Machine Learning-Based Model for the Prognosis of Postoperative Gastric Cancer

Prognostication: A fading Hippocratic art?

Over the past 75 years modern medicine has advanced in its ability to diagnose and treat many diseases. However, the medical profession's ability to prognosticate the course and outcome of an illness has not satisfied the needs of many patients. Physicians must not lose the ability, or desire, to consider the whole person in relation to a patient's disease. We need to ask ourselves what person has the disease, not what disease the person has. Here I endeavor to demonstrate why Hippocrates valued prognostication highly, how its importance may have faded from the consciousness of current medical practice, and how modern technology is attempting to reinvent or revise it.

Development and validation of an inflammatory biomarkers model to predict gastric cancer prognosis: a multi-center cohort study in China

BACKGROUND

Inflammatory factors have increasingly become a more cost-effective prognostic indicator for gastric cancer (GC). The goal of this study was to develop a prognostic score system for gastric cancer patients based on inflammatory indicators.

METHODS

Patients' baseline characteristics and anthropometric measures were used as predictors, and independently screened by multiple machine learning(ML) algorithms. We constructed risk scores to predict overall survival in the training cohort and tested risk scores in the validation. The predictors selected by the model were used in multivariate Cox regression analysis and developed a nomogram to predict the individual survival of GC patients.

RESULTS

A 13-variable adaptive boost machine (ADA) model mainly comprising tumor stage and inflammation indices was selected in a wide variety of machine learning models. The ADA model performed well in predicting survival in the validation set (AUC = 0.751; 95% CI: 0.698, 0.803). Patients in the study were split into two sets - "high-risk" and "low-risk" based on 0.42, the cut-off value of the risk score. We plotted the survival curves using Kaplan-Meier analysis.

CONCLUSION

The proposed model performed well in predicting the prognosis of GC patients and could help clinicians apply management strategies for better prognostic outcomes for patients.

Deep learning model for predicting postoperative survival of patients with gastric cancer

Background

Prognostic prediction for surgical treatment of gastric cancer remains valuable in clinical practice. This study aimed to develop survival models for postoperative gastric cancer patients.

Methods

Eleven thousand seventy-five patients from the Surveillance, Epidemiology, and End Results (SEER) database were included, and 122 patients from the Chinese database were used for external validation. The training cohort was created to create three separate models, including Cox regression, RSF, and DeepSurv, using data from the SEER database split into training and test cohorts with a 7:3 ratio. Test cohort was used to evaluate model performance using c-index, Brier scores, calibration, and the area under the curve (AUC). The new risk stratification based on the best model will be compared with the AJCC stage on the test and Chinese cohorts using decision curve analysis (DCA), the net reclassification index (NRI), and integrated discrimination improvement (IDI).

Results

It was discovered that the DeepSurv model predicted postoperative gastric cancer patients' overall survival (OS) with a c-index of 0.787; the area under the curve reached 0.781, 0.798, 0.868 at 1-, 3- and 5- years, respectively; the Brier score was below 0.25 at different time points; showing an advantage over the Cox and RSF models. The results are also validated in the China cohort. The calibration plots demonstrated good agreement between the DeepSurv model's forecast and actual results. The NRI values (test cohort: 0.399, 0.288, 0.267 for 1-, 3- and 5-year OS prediction; China cohort:0.399, 0.288 for 1- and 3-year OS prediction) and IDI (test cohort: 0.188, 0.169, 0.157 for 1-, 3- and 5-year OS prediction; China cohort: 0.189, 0.169 for 1- and 3-year OS prediction) indicated that the risk score stratification performed significantly better than the AJCC staging alone (P < 0.05). DCA showed that the risk score stratification was clinically useful and had better discriminative ability than the AJCC staging. Finally, an interactive native web-based prediction tool was constructed for the survival prediction of patients with postoperative gastric cancer.

Conclusion

In this study, a high-performance prediction model for the postoperative prognosis of gastric cancer was developed using DeepSurv, which offers essential benefits for risk stratification and prognosis prediction for each patient.

Development and validation of a deep learning model for predicting postoperative survival of patients with gastric cancer

BACKGROUND

Deep learning (DL), a specialized form of machine learning (ML), is valuable for forecasting survival in various diseases. Its clinical applicability in real-world patients with gastric cancer (GC) has yet to be extensively validated.

METHODS

A combined cohort of 11,414 GC patients from the Surveillance, Epidemiology and End Results (SEER) database and 2,846 patients from a Chinese dataset were utilized. The internal validation of different algorithms, including DL model, traditional ML models, and American Joint Committee on Cancer (AJCC) stage model, was conducted by training and testing sets on the SEER database, followed by external validation on the Chinese dataset. The performance of the algorithms was assessed using the area under the receiver operating characteristic curve, decision curve, and calibration curve.

RESULTS

DL model demonstrated superior performance in terms of the area under the curve (AUC) at 1, 3, and, 5 years post-surgery across both datasets, surpassing other ML models and AJCC stage model, with AUCs of 0.77, 0.80, and 0.82 in the SEER dataset and 0.77, 0.76, and 0.75 in the Chinese dataset, respectively. Furthermore, decision curve analysis revealed that the DL model yielded greater net gains at 3 years than other ML models and AJCC stage model, and calibration plots at 3 years indicated a favorable level of consistency between the ML and actual observations during external validation.

CONCLUSIONS

DL-based model was established to accurately predict the survival rate of postoperative patients with GC.

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.

Prediction of HER2 status via random forest in 3257 Chinese patients with gastric cancer

The accurate evaluation of human epidermal growth factor receptor 2 (HER2) is crucial for successful trastuzumab-based therapy in individuals with gastric cancer (GC). The present study, involving a retrospective cohort (N = 2865) from Wuhan Union Hospital and a prospective cohort (N = 392) from Renmin Hospital of Wuhan University, evaluated the benefits of clinical features using random forest and logistic regression models for the detection of HER2 status in patients with GC. Patients from the Union cohort were randomly assigned to either a training (N = 2005) or an internal validation (N = 860) group. Data processing and feature selection were done in Python, which was also used to build random forest and logistic regression models for the prediction of HER2 overexpression. The Renmin cohort (N = 392) was used as the external validation group. Ten features were closely correlated with HER2 overexpression, including age, albumin/globulin ratio, globulin, activated partial thromboplastin time, tumor stage, node stage, tumor node metastasis stage, tumor size, tumor differentiation, and neuron-specific enolase (NSE). Random forest and logistic regression had areas under the curve (AUC) of 0.9995 and 0.6653 in the training group and 0.923 and 0.667 in the internal validation group, respectively. When the two predictive models were validated using data from the Renmin cohort, random forest and logistic regression had AUCs of 0.9994 and 0.627, respectively. This is the first multicenter study to predict HER2 overexpression in individuals with GC, based on clinical variables. The random forest model significantly outperformed the logistic regression model.

Application of Machine Learning Based on Structured Medical Data in Gastroenterology

The era of big data has led to the necessity of artificial intelligence models to effectively handle the vast amount of clinical data available. These data have become indispensable resources for machine learning. Among the artificial intelligence models, deep learning has gained prominence and is widely used for analyzing unstructured data. Despite the recent advancement in deep learning, traditional machine learning models still hold significant potential for enhancing healthcare efficiency, especially for structured data. In the field of medicine, machine learning models have been applied to predict diagnoses and prognoses for various diseases. However, the adoption of machine learning models in gastroenterology has been relatively limited compared to traditional statistical models or deep learning approaches. This narrative review provides an overview of the current status of machine learning adoption in gastroenterology and discusses future directions. Additionally, it briefly summarizes recent advances in large language models.

Novel nomogram to predict the overall survival of postoperative patients with gastric signet

BACKGROUND

The TNM staging system cannot accurately predict the prognosis of postoperative gastric signet ring cell carcinoma (GSRC) given its unique biological behavior, epidemiological features, and various prognostic factors. Therefore, a reliable postoperative prognostic evaluation system for GSRC is required. This study aimed to establish a nomogram to predict the overall survival (OS) rate of postoperative patients with GSRC and validate it in the real world.

METHODS

Clinical data of postoperative patients with GSRC from 2002 to 2014 were collected from the Surveillance, Epidemiology, and End Results database and randomly assigned to training and internal validation sets at a 7:3 ratio. The external validation set used data from 124 postoperative patients with GSRC who were admitted to the Affiliated Tumor Hospital of Harbin Medical University between 2002 and 2014. The independent risk factors affecting OS were screened using univariate and multivariate analyses to construct a nomogram. The performance of the model was evaluated using the C-index, receiver operating characteristic curve (ROC), calibration curve, decision analysis (DCA) curve, and adjuvant chemotherapy decision analysis.

RESULTS

Univariate/multivariate analysis indicated that age, stage, T, M, regional nodes optimized (RNE), and lymph node metastasis rate (LNMR) were independent risk factors affecting prognosis. The C-indices of the training, internal validation, and external validation sets are 0.741, 0.741, and 0.786, respectively. The ROC curves for the first, third, and fifth years in three sets had higher areas under the curves, (training set, 0.782, 0.864, 0.883; internal validation set, 0.781, 0.863, 0.877; external validation set, 0.819, 0.863, 0.835). The calibration curve showed high consistency between the nomogram-predicted 1-, 3-, and 5-year OS and the actual OS in the three queues. The DCA curve indicated that applying the nomogram enhanced the net clinical benefits. The nomogram effectively distinguished patients in each subgroup into high- and low-risk groups. Adjuvant chemotherapy can significantly improve OS in high-risk group (P = 0.034), while the presence or absence of adjuvant chemotherapy in low-risk group has no significant impact on OS (P = 0.192).

CONCLUSIONS

The nomogram can effectively predict the OS of patients with GSRC and may help doctors make personalized prognostic judgments and clinical treatment decisions.

Study of Patient and Physician Attitudes Toward Automated Prognostic Models for Patients With Metastatic Cancer

PURPOSE

For patients with cancer and their doctors, prognosis is important for choosing treatments and supportive care. Oncologists' life expectancy estimates are often inaccurate, and many patients are not aware of their general prognosis. Machine learning (ML) survival models could be useful in the clinic, but there are potential concerns involving accuracy, provider training, and patient involvement. We conducted a qualitative study to learn about patient and oncologist views on potentially using a ML model for patient care.

METHODS

Patients with metastatic cancer (n = 15) and their family members (n = 5), radiation oncologists (n = 5), and medical oncologists (n = 5) were recruited from a single academic health system. Participants were shown an anonymized report from a validated ML survival model for another patient, which included a predicted survival curve and a list of variables influencing predicted survival. Semistructured interviews were conducted using a script.

RESULTS

Every physician and patient who completed their interview said that they would want the option for the model to be used in their practice or care. Physicians stated that they would use an AI prognosis model for patient triage and increasing patient understanding, but had concerns about accuracy and explainability. Patients generally said that they would trust model results completely if presented by their physician but wanted to know if the model was being used in their care. Some reacted negatively to being shown a median survival prediction.

CONCLUSION

Patients and physicians were supportive of use of the model in the clinic, but had various concerns, which should be addressed as predictive models are increasingly deployed in practice.

Establishing machine learning models to predict the early risk of gastric cancer based on lifestyle factors

BACKGROUND

Gastric cancer is one of the leading causes of death worldwide. Screening for gastric cancer greatly relies on endoscopy and pathology biopsy, which are invasive and pose financial burdens. Thus, the prevention of the disease by modifying lifestyle-related behaviors and dietary habits or even the prevention of risk factor formation is of great importance. This study aimed to construct an inexpensive, non-invasive, fast, and high-precision diagnostic model using six machine learning (ML) algorithms to classify patients at high or low risk of developing gastric cancer by analyzing individual lifestyle factors.

METHODS

This retrospective study used the data of 2029 individuals from the gastric cancer database of Ayatollah Taleghani Hospital in Abadan City, Iran. The data were randomly separated into training and test sets (ratio 0.7:0.3). Six  ML methods, including multilayer perceptron (MLP), support vector machine (SVM) (linear kernel), SVM (RBF kernel), k-nearest neighbors (KNN) (K = 1, 3, 7, 9), random forest (RF), and eXtreme Gradient Boosting (XGBoost), were trained to construct prognostic models before and after performing the relief feature selection method. Finally, to evaluate the models' performance, the metrics derived from the confusion matrix were calculated via a test split and cross-validation.

RESULTS

This study found 11 important influence factors for the risk of gastric cancer, such as Helicobacter pylori infection, high salt intake, and chronic atrophic gastritis, among other factors. Comparisons indicated that the XGBoost had the best performance for the risk prediction of gastric cancer.

CONCLUSIONS

The results suggest that based on simple baseline patient data, the ML techniques have the potential to start the prescreening of gastric cancer and identify high-risk individuals who should proceed with invasive examinations. Our model could also considerably lessen the number of cases that need endoscopic surveillance. Future studies are required to validate the efficacy of the models in a larger and multicenter population.

Validation of the Memorial Sloan Kettering Gastric Cancer Post-Resection Survival Nomogram: Does It Stand the Test of Time?

BACKGROUND

The Memorial Sloan Kettering Cancer Center (MSK) nomogram combined both gastroesophageal junction (GEJ) and gastric cancer patients and was created in an era from patients who generally did not receive neoadjuvant chemotherapy. We sought to reevaluate the MSK nomogram in the era of multidisciplinary treatment for GEJ and gastric cancer.

STUDY DESIGN

Using data on patients who underwent R0 resection for GEJ or gastric cancer between 2002 and 2016, the C-index of prediction for disease-specific survival (DSS) was compared between the MSK nomogram and the American Joint Committee on Cancer (AJCC) 8th edition staging system after segregating patients by tumor location (GEJ or gastric cancer) and neoadjuvant treatment. A new nomogram was created for the group for which both systems poorly predicted prognosis.

RESULTS

During the study period, 886 patients (645 gastric and 241 GEJ cancer) underwent up-front surgery, and 999 patients (323 gastric and 676 GEJ) received neoadjuvant treatment. Compared with the AJCC staging system, the MSK nomogram demonstrated a comparable C-index in gastric cancer patients undergoing up-front surgery (0.786 vs 0.753) and a better C-index in gastric cancer patients receiving neoadjuvant treatment (0.796 vs 0.698). In GEJ cancer patients receiving neoadjuvant chemotherapy, neither the MSK nomogram nor the AJCC staging system performed well (C-indices 0.647 and 0.646). A new GEJ nomogram was created based on multivariable Cox regression analysis and was validated with a C-index of 0.718.

CONCLUSIONS

The MSK gastric cancer nomogram's predictive accuracy remains high. We developed a new GEJ nomogram that can effectively predict DSS in patients receiving neoadjuvant treatment.

Machine Learning-based Correlation Study between Perioperative Immunonutritional Index and Postoperative Anastomotic Leakage in Patients with Gastric Cancer

Backgrounds: The immunonutritional index showed great potential for predicting postoperative complications in various malignant diseases, while risk assessment based on machine learning (ML) methods is becoming popular in clinical practice. Early detection and prevention for postoperative anastomotic leakage (AL) play an important role in prognosis improvement among patients with gastric cancer (GC). Methods: This retrospective study included 297 patients with gastric cancer receiving gastrectomy between 2018 and 2021 in general surgery department of Xinhua Hospital. Perioperative clinical variables were collected to evaluate the predictive value for postoperative AL with 5 ML models. Then, AUROC was applied to identify the optimal perioperative clinical index and ML model for predicting postoperative AL. Results: The incidence of postoperative AL was 6.1% (n=18). After the training of 5 ML classification models, we found that immunonutritional index had significantly better classification ability than inflammatory or nutritional index alone separately (AUROC=0.87 vs. 0.83, P=0.01; AUROC=0.87 vs. 0.68, P<0.01). Next, we found that support vector machine (SVM), one of the ML methods, with selected immunonutritional index showed significantly greater classification ability than optimal univariant parameter [CRP on postoperative day 4 (AUROC=0.89 vs.0.86, P=0.02)]. Also, statistical analysis revealed multiple variables with significant relevance to postoperative AL, including serum CRP and albumin on postoperative day 4, NLR and SII etc. Conclusion: This study showed that perioperative immunonutritional index could act as an indicator for postoperative AL. Also, ML methods could significantly enhance the classification ability, and therefore, could be applied as a powerful tool for postoperative risk assessment for patients with GC.