Jiaxing University Master Degree Cultivation Base, Zhejiang Chinese Medical University, Jiaxing, Zhejiang, China.
Department of Hepatobiliary and Pancreatic Surgery, First Hospital of Jiaxing, Affiliated Hospital of Jiaxing University, Jiaxing, Zhejiang, China.
BMC Gastroenterol. 2024 Oct 31;24(1):387. doi: 10.1186/s12876-024-03469-4.
Deep learning has made significant advancements in the field of digital pathology, and the integration of multiple models has further improved accuracy. In this study, we aimed to construct a combined prognostic model using deep learning-extracted features from digital pathology images of pancreatic ductal adenocarcinoma (PDAC) alongside clinical predictive indicators and to explore its prognostic value.
A retrospective analysis was conducted on 142 postoperative pathologically confirmed PDAC cases. These cases were divided into training (n = 114) and testing sets (n = 28) at an 8:2 ratio. Tumor whole-slide imaging features were extracted and screened to construct a pathological risk model based on a pre-trained deep learning model. Clinical and pathological data from the training set were used to select independent predictive factors for PDAC and establish a clinical risk model using LASSO, univariate, and multivariate Cox regression analyses. Based on the pathological and clinical risk models, a combined model was developed. The Harrell concordance index (C-index) was computed to assess the predictive performance of each model for PDAC survival prognosis.
For the training and testing sets, the C-index values for the clinical risk model were 0.76 and 0.75, respectively; for the pathological risk model, they were 0.82 and 0.73, respectively; and for the combined model, they were 0.86 and 0.77, respectively. The combined model exhibited appropriate calibration at 1-, 3-, and 5-year time points, as well as a superior area under the curve of the receiver operating characteristic curve and clinical net benefit compared to the single models.
Integrating the pathological and clinical risk models may provide a higher predictive value for survival prognosis.
深度学习在数字病理学领域取得了重大进展，并且多个模型的集成进一步提高了准确性。在这项研究中，我们旨在构建一个联合预后模型，该模型使用来自胰腺导管腺癌（PDAC）数字病理学图像的深度学习提取特征，以及临床预测指标，并探讨其预后价值。
对 142 例术后经病理证实的 PDAC 病例进行回顾性分析。这些病例按照 8:2 的比例分为训练集（n=114）和测试集（n=28）。提取和筛选肿瘤全切片成像特征，基于预训练的深度学习模型构建病理风险模型。使用 LASSO、单因素和多因素 Cox 回归分析从训练集中选择 PDAC 的独立预测因素，并建立临床风险模型。基于病理和临床风险模型，开发联合模型。计算 Harrell 一致性指数（C 指数）以评估每个模型对 PDAC 生存预后的预测性能。
对于训练集和测试集，临床风险模型的 C 指数值分别为 0.76 和 0.75；病理风险模型的 C 指数值分别为 0.82 和 0.73；联合模型的 C 指数值分别为 0.86 和 0.77。联合模型在 1、3 和 5 年时间点的校准度适当，并且与单模型相比，曲线下面积和临床净效益的受试者工作特征曲线更优。
整合病理和临床风险模型可能为生存预后提供更高的预测价值。
