cancer (NSCLC) treated with platinum-based chemotherapy.MethodsIn this retrospective study, four independent cohorts of stage IV NSCLC patients treated with platinum-based chemotherapy were included for model construction and validation (Discovery: n=159; Internal validation: n=156; External validation: n=81, Mutation validation: n=64). First, a total of 1,182 three-dimensional radiomics features were extracted from pre-treatment computed tomography (CT) images of each patient. Then, a radiomics signature was constructed using the least absolute shrinkage and selection operator method (LASSO) penalized Cox regression analysis. Finally, an individualized prognostic scoring system incorporating radiomics signature and clinicopathologic risk factors was proposed for PFS prediction.ResultsThe established radiomics signature consisting of 16 features showed good discrimination for classifying patients with high-risk and low-risk progression to chemotherapy in all cohorts (All P<0.05). On the multivariable analysis, independent factors for PFS were radiomics signature, performance status (PS), and N stage, which were all selected into construction of RPSS. The RPSS showed significant prognostic performance for predicting PFS in discovery [C-index: 0.772, 95% confidence interval (95% CI): 0.765−0.779], internal validation (C-index: 0.738, 95% CI: 0.730−0.746), external validation (C-index: 0.750, 95% CI: 0.734−0.765), and mutation validation (C-index: 0.739, 95% CI: 0.720−0.758). Decision curve analysis revealed that RPSS significantly outperformed the clinicopathologic-based model in terms of clinical usefulness (All P<0.05).ConclusionsThis study established a radiomics prognostic scoring system as RPSS that can be conveniently used to achieve individualized prediction of PFS probability for stage IV NSCLC patients treated with platinum-based chemotherapy, which holds promise for guiding personalized pre-therapy of stage IV NSCLC.     

Coupling radiomics analysis of CT image with diversification of tumor ecosystem: A new insight to overall survival in stage I−III colorectal cancer

ObjectiveThis study aimed to establish a method to predict the overall survival (OS) of patients with stage I−III colorectal cancer (CRC) through coupling radiomics analysis of CT images with the measurement of tumor ecosystem diversification.MethodsWe retrospectively identified 161 consecutive patients with stage I−III CRC who had underwent radical resection as a training cohort. A total of 248 patients were recruited for temporary independent validation as external validation cohort 1, with 103 patients from an external institute as the external validation cohort 2. CT image features to describe tumor spatial heterogeneity leveraging the measurement of diversification of tumor ecosystem, were extracted to build a marker, termed the EcoRad signature. Multivariate Cox regression was used to assess the EcoRad signature, with a prediction model constructed to demonstrate its incremental value to the traditional staging system for OS prediction.ResultsThe EcoRad signature was significantly associated with OS in the training cohort [hazard ratio (HR)=6.670; 95% confidence interval (95% CI): 3.433−12.956; P<0.001), external validation cohort 1 (HR=2.866; 95% CI: 1.646−4.990; P<0.001) and external validation cohort 2 (HR=3.342; 95% CI: 1.289−8.663; P=0.002). Incorporating the EcoRad signature into the prediction model presented a higher prediction ability (P<0.001) with respect to the C-index (0.813, 95% CI: 0.804−0.822 in the training cohort; 0.758, 95% CI: 0.751−0.765 in the external validation cohort 1; and 0.746, 95% CI: 0.722−0.770 in external validation cohort 2), compared with the reference model that only incorporated tumor, node, metastasis (TNM) system, as well as a better calibration, improved reclassification and superior clinical usefulness.ConclusionsThis study establishes a method to measure the spatial heterogeneity of CRC through coupling radiomics analysis with measurement of diversification of the tumor ecosystem, and suggests that this approach could effectively predict OS and could be used as a supplement for risk stratification among stage I−III CRC patients.     

Nomogram Based on Clinical and Radiomics Data for Predicting Radiation-induced Temporal Lobe Injury in Patients with Non-metastatic Stage T4 Nasopharyngeal Carcinoma

AimsTo use pre-treatment magnetic resonance imaging-based radiomics data with clinical data to predict radiation-induced temporal lobe injury (RTLI) in nasopharyngeal carcinoma (NPC) patients with stage T4/N0–3/M0 within 5 years after radiotherapy.Materials and methodsThis study retrospectively examined 98 patients (198 temporal lobes) with stage T4/N0–3/M0 NPC. Participants were enrolled into a training cohort or a validation cohort in a ratio of 7:3. Radiomics features were extracted from pre-treatment magnetic resonance imaging that were T1-and T2-weighted. Spearman rank correlation, the t-test and the least absolute shrinkage and selection operator (LASSO) algorithm were used to select significant radiomics features; machine-learning models were used to generate radiomics signatures (Rad-Scores). Rad-Scores and clinical factors were integrated into a nomogram for prediction of RTLI. Nomogram discrimination was evaluated using receiver operating characteristic analysis and clinical benefits were evaluated using decision curve analysis.ResultsParticipants were enrolled into a training cohort (n = 139) or a validation cohort (n = 59). In total, 3568 radiomics features were initially extracted from T1-and T2-weighted images. Age, D_max, D_1cc and 16 stable radiomics features (six from T1-weighted and 10 from T2-weighted images) were identified as independent predictive factors. A greater Rad-Score was associated with a greater risk of RTLI. The nomogram showed good discrimination, with a C-index of 0.85 (95% confidence interval 0.79–0.92) in the training cohort and 0.82 (95% confidence interval 0.71–0.92) in the validation cohort.ConclusionWe developed models for the prediction of RTLI in patients with stage T4/N0–3/M0 NPC using pre-treatment radiomics data and clinical data. Nomograms from these pre-treatment data improved the prediction of RTLI. These results may allow the selection of patients for earlier clinical interventions.     

Radiomic Nomogram for Pretreatment Prediction of Pathologic Complete Response to Neoadjuvant Therapy in Breast Cancer: Predictive Value of Staging Contrast-enhanced CT

IntroductionThe purpose of this study was to predict pathologic complete response (pCR) to neoadjuvant therapy in breast cancer using radiomics based on pretreatment staging contrast-enhanced computed tomography (CECT).Patients and MethodsA total of 215 patients were retrospectively analyzed. Based on the intratumoral and peritumoral regions of CECT images, radiomic features were extracted and selected, respectively, to develop an intratumoral signature and a peritumoral signature with logistic regression in a training dataset (138 patients from November 2015 to October 2017). We also developed a clinical model with the molecular characterization of the tumor. A radiomic nomogram was further constructed by incorporating the intratumoral and peritumoral signatures with molecular characterization. The performance of the nomogram was validated in terms of discrimination, calibration, and clinical utility in an independent validation dataset (77 patients from November 2017 to December 2018). Stratified analysis was performed to develop a subtype-specific radiomic signature for each subgroup.ResultsCompared with the clinical model (area under the curve [AUC], 0.756), the radiomic nomogram (AUC, 0.818) achieved better performance for pCR prediction in the validation dataset with continuous net reclassification improvement of 0.787 and good calibration. Decision curve analysis suggested the nomogram was clinically useful. Subtype-specific radiomic signatures showed improved AUCs (luminal subgroup, 0.936; human epidermal growth factor receptor 2-positive subgroup, 0.825; and triple negative subgroup, 0.858) for pCR prediction.ConclusionThis study has revealed a predictive value of pretreatment staging-CECT and successfully developed and validated a radiomic nomogram for individualized prediction of pCR to neoadjuvant therapy in breast cancer, which could assist clinical decision-making and improve patient outcome.     

Development and External Validation of a Clinical Nomogram for Individually Predicting Survival of Metaplastic Breast Cancer

BackgroundFew studies have concerned the prognosis of metaplastic breast cancer (MpBC), a rare and diverse malignancy. A prognostic index estimating the MpBC survival would be attractive in clinical practice.Patients and MethodsWe retrospectively analyzed MpBC patients from the Surveillance, Epidemiology, and End Results (SEER) database. Prognostic factors were identified and the final nomogram was developed to predict the 1-, 3-, or 5-year overall survival (OS). Calibration curves were provided to internally validate the performance of the nomogram and discriminative ability was appraised by concordance index (C-index).ResultsA total of 1017 MpBC patients diagnosed between 2010 and 2015 were assigned into 3:1 as training set (n = 763) and SEER validation set (n = 254). An external validation was performed by an individual set of 94 MpBC patients from National Cancer Center in China from 2010 to 2018. The nomogram finally consisted of 7 independent prognostic factors and presented a good accuracy for predicting the OS with the C-index of 0.77 (95% CI: 0.751-0.786). Interestingly, the nomogram based on the western (including 92.5% non-Asian) SEER validation population (C-index of nomogram: 0.76, 95% CI: 0.737-0.796) also has an optimal discrimination in Asian population (C-index of nomogram: 0.70). The calibration plots of the nomogram predictions were also accurate and corresponded closely with the actual survival rates.ConclusionThis novel nomogram was accurate enough to predict the OS by using readily available clinicopathologic factors in MpBC general population, which could provide individualized recommendations for patients and clinical decisions for physicians.     

术前预测结直肠癌淋巴结转移的临床-影像组学列线图的建立和验证

背景与目的：术前准确预测淋巴结转移对于结直肠癌患者的肿瘤分期、治疗决策、预后及复发等至关重要。建立和验证用于术前预测结直肠癌淋巴结转移的临床-影像组学组合模型。方法：收集复旦大学附属肿瘤医院收治的767例经病理学检查确诊为结直肠癌的患者（实验组537例，验证组230例）。然后纳入9个重要临床危险因素［年龄、性别、术前癌胚抗原（carcinoembryonic antigen，CEA）水平、术前糖类抗原19-9（carbohydrate antigen 19-9，CA19-9）水平、病理学分级、组织学类型、肿瘤位置、肿瘤大小和M分期］来构建临床模型；采用ANOVA、Relief和递归特征消除（recursive feature elimination，RFE）进行特征选择（包括临床危险因素、原发病灶和周围淋巴结的影像组学特征），通过逻辑回归分析建立各自的分类模型，并通过one-standard-error准则选择最优模型，然后组合最优模型下的临床危险因素、原发灶影像组学特征、周围淋巴结影像组学特征建立联合预测模型。接着使用受试者工作特征（receiver operating characteristic，ROC）曲线及曲线下面积（area under curve，AUC）来量化预测准确率。最后应用决策曲线分析（decision curve analysis，DCA）和列线图来评估该模型的临床应用价值。结果：临床-原发灶-周围淋巴结影像组学联合模型的AUC最高（0.743 0），为最佳模型。该临床-影像组学模型在实验队列和验证队列中都显示出良好的鉴别和校正能力。DCA表明，临床-影像组学列线图在临床上具有应用价值。结论：提出了一种基于影像组学特征和临床危险因素的临床-影像组学列线图，可用于结直肠癌患者术前预测淋巴结转移。     

Development and validation of prognostic nomogram based on log odds of positive lymph nodes for patients with gastric signet ring cell carcinoma

ObjectiveOur aims were to establish novel nomogram models, which directly targeted patients with signet ring cell carcinoma (SRC), for individualized prediction of overall survival (OS) rate and cancer-specific survival (CSS).MethodsWe selected 1,365 SRC patients diagnosed from 2010 to 2015 from Surveillance, Epidemiology and End Results (SEER) database, and then randomly partitioned them into a training cohort and a validation cohort. Independent predicted indicators, which were identified by using univariate testing and multivariate analyses, were used to construct our prognostic nomogram models. Three methods, Harrell concordance index (C-index), receiver operating characteristics (ROC) curve and calibration curve, were used to assess the ability of discrimination and predictive accuracy. Integrated discrimination improvement (IDI), net reclassification improvement (NRI) and decision curve analysis (DCA) were used to assess clinical utility of our nomogram models.ResultsSix independent predicted indicators, age, race, log odds of positive lymph nodes (LODDS), T stage, M stage and tumor size, were associated with OS rate. Nevertheless, only five independent predicted indicators were associated with CSS except race. The developed nomograms based on those independent predicted factors showed reliable discrimination. C-index of our nomogram for OS and CSS was 0.760 and 0.763, which were higher than American Joint Committee on Cancer (AJCC) 8th edition tumor-node-metastasis (TNM) staging system (0.734 and 0.741, respectively). C-index of validation cohort for OS was 0.757 and for CSS was 0.773. The calibration curves also performed good consistency. IDI, NRI and DCA showed the nomograms for both OS and CSS had a comparable clinical utility than the TNM staging system.ConclusionsThe novel nomogram models based on LODDS provided satisfying predictive ability of SRC both in OS and CSS than AJCC 8th edition TNM staging system alone.     

Prognostic impact of lymph node harvest for patients with node-negative esophageal squamous cell carcinoma: a large-scale multicenter study

BackgroundWe examined the association between the number of resected lymph nodes and survival to determine the optimal lymphadenectomy for thoracic esophageal squamous cell carcinoma (ESCC) patients with negative lymph node.MethodsWe included 1,836 patients from Chinese three high-volumed hospitals with corresponding clinicopathological characters such as gender, age, tumor location, tumor grade and TNM stage of patients. The median follow-up of included patients was 45.7 months (range, 1.03–117.3 months). X-Tile plot was used to identify the lowest number of lymphadenectomy. The multivariate model’s construction was in use of parameters with clinical significance for survival and a nomogram based on clinical variable with P<0.05 in Cox regression analysis. Both two models were validated using a cohort extracted from the Surveillance, Epidemiology, and End Results (SEER) 18 registries database between 1975 and 2016 (n=951).ResultsMore lymphadenectomy numbers were significantly associated with better survival in patients both in training cohort [hazard ratio (HR) =0.980; 95% confidence interval (CI): 0.971–0.988; P<0.001] and validation cohort (HR =0.980; 95% CI: 0.968–0.991; P=0.001). Cut-off point analysis determined the lowest number of 9 for thoracic ESCC patients in N0 stage through training cohort (C-index: 0.623; sensitivity: 80.7%; 1 − specificity: 72.5%) when compared with 10 in validation cohort (C-index: 0.643; sensitivity: 78.2%; 1 − specificity: 63.0%). The cut-off points of 9 were examined in training cohort and validated in the divided cohort from validation cohort (all P<0.05). Meanwhile, nomograms for both cohorts were constructed and the calibration curves for both cohorts agreed well with the actual observations in terms of predicting 3- and 5-year survival, respectively.ConclusionsLarger number for lymphadenectomy was associated with better survival in thoracic ESCC patients in N0 stage. Nine was what we got as the lowest number for lymphadenectomy in pN0 ESCC patients through this study, and our result should be confirmed further.     

前列腺穿刺对根治性前列腺切除术后标本ISUP升级预测列线图模型的建立及其应用

目的:构建一个从前列腺穿刺组织到根治性前列腺切除术（RP）后标本ISUP分级升高(ISUP grade upgrading,IGU)风险的预测列线图模型并进行内部验证。方法:对2019年05月至2020年05月我院泌尿外科收治的166例前列腺癌患者临床和病理学资料进行回顾性分析。采用单因素及多因素Logistic回归分析得到IGU的独立危险因素,后根据这些因素构建列线图预测模型。通过校准图进行模型校准,C-指数评估模型的预测能力,决策曲线分析用于检验临床效用,采用Bootstrap resampling对模型进行诊断效能内部验证。结果:该研究中ISUP升级组有47例（28.3%）患者,未升级组有119例（71.7%）患者。多因素logistic回归分析发现前列腺穿刺活检组织Gleason评分（P=0.001）、前列腺穿刺活检方法（P=0.03）和穿刺阳性针数（P=0.04）是IGU的独立危险因素。IGU列线图模型是基于上述独立因素而构建,模型的ROC曲线下面积为0.802,C-指数为0.798,校准图显示预测曲线与实际曲线有较好的相符度。列线图模型在内部验证中C-指数达到0.772。决策曲线分析表明,RP-ISUP升级风险的区间阈值为3%~67%。结论:该研究构建了一个准确性相对较高的列线图模型,有助于临床医生评估RP术后标本ISUP分级升高（特别是经直肠穿刺活检诊断的低风险前列腺癌）的风险。     

基于SEER数据库构建1~2枚淋巴结阳性且乳房全切的老年早期乳腺癌患者不同腋窝手术方式的生存预测模型

背景与目的：指南推荐1~2枚前哨淋巴结阳性的保乳并计划行全乳放疗的T1-2期乳腺癌患者可以豁免腋窝淋巴结清扫。探讨1~2枚淋巴结阳性且乳房全切的老年早期乳腺癌患者的预后危险因素,并构建不同腋窝处理手术方式下的生存预测模型。方法：从SEER数据库收集2010—2015年期间65岁及以上、T 1-2 期、1~2枚淋巴结阳性且乳房全切的乳腺癌患者并随机分为验证集和训练集。对训练集进行单因素及多因素COX比例风险回归分析筛选出影响总生存的独立预后因素,利用R软件构建预测患者3年和5年总生存率的列线图,利用一致性指数（C指数）和校正曲线对预测模型进行内部（训练集）和外部（验证集）验证。结果：共纳入4 863例患者,中位随访42个月,训练集（3 647例）和验证集（1 216例）的基线分布符合简单随机分组。将多因素COX回归分析筛选出的年龄、种族、婚姻状态、组织学分级、分子分型、T分期、腋窝手术方式、是否放化疗共9个总生存的独立风险因素（P<0.05）用于构建列线图预测模型。训练集（即内部验证）和验证集（即外部验证）的C指数分别为0.710（95% CI：0.689~0.731）和0.728（95 % CI：0.691~0.765）,两组的校正曲线均靠近45°参考线,表明列线图具有良好的预测能力。结论：本研究构建的列线图预测模型具有良好的预测价值,有利于指导临床对患者进行个体化治疗。     

原发性肝癌射频消融术后复发预测模型的建立及评价

目的 构建和评价用于预测原发性肝癌（primary liver cancer,PLC）患者射频消融（radiofrequency ablation,RFA） 术后无瘤生存率的列线图模型。 方法 回顾性分析2009年6月至2017年5月于广西医科大学附属肿瘤医院接受射频消融治疗的213例PLC患者的临床资料。ＰＬＣ患者被随机分为训练组（n=133）和验证组（n=80）。采用Cox回归模型分析射频消融术后复发的因素,并建立复发的列线图模型。通过校准曲线评估模型的预测符合度,Kaplan-Meier 曲线评估模型的实用性,一致性指数（C-index）评估模型的准确度。结果 训练组1年、3年、5年无瘤生存率分别为65.25%、40.91%、26.99%,验证组分别为66.29%、48.10%、24.59%,两组生存曲线比较差异无统计学意义（P=0.785）。Cox回归分析结果显示,肿瘤数目（HR=1.921, 95%CI：1.136~3.251）、丙肝抗体阳性（HR=4.545,95%CI：1.700~12.149）、HBV-DNA≥10² IU/mL（HR=1.993,95%CI：1.209~3.284）及血清前白蛋白（HR=0.996,95%CI：0.993~0.999）为无瘤生存率的影响因素。基于肿瘤数目、HBV-DNA和血清前白蛋白等因素建立列线图模型,训练组和验证组的 C-index 分别为 0.649（95%CI：0.588~0.710）、0.641（95%CI：0.556~0.724）,校准图形中标准曲线与预测校准曲线贴合良好。采用列线图将患者分为高风险组和低风险组,高风险组无瘤生存率低于低风险组（P<0.05）。结论 基于肿瘤数目、HBV-DNA和血清前白蛋白等因素建立的列线图测模型可预测PLC射频消融术后的无瘤生存率,对患者辅助治疗具有一定指导价值。     

皮肤梭形细胞黑色素瘤患者生存预测模型的构建及验证

背景与目的：梭形细胞黑色素瘤（spindle cell melanoma,SCM）是一种罕见的黑色素瘤类型,有关SCM患者生存预后的研究较少。通过提取公共数据库中的SCM临床信息,构建并验证皮肤SCM患者5和10年癌症特异性生存率（cancer-specific survival,CSS）和总生存率（overall survival,OS）的生存预测模型。方法：从美国国立癌症研究所监测、流行病学和最终结果（Surveillance, Epidemiology, and End Results,SEER）数据库筛选出共1 445例患者,分成建模组（n=1 011）和验证组（n=434）。通过单因素和多因素COX回归分析确定独立预后影响因素,建立列线图预测模型。利用一致性指数（concordance index,C-index）、受试者工作特征（receiver operating characteristic,ROC）曲线和校准曲线评估模型的区分度和准确性,利用决策曲线分析（decision curve analysis,DCA）评估模型的临床实用性。结果：年龄、肿瘤部位、肿瘤厚度、溃疡、N分期、M分期及手术共7个独立预后影响因素纳入预测模型,CSS和OS预测模型在建模组中的C-index分别为0.778和0.753,在验证组中的C-index为0.749和0.712。建模组5和10年CSS的曲线下面积（area under curve,AUC）分别为0.815和0.825,5和10年OS的AUC分别为0.803和0.825,验证组5和10年CSS的AUC分别为0.777和0.836,5和10年OS的AUC分别为0.754和0.799。校准曲线与45°线贴合良好,DCA显示,列线图模型在较广泛阈概率范围内有临床净收益,具有良好的临床应用价值。结论：列线图对于皮肤SCM患者预后具有良好的预测能力和临床应用价值。     

基于影像组学的食管鳞状细胞癌放疗后生存预测模型的建立与验证

  目的  利用增强CT图像特征构建模型,预测食管鳞状细胞癌患者放疗后原发病灶的局部控制情况。  方法  2016年7月至2017年12月218例于河北医科大学第四医院接受放化疗且病理诊断为鳞状细胞癌的食管癌患者随机分为训练组（153例）和验证组（65例）,提取训练组患者的增强CT图像影像组学特征,构建并验证模型预测食管癌患者放疗后原发病灶局部控制的效能。采用ROC曲线、C-index曲线、校准曲线和决策曲线评价不同模型的性能。  结果  在训练组筛选出6个有意义的影像组学特征,构建预测食管鳞状细胞癌放疗后原发病灶局部控制的放射学标签。训练组和验证组的ROC曲线下面积分别为0.758和0.728;C-index为0.709和0.695;以放射学标签得分?0.22为界值分为高危组和低危组,低危组患者的1、3、5年无原发病灶复发生存率均高于高危组患者（P<0.05）。结合临床因素与放射学标签构建食管癌放疗后无原发病灶复发生存的影像组学列线图模型,ROC曲线评价预测效能的曲线下面积在训练组和对照组分别为0.775和0.740;C-index分别为0.722和0.707;以影像组学列线图模型得分0.55为界值分为高危组和低危组,低危组患者的1、3、5年无原发病灶复发生存率均高于高危组患者（P<0.05）。  结论  成功构建预测食管癌放疗后无原发病灶复发生存的模型,模型具有较好的临床预测价值。      

基于阴性淋巴结数目的胃印戒细胞癌预后评估模型的建立与验证

目的 探讨阴性淋巴结数目（NLNC）对胃印戒细胞癌（GSRC）患者预后的影响及构建G S R C 患者的预后预测模型。方法 基于SEER数据库收集GSRC患者2101例，随机分为建模组和验证组，检验临床病理特征与GSRC预后的关系。多因素Cox比例风险回归模型分析影响总生存的独立危险因素并建立预后预测模型。一致性指数（C?index）、校准曲线、净分类指数（NRI）、综合判别指数（IDI）和临床决策曲线（DCA）对列线图进行准确性和临床适用性评估。结果 所有患者按照7:3比例划分，建模组1473例，验证组628例。NLNC>10是GSRC患者预后的保护因素（HR=0.578, 95%CI: 0.504~0.662），根据多因素Cox比例风险回归模型筛选的变量建立Nomogram图，建模组和验证组的C-index分别为0.737（95%CI: 0.720~0.753）和0.724（95%CI: 0.699~0.749），区分度良好，校准曲线显示模型的一致性较高。NRI=17.77%，连续NRI=36.34%，IDI=4.2%，表明该模型较传统模型是正向收益，DCA决策曲线远离基准线表明模型临床适用性好。结论 NLNC增加是GSRC患者预后的有利因素。本研究建立的列线图相对准确，可预测GSRC患者的预后。     

基于CT影像组学的列线图模型预测肺部肿瘤立体定向放射治疗疗效

目的:基于治疗前CT图像筛选放射组学特征构建列线图模型预测早期非小细胞肺癌（early stage-non-small cell lung cancer,ES-NSCLC）和肺部寡转移癌的放疗疗效。方法:本研究纳入122例接受立体定向放射治疗（stereotactic body radiotherapy,SBRT）的ES-NSCLC和肺部寡转移癌的患者,随机分为训练集和验证集。使用最小绝对收缩和选择算子（least absolute shrinkage and selection operator,LASSO）和逻辑回归（logistic regression）筛选训练集中与放疗疗效相关的放射组学特征以建立列线图模型。用受试者工作特征曲线（receiver operating characteristic curves,ROC）下面积（area under the curve,AUC）、校准曲线和决策曲线（decision curve analysis,DCA）评价模型性能。结果:经筛选得出6个放射组学特征形成放射组学特征分数（radiomics score,Rad-score）以建立列线图模型。模型训练集的AUC值为0.808（95%CI:0.712~0.884,P<0.001）,验证集的AUC为0.741（95%CI:0.556~0.879,P=0.003）。Delong检测显示模型表现均衡（P=0.496）,校准曲线和DCA均显示了模型较好的预测性能和较高的临床价值。结论:我们基于治疗前CT图像开发并验证了用于预测肺部肿瘤SBRT治疗疗效的列线图模型,该模型具有较高的预测性能和临床实用性。     

基于列线图构建和验证肝细胞癌伴门静脉癌栓患者肝切除术后的预后评估模型

目的 分析影响肝细胞癌伴门静脉癌栓（PVTT-HCC）患者肝切除术后预后的影响因素,并基于列线图模型构建和验证预后评估模型。方法 本研究为回顾性队列研究,选择2008年1月—2017年11月在本院行肝切除术的PVTT-HCC患者为研究对象,随访截至2021年1月。主要预测结局为1、3、5年总生存率。按照7∶3的比例将患者随机分为训练集和验证集,在训练集中采用Cox比例风险回归分析影响预后的影响,并基于影响因素构建列线图模型。同时在训练集和验证集中采用C-index评价模型的区分度,一致性曲线评估模型的校准度。结果 共231例患者符合纳入排除标准纳入分析,其中训练集162例,验证集69例。Cox比例风险回归模型显示,AFP≥400 μg/L、AST≥40 U/L、ALP≥80 U/L、肿瘤个数>1个及肿瘤包膜不完整是影响预后的危险因素。在训练集中,列线图模型预测1、3、5年总生存率的C-index分别为0.826（95%CI: 0.791~0.861）、0.818（95%CI：0.782~0.854）、0.781（95%CI：0.742~0.820）,在验证集中分别为0.814（95%CI：0.777~0.851）、0.798（95%CI：0.758~0.837）、0.769（95%CI：0.728~0.810）。校正曲线显示列线图模型在训练集和验证集均有较好的校准度。结论 本研究构建的列线图模型可准确预测PVTT-HCC患者的预后。     

CT-based radiomics nomogram for preoperative prediction of No.10 lymph nodes metastasis in advanced proximal gastric cancer

IntroductionPreoperative diagnosis of No.10 lymph nodes (LNs) metastases in advanced proximal gastric cancer (APGC) patients remains a challenge. The aim of this study was to develop a CT-based radiomics nomogram for identification of No.10 LNs status in APGCs.Materials and methodsA total of 515 patients with primary APGCs were retrospectively selected and divided into a training cohort (n = 340) and a validation cohort (n = 175). Total incidence of No.10 LNM was 12.4% (64/515). CT based radiomics nomogram combining with radiomic signature calculated from venous CT imaging features and CT-defined No.10 LNs status evaluated by radiologists was built and tested to predict the No.10 LNs status in APGCs.ResultsCT based radiomics nomogram yielded classification accuracy with areas under ROC curves, AUC = 0.896 and 0.814 in training and validation cohort, respectively, while radiomic signature and radiologist’ diagnosis based on contrast-enhanced CT images yielded lower AUCs ranging in 0.742–0.866 and 0.619–0.685, respectively. In the specificity higher than 80%, the sensitivity of using radiomics nomogram, radiomic signature and radiologists’ evaluation to detect No.10 LNs positive cases was 82.8% (53/64), 67.2% (43/64) and 39.1% (25/64), respectively.ConclusionsThe CT-based radiomics nomogram provides a promising and more effective method to yield high accuracy in identification of No.10 LNs metastases in APGC patients.     

Nomograms to predict pathologic complete response and metastasis-free survival after preoperative chemotherapy for breast cancer.

PURPOSE: To combine clinical variables associated with pathologic complete response (pCR) and distant metastasis-free survival (DMFS) after preoperative chemotherapy (PC) into a prediction nomogram. PATIENTS AND METHODS: Data from 496 patients treated with anthracycline PC at the Institut Gustave Roussy were used to develop and calibrate a nomogram for pCR based on multivariate logistic regression. This nomogram was tested on two independent cohorts of patients treated at the M.D. Anderson Cancer Center. The first cohort (n = 337) received anthracycline; the second cohort (n = 237) received a combination of paclitaxel and anthracycline PC. A separate nomogram to predict DMFS was developed using Cox proportional hazards regression model. RESULTS: The pCR nomogram based on clinical stage, estrogen receptor status, histologic grade, and number of preoperative chemotherapy cycles had good discrimination and calibration in the training and the anthracycline-treated validation sets (concordance indices, 0.77, 0.79). In the paclitaxel plus anthracycline group, when the predicted pCR rate was less than 14%, the observed rate was 7.5%; for a predicted rate of > or = 38%, the actual rate was 85%. For a predicted rate between 14% to 38%, the observed rates were 50% with weekly and 27% with 3-weekly paclitaxel. This indicates that patients with intermediate chemotherapy sensitivity benefit the most from the optimized schedule of paclitaxel. Patients unlikely to achieve pCR to anthracylines remain at low probability for pCR, even after inclusion of paclitaxel. The nomogram for DMFS had a concordance index of 0.72 in the validation set and outperformed other prediction tools (P = .02). CONCLUSION: Our nomograms predict pCR accurately and can serve as a basis to integrate future molecular markers into a clinical prediction model.     

Lung Metastasis Probability in Ewing Sarcoma: A Nomogram Based on the SEER Database

Background. Up to now, an accurate nomogram to predict the lung metastasis probability in Ewing sarcoma (ES) at initial diagnosis is lacking. Our objective was to construct and validate a nomogram for the prediction of lung metastasis in ES patients. Methods. A total of 1157 patients with ES from the Surveillance, Epidemiology, and End Results (SEER) database were retrospectively collected. The predictors of lung metastasis were identified via the least absolute shrinkage and selection operator (LASSO) and multivariate logistic analysis. The discrimination and calibration of the nomogram were validated by receiver operating characteristic (ROC) curve and calibration curve. Decision curve analysis (DCA) was used to evaluate the clinical usefulness and net benefits of the prediction model. Results. Factors including age, tumor size, primary site, tumor extension, and other site metastasis were identified as the ultimate predictors for the nomogram. The calibration curves for the training and validation cohorts both revealed good agreement, and the Hosmer–Lemeshow test identified that the model was well fitted (p > 0.05). In addition, the area under the ROC curve (AUC) values in the training and validation cohorts were 0.732 (95% confidence interval, CI: 0.607–0.808) and 0.741 (95% CI: 0.602–0.856), respectively, indicating good predictive discrimination. The DCA showed that when the predictive metastasis probability was between 1% and 90%, the nomogram could provide clinical usefulness and net benefit. Conclusion. The nomogram constructed and validated by us could provide a convenient and effective tool for clinicians that can improve prediction of the probability of lung metastasis in patients with ES at initial diagnosis.     

Development and validation of a new clinical staging system to predict survival for esophageal squamous cell carcinoma patients: Application of the nomogram

IntroductionSurvival of patients with the same clinical stage varies widely and effective tools to evaluate the prognosis utilizing clinical staging information is lacking. This study aimed to develop a clinical nomogram for predicting survival of patients with Esophageal Squamous Cell Carcinoma (ESCC).Materials and methodsOn the basis of data extracted from the SEER database (training cohort, n = 3375), we identified and integrated significant prognostic factors for nomogram development and internal validation. The model was then subjected to external validation with a separate dataset obtained from Jinling Hospital of Nanjing Medical University (validation cohort, n = 1187). The predictive accuracy and discriminative ability of the nomogram were determined by concordance index (C-index), Akaike information criterion (AIC) and calibration curves. And risk group stratification was performed basing on the nomogram scores.ResultsOn multivariable analysis of the training cohort, seven independent prognostic factors were identified and included into the nomogram. Calibration curves presented good consistency between the nomogram prediction and actual observation for 1-, 3-, and 5-year OS. The AIC value of the nomogram was lower than that of the 8th edition American Joint Committee on Cancer TNM (AJCC) staging system, whereas the C-index of the nomogram was significantly higher than that of the AJCC staging system. The risk groups stratified by CART allowed significant distinction between survival curves within respective clinical TNM categories.ConclusionsThe risk stratification system presented better discriminative ability for survival prediction than current clinical staging system and might help clinicians in decision making.