Predicting Survival of Patients With Rectal Neuroendocrine Tumors Using Machine Learning: A SEER-Based Population Study

GATIS score: An innovative prognostic score for rectal neuroendocrine neoplasms

In this article, we discussed the article by Zeng et al, published in a recent issue of the World Journal of Gastroenterology. The publication represents a significant advancement in the prognostic evaluation of rectal neuroendocrine neoplasms. The GATIS score is a single nomogram model that incorporates five key prognostic factors: Tumor grade; T stage; tumor size; age; and the prognostic nutritional index. This innovation optimizes the prognostic process, delivering more accurate predictions of overall survival and progression-free survival compared to traditional TNM staging and World Health Organization classification systems. The findings of the study were based on a retrospective analysis spanning 12 years and involving 1408 patients from 17 reference centers in China. In this editorial, we specifically examined the strengths and limitations of the study, the clinical implications of the GATIS score, and the questions arising from its conclusions.

User-friendly prognostic model for rectal neuroendocrine tumours: In the era of precision management

In this letter, we explore into the potential role of the recent study by Zeng et al. Rectal neuroendocrine tumours (rNETs) are rare, originate from peptidergic neurons and neuroendocrine cells, and express corresponding markers. Although most rNETs patients have a favourable prognosis, the median survival period significantly decreases when high-risk factors, such as larger tumours, poorer differentiation, and lymph node metastasis exist, are present. Clinical prediction models play a vital role in guiding diagnosis and prognosis in health care, but their complex calculation formulae limit clinical use. Moreover, the prognostic models that have been developed for rNETs to date still have several limitations, such as insufficient sample sizes and the lack of external validation. A high-quality prognostic model for rNETs would guide treatment and follow-up, enabling the precise formulation of individual patient treatment and follow-up plans. The future development of models for rNETs should involve closer collaboration with statistical experts, which would allow the construction of clinical prediction models to be standardized and robust, accurate, and highly generalizable prediction models to be created, ultimately achieving the goal of precision medicine.

New perspectives on cancer clinical research in the era of big data and machine learning

In the 21st century, the development of medical science has entered the era of big data, and machine learning has become an essential tool for mining medical big data. The establishment of the SEER database has provided a wealth of epidemiological data for cancer clinical research, and the number of studies based on SEER and machine learning has been growing in recent years. This article reviews recent research based on SEER and machine learning and finds that the current focus of such studies is primarily on the development and validation of models using machine learning algorithms, with the main directions being lymph node metastasis prediction, distant metastasis prediction, and prognosis-related research. Compared to traditional models, machine learning algorithms have the advantage of stronger adaptability, but also suffer from disadvantages such as overfitting and poor interpretability, which need to be weighed in practical applications. At present, machine learning algorithms, as the foundation of artificial intelligence, have just begun to emerge in the field of cancer clinical research. The future development of oncology will enter a more precise era of cancer research, characterized by larger data, higher dimensions, and more frequent information exchange. Machine learning is bound to shine brightly in this field.

Application of machine learning algorithms to predict lymph node metastasis in gastric neuroendocrine neoplasms

Background

Neuroendocrine neoplasms (NENs) are tumors that originate from secretory cells of the diffuse endocrine system and typically produce bioactive amines or peptide hormones. This paper describes the development and validation of a predictive model of the risk of lymph node metastasis among gastric NEN patients based on machine learning platform.

Methods

In this investigation, data from 1256 patients were used, of whom 119 patients from the First Affiliated Hospital of Soochow University in China and 1137 cases from the surveillance epidemiology and end results (SEER) database were combined. Six machine learning algorithms, including the logistic regression model (LR), random forest (RF), decision tree (DT), Naive Bayes (NB), support vector machine (SVM), and k-nearest neighbor algorithm (KNN), were used to build the predictive model. The performance of the models was evaluated using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity.

Results

Among the 1256 patients with gastric NENs, 276 patients (21.97 %) developed lymph node metastasis. T stage, tumor size, degree of differentiation, and sex were predictive factors of lymph node metastasis. The RF model achieved the best predictive performance among the six machine learning models, with an AUC, accuracy, sensitivity, and specificity of 0.81, 0.78, 0.76, and 0.82, respectively.

Conclusion

The RF model provided the best prediction and can help physicians determine the lymph node metastasis risk of gastric NEN patients to formulate individualized medical strategies.

Development and External Validation of Machine Learning-Based Models for Predicting Lung Metastasis in Kidney Cancer: A Large Population-Based Study

The accuracy of indices widely used to evaluate lung metastasis (LM) in patients with kidney cancer (KC) is insufficient. Therefore, we aimed at developing a model to estimate the risk of developing LM in KC based on a large population size and machine learning algorithms. Demographic and clinicopathologic variables of patients with KC diagnosed between 2004 and 2017 were retrospectively analyzed. We performed a univariate logistic regression analysis to identify risk factors for LM in patients with KC. Six machine learning (ML) classifiers were established and tuned using the ten-fold cross-validation method. External validation was performed using clinicopathologic information from 492 patients from the Southwest Hospital, Chongqing, China. Algorithm performance was estimated by analyzing the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, precision, recall, F1 score, clinical decision analysis (DCA), and clinical utility curve (CUC). A total of 52,714 eligible patients diagnosed with KC were enrolled, of whom 2,618 developed LM. Variables of age, sex, race, T stage, N stage, tumor size, histology, and grade were identified as important for the prediction of LM. The extreme gradient boosting (XGB) algorithm performed better than other models in both the internal validation (AUC: 0.913, sensitivity: 0.873, specificity: 0.809, and F1 score: 0.325) and the external validation (AUC: 0.904, sensitivity: 0.750, specificity: 0.878, and F1 score: 0.364). This study established a predictive model for LM in KC patients based on ML algorithms which showed high accuracy and applicative value. A web-based predictor was built using the XGB model to help clinicians make more rational and personalized decisions.

The genetic alterations of rectal neuroendocrine tumor and indications for therapy and prognosis: a systematic review

Neuroendocrine tumors (NETs) are a type of rare tumor that can occur at multiple organs. Rectal NETs are the most common NETs in gastrointestinal tract. Due to the rarity of rectal NETs in rectal cancer, the molecular features and the correlation with patient therapeutic response and prognosis have not been investigated in detail. In this review, we focused on the molecular features, potential therapeutic targets and prognosis of rectal NETs. By summarizing the relevant studies, we established the mutational landscape of rectal NETs and identified a series of large fragment variations. Driver genes including TP53, APC, KRAS, BRAF, RB1, CDKN2A and PTEN were found as the top mutated genes. Large fragment alterations mainly involved known driver genes, including APC, TP53, CCNE1, MYC, TERT, RB1 and ATM. Germline mutations of APC, MUTYH, MSH6, MLH1 and MSH2 associated with Lynch syndrome or FAP were also found in rectal NETs. The BRAF-V600E mutation was reported as an actionable target in rectal NETs, and the combined BRAF/MEK inhibitors were found to be effective targeting BRAF-V600E in advanced or metastatic NETs. The known prognostic risk factors of rectal adenocarcinoma, including a series of demographic and clinicopathological factors were also prognostic factors for rectal NETs. Furthermore, three types of markers, including genetic alterations, protein expression levels and methylation, were also suggested as prognostic factors for rectal NETs. In summary, we established the landscape of mutations and large-fragment alterations of rectal NETs, and identified potential therapeutic targets and a series of prognostic factors. Future studies may focus on the optimization of therapeutic strategies based on potential actionable biomarkers.

Development and validation of an XGBoost model to predict 5-year survival in elderly patients with intrahepatic cholangiocarcinoma after surgery: a SEER-based study

Background

Nomograms have been established to predict survival in postoperative or elderly intrahepatic cholangiocarcinoma (ICC) patients. There are no models to predict postoperative survival in elderly ICC patients. Extreme gradient boosting (XGBoost) can adjust the errors generated by existing models. This retrospective cohort study aimed to develop and validate an XGBoost model to predict postoperative 5-year survival in elderly ICC patients.

Methods

The Surveillance, Epidemiology, and End Results (SEER) program provided data on elderly ICC patients aged 60 years or older and undergoing surgery. The median follow-up time was 20 months. Totally 1,055 patients were classified as training (n=738) and testing (n=317) sets at a ratio of 7:3. The outcome was postoperative 5-year survival. Demographic, tumor-related and treatment-related variables were collected. Variables were screened using the XGBoost model. The predictive performance of the model was assessed by the area under the receiver operating characteristic (ROC) curve (AUC), sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and Kaplan-Meier curve. Cox regression analysis was conducted to estimate the risk of death in the predicted populations. The predictive abilities of the XGBoost model and the American Joint Commission on Cancer (AJCC) system (7th edition) were compared.

Results

The XGBoost model achieved an AUC of 0.811, a sensitivity of 0.573, a specificity of 0.890, and a PPV of 0.849 in the training set. In the testing set, the model had an AUC of 0.713, a sensitivity of 0.478, a specificity of 0.814, and a PPV of 0.726. The 5-year mortality risk of patients predicted to die was 2.91 times that of patients predicted to survive [hazard ratio (HR) =2.91, 95% confidence interval (CI): 2.42-3.50]. The XGBoost model showed a better predictive performance than the AJCC staging system both in the training and testing sets. AJCC stage, multiple (satellite) tumors/nodules, tumor-node-metastasis (TNM) stage, more than one lobe invaded, direct invasion of adjacent organs, tumor size, and radiotherapy were relatively important features in survival prediction.

Conclusions

The XGBoost model exhibited some predictive capacity, which may be applied to predict postoperative 5-year survival for elderly ICC patients.

Artificial Intelligence and Machine Learning in the Diagnosis and Management of Gastroenteropancreatic Neuroendocrine Neoplasms-A Scoping Review

Neuroendocrine neoplasms (NENs) and tumors (NETs) are rare neoplasms that may affect any part of the gastrointestinal system. In this scoping review, we attempt to map existing evidence on the role of artificial intelligence, machine learning and deep learning in the diagnosis and management of NENs of the gastrointestinal system. After implementation of inclusion and exclusion criteria, we retrieved 44 studies with 53 outcome analyses. We then classified the papers according to the type of studied NET (26 Pan-NETs, 59.1%; 3 metastatic liver NETs (6.8%), 2 small intestinal NETs, 4.5%; colorectal, rectal, non-specified gastroenteropancreatic and non-specified gastrointestinal NETs had from 1 study each, 2.3%). The most frequently used AI algorithms were Supporting Vector Classification/Machine (14 analyses, 29.8%), Convolutional Neural Network and Random Forest (10 analyses each, 21.3%), Random Forest (9 analyses, 19.1%), Logistic Regression (8 analyses, 17.0%), and Decision Tree (6 analyses, 12.8%). There was high heterogeneity on the description of the prediction model, structure of datasets, and performance metrics, whereas the majority of studies did not report any external validation set. Future studies should aim at incorporating a uniform structure in accordance with existing guidelines for purposes of reproducibility and research quality, which are prerequisites for integration into clinical practice.