Artificial Intelligence Combined With Big Data to Predict Lymph Node Involvement in Prostate Cancer: A Population-Based Study

Prediction of prostate biopsy outcomes at different cut-offs of prostate-specific antigen using machine learning: a multicenter study

BACKGROUND

Machine learning (ML) is a significant area of artificial intelligence, which can improve the accuracy of predictive or diagnostic models for differentiating between prostate biopsy outcomes. This study aims to develop a novel decision-support ML model for classifying patients with biopsy-negative (cancer-free), clinically significant, and non-clinically significant prostate cancer across two prostate-specific antigen (PSA) cut-offs ≤ 10 ng/ml and > 10 ng/ml.

METHODS

The data for the current study were retrieved from the records of two main hospitals in Riyadh, Saudi Arabia from July 2018 through July 2024. Six machine learning algorithms were employed, and the dataset was randomly divided into a training set and a validation set at a ratio of 8:2. The following metrics were used as performance indicators across the six algorithms: Accuracy, Precision, Recall, F1-score, and area under the curve. Recent data from the two hospitals was utilized for external validation.

RESULTS

The metrics for Random Forest, Extra Tree, and Decision Tree algorithms showed excellent capability in classifying the outcomes of prostate biopsy for the two PSA cut-offs. However, the metrics for the PSA cut-off > 10 ng/ml are higher than those for PSA ≤ 10 ng/ml. For the three-class classification, the accuracy and area under the curve for the cut-off > 10 ng/ml were 0.96 and 0.99, respectively. While for the cut-off ≤ 10 ng/ml they were 0.92 and 0.94 for Random Forest and 0.94 and 0.95 for the Extra Tree algorithm. The metrics of non-clinically significant and biopsy-negative cases outperformed those of clinically significant cases.

CONCLUSION

ML models are proving to be effective tools in differentiating between prostate biopsy outcomes, enhancing diagnostic accuracy, and potentially transforming clinical practices in prostate cancer management.

Utility of Machine Learning Models to Predict Lymph Node Metastasis of Japanese Localized Prostate Cancer

BACKGROUND/OBJECTIVES

Extended pelvic lymph node dissection is a crucial surgical technique for managing intermediate to high-risk prostate cancer. Accurately predicting lymph node metastasis before surgery can minimize unnecessary lymph node dissections and their associated complications. This study assessed the efficacy of various machine learning models for predicting lymph node metastasis in a cohort of Japanese patients who underwent robot-assisted laparoscopic radical prostatectomy.

METHODS

Data from 625 patients who underwent extended pelvic lymph node dissection or standard dissection with lymph node metastasis between October 2010 and February 2023 were analyzed. Four machine learning models-Random Forest, Light Gradient-Boosting Machine, Logistic Regression, and Support Vector Machine-were used to predict lymph node metastasis. Their performance was assessed using receiver operating characteristic curves, a decision curve analysis, and predictive values at different thresholds.

RESULTS

Lymph node metastasis was observed in 34 patients (5.4%). The Light Gradient-Boosting Machine had the highest AUC of 0.924, followed by the Random Forest model with an AUC of 0.894. The decision curve analysis indicated substantial net benefits for both models, particularly at low threshold probabilities. The Light Gradient-Boosting Machine demonstrated superior accuracy, achieving 95.6% at the 0.05 threshold and 96.7% at the 0.10 threshold, outperforming other models and conventional nomograms in the validation dataset.

CONCLUSION

Machine learning models, especially Light Gradient-Boosting Machine and Random Forest, show significant potential for predicting lymph node metastasis in prostate cancer, thereby aiding in reducing unnecessary surgical interventions.

Machine learning and explainable artificial intelligence to predict pathologic stage in men with localized prostate cancer

BACKGROUND

Though several nomograms exist, machine learning (ML) approaches might improve prediction of pathologic stage in patients with prostate cancer. To develop ML models to predict pathologic stage that outperform existing nomograms that use readily available clinicopathologic variables.

METHODS

Patients with prostate adenocarcinoma who underwent surgery were identified in the National Cancer Database. Seven ML models were trained to predict organ-confined (OC) disease, extracapsular extension, seminal vesicle invasion (SVI), and lymph node involvement (LNI). Model performance was measured using area under the curve (AUC) on a holdout testing data set. Clinical utility was evaluated using decision curve analysis (DCA). Performance metrics were confirmed on an external validation data set.

RESULTS

The ML-based extreme gradient boosted trees model achieved the best performance with an AUC of 0.744, 0.749, 0.816, 0.811 for the OC, ECE, SVI, and LNI models, respectively. The MSK nomograms achieved an AUC of 0.708, 0.742, 0.806, 0.802 for the OC, ECE, SVI, and LNI models, respectively. These models also performed the best on DCA. Findings were consistent on both a holdout internal validation data set as well as an external validation data set.

CONCLUSIONS

Our ML models better predicted pathologic stage relative to existing nomograms at predicting pathologic stage. Accurate prediction of pathologic stage can help oncologists and patients determine optimal definitive treatment options for patients with prostate cancer.

A Comparison of Systematic, Targeted, and Combined Biopsy Using Machine Learning for Prediction of Prostate Cancer Risk: A Multi-Center Study

OBJECTIVES

The aims of the study were to construct a new prognostic prediction model for detecting prostate cancer (PCa) patients using machine-learning (ML) techniques and to compare those models across systematic and target biopsy detection techniques.

METHODS

The records of the two main hospitals in Riyadh, Saudi Arabia, were analyzed for data on diagnosed PCa from 2019 to 2023. Four ML algorithms were utilized for the prediction and classification of PCa.

RESULTS

A total of 528 patients with prostate-specific antigen (PSA) greater than 3.5 ng/mL who had undergone transrectal ultrasound-guided prostate biopsy were evaluated. The total number of confirmed PCa cases was 234. Age, prostate volume, PSA, body mass index (BMI), multiparametric magnetic resonance imaging (mpMRI) score, number of regions of interest detected in MRI, and the diameter of the largest size lesion were significantly associated with PCa. Random Forest (RF) and XGBoost (XGB) (ML algorithms) accurately predicted PCa. Yet, their performance for classification and prediction of PCa was higher and more accurate for cases detected by targeted and combined biopsy (systematic and targeted together) compared to systematic biopsy alone. F1, the area under the curve (AUC), and the accuracy of XGB and RF models for targeted biopsy and combined biopsy ranged from 0.94 to 0.97 compared to the AUC of systematic biopsy for RF and XGB algorithms, respectively.

CONCLUSIONS

The RF model generated and presented an excellent prediction capability for the risk of PCa detected by targeted and combined biopsy compared to systematic biopsy alone. ML models can prevent missed PCa diagnoses by serving as a screening tool.

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.

Development and External Validation of a Machine Learning Model for Prediction of Lymph Node Metastasis in Patients with Prostate Cancer

BACKGROUND

Pelvic lymph node dissection (PLND) is the gold standard for diagnosis of lymph node involvement (LNI) in patients with prostate cancer. The Roach formula, Memorial Sloan Kettering Cancer Center (MSKCC) calculator, and Briganti 2012 nomogram are elegant and simple traditional tools used to estimate the risk of LNI and select patients for PLND.

OBJECTIVE

To determine whether machine learning (ML) can improve patient selection and outperform currently available tools for predicting LNI using similar readily available clinicopathologic variables.

DESIGN, SETTING, AND PARTICIPANTS

Retrospective data for patients treated with surgery and PLND between 1990 and 2020 in two academic institutions were used.

OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS

We trained three models (two logistic regression models and one gradient-boosted trees-based model [XGBoost]) on data provided from one institution (n = 20267) with age, prostate-specific antigen (PSA) levels, clinical T stage, percentage positive cores, and Gleason scores as inputs. We externally validated these models using data from another institution (n = 1322) and compared their performance to that of the traditional models using the area under the receiver operating characteristic curve (AUC), calibration, and decision curve analysis (DCA).

RESULTS AND LIMITATIONS

LNI was present in 2563 patients (11.9%) overall, and in 119 patients (9%) in the validation data set. XGBoost had the best performance among all the models. On external validation, its AUC outperformed that of the Roach formula by 0.08 (95% confidence interval [CI] 0.042-0.12), the MSKCC nomogram by 0.05 (95% CI 0.016-0.070), and the Briganti nomogram by 0.03 (95% CI 0.0092-0.051; all p < 0.05). It also had better calibration and clinical utility in terms of net benefit on DCA across relevant clinical thresholds. The main limitation of the study is its retrospective design.

CONCLUSIONS

Taking all measures of performance together, ML using standard clinicopathologic variables outperforms traditional tools in predicting LNI.

PATIENT SUMMARY

Determining the risk of cancer spread to the lymph nodes in patients with prostate cancer allows surgeons to perform lymph node dissection only in patients who need it and avoid the side effects of the procedure in those who do not. In this study, we used machine learning to develop a new calculator to predict the risk of lymph node involvement that outperformed traditional tools currently used by oncologists.

The predictive value of machine learning and nomograms for lymph node metastasis of prostate cancer: a systematic review and meta-analysis

BACKGROUND

In clinical practice, there are currently a variety of nomograms for predicting lymph node metastasis (LNM) of prostate cancer. At the same time, some scholars have introduced machine learning (ML) into the prediction of LNM of prostate cancer. However, the predictive value of nomograms and ML remains controversial. Based on this situation, this systematic review and meta-analysis was performed to explore the predictive value of various nomograms currently recommended and newly-developed ML models for LNM in prostate cancer patients.

EVIDENCE ACQUISITION

Cochrane, PubMed, Embase, and Web of Science were searched up to November 1, 2022. The risk of bias in the included studies was evaluated using the Prediction model Risk of Bias Assessment Tool (PROBAST). The concordance index (C-index), sensitivity, and specificity were adopted to evaluate the predictive accuracy of the models.

RESULTS

Thirty-one studies (18,803 patients) were included. Seven kinds of nomograms currently recommended, dominated by Briganti nomogram or MSKCC nomogram, were covered in the included studies. For newly-developed ML models, the C-index for LNM prediction in the training set and validation set was 0.846 [95%CI (0.818, 0.873)] and 0.862 [95%CI (0.819-0.905)] respectively. Most ML models in the training set were based on Logistic Regression (LR), which had a sensitivity of 0.78 [95%CI (0.70, 0.85)] and a specificity of 0.85 [95%CI (0.77, 0.90)] in the training set, and a sensitivity of 0.81 [95%CI (0.67, 0.89)] and a specificity of 0.82 [95%CI (0.75, 0.88)] in the validation set. For the recommended nomograms, the C-index in the validation set was 0.745 [95%CI (0.701, 0.790)] for the Briganti nomogram and 0.714 [95%CI (0.662, 0.765)] for the MSKCC nomogram.

CONCLUSION

The predictive accuracy of ML is superior to existing clinically recommended nomograms, and appropriate updates can be conducted to existing nomograms according to special situations.

A machine learning-based model for predicting the risk of early-stage inguinal lymph node metastases in patients with squamous cell carcinoma of the penis

Objective

Inguinal lymph node metastasis (ILNM) is significantly associated with poor prognosis in patients with squamous cell carcinoma of the penis (SCCP). Patient prognosis could be improved if the probability of ILNM incidence could be accurately predicted at an early stage. We developed a predictive model based on machine learning combined with big data to achieve this.

Methods

Data of patients diagnosed with SCCP were obtained from the Surveillance, Epidemiology, and End Results Program Research Data. By combing variables that represented the patients' clinical characteristics, we applied five machine learning algorithms to create predictive models based on logistic regression, eXtreme Gradient Boosting, Random Forest, Support Vector Machine, and k-Nearest Neighbor. Model performance was evaluated by ten-fold cross-validation receiver operating characteristic curves, which were used to calculate the area under the curve of the five models for predictive accuracy. Decision curve analysis was conducted to estimate the clinical utility of the models. An external validation cohort of 74 SCCP patients was selected from the Affiliated Hospital of Xuzhou Medical University (February 2008 to March 2021).

Results

A total of 1,056 patients with SCCP from the SEER database were enrolled as the training cohort, of which 164 (15.5%) developed early-stage ILNM. In the external validation cohort, 16.2% of patients developed early-stage ILNM. Multivariate logistic regression showed that tumor grade, inguinal lymph node dissection, radiotherapy, and chemotherapy were independent predictors of early-stage ILNM risk. The model based on the eXtreme Gradient Boosting algorithm showed stable and efficient prediction performance in both the training and external validation groups.

Conclusion

The ML model based on the XGB algorithm has high predictive effectiveness and may be used to predict early-stage ILNM risk in SCCP patients. Therefore, it may show promise in clinical decision-making.

A 5‐year survival status prognosis of nonmetastatic cervical cancer patients through machine learning algorithms

BACKGROUND

Prediction models with high accuracy rates for nonmetastatic cervical cancer (CC) patients are limited. This study aimed to construct and compare predictive models on the basis of machine learning (ML) algorithms for predicting the 5-year survival status of CC patients through using the Surveillance, Epidemiology, and End Results public database of the National Cancer Institute.

METHODS

The data registered from 2004 to 2016 were extracted and randomly divided into training and validation cohorts (8:2). The least absolute shrinkage and selection operator (LASSO) regression was employed to identify significant factors. Then, four predictive models were constructed, including logistic regression (LR), random forest (RF), support vector machine (SVM), and extreme gradient boosting (XGBoost). The predictive models were evaluated and compared using Receiver-operating characteristics with areas under the curves (AUCs) and decision curve analysis (DCA), respectively.

RESULTS

A total of 13,802 patients were involved and classified into training (N = 11,041) and validation (N = 2761) cohorts. By using the LASSO regression method, seven factors were identified. In the training cohort, the XGBoost model showed the best performance (AUC = 0.8400) compared to the other three models (all p < 0.05 by Delong's test). In the validation cohort, the XGBoost model also demonstrated a superior prediction ability (AUC = 0.8365) than LR and SVM models (both p < 0.05 by Delong's test), although the difference was not statistically significant between the XGBoost and the RF models (p = 0.4251 by Delong's test). Based on the DCA results, the XGBoost model was also superior, and feature importance analysis indicated that the tumor stage was the most important variable among the seven factors.

CONCLUSIONS

The XGBoost model proved to be an effective algorithm with better prediction abilities. This model is proposed to support better decision-making for nonmetastatic CC patients in the future.

A Machine Learning Approach Using XGBoost Predicts Lung Metastasis in Patients with Ovarian Cancer

Background

Liver metastasis (LM) is an independent risk factor that affects the prognosis of patients with ovarian cancer; however, there is still a lack of prediction. This study developed a limit gradient enhancement (XGBoost) to predict the risk of lung metastasis in newly diagnosed patients with ovarian cancer, thereby improving prediction efficiency. Patients and Methods. Data of patients diagnosed with ovarian cancer in the Surveillance, Epidemiology, and Final Results (SEER) database from 2010 to 2015 were retrospectively collected. The XGBoost algorithm was used to establish a lung metastasis model for patients with ovarian cancer. The performance of the predictive model was tested by the area under the curve (AUC) of the receiver operating characteristic curve (ROC).

Results

The results of the XGBoost algorithm showed that the top five important factors were age, laterality, histological type, grade, and marital status. XGBoost showed good discriminative ability, with an AUC of 0.843. Accuracy, sensitivity, and specificity were 0.982, 1.000, and 0.686, respectively.

Conclusion

This study is the first to develop a machine-learning-based prediction model for lung metastasis in patients with ovarian cancer. The prediction model based on the XGBoost algorithm has a higher accuracy rate than traditional logistic regression and can be used to predict the risk of lung metastasis in newly diagnosed patients with ovarian cancer.

Machine learning model for the prediction of prostate cancer in patients with low prostate-specific antigen levels: A multicenter retrospective analysis

Objective

The aim of this study was to develop a predictive model to improve the accuracy of prostate cancer (PCa) detection in patients with prostate specific antigen (PSA) levels ≤20 ng/mL at the initial puncture biopsy.

Methods

A total of 146 patients (46 with Pca, 31.5%) with PSA ≤20 ng/mL who had undergone transrectal ultrasound-guided 12+X prostate puncture biopsy with clear pathological results at the First Affiliated Hospital of Guangxi Medical University (November 2015 to December 2021) were retrospectively evaluated. The validation group was 116 patients drawn from Changhai Hospital(52 with Pca, 44.8%). Age, body mass index (BMI), serum PSA, PSA-derived indices, several peripheral blood biomarkers, and ultrasound findings were considered as predictive factors and were analyzed by logistic regression. Significant predictors (P < 0.05) were included in five machine learning algorithm models. The performance of the models was evaluated by receiver operating characteristic curves. Decision curve analysis (DCA) was performed to estimate the clinical utility of the models. Ten-fold cross-validation was applied in the training process.

Results

Prostate-specific antigen density, alanine transaminase-to-aspartate transaminase ratio, BMI, and urine red blood cell levels were identified as independent predictors for the differential diagnosis of PCa according to multivariate logistic regression analysis. The RandomForest model exhibited the best predictive performance and had the highest net benefit when compared with the other algorithms, with an area under the curve of 0.871. In addition, DCA had the highest net benefit across the whole range of cut-off points examined.

Conclusion

The RandomForest-based model generated showed good prediction ability for the risk of PCa. Thus, this model could help urologists in the treatment decision-making process.

Patients with Positive Lymph Nodes after Radical Prostatectomy and Pelvic Lymphadenectomy-Do We Know the Proper Way of Management?

Lymph node invasion in prostate cancer is a significant prognostic factor indicating worse prognosis. While it significantly affects both survival rates and recurrence, proper management remains a controversial and unsolved issue. The thorough evaluation of risk factors associated with nodal involvement, such as lymph node density or extracapsular extension, is crucial to establish the potential expansion of the disease and to substratify patients clinically. There are multiple strategies that may be employed for patients with positive lymph nodes. Nowadays, therapeutic methods are generally based on observation, radiotherapy, and androgen deprivation therapy. However, the current guidelines are incoherent in terms of the most effective management approach. Future management strategies are expected to make use of novel diagnostic tools and therapies, such as photodynamic therapy or diagnostic imaging with prostate-specific membrane antigen. Nevertheless, this heterogeneous group of men remains a great therapeutic concern, and both the clarification of the guidelines and the optimal substratification of patients are required.