Nomograms in urologic oncology, advantages and disadvantages

A novel conditional survival nomogram for monitoring real-time prognosis of non-metastatic colorectal cancer

AIMS

The aim of this study is to enhance the accuracy of monitoring and treatment information for patients diagnosed with colorectal cancer (CRC).

METHODS

Utilizing the Surveillance, Epidemiology, and End Results (SEER) database, a cohort of 335,948 eligible CRC patients was included in this investigation. Conditional survival probability and actuarial overall survival were employed as methodologies to investigate the association between clinicopathological characteristics and cancer prognosis.

RESULTS

Among CRC patients, the 5-year survival rate was 59%, while the 10-year survival rate was 42%. Over time, conditional survival showed a consistent increase, with rates reaching 45% and 48% for individuals surviving 1 and 2 years, respectively. Notably, patients with unfavorable tumor stages exhibited substantial improvements in conditional survival, thereby narrowing the disparity with actuarial overall survival over time.

CONCLUSION

This study underscores the significance of time-dependent conditional survival probability, particularly for patients with a poorer prognosis. The findings suggest that long-term CRC survivors may experience improved cancer prognosis over time.

Risk factor analysis and nomogram for predicting gastroparesis in patients with type 2 diabetes mellitus

Purpose

The incidence of gastroparesis is higher in individuals diagnosed with type 2 diabetes mellitus (T2DM) compared to the healthy individuals. Our study aimed to explore the risk factors for gastroparesis in T2DM and to establish a clinical prediction model (nomogram).

Methods

Our study enlisted 694 patients with T2DM from two medical centers over a period of time. From January 2020 to December 2022, 347 and 149 patients were recruited from the Beilun branch of Zhejiang University's First Affiliated Hospital in the training and internal validation cohorts, respectively. The external validation cohort consisted of 198 patients who were enrolled at Nanchang University's First Affiliated Hospital from October 2020 to September 2021. We conducted univariate and multivariate logistic regression analyses to select the risk factors for gastroparesis in patients with T2DM; subsequently,we developed a nomogram model. The performance of the nomogram was evaluated using the area under the receiver operating characteristic (ROC) curve (AUC), calibration curve, and decision curve analysis(DCA).

Results

Four clinical variables, including age, regular exercise, glycated hemoglobin level(HbA1c), and Helicobacter pylori (H. pylori) infection, were identified and included in the model. The model demonstrated excellent discrimination, with an AUC of 0.951 (95% CI = 0.925-0.978) in the training group, and 0.910 (95% CI = 0.859-0.961) and 0.875 (95% CI = 0.813-0.937) in the internal and external validation groups, respectively. The calibration curve showed good consistency between prediction of the model and observed gastroparesis. The DCA also demonstrated good clinical efficacy.

Conclusion

The nomogram model developed in this study showed good performance in predicting gastroparesis in patients with T2DM.

Exploration of the diagnostic capacity of PSAMR combined with PI-RADS scoring for clinically significant prostate cancer and establishment and validation of the Nomogram prediction model

PURPOSE

The objective of this investigation was to explore the diagnostic capability of Prostate Specific Antigen Mass Ratio (PSAMR) combined with Prostate Imaging Reporting and Data System (PI-RADS) scoring for clinically significant prostate cancer (CSPC), develop and validate a Nomogram prediction model for the probability of prostate cancer occurrence in patients who have not undergone prostate biopsy.

METHODS

Initially, we retrospectively collected clinical and pathological data of patients who underwent trans-perineal prostate puncture at Yijishan Hospital of Wanan Medical College from July 2021 to January 2023. Through logistic univariate and multivariate regression analysis, independent risk factors for CSPC were determined. Receiver Operating Characteristic (ROC) curves were generated to compare the ability of different factors for diagnosis of CSPC. Then, we split the dataset into a training set and validation set, compared their heterogeneity, and developed a Nomogram prediction model based on the training set. Finally, we validated the Nomogram prediction model in terms of discrimination, calibration, and clinical usefulness.

RESULTS

Logistic multivariate regression analysis illustrated that age [64-69 (OR = 2.736, P = 0.029); 69-75 (OR = 4.728, P = 0.001); > 75 (OR = 11.344, P < 0.001)], PSAMR [0.44-0.73 (OR = 4.144, P = 0.028); 0.73-1.64(OR = 13.022, P < 0.001); > 1.64(OR = 50.541, P < 0.001)], and PI-RADS score [4 points (OR = 7.780, P < 0.001); 5 points (OR = 24.533, P < 0.001)] were independent risk factors for CSPC. The Area Under the Curve (AUC) of the ROC curves of PSA, PSAMR, PI-RADS score, and PSAMR combined with PI-RADS score were respectively 0.797, 0.874, 0.889, and 0.928. The performance of PSAMR and PI-RADS score for diagnosis of CSPC was superior to PSA, but inferior to PSAMR combined with PI-RADS. Age, PSAMR, and PI-RADS were included in the Nomogram prediction model. The AUCs of the training set ROC curve and the validation set ROC curve were 0.943 (95% CI 0.917-0.970) and 0.878 (95% CI 0.816-0.940), respectively, in the discrimination validation. The calibration curve showed good consistency, and the decision analysis curve suggested the model had good clinical efficacy.

CONCLUSIONS

We found that PSAMR combined with PI-RADS scoring had a strong diagnostic capability for CSPC, and provided a Nomogram prediction model to predict the probability of prostate cancer occurrence combined with clinical data.

Establishment of Surgical Difficulty Grading System and Application of MRI-Based Artificial Intelligence to Stratify Difficulty in Laparoscopic Rectal Surgery

(1) Background: The difficulty of pelvic operation is greatly affected by anatomical constraints. Defining this difficulty and assessing it based on conventional methods has some limitations. Artificial intelligence (AI) has enabled rapid advances in surgery, but its role in assessing the difficulty of laparoscopic rectal surgery is unclear. This study aimed to establish a difficulty grading system to assess the difficulty of laparoscopic rectal surgery, as well as utilize this system to evaluate the reliability of pelvis-induced difficulties described by MRI-based AI. (2) Methods: Patients who underwent laparoscopic rectal surgery from March 2019 to October 2022 were included, and were divided into a non-difficult group and difficult group. This study was divided into two stages. In the first stage, a difficulty grading system was developed and proposed to assess the surgical difficulty caused by the pelvis. In the second stage, AI was used to build a model, and the ability of the model to stratify the difficulty of surgery was evaluated at this stage, based on the results of the first stage; (3) Results: Among the 108 enrolled patients, 53 patients (49.1%) were in the difficult group. Compared to the non-difficult group, there were longer operation times, more blood loss, higher rates of anastomotic leaks, and poorer specimen quality in the difficult group. In the second stage, after training and testing, the average accuracy of the four-fold cross validation models on the test set was 0.830, and the accuracy of the merged AI model was 0.800, the precision was 0.786, the specificity was 0.750, the recall was 0.846, the F1-score was 0.815, the area under the receiver operating curve was 0.78 and the average precision was 0.69; (4) Conclusions: This study successfully proposed a feasible grading system for surgery difficulty and developed a predictive model with reasonable accuracy using AI, which can assist surgeons in determining surgical difficulty and in choosing the optimal surgical approach for rectal cancer patients with a structurally difficult pelvis.

An ultrasound-based radiomics model to distinguish between sclerosing adenosis and invasive ductal carcinoma

Objectives

We aimed to develop an ultrasound-based radiomics model to distinguish between sclerosing adenosis (SA) and invasive ductal carcinoma (IDC) to avoid misdiagnosis and unnecessary biopsies.

Methods

From January 2020 to March 2022, 345 cases of SA or IDC that were pathologically confirmed were included in the study. All participants underwent pre-surgical ultrasound (US), from which clinical information and ultrasound images were collected. The patients from the study population were randomly divided into a training cohort (n = 208) and a validation cohort (n = 137). The US images were imported into MaZda software (Version 4.2.6.0) to delineate the region of interest (ROI) and extract features. Intragroup correlation coefficient (ICC) was used to evaluate the consistency of the extracted features. The least absolute shrinkage and selection operator (LASSO) logistic regression and cross-validation were performed to obtain the radiomics score of the features. Based on univariate and multivariate logistic regression analyses, a model was developed. 56 cases from April 2022 to December 2022 were included for independent validation of the model. The diagnostic performance of the model and the radiomics scores were evaluated by performing the receiver operating characteristic (ROC) analysis. The calibration curve and decision curve analysis (DCA) were used for calibration and evaluation. Leave-One-Out Cross-Validation (LOOCV) was used for the stability of the model.

Results

Three predictors were selected to develop the model, including radiomics score, palpable mass and BI-RADS. In the training cohort, validation cohort and independent validation cohort, AUC of the model and radiomics score were 0.978 and 0.907, 0.946 and 0.886, 0.951 and 0.779, respectively. The model showed a statistically significant difference compared with the radiomics score (p<0.05). The Kappa value of the model was 0.79 based on LOOCV. The Brier score, calibration curve, and DCA showed the model had a good calibration and clinical usefulness.

Conclusions

The model based on radiomics, ultrasonic features, and clinical manifestations can be used to distinguish SA from IDC, which showed good stability and diagnostic performance. The model can be considered a potential candidate diagnostic tool for breast lesions and can contribute to effective clinical diagnosis.

Establishment and validation of an ultrasound-based nomogram with risk stratification for short disease-free survival in breast cancer

PURPOSE

This retrospective study aimed to develop and validate an Ultrasound (US)-based nomogram to predict short disease-free survival (short-DFS, less than 120 months DFS) in breast cancer (BC).

METHODS

Nomogram was established based on a training data of 311 BC patients by multivariable logistic regression, and were assessed by discrimination, calibration, and clinical usefulness. Risk stratification was performed by X-tile. An independent testing data of 200 patients with BC was used for external validation.

RESULTS

Nine predictors including three US features and six clinical parameters were screened into the nomogram by Lasso (log λ = -3.594) in training data. Better performance was obtained in the training data (C-index: 0.942) and testing data (C-index: 0.914). Calibration analysis indicated optimal agreement between nomogram predictions and actual observations (p = 0.67). Decision curve analysis showed a great clinical benefit (Youden index: 0.634). Three risk levels are low-risk (<184.0), moderate-risk (184.0-345.3) and high-risk (>345.3). Our nomograms had larger area under the receiver operating characteristic (ROC) curves compared with Magee Equation and Nottingham Prognostic models (0.942 vs. 0.824, 0.790).

CONCLUSION

The US-based nomogram and the practical score system facilitate individualized prediction of short-DFS to optimize clinical decisions and improve prognosis in patients with BC.

Development and Validation of a Risk Nomogram Model for Predicting Constipation in Patients with Type 2 Diabetes Mellitus

Purpose

Constipation is a common complication of diabetic patients, which has a negative impact on their own health. This study aims to establish and internally validate the risk nomogram of constipation in patients with type 2 diabetes mellitus (T2DM) and to test its predictive ability.

Patients and Methods

This retrospective study included 746 patients with T2DM at two medical centers. Among the 746 patients with T2DM, 382 and 163 patients in the Beilun branch of the First Affiliated Hospital of Zhejiang University were enrolled in the training cohort and the validation cohort, respectively. A total of 201 patients in the First Affiliated Hospital of Nanchang University were enrolled in external validation cohorts. The nomogram was established by optimizing the predictive factors through univariate and multivariable logistic regression analysis. The prediction performance of the nomogram was measured by the area under the receiver operating characteristic curve (AUROC), the calibration curve, and the decision curve analysis (DCA). Furthermore, its applicability was internally and independently validated.

Results

Among the 16 clinicopathological features, five variables were selected to develop the prediction nomogram, including age, glycated hemoglobin (HbA1c), calcium, anxiety, and regular exercise. The nomogram revealed good discrimination with an area under the receiver operating characteristic curve (AUROC) of 0.908 (95% CI = 0.865-0.950) in the training cohort, and 0.867 (95% CI = 0.790-0.944) and 0.816 (95% CI = 0.751-0.881) in the internal and external validation cohorts, respectively. The calibration curve presented a good agreement between the prediction by the nomogram and the actual observation. The DCA revealed that the nomogram had a high clinical application value.

Conclusion

In this study, the nomogram for pretreatment risk management of constipation in patients with T2DM was developed which could help in making timely personalized clinical decisions for different risk populations.

From past to future: Bibliometric analysis of global research productivity on nomogram (2000-2021)

Background

Nomogram, a visual clinical predictive model, provides a scientific basis for clinical decision making. Herein, we investigated 20 years of nomogram research responses, focusing on current and future trends and analytical challenges.

Methods

We mined data of scientific literature from the Core Collection of Web of Science, searching for the original articles with title "Nomogram^*/Parton Table^*/Parton Nomogram^*", published within January 1st, 2000 to December 30th, 2021. Data records were validated using HistCite Version and analyzed with a transformable statistical method, the Bibliometrix 3.0 package of R Studio.

Results

In total, 4,176 original articles written by 19,158 authors were included from 915 sources. Annually, Nomogram publications are continually produced, which have rapidly grown since 2018. China published the most articles; however, its total citations ranked second after the United States. Both total citations and average article citations in the United States rank first globally, and a high degree of cooperation exists between countries. Frontiers in Oncology published the most papers (238); this number has grown rapidly since 2019. Journal of Urology had the highest H-index, with an average increase in publications over the past 20 years. Most research topics were tumor-related, among which tumor risk prediction and prognostic evaluation were the main contents. Research on prognostic assessment is more published and advanced, while risk prediction and diagnosis have good developmental prospects. Furthermore, nomogram of the urinary system has been highly developed. Following advancements in nomogram modeling, it has recently been applied to non-oncological subjects.

Conclusion

This bibliometric analysis provides a comprehensive overview of the current nomogram status, which could enable better understanding of its development over the years, and provide global researchers a comprehensive analysis and structured information to help identify hot spots and gaps in future research.

CD3D: a prognostic biomarker associated with immune infiltration and immunotherapeutic response in head and neck squamous cell carcinoma

Recent studies have demonstrated that CD3D activates T-cell-related signal transduction and is associated with the antitumor immune response in several cancers. This study explored the role of CD3D in head and neck squamous cell carcinoma (HNSCC). A total of 499 HNSCC tissues and 44 normal controls were acquired from The Cancer Genome Atlas as the training cohort. GSE65858 included 270 HNSCC patients and was obtained from the Gene Expression Omnibus database as the test cohort. Overall, 172 HNSCC patients were collected as the validation cohort. CD3D expression in the validation cohort was measured by quantitative real-time polymerase chain reaction. The Kaplan-Meier plot revealed that high CD3D expression was associated with longer overall survival in HNSCC patients. Univariate and multivariate analyses showed that CD3D expression was an independent prognostic factor for HNSCC patients, which was confirmed in the test cohort and validation cohort. Furthermore, GO, KEGG, and GSEA analyses revealed the association of CD3D with immune-related pathways. Subsequently, ESTIMATE analysis showed the association between CD3D and the tumor microenvironment, while ssGSEA showed a remarkable positive link between CD3D and immune-related functions. Multiple algorithms demonstrated that high CD3D expression was associated with more immune effector cell infiltration. Finally, the tumor immune dysfunction and exclusion (TIDE) score and immunophenoscore (IPS) showed that patients with high CD3D could benefit from immunotherapy. In summary, CD3D was an independent favorable prognostic biomarker and correlated with immune cell infiltration and immune-related function, as well as an efficient indicator of immunotherapy response for HNSCC patients.

Utility of Lymphadenectomy in Prostate Cancer: Where Do We Stand?

The purpose of this review is to summarize the current knowledge on lymph node dissection (LND) in prostate cancer (PCa) patients undergoing radical prostatectomy (RP). Despite a growing body of evidence, the utility and therapeutic and prognostic value of such an approach, as well as the optimal extent of LND, remain unsolved issues. Although LND is the most accurate staging procedure, the direct therapeutic effect is still not evident from the current literature, which limits the possibility of establishing clear recommendations. This indicates the need for further robust and adequately designed high-quality clinical trials.

The hypermethylation of FOXP3 gene as an epigenetic marker for the identification of arsenic poisoning risk

Background and Purpose: Arsenic exposure can lead to skin lesions and multiple organ damage, which are not easily reversible and for which there is no effective therapeutics. Identification of reliable epigenetic markers is essential for early recognition of arsenic poisoning risk. Anomalous DNA methylation of immune homeostasis regulator FOXP3 is a critical mechanism for triggering arsenic poisoning. This study aims to explore the value of FOXP3 methylation in the identification of arsenic poisoning risk.Methods: 88 arsenic poisoning subjects and 41 references were recruited. Urinary arsenic contents and FOXP3 methylation in PBLCs was measured by ICP-MS and pyrosequencing, respectively.Results: The results showed that the elevated FOXP3 methylation in PBLCs were associated with the increased levels of urinary arsenic and were positively associated with the increased risk of arsenic poisoning and its progression. The result of mediation analysis revealed that 24.3% of the effect of arsenic exposure on the risk of arsenic poisoning was mediated by increased FOXP3 methylation. Additionally, we constructed a nomogram model with FOXP3 methylation as an epigenetic predictor to assess the probability of individual arsenic poisoning. The model showed a robust ability in the discrimination of arsenic poisoning risk, with an area under receiver operating characteristics curve of 0.897(0.845-0.949) and more than 70% accuracy. The calibration curves and the Harrell concordance index showed that the consistency rate between the probability predicted by the nomogram model and the actual probability is 89.7%.Conclusions: Taken together, we found the great potential of FOXP3 methylation for the identification of arsenic poisoning risk and provided a new approach to the application of epigenetic markers in accurately quantifying the risk of adverse outcomes.

The risk factors and predictive nomogram of human albumin infusion during the perioperative period of posterior lumbar interbody fusion: a study based on 2015-2020 data from a local hospital

BACKGROUND

Perioperative hypoalbuminemia of the posterior lumbar interbody fusion (PLIF) can increase the risk of infection of the incision site, and it is challenging to accurately predict perioperative hypoproteinemia. The objective of this study was to create a clinical predictive nomogram and validate its accuracy by finding the independent risk factors for perioperative hypoalbuminemia of PLIF.

METHODS

The patients who underwent PLIF at the Affiliated Hospital of Qingdao University between January 2015 and December 2020 were selected in this study. Besides, variables such as age, gender, BMI, current and past medical history, indications for surgery, surgery-related information, and results of preoperative blood routine tests were also collected from each patient. These patients were divided into injection group and non-injection group according to whether they were injected with human albumin. And they were also divided into training group and validation group, with the ratio of 4:1. Univariate and multivariate logistic regression analyses were performed in the training group to find the independent risk factors. The nomogram was developed based on these independent predictors. In addition, the area under the curve (AUC), the calibration curve and the decision curve analysis (DCA) were drawn in the training and validation groups to evaluate the prediction, calibration and clinical validity of the model. Finally, the nomograms in the training and validation groups and the receiver operating characteristic (ROC) curves of each independent risk factor were drawn to analyze the performance of this model.

RESULTS

A total of 2482 patients who met our criteria were recruited in this study and 256 (10.31%) patients were injected with human albumin perioperatively. There were 1985 people in the training group and 497 in the validation group. Multivariate logistic regression analysis revealed 5 independent risk factors, including old age, accompanying T2DM, level of preoperative albumin, amount of intraoperative blood loss and fusion stage. We drew nomograms. The AUC of the nomograms in the training group and the validation group were 0.807, 95% CI 0.774-0.840 and 0.859, 95% CI 0.797-0.920, respectively. The calibration curve shows consistency between the prediction and observation results. DCA showed a high net benefit from using nomograms to predict the risk of perioperative injection of human albumin. The AUCs of nomograms in the training and the validation groups were significantly higher than those of five independent risk factors mentioned above (P < 0.001), suggesting that the model is strongly predictive.

CONCLUSION

Preoperative low protein, operative stage ≥ 3, a relatively large amount of intraoperative blood loss, old age and history of diabetes were independent predictors of albumin infusion after PLIF. A predictive model for the risk of albumin injection during the perioperative period of PLIF was created using the above 5 predictors, and then validated. The model can be used to assess the risk of albumin injection in patients during the perioperative period of PLIF. The model is highly predictive, so it can be clinically applied to reduce the incidence of perioperative hypoalbuminemia.

External validation of a prostate cancer nomogram on magnetic resonance/transrectal ultrasound fusion biopsy in men with prior negative systematic biopsy

OBJECTIVE

To observe how the nomogram, which was created by Truong et al, works in an independent patient group by performing external validation.

PATIENTS AND METHODS

One hundred and eighty-one patients who had at least one prior negative 12-core standard systematic biopsy and lesions with PI-RADS scores of 3 or higher that were detected as a result of mpMRI were included in the study. Targeted biopsy with 12-core standard systematic biopsy was performed on all patients. Clinical and pathological features of the patients were recorded. The discrimination, calibration and decision curve analysis were performed to externally validate the nomogram.

RESULTS

A total of 181 patients with previous negative 12-core systematic biopsies were analysed. One hundred and thirty-four patients (74%) had benign pathology. Radiological volume and PI-RADS scores of 4 and 5 were found as independent predictors of benign pathology. The area under the curve (CI 95%) was found to be 0.80 (0.73-0.87), indicating good discrimination. The median residual was calculated as -0.0873, the intercept as -0.0690, the slope as 0.8927 and r² as 0.2586, indicating good calibration. The standardised net benefit of follow-up decisions was found to be 0.54 and 0.36 at the probability threshold of 0.7 and 0.8, respectively.

CONCLUSION

The original model showed good discrimination and calibration with our data. Defining a high probability threshold for clinical use would be appropriate for centres with high benign biopsy rates similar to our centre.

Nomograms in Urologic Oncology: Lights and Shadows

Decision-making in urologic oncology involves integrating multiple clinical data to provide an answer to the needs of a single patient. Although the practice of medicine has always been an “art” involving experience, clinical data, scientific evidence and judgment, the creation of specialties and subspecialties has multiplied the challenges faced every day by physicians. In the last decades, with the field of urologic oncology becoming more and more complex, there has been a rise in tools capable of compounding several pieces of information and supporting clinical judgment and experience when approaching a difficult decision. The vast majority of these tools provide a risk of a certain event based on various information integrated in a mathematical model. Specifically, most decision-making tools in the field of urologic focus on the preoperative or postoperative phase and provide a prognostic or predictive risk assessment based on the available clinical and pathological data. More recently, imaging and genomic features started to be incorporated in these models in order to improve their accuracy. Genomic classifiers, look-up tables, regression trees, risk-stratification tools and nomograms are all examples of this effort. Nomograms are by far the most frequently used in clinical practice, but are also among the most controversial of these tools. This critical, narrative review will focus on the use, diffusion and limitations of nomograms in the field of urologic oncology.

External validation of a nomogram predicting risk of bleeding control interventions after high-grade renal trauma: The Multi-institutional Genito-Urinary Trauma Study

BACKGROUND

Renal trauma grading has a limited ability to distinguish patients who will need intervention after high-grade renal trauma (HGRT). A nomogram incorporating both clinical and radiologic factors has been previously developed to predict bleeding control interventions after HGRT. We aimed to externally validate this nomogram using multicenter data from level 1 trauma centers.

METHODS

We gathered data from seven level 1 trauma centers. Patients with available initial computed tomography (CT) scans were included. Each CT scan was reviewed by two radiologists blinded to the intervention data. Nomogram variables included trauma mechanism, hypotension/shock, concomitant injuries, vascular contrast extravasation (VCE), pararenal hematoma extension, and hematoma rim distance (HRD). Mixed-effect logistic regression was used to assess the associations between the predictors and bleeding intervention. The prediction accuracy of the nomogram was assessed using the area under the receiver operating characteristic curve and its 95% confidence interval (CI).

RESULTS

Overall, 569 HGRT patients were included for external validation. Injury mechanism was blunt in 89%. Using initial CT scans, 14% had VCE and median HRD was 1.7 (0.9-2.6) cm. Overall, 12% underwent bleeding control interventions including 34 angioembolizations and 24 nephrectomies. In the multivariable analysis, presence of VCE was associated with a threefold increase in the odds of bleeding interventions (odds ratio, 3.06; 95% CI, 1.44-6.50). Every centimeter increase in HRD was associated with 66% increase in odds of bleeding interventions. External validation of the model provided excellent discrimination in predicting bleeding interventions with an area under the curve of 0.88 (95% CI, 0.84-0.92).

CONCLUSION

Our results reinforce the importance of radiologic findings such as VCE and hematoma characteristics in predicting bleeding control interventions after renal trauma. The prediction accuracy of the proposed nomogram remains high using external data. These variables can help to better risk stratify high-grade renal injuries.

LEVEL OF EVIDENCE

Prognostic and epidemiological study, level III.

A Machine Learning-Based Investigation of Gender-Specific Prognosis of Lung Cancers

Background and Objective: Primary lung cancer is a lethal and rapidly-developing cancer type and is one of the most leading causes of cancer deaths. Materials and Methods: Statistical methods such as Cox regression are usually used to detect the prognosis factors of a disease. This study investigated survival prediction using machine learning algorithms. The clinical data of 28,458 patients with primary lung cancers were collected from the Surveillance, Epidemiology, and End Results (SEER) database. Results: This study indicated that the survival rate of women with primary lung cancer was often higher than that of men (p < 0.001). Seven popular machine learning algorithms were utilized to evaluate one-year, three-year, and five-year survival prediction The two classifiers extreme gradient boosting (XGB) and logistic regression (LR) achieved the best prediction accuracies. The importance variable of the trained XGB models suggested that surgical removal (feature “Surgery”) made the largest contribution to the one-year survival prediction models, while the metastatic status (feature “N” stage) of the regional lymph nodes was the most important contributor to three-year and five-year survival prediction. The female patients’ three-year prognosis model achieved a prediction accuracy of 0.8297 on the independent future samples, while the male model only achieved the accuracy 0.7329. Conclusions: This data suggested that male patients may have more complicated factors in lung cancer than females, and it is necessary to develop gender-specific diagnosis and prognosis models.

Clinician Versus Nomogram Predicted Estimates of Kidney Stone Recurrence Risk

Purpose: Kidney stone recurrence rates vary between patients. A patient's risk informs the frequency and intensity of preventative interventions. Clinicians routinely use clinical experience to estimate risk. We sought to compare clinician estimated recurrence risk with the recurrence of kidney stones (ROKS) nomogram. Materials and Methods: We surveyed members of the Endourological Society with clinical expertise in kidney stones. Respondents estimated the risk of recurrence for patients in three clinical vignettes corresponding to low, intermediate, and high recurrence risk from the nomogram. Clinician estimates were compared with ROKS estimates. Results: The majority of the 318 respondents were from North America (n = 127, 40%). The most commonly estimated recurrence was 50% at 5 years. The respondents' estimates were significantly different from the ROKS predicted recurrence rate for all cases (Case 1, 50% vs 93% p < 0.0001; Case 2, 50% vs 60% p < 0.0001; Case 3, 60% vs 22% p < 0.0001). The ROKS predicted estimates ranged from 22% to 93%, whereas the median urologist-derived 5-year risk estimates for each case ranged from 50% to 60%. The median range of estimates by respondents across cases was 20%, narrower than the 71% for the ROKS nomogram. The majority of respondents (95%) do not use nomograms in practice, mostly because of lack of awareness of useful nomograms (59%). Conclusions: This study suggests that clinicians may not be able to distinguish those with high and low recurrence risk when compared with peers and when compared with a nomogram. Clinical decision support tools are needed to enable clinicians to better estimate stone recurrence risk.

HLA Class I Allele Expression and Clinical Outcome in De Novo Metastatic Prostate Cancer

The prognostic value of human leukocyte antigen (HLA) class I molecules in prostate cancer (PCa) remains unclear. Herein, we investigated the prognostic relevance of the most frequently expressed HLA-A alleles in Greece (A*02:01 and HLA-A*24:02) in de novo metastatic hormone-sensitive PCa (mPCa), which is a rare and aggressive disease characterized by a rapid progression to castration-resistance (CR) and poor overall survival (OS), contributing to almost 50% of PCa-related deaths. We identified 56 patients who had either progressed to CR (these patients were retrospectively analyzed for the time to the progression of CR and prospectively for OS) or had at least three months’ follow-up postdiagnosis without CR progression and, thus, were prospectively analyzed for both CR and OS. Patients expressing HLA-A*02:01 showed poor clinical outcomes vs. HLA-A*02:01⁻negative patients. HLA-A*24:02⁻positive patients progressed slower to CR and had increased OS. Homozygous HLA-A*02:01 patients progressed severely to CR, with very short OS. Multivariate analyses ascribed to both HLA alleles significant prognostic values for the time to progression (TTP) to CR and OS. The presence of HLA-A*02:01 and HLA-A*24:02 alleles in de novo mPCa patients are significantly and independently associated with unfavorable or favorable clinical outcomes, respectively, suggesting their possible prognostic relevance for treatment decision-making in the context of precision medicine.

Personalized strategies in population screening for prostate cancer

This review discusses evidence for population-based screening with contemporary screening tools. In Europe, prostate-specific antigen (PSA)-based screening led to a relative reduction of prostate cancer (PCa) mortality, but also to a substantial amount of overdiagnosis and unnecessarily biopsies. Risk stratification based on a single variable (a clinical variable or based on the presence of a lesion on prostate imaging) or based on multivariable approaches can aid in reducing unnecessary prostate biopsies and overdiagnosis by selecting men who can benefit from further clinical assessment. Multivariable approaches include clinical variables, and biomarkers, often combined in risk calculators or nomograms. These risk calculators can also incorporate the result of MRI imaging. In general, as compared to a purely PSA based approach, the combination of relevant prebiopsy information results in superior selection of men at higher risk of harboring clinically significant prostate cancer. Currently, it is not possible to draw any conclusions on the superiority of these multivariable risk-based approaches since head-to-head comparisons are virtually lacking. Recently initiated large population-based screening studies in Finland, Germany and Sweden, incorporating various multivariable risk stratification approaches will hopefully give more insight in whether the harm-benefit ratio can be improved, that is, maintain (or improving) the ability to reduce metastatic disease and prostate cancer mortality while reducing harm caused by unnecessary testing and overdiagnosis including related overtreatment.

Comparison between Zumsteg classification and Briganti nomogram for the risk of lymph-node invasion before radical prostatectomy

PURPOSE

To evaluate the performance of the Zumsteg classification to estimate the risk of lymph-node invasion (LNI) compared with the Briganti nomogram (BN) in prostatectomy patients with intermediate-risk prostate cancer (IRPC).

METHODS

We included consecutive patients who had extended pelvic lymph-node dissection associated with radical prostatectomy for IRPC. To be classified favorable intermediate risk (FIR), patients could only have one intermediate-risk factor, fewer than 50% positive biopsies and no primary Gleason score of 4.

RESULTS

On the 387 patients included, 149 (38.5%) and 238 (54.3%) were classified FIR and unfavorable intermediate risk (UIR), respectively, and 212 (54.8%) had a BN inferior to 5%. Thirty-eight patients (9.8%) had LNI: 6 FIR patients (4.0%) versus 32 UIR patients (13.4%) and 14 patients (6.6%) with a BN inferior to 5% versus 24 patients (13.7%) with a BN superior to 5%. Eight patients with a BN inferior to 5%, but classified UIR, had LNI. Sensitivity to detect LNI was higher with the Zumsteg classification than with the BN: 84.2% (CI 95% [68-93]) versus 63.2% (CI 95% [46-78]). Both screening tests were concordant to predict LNI (kappa coefficient of 0.076, p < 0.05 for Zumsteg and Briganti) CONCLUSIONS: Zumsteg classification appeared to be more sensitive and as effective (despite the impossibility to make decision curve analysis) than the BN to estimate the risk of LNI. Regarding the modest number of pN+ patients, further studies are needed to see the interest of proposing ePLND for UIR patients only.

Incremental Utility of Adjuvant Chemotherapy in Muscle-invasive Bladder Cancer: Quantifying the Relapse Risk Associated with Therapeutic Effect

The availability of new potent systemic therapies for urothelial carcinoma may change the way we use standard chemotherapy perioperatively. In particular, identifying which patients with muscle-invasive bladder cancer (MIBC) would benefit from adjuvant chemotherapy (AC) is compelling. From a multicenter database we selected 950 patients with cT2-4N0M0 MIBC treated with radical cystectomy (RC), with or without neoadjuvant chemotherapy (NAC), and AC. We used Kaplan-Meier analyses to test 1-yr recurrence-free survival (RFS) rates according to AC use. Nomogram-derived probabilities of 1-yr recurrence after RC were plotted against actual recurrence rates according to AC use. Overall, we did not see evidence of an AC effect on the 1-yr RFS rate (p=0.6). Conversely, the 1-yr RFS rate was higher among patients with pT3-4 or pN1 disease who received AC (75% vs 54%; p<0.001). We were unable to demonstrate a difference between AC and no AC among patients who received prior NAC (1-yr RFS 57% vs 76%; p=0.057). As the most important finding, AC was associated with incremental RFS benefits only for patients with a nomogram-derived 1-yr recurrence probability of >40%. Patient summary: Maximizing disease control with adjuvant chemotherapy was beneficial for patients with muscle-invasive bladder cancer who had a calculated recurrence risk of >40% and did not impact cancer recurrence in lower-risk disease. Therefore, patient stratification using the nomogram available for predicting recurrence is advisable pending external validation.

BioScore (B7-H1, survivin, and Ki-67) does not predict cancer-specific mortality in surgically treated patients with renal cell carcinoma: An external validation study

BACKGROUND

To externally validate' BioScore', a biomarker-based scoring system using immunohistochemical tumor expression levels of B7-H1, survivin, and Ki-67, in a single-center cohort of renal cell carcinoma (RCC) patients. Additionally, we investigated the potential benefit of BioScore as compared to the Mayo Clinic stage, size, grade, and necrosis (SSIGN) score.

MATERIALS AND METHODS

The validation cohort comprised 393 nonmetastatic RCC patients treated with radical nephrectomy or nephron-sparing surgery from 1999 to 2004. Kaplan-Meier estimators, the log-rank test, uni- and multivariable Cox regression models, and measures of discrimination were used to quantify the prognostic performance of BioScore regarding cancer-specific mortality (CSM).

RESULTS

During a median follow-up of 7.8 years, 69/132 (52%) deaths were adjudicated to progressive disease. BioScore was weakly associated with CSM in univariable analysis (hazard ratio per 1 point increase = 1.12, 95% confidence interval = 1.02-1.23, P = 0.023). However, this association did not prevail after adjusting for other adverse prognostic factors as represented by the SSIGN score. The discriminative performance of BioScore was very modest (Harrell's C-Index = 0.60) and did not improve the SSIGN score (P = 0.341), which already showed an excellent discrimination, as evidenced by Harrell's C-Index of 0.81. In a sensitivity analysis regarding clear cell RCC patients only, B7-H1 positivity did not emerge as a statistically significant predictor of CSM.

CONCLUSION

Although a higher BioScore was significantly associated with a higher CSM, the magnitude of this association was weak and not independent from other prognosticators. Moreover, BioScore did not improve the prognostic accuracy of the SSIGN score.