Renal cell carcinoma (RCC) is one of the most common malignant tumors affecting the urinary system. The incidence of renal cancer in China has shown a continuous upward trend in recent years, with approximately 73,700 new cases in 2022 and a standardized incidence rate of approximately 6.7 per 100,000 [1]. The incidence rate is significantly higher in males than in females (2–3 times). Risk factors for RCC include smoking, obesity, hypertension, occupational exposure, and genetic factors. RCC primarily comprises three histopathological types: clear cell RCC, papillary RCC, and chromophobe RCC, with clear cell RCC accounting for 70%-80% of cases, papillary RCC accounting for 10%-15%, and chromophobe RCC accounting for 5% [2]. The survival of RCC patients has improved owing to surgical management and the use of targeted and immune drugs [3, 4]. However, a large proportion of RCC patients present with high-stage disease, with a poor prognosis because of distant metastases [5–7]. Thus, tumor metastasis is a critical factor in determining the prognosis of RCC patients.

Seventy percent of patients are diagnosed with stage I RCC, and 11% of patients are diagnosed with stage IV RCC [8]. The lungs are the most common affected site of metastasis, followed by regional lymph nodes, brain, bone, and soft tissue. Lee CH et al. [9] analyzed the Korean Renal Cancer Study Group metastatic RCC (mRCC) database. The results revealed the most common sites of metastasis (> 5%), and the median cancer-specific survival (CSS) ranged from 13.9 (liver) to 29.1 months (lung). Through continuous efforts in RCC research, for advanced or mRCC, combinations of immune checkpoint inhibitors or combinations of immune checkpoint inhibitors with tyrosine kinase inhibitors are associated with a tumor response of 42–71%, with a median overall survival of 46 to 56 months [8]. These results indicate that the prognosis of mRCC patients is still poor, regardless of the presence of lymph node metastasis or other organ metastasis [9, 10]. Early detection of distant metastasis is the top priority of clinical work.

Identifying the clinicopathological risk factors that promote RCC distant metastasis is vital. In recent years, several clinical diagnostic tools have been built using different prognostic and prediction models. Although predictive factors and models for mRCC have been developed, the limited data commonly restrict individualized accurate prediction. These studies have significant limitations, such as the use of older tools and limited data. The Surveillance, Epidemiology, and End Results (SEER) database represents 28% of the U.S. population today; it includes large, multi-institutional patients and could be an essential source of mRCC research to provide greater statistical power. Additionally, machine learning (ML), a major subbranch of artificial intelligence, is a promising statistical method and can handle heterogeneous and large amounts of data. ML techniques have not been used in many studies, and some models lack interpretability to fully capture the complex relationships among variables and to provide clinically actionable explanations. Previously, we used ML algorithms as auxiliary tools to predict the overall survival in RCC patients [11]. This technique could be used to quantify the possibility of recurrence in patients and help with more individualized postoperative clinical management.

In our study, we aimed to develop and validate an explainable ML model for the prediction of RCC metastasis. We collected a large amount of data from the SEER database and the Chinese National Cancer Center (CNCC) dataset. The RCC cases were subjected to data standardization and included multiple clinical parameters, such as tumor grade, side, pathology type, T stage, and N stage. The RCC M0/M1 metastasis prediction algorithm was explored and visualized.

We extracted RCC data, including data from the SEER database between 2004 and 2015 (n = 192,912) and from the CNCC database between 2010 and 2020 (n = 3034). After data cleaning and screening, 121,741 cases remained in the SEER dataset, and 2803 cases remained in the CNCC external test set. The flowchart is shown in Fig. 1. Given the substantial volume of the SEER data and the presence of incomplete data for some features, the dataset was first divided into training and testing sets at a 9:1 ratio, resulting in approximately 109,567 cases for the training set and 12,174 cases for the testing set. From all the cases with complete data, 12,174 cases were randomly selected as the testing set, with the remaining 109,567 cases allocated to the training set. Among the 109,567 cases, 80,119 cases had complete data, and 29,448 cases had incomplete data.

To facilitate extraction and analysis, numerical characterization of the clinicopathologic data of RCC patients was first conducted through different number assignments.

The random forest interpolation method was used to supplement missing values. First, a random forest regression model was trained based on available complete data. The average values were subsequently used to supplement all missing features. Finally, the random forest regression model was used to regress and predict each missing feature one by one, replacing the missing values with the original average values.

To improve the generalizability of the model, continuous features such as age and tumor size were discretized and binarized. This study employs a feature discretization method grounded in information entropy, which is a supervised approach. Information entropy serves as a metric for quantifying the uncertainty of an event, and higher entropy values indicate greater uncertainty. The formula for calculating information entropy is as follows:

where X represents all possible categories of the sample, k denotes the total number of categories, and p(x_i) signifies the probability of the sample belonging to category i. The discretization method finds the threshold that maximizes the decrease in the entropy of category information in the training set. On the basis of this threshold, all features are discretized into binary values.

ML models were constructed using fivefold cross-validation based on the training set of 80,119 cases with complete data and the supplemented training set of 109,567 cases by a random forest regressor. Additionally, the internal test set included 12,174 cases, and the external test set included 2,803 cases. The specific division results are shown in Table 1 and Table 2.

With respect to model development, although nomograms are currently the most commonly used prediction models, ML models are favored by an increasing number of medical workers because of their practicality, innovation and accuracy [12–14]. In clinical practice, tumor-related models can accurately predict prognosis by combining multiple factors, such as tumor pathological subtype, tumor stage, tumor diameter, and molecular marker expression. However, few researchers have attempted to use ML methods to explore the prediction of metastasis in RCC patients. In this study, we used a variety of ML algorithms to predict RCC metastasis through many samples from 2 databases, which indicated good sensitivity and specificity. These algorithms can be applied to accurately predict whether RCC patients have metastasis, providing assistance for the judgment of clinical metastasis.

Various statistics facilitate the understanding and interpretation of data. However, the limitations and efficiency of processing big data limit computing power and accuracy. In recent years, ML has included algorithmic methods that enable machines to solve problems without specific computer programming, leading the way in predictive modeling tasks [15]. The integration of big data with ML algorithms is becoming a clinical necessity. In RCC studies, ML models can be applied to analyze the risk factors associated with specific diseases on the basis of patient information. Yin et al. [16] integrated convolutional neural network models with Cox regression to identify potential prognostic biomarkers for overall survival. Terrematte P et al. [17] created a novel ML 13-gene signature, improving risk analysis and survival prediction for RCC patients. Chen S et al. [18] developed and validated an ML-based prognosis prediction model, which could contribute to clinical decision-making for patients with RCC. Similarly, in our previous study, we investigated and demonstrated that ML algorithms could be used as auxiliary tools to predict the overall survival of patients with RCC using the SEER data [11].

Once distant metastasis occurs in RCC, patient prognosis becomes very poor. Therefore, prediction of distant metastasis in RCC patients is very important. Many clinical studies have used clinicopathological factors to establish models to predict metastatic risk in RCC. Fan Z et al. [19] established nomograms using the SEER database to predict the risk of bone metastasis in patients with RCC. The calibration curve, ROC curve, and DCA confirmed good performance using diagnostic and prognostic nomograms. Wang J et al. [20] developed and validated a nomogram to predict distant metastasis in elderly patients with RCC. The AUCs of the training and validation cohorts indicated excellent predictive ability. DCA indicated that the nomogram had better clinical application value than traditional TN staging did. Some scholars have also explored the use of ML algorithm models to make predictions. Xu C et al. [21] used data from 40,355 RCC patients in the SEER database to build an ML model to predict the risk of bone metastasis in RCC patients. Among the prediction models established by the six ML algorithms, the XGBoost model achieved the best prediction performance (AUC = 0.891). Dong J and colleagues also used the SEER database to predict distant metastasis in RCC patients on the basis of interpretable ML models [22]. The calibration curve indicated that the predicted values are highly consistent with the actual observed values.

The above studies indicate that ML models for predicting RCC metastasis are feasible and highly accurate. However, most of these studies are based on SEER data and lack external validation. In contrast, in this study, we collected RCC data from the SEER database (training set) and the CNCC database (external test set). First, all the data were preprocessed. Preprocessing of feature data consists of two steps: Step 1. Clinicopathologic data including sex, tumor grade, side, pathology type, N stage, T stage, surgery and marital status were conducted numerical characterization through different number assignments. Step 2. For the two features of age and tumor size, the features in the training set and the internal and external test sets are discretized separately. Second, we compared the performance of models constructed by different ML algorithms for incomplete data and complete data. The accuracy of the ML models with complete datasets is significantly higher than that with incomplete datasets. Finally, to overcome the problem of large differences between positive and negative samples in the dataset, we also used up- and downsampling methods to reconstruct the model and test its performance. The results showed that the accuracy of the model was further improved. Our study is the first to combine the SEER database with an external dataset to predict the distant metastasis of RCC. The results showed that after validation with the external dataset, our ML model achieved high accuracy, which provides great guiding value for clinical decision-making.

This study has several limitations. First, the data from the external validation cohort and the SEER database were selected retrospectively, which may introduce some inherent bias. In addition, to validate our prediction model in the general population, prospective clinical studies with larger sample sizes are necessary. Second, we were unable to obtain biomarkers or blood test results from the SEER database. We expect that the addition of data from external data validation will result in a more sophisticated and effective adoption of ML models as supplementary tools for prediction research.

In summary, through data from the SEER database and CNCC dataset, this study explored the factors related to the prediction of RCC metastasis through multialgorithm ML models. Relevant algorithms were established to predict the possibility of distant metastasis in RCC patients. The findings show that ML algorithms can effectively predict distant metastasis in patients with RCC and play a positive role in clinical applications.