Individual prognosis at diagnosis in nonmetastatic prostate cancer: Development and external validation of the PREDICT Prostate multivariable model

Utilisation and impact of predict prostate on decision-making among clinicians and patients in a specialist tertiary referral centre: A retrospective cohort study

Background

Patients with intermediate-risk prostate cancer are faced with the decision of whether to undergo radical treatment. Decision-making aids, such as Predict Prostate, can empower both clinicians and patients to make treatment decisions with personalised information, but their impact on multi-disciplinary team (MDT) decision-making and uptake of radical treatment remains unknown.

Objective

The objective of this study is to assess the utilisation and utility of Predict Prostate in informing treatment decisions for patients with intermediate-risk prostate cancer.

Patients and Methods

A retrospective cohort study was conducted in Cambridge University Hospitals (CUH) of patients referred to the prostate cancer specialist multi-disciplinary team (pcSMDT) and robotic prostatectomy clinic (ROPD) between September 2019 and August 2021 for consideration of radical prostatectomy (RARP). Data on patient characteristics, use of PredictProstate and management decisions were collected from the Epic electronic medical record (EMR) of 839 patients, of whom 386 had intermediate-risk prostate cancer.

Results

The use of Predict Prostate at the pcSMDT increased in the second half of the study period (34.5% vs. 23.8%, p < 0.001). The use of Predict Prostate was associated with an increased likelihood of attending ROPD for men with CPG2 prostate cancer (OR = 2.155, 95% CI = 1.158-4.013, p = 0.015) but a reduced likelihood of proceeding with RARP for men with CPG2 (OR = 0.397, 95% CI = 0.209-0.753, p = 0.005) and CPG3 (OR = 0.305, 95% CI = 0.108-0.861, p = 0.025) prostate cancer.

Conclusion

Our study showed that the use of Predict Prostate for patients with intermediate-risk prostate cancer is associated with increased attendance at specialist surgical clinic and a reduced chance of undergoing radical prostate surgery.

Artificial Intelligence and Pathomics: Prostate Cancer

Artificial intelligence (AI) has the potential to transform pathologic diagnosis and cancer patient management as a predictive and prognostic biomarker. AI-based systems can be used to examine digitally scanned histopathology slides and differentiate benign from malignant cells and low from high grade. Deep learning models can analyze patient data from individual or multimodal combinations and identify patterns to be used to predict the response to different therapeutic options, the risk of recurrence or progression, and the prognosis of the newly diagnosed patient. AI-based models will improve treatment planning for patients with prostate cancer and improve the efficiency and cost-effectiveness of the pathology laboratory.

Adaption and National Validation of a Tool for Predicting Mortality from Other Causes Among Men with Nonmetastatic Prostate Cancer

BACKGROUND

An electronic health record-based tool could improve accuracy and eliminate bias in provider estimation of the risk of death from other causes among men with nonmetastatic cancer.

OBJECTIVE

To recalibrate and validate the Veterans Aging Cohort Study Charlson Comorbidity Index (VACS-CCI) to predict non-prostate cancer mortality (non-PCM) and to compare it with a tool predicting prostate cancer mortality (PCM).

DESIGN, SETTING, AND PARTICIPANTS

An observational cohort of men with biopsy-confirmed nonmetastatic prostate cancer, enrolled from 2001 to 2018 in the national US Veterans Health Administration (VA), was divided by the year of diagnosis into the development (2001-2006 and 2008-2018) and validation (2007) sets.

OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS

Mortality (all cause, non-PCM, and PCM) was evaluated. Accuracy was assessed using calibration curves and C statistic in the development, validation, and combined sets; overall; and by age (<65 and 65+ yr), race (White and Black), Hispanic ethnicity, and treatment groups.

RESULTS AND LIMITATIONS

Among 107 370 individuals, we observed 24 977 deaths (86% non-PCM). The median age was 65 yr, 4947 were Black, and 5010 were Hispanic. Compared with CCI and age alone (C statistic 0.67, 95% confidence interval [CI] 0.67-0.68), VACS-CCI demonstrated improved validated discrimination (C statistic 0.75, 95% CI 0.74-0.75 for non-PCM). The prostate cancer mortality tool also discriminated well in validation (C statistic 0.81, 95% CI 0.78-0.83). Both were well calibrated overall and within subgroups. Owing to missing data, 18 009/125 379 (14%) were excluded, and VACS-CCI should be validated outside the VA prior to outside application.

CONCLUSIONS

VACS-CCI is ready for implementation within the VA. Electronic health record-assisted calculation is feasible, improves accuracy over age and CCI alone, and could mitigate inaccuracy and bias in provider estimation.

PATIENT SUMMARY

Veterans Aging Cohort Study Charlson Comorbidity Index is ready for application within the Veterans Health Administration. Electronic health record-assisted calculation is feasible, improves accuracy over age and Charlson Comorbidity Index alone, and might help mitigate inaccuracy and bias in provider estimation of the risk of non-prostate cancer mortality.

What Affects Perceived Trustworthiness of Online Medical Information and Subsequent Treatment Decision Making? Randomized Trials on the Role of Uncertainty and Institutional Cues

Background. Online, algorithmically driven prognostic tools are increasingly important in medical decision making. Institutions developing such tools need to be able to communicate the precision and accuracy of the information in a trustworthy manner, and so many attempt to communicate uncertainties but also use institutional logos to underscore their trustworthiness. Bringing together theories on trust, uncertainty, and psychological distance in a novel way, we tested whether and how the communication of uncertainty and the presence of institutional logos together affected trust in medical information, the prognostic tool itself, and treatment decisions. Methods. A pilot and 2 online experiments in which UK (experiment 1) and worldwide (experiment 2) participants (Ntotal = 4,724) were randomized to 1 of 12 arms in a 3 (uncertainty cue) × 4 (institutional cue) between-subjects design. The stimulus was based on an existing medical prognostic tool. Results. Institutional trust was consistently associated with trust in the prognostic tool itself, while uncertainty information had no consistent effect. Institutional trust predicted the amount of weight participants reported placing on institutional endorsements in their decision making and the likelihood of switching from passive to active treatment in a hypothetical scenario. There was also a significant effect of psychological distance to (perceived hypotheticality of) the scenario. Conclusions/Implications. These results underline the importance of institutions demonstrating trustworthiness and building trust with their users. They also suggest that users tend to be insensitive to communications of uncertainty and that communicators may need to be highly explicit when attempting to warn of low precision or quality of evidence. The effect of the perceived hypotheticality of the scenario underscores the importance of realistic decision-making scenarios for studies and the role of familiarity with the decision dilemma generally.

Highlights

In a world where information for medical decision making is increasingly going to be provided through digital, online tools, institutions providing such tools need guidance on how best to communicate about their trustworthiness and precision.We find that people are fairly insensitive to cues designed to communicate uncertainty around the outputs of such tools. Even putting "ATTENTION" in bold font or explicitly pointing out the weaknesses in the data did not appear to affect people's decision making using the tool's outputs. Institutions should take note, and further work is required to determine how best to communicate uncertainty in a way that elicits appropriate caution in lay users.People were much more sensitive to institutional logos associated with the outputs. Generalized institutional trust (rather than trust in the specific institution whose logo was shown) was associated with how trustworthy, accurate, and reliable the tool, its algorithm, and the numbers it produced were perceived to be. This underscores the role of societal trust in institutions at large.Finally, as a note to researchers, we found a significant effect of how hypothetical or believable participants felt the experimental scenario was. This is a variable that seems rarely controlled for in studies and yet played as much of a role as some of our variables of interest, so we suggest that it is measured in future experiments.

Using temporal recalibration to improve the calibration of risk prediction models in competing risk settings when there are trends in survival over time

We have previously proposed temporal recalibration to account for trends in survival over time to improve the calibration of predictions from prognostic models for new patients. This involves first estimating the predictor effects using data from all individuals (full dataset) and then re-estimating the baseline using a subset of the most recent data whilst constraining the predictor effects to remain the same. In this article, we demonstrate how temporal recalibration can be applied in competing risk settings by recalibrating each cause-specific (or subdistribution) hazard model separately. We illustrate this using an example of colon cancer survival with data from the Surveillance Epidemiology and End Results (SEER) program. Data from patients diagnosed in 1995-2004 were used to fit two models for deaths due to colon cancer and other causes respectively. We discuss considerations that need to be made in order to apply temporal recalibration such as the choice of data used in the recalibration step. We also demonstrate how to assess the calibration of these models in new data for patients diagnosed subsequently in 2005. Comparison was made to a standard analysis (when improvements over time are not taken into account) and a period analysis which is similar to temporal recalibration but differs in the data used to estimate the predictor effects. The 10-year calibration plots demonstrated that using the standard approach over-estimated the risk of death due to colon cancer and the total risk of death and that calibration was improved using temporal recalibration or period analysis.

Cohort profile: the Turin prostate cancer prognostication (TPCP) cohort

Introduction

Prostate cancer (PCa) is the most frequent tumor among men in Europe and has both indolent and aggressive forms. There are several treatment options, the choice of which depends on multiple factors. To further improve current prognostication models, we established the Turin Prostate Cancer Prognostication (TPCP) cohort, an Italian retrospective biopsy cohort of patients with PCa and long-term follow-up. This work presents this new cohort with its main characteristics and the distributions of some of its core variables, along with its potential contributions to PCa research.

Methods

The TPCP cohort includes consecutive non-metastatic patients with first positive biopsy for PCa performed between 2008 and 2013 at the main hospital in Turin, Italy. The follow-up ended on December 31st 2021. The primary outcome is the occurrence of metastasis; death from PCa and overall mortality are the secondary outcomes. In addition to numerous clinical variables, the study's prognostic variables include histopathologic information assigned by a centralized uropathology review using a digital pathology software system specialized for the study of PCa, tumor DNA methylation in candidate genes, and features extracted from digitized slide images via Deep Neural Networks.

Results

The cohort includes 891 patients followed-up for a median time of 10 years. During this period, 97 patients had progression to metastatic disease and 301 died; of these, 56 died from PCa. In total, 65.3% of the cohort has a Gleason score less than or equal to 3 + 4, and 44.5% has a clinical stage cT1. Consistent with previous studies, age and clinical stage at diagnosis are important prognostic factors: the crude cumulative incidence of metastatic disease during the 14-years of follow-up increases from 9.1% among patients younger than 64 to 16.2% for patients in the age group of 75-84, and from 6.1% for cT1 stage to 27.9% in cT3 stage.

Discussion

This study stands to be an important resource for updating existing prognostic models for PCa on an Italian cohort. In addition, the integrated collection of multi-modal data will allow development and/or validation of new models including new histopathological, digital, and molecular markers, with the goal of better directing clinical decisions to manage patients with PCa.

A Personalized Clinical Dynamic Prediction Model to Characterize Prognosis for Patients With Localized Prostate Cancer: Analysis of the CHHiP Phase 3 Trial

PURPOSE

The CHHiP trial assessed moderately hypofractionated radiation therapy in localized prostate cancer. We utilized longitudinal prostate-specific antigen (PSA) measurements collected over time to evaluate and characterize patient prognosis.

METHODS AND MATERIALS

We developed a clinical dynamic prediction joint model to predict the risk of biochemical or clinical recurrence. Modeling included repeated PSA values and adjusted for baseline prognostic risk factors of age, tumor characteristics, and treatment received. We included 3071 trial participants for model development using a mixed-effect submodel for the longitudinal PSAs and a time-to-event hazard submodel for predicting recurrence of prostate cancer. We evaluated how baseline prognostic factor subgroups affected the nonlinear PSA levels over time and quantified the association of PSA on time to recurrence. We assessed bootstrapped optimism-adjusted predictive performance on calibration and discrimination. Additionally, we performed comparative dynamic predictions on patients with contrasting prognostic factors and investigated PSA thresholds over landmark times to correlate with prognosis.

RESULTS

Patients who developed recurrence had generally higher baseline and overall PSA values during follow-up and had an exponentially rising PSA in the 2 years before recurrence. Additionally, most baseline risk factors were significant in the mixed-effect and relative-risk submodels. PSA value and rate of change were predictive of recurrence. Predictive performance of the model was good across different prediction times over an 8-year period, with an overall mean area under the curve of 0.70, mean Brier score of 0.10, and mean integrated calibration index of 0.048; these were further improved for predictions after 5 years of accrued longitudinal posttreatment PSA assessments. PSA thresholds <0.23 ng/mL after 3 years were indicative of a minimal risk of recurrence by 8 years.

CONCLUSIONS

We successfully developed a joint statistical model to predict prostate cancer recurrence, evaluating prognostic factors and longitudinal PSA. We showed dynamically updated PSA information can improve prognostication, which can be used to guide follow-up and treatment management options.

Artificial intelligence in theranostics of gastric cancer, a review

Gastric cancer (GC) is one of the commonest cancers with high morbidity and mortality in the world. How to realize precise diagnosis and therapy of GC owns great clinical requirement. In recent years, artificial intelligence (AI) has been actively explored to apply to early diagnosis and treatment and prognosis of gastric carcinoma. Herein, we review recent advance of AI in early screening, diagnosis, therapy and prognosis of stomach carcinoma. Especially AI combined with breath screening early GC system improved 97.4 % of early GC diagnosis ratio, AI model on stomach cancer diagnosis system of saliva biomarkers obtained an overall accuracy of 97.18 %, specificity of 97.44 %, and sensitivity of 96.88 %. We also discuss concept, issues, approaches and challenges of AI applied in stomach cancer. This review provides a comprehensive view and roadmap for readers working in this field, with the aim of pushing application of AI in theranostics of stomach cancer to increase the early discovery ratio and curative ratio of GC patients.

Immune-Activated B Cells Are Dominant in Prostate Cancer

B cells are multifaceted immune cells responding robustly during immune surveillance against tumor antigens by presentation to T cells and switched immunoglobulin production. However, B cells are unstudied in prostate cancer (PCa). We used flow cytometry to analyze B-cell subpopulations in peripheral blood and lymph nodes from intermediate-high risk PCa patients. B-cell subpopulations were related to clinicopathological factors. B-cell-receptor single-cell sequencing and VDJ analysis identified clonal B-cell expansion in blood and lymph nodes. Pathological staging was pT2 in 16%, pT3a in 48%, and pT3b in 36%. Lymph node metastases occurred in 5/25 patients (20%). Compared to healthy donors, the peripheral blood CD19⁺ B-cell compartment was significantly decreased in PCa patients and dominated by naïve B cells. The nodal B-cell compartment had significantly increased fractions of CD19⁺ B cells and switched memory B cells. Plasmablasts were observed in tumor-draining sentinel lymph nodes (SNs). VDJ analysis revealed clonal expansion in lymph nodes. Thus, activated B cells are increased in SNs from PCa patients. The increased fraction of switched memory cells and plasmablasts together with the presence of clonally expanded B cells indicate tumor-specific T-cell-dependent responses from B cells, supporting an important role for B cells in the protection against tumors.

Artificial intelligence applications in pediatric oncology diagnosis

Artificial intelligence (AI) algorithms have been applied in abundant medical tasks with high accuracy and efficiency. Physicians can improve their diagnostic efficiency with the assistance of AI techniques for improving the subsequent personalized treatment and surveillance. AI algorithms fundamentally capture data, identify underlying patterns, achieve preset endpoints, and provide decisions and predictions about real-world events with working principles of machine learning and deep learning. AI algorithms with sufficient graphic processing unit power have been demonstrated to provide timely diagnostic references based on preliminary training of large amounts of clinical and imaging data. The sample size issue is an inevitable challenge for pediatric oncology considering its low morbidity and individual heterogeneity. However, this problem may be solved in the near future considering the exponential advancements of AI algorithms technically to decrease the dependence of AI operation on the amount of data sets and the efficiency of computing power. For instance, it could be a feasible solution by shifting convolutional neural networks (CNNs) from adults and sharing CNN algorithms across multiple institutions besides original data. The present review provides important insights into emerging AI applications for the diagnosis of pediatric oncology by systematically overviewing of up-to-date literature.

Combining Molecular Subtypes with Multivariable Clinical Models Has the Potential to Improve Prediction of Treatment Outcomes in Prostate Cancer at Diagnosis

Clinical management of prostate cancer is challenging because of its highly variable natural history and so there is a need for improved predictors of outcome in non-metastatic men at the time of diagnosis. In this study we calculated the model score from the leading clinical multivariable model, PREDICT prostate, and the poor prognosis DESNT molecular subtype, in a combined expression and clinical dataset that were taken from malignant tissue at prostatectomy (n = 359). Both PREDICT score (p < 0.0001, IQR HR = 1.59) and DESNT score (p < 0.0001, IQR HR = 2.08) were significant predictors for time to biochemical recurrence. A joint model combining the continuous PREDICT and DESNT score (p < 0.0001, IQR HR = 1.53 and 1.79, respectively) produced a significantly improved predictor than either model alone (p < 0.001). An increased probability of mortality after diagnosis, as estimated by PREDICT, was characterised by upregulation of cell-cycle related pathways and the downregulation of metabolism and cholesterol biosynthesis. The DESNT molecular subtype has distinct biological characteristics to those associated with the PREDICT model. We conclude that the inclusion of biological information alongside current clinical prognostic tools has the potential to improve the ability to choose the optimal treatment pathway for a patient.

Survival analysis of localized prostate cancer with deep learning

In recent years, data-driven, deep-learning-based models have shown great promise in medical risk prediction. By utilizing the large-scale Electronic Health Record data found in the U.S. Department of Veterans Affairs, the largest integrated healthcare system in the United States, we have developed an automated, personalized risk prediction model to support the clinical decision-making process for localized prostate cancer patients. This method combines the representative power of deep learning and the analytical interpretability of parametric regression models and can implement both time-dependent and static input data. To collect a comprehensive evaluation of model performances, we calculate time-dependent C-statistics [Formula: see text] over 2-, 5-, and 10-year time horizons using either a composite outcome or prostate cancer mortality as the target event. The composite outcome combines the Prostate-Specific Antigen (PSA) test, metastasis, and prostate cancer mortality. Our longitudinal model Recurrent Deep Survival Machine (RDSM) achieved [Formula: see text] 0.85 (0.83), 0.80 (0.83), and 0.76 (0.81), while the cross-sectional model Deep Survival Machine (DSM) attained [Formula: see text] 0.85 (0.82), 0.80 (0.82), and 0.76 (0.79) for the 2-, 5-, and 10-year composite (mortality) outcomes, respectively. In addition to estimating the survival probability, our method can quantify the uncertainty associated with the prediction. The uncertainty scores show a consistent correlation with the prediction accuracy. We find PSA and prostate cancer stage information are the most important indicators in risk prediction. Our work demonstrates the utility of the data-driven machine learning model in prostate cancer risk prediction, which can play a critical role in the clinical decision system.

Joint models for dynamic prediction in localised prostate cancer: a literature review

BACKGROUND

Prostate cancer is a very prevalent disease in men. Patients are monitored regularly during and after treatment with repeated assessment of prostate-specific antigen (PSA) levels. Prognosis of localised prostate cancer is generally good after treatment, and the risk of having a recurrence is usually estimated based on factors measured at diagnosis. Incorporating PSA measurements over time in a dynamic prediction joint model enables updates of patients' risk as new information becomes available. We review joint model strategies that have been applied to model time-dependent PSA trajectories to predict time-to-event outcomes in localised prostate cancer.

METHODS

We identify articles that developed joint models for prediction of localised prostate cancer recurrence over the last two decades. We report, compare, and summarise the methodological approaches and applications that use joint modelling accounting for two processes: the longitudinal model (PSA), and the time-to-event process (clinical failure). The methods explored differ in how they specify the association between these two processes.

RESULTS

Twelve relevant articles were identified. A range of methodological frameworks were found, and we describe in detail shared-parameter joint models (9 of 12, 75%) and joint latent class models (3 of 12, 25%). Within each framework, these articles presented model development, estimation of dynamic predictions and model validations.

CONCLUSIONS

Each framework has its unique principles with corresponding advantages and differing interpretations. Regardless of the framework used, dynamic prediction models enable real-time prediction of individual patient prognosis. They utilise all available longitudinal information, in addition to baseline prognostic risk factors, and are superior to traditional baseline-only prediction models.

In with the old, in with the new: machine learning for time to event biomedical research

The predictive modeling literature for biomedical applications is dominated by biostatistical methods for survival analysis, and more recently some out of the box machine learning approaches. In this article, we show a presentation of a machine learning method appropriate for time-to-event modeling in the area of prostate cancer long-term disease progression. Using XGBoost adapted to long-term disease progression, we developed a predictive model for 118 788 patients with localized prostate cancer at diagnosis from the Department of Veterans Affairs (VA). Our model accounted for patient censoring. Harrell's c-index for our model using only features available at the time of diagnosis was 0.757 95% confidence interval [0.756, 0.757]. Our results show that machine learning methods like XGBoost can be adapted to use accelerated failure time (AFT) with censoring to model long-term risk of disease progression. The long median survival justifies and requires censoring. Overall, we show that an existing machine learning approach can be used for AFT outcome modeling in prostate cancer, and more generally for other chronic diseases with long observation times.

A Novel Risk Score (P-score) Based on a Three-Gene Signature, for Estimating the Risk of Prostate Cancer-Specific Mortality

Purpose

To develop and validate a risk score (P-score) algorithm which includes previously described three-gene signature and clinicopathological parameters to predict the risk of death from prostate cancer (PCa) in a retrospective cohort.

Patients and Methods

A total of 591 PCa patients diagnosed between 2003 and 2008 in Stockholm, Sweden, with a median clinical follow-up time of 7.6 years (1–11 years) were included in this study. Expression of a three-gene signature (IGFBP3, F3, VGLL3) was measured in formalin-fixed paraffin-embedded material from diagnostic core needle biopsies (CNB) of these patients. A point-based scoring system based on a Fine-Gray competing risk model was used to establish the P-score based on the three-gene signature combined with PSA value, Gleason score and tumor stage at diagnosis. The endpoint was PCa-specific mortality, while other causes of death were treated as a competing risk. Out of the 591 patients, 315 patients (estimation cohort) were selected to develop the P-score. The P-score was subsequently validated in an independent validation cohort of 276 patients.

Results

The P-score was established ranging from the integers 0 to 15. Each one-unit increase was associated with a hazard ratio of 1.39 (95% confidence interval: 1.27–1.51, p < 0.001). The P-score was validated and performed better in predicting PCa-specific mortality than both D’Amico (0.76 vs 0.70) and NCCN (0.76 vs 0.71) by using the concordance index for competing risk. Similar improvement patterns are shown by time-dependent area under the curve. As demonstrated by cumulative incidence function, both P-score and gene signature stratified PCa patients into significantly different risk groups.

Conclusion

We developed the P-score, a risk stratification system for newly diagnosed PCa patients by integrating a three-gene signature measured in CNB tissue. The P-score could provide valuable decision support to distinguish PCa patients with favorable and unfavorable outcomes and hence improve treatment decisions.

Development and validation of a cell cycle progression signature for decentralized testing of men with prostate cancer

Aim: The 46-gene Prolaris^® cell cycle progression test provides information on the risk of prostate cancer progression. Here we developed and validated a 16-gene kit-based version. Methods: RNA was extracted from prostate cancer biopsy tissue. Amplification efficiency, minimum tumor content, repeatability, reproducibility and equivalence with the 46-gene test were evaluated. Results: Amplification efficiencies for all genes were within the acceptable range (90-110%), and samples with ≥50% tumor content were appropriate for the 16-gene test. Results were repeatable (standard deviation: 0.085) and reproducible (standard deviation: 0.115). Instrument, operator and kit lot had minimal impact on results. Cell cycle progression scores from the 46- and 16-gene tests were highly correlated (r = 0.969; bias = 0.217). Conclusion: The 16-gene test performs consistently and similarly to the 46-gene test.

Evaluation of Prognostic and Predictive Models in the Oncology Clinic

Predictive and prognostic models hold great potential to support clinical decision making in oncology and could ultimately facilitate a paradigm shift to a more personalised form of treatment. While a large number of models relevant to the field of oncology have been developed, few have been translated into clinical use and assessment of clinical utility is not currently considered a routine part of model development. In this narrative review of the clinical evaluation of prediction models in oncology, we propose a high-level process diagram for the life cycle of a clinical model, encompassing model commissioning, clinical implementation and ongoing quality assurance, which aims to bridge the gap between model development and clinical implementation.

Isolation and characterization of urine microvesicles from prostate cancer patients: different approaches, different visions

BACKGROUND

Because of their specific and biologically relevant cargo, urine extracellular vesicles (EVs) constitute a valuable source of potential non-invasive biomarkers that could support the clinical decision-making to improve the management of prostate cancer (PCa) patients. Different EV isolation methods differ in terms of complexity and yield, conditioning, as consequence, the analytical result.

METHODS

The aim of this study was to compare three different isolation methods for urine EVs: ultracentrifugation (UC), size exclusion chromatography (SEC), and a commercial kit (Exolute® Urine Kit). Urine samples were collected from 6 PCa patients and 4 healthy donors. After filtered through 0.22 µm filters, urine was divided in 3 equal volumes to perform EVs isolation with each of the three approaches. Isolated EVs were characterized by spectrophotometric protein quantification, nanoparticle tracking analysis, transmission electron microscopy, AlphaScreen Technology, and whole miRNA Transcriptome.

RESULTS

Our results showed that UC and SEC provided better results in terms of EVs yield and purity than Exolute®, non-significant differences were observed in terms of EV-size. Interestingly, luminescent AlphaScreen assay demonstrated a significant enrichment of CD9 and CD63 positive microvesicles in SEC and UC methods compared with Exolute®. This heterogeneity was also demonstrated in terms of miRNA content indicating that the best correlation was observed between UC and SEC.

CONCLUSIONS

Our study highlights the importance of standardizing the urine EV isolation methods to guaranty the analytical reproducibility necessary for their implementation in a clinical setting.

Clinical Impact of the Predict Prostate Risk Communication Tool in Men Newly Diagnosed with Nonmetastatic Prostate Cancer: A Multicentre Randomised Controlled Trial

BACKGROUND

Predict Prostate is a freely available online personalised risk communication tool for men with nonmetastatic prostate cancer. Its accuracy has been assessed in multiple validation studies, but its clinical impact among patients has not hitherto been assessed.

OBJECTIVE

To assess the impact of the tool on patient decision-making and disease perception.

DESIGN, SETTING, AND PARTICIPANTS

A multicentre randomised controlled trial was performed across eight UK centres among newly diagnosed men considering either active surveillance or radical treatment. A total of 145 patients were included between 2018 and 2020, with median age 67 yr (interquartile range [IQR] 61-72) and prostate-specific antigen 6.8 ng/ml (IQR 5.1-8.8).

INTERVENTION

Participants were randomised to either standard of care (SOC) information or SOC and a structured presentation of the Predict Prostate tool.

OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS

Validated questionnaires were completed by assessing the impact of the tool on decisional conflict, uncertainty, anxiety, and perception of survival.

RESULTS AND LIMITATIONS

Mean Decisional Conflict Scale scores were 26% lower in the Predict Prostate group (mean = 16.1) than in the SOC group (mean = 21.7; p = 0.027). Scores on the "support", "uncertainty", and "value clarity" subscales all favoured Predict Prostate (all p < 0.05). There was no significant difference in anxiety scores or final treatment selection between the two groups. Patient perception of 15-yr prostate cancer-specific mortality (PCSM) and overall survival benefit from radical treatment were considerably lower and more accurate among men in the Predict Prostate group (p < 0.001). In total, 57% of men reported that the Predict Prostate estimates for PCSM were lower than expected, and 36% reported being less likely to select radical treatment. Over 90% of patients in the intervention group found it useful and 94% would recommend it to others.

CONCLUSIONS

Predict Prostate reduces decisional conflict and uncertainty, and shifts patient perception around prognosis to be more realistic. This randomised trial demonstrates that Predict Prostate can directly inform the complex decision-making process in prostate cancer and is felt to be useful by patients. Future larger trials are warranted to test its impact upon final treatment decisions.

PATIENT SUMMARY

In this national study, we assessed the impact of an individualised risk communication tool, called Predict Prostate, on patient decision-making after a diagnosis of localised prostate cancer. Men were randomly assigned to two groups, which received either standard counselling and information, or this in addition to a structured presentation of the Predict Prostate tool. Men who saw the tool were less conflicted and uncertain in their decision-making, and recommended the tool highly. Those who saw the tool had more realistic perception about their long-term survival and the potential impact of treatment upon this.

TAKE HOME MESSAGE

The use of an individualised risk communication tool, such as Predict Prostate, reduces patient decisional conflict and uncertainty when deciding about treatment for nonmetastatic prostate cancer. The tool leads to more realistic perceptions about survival outcomes and prognosis.

Cost-effectiveness of MRI targeted biopsy strategies for diagnosing prostate cancer in Singapore

BACKGROUND

To evaluate the cost-effectiveness of six diagnostic strategies involving magnetic resonance imaging (MRI) targeted biopsy for diagnosing prostate cancer in initial and repeat biopsy settings from the Singapore healthcare system perspective.

METHODS

A combined decision tree and Markov model was developed. The starting model population was men with mean age of 65 years referred for a first prostate biopsy due to clinical suspicion of prostate cancer. The six diagnostic strategies were selected for their relevance to local clinical practice. They comprised MRI targeted biopsy following a positive pre-biopsy multiparametric MRI (mpMRI) [Prostate Imaging - Reporting and Data System (PI-RADS) score ≥ 3], systematic biopsy, or saturation biopsy employed in different testing combinations and sequences. Deterministic base case analyses with sensitivity analyses were performed using costs from the healthcare system perspective and quality-adjusted life years (QALY) gained as the outcome measure to yield incremental cost-effectiveness ratios (ICERs).

RESULTS

Deterministic base case analyses showed that Strategy 1 (MRI targeted biopsy alone), Strategy 2 (MRI targeted biopsy ➔ systematic biopsy), and Strategy 4 (MRI targeted biopsy ➔ systematic biopsy ➔ saturation biopsy) were cost-effective options at a willingness-to-pay (WTP) threshold of US$20,000, with ICERs ranging from US$18,975 to US$19,458. Strategies involving MRI targeted biopsy in the repeat biopsy setting were dominated. Sensitivity analyses found the ICERs were affected mostly by changes to the annual discounting rate and prevalence of prostate cancer in men referred for first biopsy, ranging between US$15,755 to US$23,022. Probabilistic sensitivity analyses confirmed Strategy 1 to be the least costly, and Strategies 2 and 4 being the preferred strategies when WTP thresholds were US$20,000 and US$30,000, respectively.

LIMITATIONS AND CONCLUSIONS

This study found MRI targeted biopsy to be cost-effective in diagnosing prostate cancer in the biopsy-naïve setting in Singapore.

Validation of the cell cycle progression score to differentiate indolent from aggressive prostate cancer in men diagnosed through transurethral resection of the prostate biopsy

Background

Validation of biomarker‐based prognostic models to improve risk stratification in men with localized prostate cancer (PrCa) remains a clinical need. It has previously been shown that the cell cycle progression (CCP) test provides significant, independent prognostic information for men who were incidentally diagnosed with PrCa after transurethral resection of the prostate (TURP) and were conservatively managed.

Aim

The results have been extended in a newly analyzed retrospective cohort of UK men diagnosed through TURP biopsy (TURP1B; N = 305).

Methods and Results

The CCP score was derived from TURP biopsy tissue and combined with a modified UCSF Cancer of the Prostate Risk Assessment score (CAPRA) to generate the clinical cell‐cycle risk score (CCR). The primary endpoint was PrCa‐specific mortality (PSM). Hazard ratios (HR) were calculated for a one‐unit change in score. Median follow‐up was 9.6 (IQR: 5.4, 14.1) years, and 67 (22%) men died from PrCa within 10 years of diagnosis. The median CCP score was 1.1 (IQR: 0.6, 1.7). In univariate analyses, CCR proved a significant prognosticator of PSM (HR per unit score change = 2.28; 95% CI: 1.89, 2.74; P = 1.0 × 10⁻¹⁹). In multivariate analyses, CCR remained a significant prognosticator of PSM after adjusting for CAPRA (HR per unit score change = 4.36; 95% CI: 2.65, 7.16; P = 1.3 × 10⁻⁸), indicating that its molecular component, CCP, provides significant, independent prognostic information.

Conclusion

These findings validate a combined clinicopathologic and molecular prognostic model for conservatively managed men who are diagnosed through TURP, supporting the use of CCR to inform clinical management.

Redevelopment of the Predict: Breast Cancer website and recommendations for developing interfaces to support decision-making

Objectives

To develop a new interface for the widely used prognostic breast cancer tool: Predict: Breast Cancer. To facilitate decision‐making around post‐surgery breast cancer treatments. To derive recommendations for communicating the outputs of prognostic models to patients and their clinicians.

Method

We employed a user‐centred design process comprised of background research and iterative testing of prototypes with clinicians and patients. Methods included surveys, focus groups and usability testing.

Results

The updated interface now caters to the needs of a wider audience through the addition of new visualisations, instantaneous updating of results, enhanced explanatory information and the addition of new predictors and outputs. A programme of future research was identified and is now underway, including the provision of quantitative data on the adverse effects of adjuvant breast cancer treatments.

Based on our user‐centred design process, we identify six recommendations for communicating the outputs of prognostic models including the need to contextualise statistics, identify and address gaps in knowledge, and the critical importance of engaging with prospective users when designing communications.

Conclusions

For prognostic algorithms to fulfil their potential to assist with decision‐making they need carefully designed interfaces. User‐centred design puts patients and clinicians needs at the forefront, allowing them to derive the maximum benefit from prognostic models.

Development and Validation of an Interpretable Artificial Intelligence Model to Predict 10-Year Prostate Cancer Mortality

Simple Summary

This article presents a gradient-boosted model that can predict 10-year prostate cancer mortality with high accuracy. The model was developed and validated on prospective multicenter data from the PLCO trial. Using XGBoost and Shapley values, it provides interpretability to understand its prediction. It can be used online to provide predictions and support informed decision-making in PCa treatment.

Abstract

Prostate cancer treatment strategies are guided by risk-stratification. This stratification can be difficult in some patients with known comorbidities. New models are needed to guide strategies and determine which patients are at risk of prostate cancer mortality. This article presents a gradient-boosting model to predict the risk of prostate cancer mortality within 10 years after a cancer diagnosis, and to provide an interpretable prediction. This work uses prospective data from the PLCO Cancer Screening and selected patients who were diagnosed with prostate cancer. During follow-up, 8776 patients were diagnosed with prostate cancer. The dataset was randomly split into a training (n = 7021) and testing (n = 1755) dataset. Accuracy was 0.98 (±0.01), and the area under the receiver operating characteristic was 0.80 (±0.04). This model can be used to support informed decision-making in prostate cancer treatment. AI interpretability provides a novel understanding of the predictions to the users.

Application of a novel machine learning framework for predicting non-metastatic prostate cancer-specific mortality in men using the Surveillance, Epidemiology, and End Results (SEER) database

BACKGROUND

Accurate prognostication is crucial in treatment decisions made for men diagnosed with non-metastatic prostate cancer. Current models rely on prespecified variables, which limits their performance. We aimed to investigate a novel machine learning approach to develop an improved prognostic model for predicting 10-year prostate cancer-specific mortality and compare its performance with existing validated models.

METHODS

We derived and tested a machine learning-based model using Survival Quilts, an algorithm that automatically selects and tunes ensembles of survival models using clinicopathological variables. Our study involved a US population-based cohort of 171 942 men diagnosed with non-metastatic prostate cancer between Jan 1, 2000, and Dec 31, 2016, from the prospectively maintained Surveillance, Epidemiology, and End Results (SEER) Program. The primary outcome was prediction of 10-year prostate cancer-specific mortality. Model discrimination was assessed using the concordance index (c-index), and calibration was assessed using Brier scores. The Survival Quilts model was compared with nine other prognostic models in clinical use, and decision curve analysis was done.

FINDINGS

647 151 men with prostate cancer were enrolled into the SEER database, of whom 171 942 were included in this study. Discrimination improved with greater granularity, and multivariable models outperformed tier-based models. The Survival Quilts model showed good discrimination (c-index 0·829, 95% CI 0·820-0·838) for 10-year prostate cancer-specific mortality, which was similar to the top-ranked multivariable models: PREDICT Prostate (0·820, 0·811-0·829) and Memorial Sloan Kettering Cancer Center (MSKCC) nomogram (0·787, 0·776-0·798). All three multivariable models showed good calibration with low Brier scores (Survival Quilts 0·036, 95% CI 0·035-0·037; PREDICT Prostate 0·036, 0·035-0·037; MSKCC 0·037, 0·035-0·039). Of the tier-based systems, the Cancer of the Prostate Risk Assessment model (c-index 0·782, 95% CI 0·771-0·793) and Cambridge Prognostic Groups model (0·779, 0·767-0·791) showed higher discrimination for predicting 10-year prostate cancer-specific mortality. c-indices for models from the National Comprehensive Cancer Care Network, Genitourinary Radiation Oncologists of Canada, American Urological Association, European Association of Urology, and National Institute for Health and Care Excellence ranged from 0·711 (0·701-0·721) to 0·761 (0·750-0·772). Discrimination for the Survival Quilts model was maintained when stratified by age and ethnicity. Decision curve analysis showed an incremental net benefit from the Survival Quilts model compared with the MSKCC and PREDICT Prostate models currently used in practice.

INTERPRETATION

A novel machine learning-based approach produced a prognostic model, Survival Quilts, with discrimination for 10-year prostate cancer-specific mortality similar to the top-ranked prognostic models, using only standard clinicopathological variables. Future integration of additional data will likely improve model performance and accuracy for personalised prognostics.

FUNDING

None.

Cancer survival statistics for patients and healthcare professionals - a tutorial of real-world data analysis

Monitoring survival of cancer patients using data collected by population-based cancer registries is an important component of cancer control. In this setting, patient survival is often summarized using net survival, that is survival from cancer if there were no other possible causes of death. Although net survival is the gold standard for comparing survival between groups or over time, it is less relevant for understanding the anticipated real-world prognosis of patients. In this review, we explain statistical concepts targeted towards patients, clinicians and healthcare professionals that summarize cancer patient survival under the assumption that other causes of death exist. Specifically, we explain the appropriate use, interpretation and assumptions behind statistical methods for competing risks, loss in life expectancy due to cancer and conditional survival. These concepts are relevant when producing statistics for risk communication between physicians and patients, planning for use of healthcare resources, or other applications when consideration of both cancer outcomes and the competing risks of death is required. To reinforce the concepts, we use Swedish population-based data of patients diagnosed with cancer of the breast, prostate, colon and chronic myeloid leukaemia. We conclude that when choosing between summary measures of survival it is critical to characterize the purpose of the study and to determine the nature of the hypothesis under investigation. The choice of terminology and style of reporting should be carefully adapted to the target audience and may range from summaries for specialist readers of scientific publications to interactive online tools aimed towards lay persons.

Laboratory-wide association study of survival with prostate cancer

BACKGROUND

Estimates of overall patient health are essential to inform treatment decisions for patients diagnosed with cancer. The authors applied XWAS methods, herein referred to as "laboratory-wide association study (LWAS)", to evaluate associations between routinely collected laboratory tests and survival in veterans with prostate cancer.

METHODS

The authors identified 133,878 patients who were diagnosed with prostate cancer between 2000 and 2013 in the Veterans Health Administration using any laboratory tests collected within 6 months of diagnosis (3,345,083 results). Using the LWAS framework, the false-discovery rate was used to test the association between multiple laboratory tests and survival, and these results were validated using training, testing, and validation cohorts.

RESULTS

A total of 31 laboratory tests associated with survival met stringent LWAS criteria. LWAS confirmed markers of prostate cancer biology (prostate-specific antigen: hazard ratio [HR], 1.07 [95% confidence interval (95% CI), 1.06-1.08]; and alkaline phosphatase: HR, 1.22 [95% CI, 1.20-1.24]) as well laboratory tests of general health (eg, serum albumin: HR, 0.78 [95% CI, 0.76-0.80]; and creatinine: HR, 1.05 [95% CI, 1.03-1.07]) and inflammation (leukocyte count: HR, 1.23 [95% CI, 1.98-1.26]; and erythrocyte sedimentation rate: HR, 1.33 [95% CI, 1.09-1.61]). In addition, the authors derived and validated separate models for patients with localized and advanced disease, identifying 28 laboratory markers and 15 laboratory markers, respectively, in each cohort.

CONCLUSIONS

The authors identified routinely collected laboratory data associated with survival for patients with prostate cancer using LWAS methodologies, including markers of prostate cancer biology, overall health, and inflammation. Broadening consideration of determinants of survival beyond those related to cancer itself could help to inform the design of clinical trials and aid in shared decision making.

LAY SUMMARY

This article examined routine laboratory tests associated with survival among veterans with prostate cancer. Using laboratory-wide association studies, the authors identified 31 laboratory tests associated with survival that can be used to inform the design of clinical trials and aid patients in shared decision making.

Effects of RNA Binding Proteins on the Prognosis and Malignant Progression in Prostate Cancer

Prostate cancer (PCa) is a common lethal malignancy in men. RNA binding proteins (RBPs) have been proven to regulate the biological processes of various tumors, but their roles in PCa remain less defined. In the present study, we used bioinformatics analysis to identify RBP genes with prognostic and diagnostic values. A total of 59 differentially expressed RBPs in PCa were obtained, comprising 28 upregulated and 31 downregulated RBP genes, which may play important roles in PCa. Functional enrichment analyses showed that these RBPs were mainly involved in mRNA processing, RNA splicing, and regulation of RNA splicing. Additionally, we identified nine RBP genes (EXO1, PABPC1L, REXO2, MBNL2, MSI1, CTU1, MAEL, YBX2, and ESRP2) and their prognostic values by a protein-protein interaction network and Cox regression analyses. The expression of these nine RBPs was validated using immunohistochemical staining between the tumor and normal samples. Further, the associations between the expression of these nine RBPs and pathological T staging, Gleason score, and lymph node metastasis were evaluated. Moreover, these nine RBP genes showed good diagnostic values and could categorize the PCa patients into two clusters with different malignant phenotypes. Finally, we constructed a prognostic model based on these nine RBP genes and validated them using three external datasets. The model showed good efficiency in predicting patient survival and was independent of other clinical factors. Therefore, our model could be used as a supplement for clinical factors to predict patient prognosis and thereby improve patient survival.

Comparative performance and external validation of the multivariable PREDICT Prostate tool for non-metastatic prostate cancer: a study in 69,206 men from Prostate Cancer data Base Sweden (PCBaSe)

BACKGROUND

PREDICT Prostate is an endorsed prognostic model that provides individualised long-term prostate cancer-specific and overall survival estimates. The model, derived from UK data, estimates potential treatment benefit on overall survival. In this study, we externally validated the model in a large independent dataset and compared performance to existing models and within treatment groups.

METHODS

Men with non-metastatic prostate cancer and prostate-specific antigen (PSA) < 100 ng/ml diagnosed between 2000 and 2010 in the nationwide population-based Prostate Cancer data Base Sweden (PCBaSe) were included. Data on age, PSA, clinical stage, grade group, biopsy involvement, primary treatment and comorbidity were retrieved. Sixty-nine thousand two hundred six men were included with 13.9 years of median follow-up. Fifteen-year survival estimates were calculated using PREDICT Prostate for prostate cancer-specific mortality (PCSM) and all-cause mortality (ACM). Discrimination was assessed using Harrell's concordance (c)-index in R. Calibration was evaluated using cumulative available follow-up in Stata (TX, USA).

RESULTS

Overall discrimination of PREDICT Prostate was good with c-indices of 0.85 (95% CI 0.85-0.86) for PCSM and 0.79 (95% CI 0.79-0.80) for ACM. Overall calibration of the model was excellent with 25,925 deaths predicted and 25,849 deaths observed. Within the conservative management and radical treatment groups, c-indices for 15-year PCSM were 0.81 and 0.78, respectively. Calibration also remained good within treatment groups. The discrimination of PREDICT Prostate significantly outperformed the EAU, NCCN and CAPRA scores for both PCSM and ACM within this cohort overall. A key limitation is the use of retrospective cohort data.

CONCLUSIONS

This large external validation demonstrates that PREDICT Prostate is a robust and generalisable model to aid clinical decision-making.

The genetic landscapes of urological cancers and their clinical implications in the era of high-throughput genome analysis

OBJECTIVE

With the advent of high-throughput genome analysis, we are increasingly able to sequence and hence understand the pathogenic processes underlying individual cancers. Recently, consortiums such as The Cancer Genome Atlas (TCGA) have performed large-scale projects to this end, providing significant amounts of information regarding the genetic landscapes of several cancers.

PATIENTS AND METHODS

We performed a narrative review of studies from the TCGA and other major studies. We aimed to summarise data exploring the clinical implications of specific genetic alterations, both prognostically and therapeutically, in four major urological cancers. These were renal cell carcinoma, muscle-invasive bladder cancer/carcinoma, prostate cancer, and testicular germ cell tumours.

RESULTS

With these four urological cancers, great strides have been made in the molecular characterisation of tumours. In particular, recent studies have focussed on identifying molecular subtypes of tumours with characteristic genetic alterations and differing prognoses. Other prognostic alterations have also recently been identified, including those pertaining to epigenetics and microRNAs. In regard to treatment, numerous options are emerging for patients with these cancers such as including immune checkpoint inhibition, epigenetic-based treatments, and agents targeting MAPK, PI3K, and DNA repair pathways. There are a multitude of trials underway investigating the effects of these novel agents, the results of which are eagerly awaited.

CONCLUSIONS

As medicine chases the era of personalised care, it is becoming increasingly important to provide individualised prognoses for patients. Understanding how specific genetic alterations affects prognosis is key for this. It will also be crucial to provide highly targeted treatments against the specific genetics of a patient's tumour. With work performed by the TCGA and other large consortiums, these aims are gradually being achieved. Our review provides a succinct overview of this exciting field that may underpin personalised medicine in urological oncology.

CD133 antibody targeted delivery of gold nanostars loading IR820 and docetaxel for multimodal imaging and near-infrared photodynamic/photothermal/chemotherapy against castration resistant prostate cancer

Due to the lack of effective strategies on the treatment of castration resistant prostate cancer (CRPC), we established a multifunctional nanoplatform (GNS@IR820/DTX-CD133) for the synergistic photothermal therapy (PTT)/photodynamic therapy (PDT)/chemotherapy (CT) under the monitoring of multimodal near-infrared (NIR) fluorescence/photoacoustic (PA) imaging. Benefiting from the guided effect of CD133 antibody, GNS@IR820/DTX-CD133 can targetedly deliver the loaded drug to the tumor tissues, which can further contribute to the combined therapeutic effect. Our experimental results prove that the bio-distribution of GNS@IR820/DTX-CD133 can be monitored with NIR fluorescence and PA imaging. In addition, the application of GNS@IR820/DTX-CD133 for in vitro and in vivo therapy achieves the excellent antitumor effects of the synergistic PTT/PDT/CT strategies under the NIR-light irradiation. Therefore, as a multifunctional nanoplatform integrating the PTT/PDT/CT strategies with tumor multimodal imaging or drug tracing, GNS@IR820/DTX-CD133 has the great potential for clinical applications in the antitumor therapy of CRPC.

ECCO Essential Requirements for Quality Cancer Care: Prostate cancer

BACKGROUND

ECCO Essential Requirements for Quality Cancer Care (ERQCC) are written by experts representing all disciplines involved in cancer care in Europe. They give oncology teams, patients, policymakers and managers an overview of essential care throughout the patient journey.

PROSTATE CANCER

Prostate cancer is the second most common male cancer and has a wide variation in outcomes in Europe. It has complex diagnosis and treatment challenges, and is a major healthcare burden. Care must only be a carried out in prostate/urology cancer units or centres that have a core multidisciplinary team (MDT) and an extended team of health professionals. Such units are far from universal in European countries. To meet European aspirations for comprehensive cancer control, healthcare organisations must consider the requirements in this paper, paying particular attention to multidisciplinarity and patient-centred pathways from diagnosis, to treatment, to survivorship.

Molecular Biomarkers in Localized Prostate Cancer: ASCO Guideline

PURPOSE

This guideline provides recommendations for available tissue-based prostate cancer biomarkers geared toward patient selection for active surveillance, identification of clinically significant disease, choice of postprostatectomy adjuvant versus salvage radiotherapy, and to address emerging questions such as the relative value of tissue biomarkers compared with magnetic resonance imaging.

METHODS

An ASCO multidisciplinary Expert Panel, with representatives from the European Association of Urology, American Urological Association, and the College of American Pathologists, conducted a systematic literature review of localized prostate cancer biomarker studies between January 2013 and January 2019. Numerous tissue-based molecular biomarkers were evaluated for their prognostic capabilities and potential for improving management decisions. Here, the Panel makes recommendations regarding the clinical use and indications of these biomarkers.

RESULTS

Of 555 studies identified, 77 were selected for inclusion plus 32 additional references selected by the Expert Panel. Few biomarkers had rigorous testing involving multiple cohorts and only 5 of these tests are commercially available currently: Oncotype Dx Prostate, Prolaris, Decipher, Decipher PORTOS, and ProMark. With various degrees of value and validation, multiple biomarkers have been shown to refine risk stratification and can be considered for select men to improve management decisions. There is a paucity of prospective studies assessing short- and long-term outcomes of patients when these markers are integrated into clinical decision making.

RECOMMENDATIONS

Tissue-based molecular biomarkers (evaluating the sample with the highest volume of the highest Gleason pattern) may improve risk stratification when added to standard clinical parameters, but the Expert Panel endorses their use only in situations in which the assay results, when considered as a whole with routine clinical factors, are likely to affect a clinical decision. These assays are not recommended for routine use as they have not been prospectively tested or shown to improve long-term outcomes-for example, quality of life, need for treatment, or survival. Additional information is available at www.asco.org/genitourinary-cancer-guidelines.

Artificial intelligence in cancer diagnosis and prognosis: Opportunities and challenges

Cancer is an aggressive disease with a low median survival rate. Ironically, the treatment process is long and very costly due to its high recurrence and mortality rates. Accurate early diagnosis and prognosis prediction of cancer are essential to enhance the patient's survival rate. Developments in statistics and computer engineering over the years have encouraged many scientists to apply computational methods such as multivariate statistical analysis to analyze the prognosis of the disease, and the accuracy of such analyses is significantly higher than that of empirical predictions. Furthermore, as artificial intelligence (AI), especially machine learning and deep learning, has found popular applications in clinical cancer research in recent years, cancer prediction performance has reached new heights. This article reviews the literature on the application of AI to cancer diagnosis and prognosis, and summarizes its advantages. We explore how AI assists cancer diagnosis and prognosis, specifically with regard to its unprecedented accuracy, which is even higher than that of general statistical applications in oncology. We also demonstrate ways in which these methods are advancing the field. Finally, opportunities and challenges in the clinical implementation of AI are discussed. Hence, this article provides a new perspective on how AI technology can help improve cancer diagnosis and prognosis, and continue improving human health in the future.

Validation of the NCCN prostate cancer favorable- and unfavorable-intermediate risk groups among men treated with I-125 low dose rate brachytherapy monotherapy

PURPOSE

To validate the 2019 NCCN subgroups of favorable- and unfavorable-intermediate risk (IR) prostate cancer among patients treated with brachytherapy, who are underrepresented in the studies used to develop the 2019 NCCN classification.

METHODS

We included all 2,705 men treated with I-125 LDR brachytherapy monotherapy at a single institution, and who could be classified into the 2019 NCCN risk groups. Biochemical failure and distant metastasis rates were calculated using cumulative incidence analysis.

RESULTS

Of 1,510 IR patients, 756 (50%) were favorable-IR, and 754 (50%) were unfavorable-IR. Median follow up was 48 months (range, 3-214). As compared to favorable-IR, the unfavorable-IR group was associated with significantly higher rates of biochemical failure (HR, 2.87; 95% CI, 2.00-4.10; p < 0.001) and distant metastasis (HR, 3.14; 95% CI, 1.78-5.50, p < 0.001). For favorable-IR vs. unfavorable-IR groups, 5-year estimates of biochemical failure were 4.3% (95% CI, 2.6-6.1%) vs. 17.0% (95% CI, 13.6-20.5%; p < 0.001), and for distant metastasis were 1.6% (95% CI, 0.5-2.6%) vs. 5.4% (95% CI, 3.3-7.4%; p < 0.001), respectively. Patients with one unfavorable-intermediate risk factor (unfavorable-IRF; HR, 2.27; 95% CI, 1.54-3.36; p < 0.001) and 2-3 unfavorable-IRFs (HR, 4.42; 95% CI, 2.89-6.76; p < 0.001) had higher biochemical failure rates; similar findings were observed for distant metastasis (1 unfavorable-IRF: HR, 2.46; 95% CI, 1.34-4.53, p = 0.004; 2-3 unfavorable-IRFs: HR, 4.76; 95% CI, 2.49-9.10, p < 0.001).

CONCLUSIONS

These findings validate the prognostic utility of the 2019 NCCN favorable-IR and unfavorable-IR prostate cancer subgroups among men treated with brachytherapy. Androgen deprivation was not beneficial in any subgroup. Alternative treatment intensification strategies for unfavorable-IR patients are warranted.

Understanding of prognosis in non-metastatic prostate cancer: a randomised comparative study of clinician estimates measured against the PREDICT prostate prognostic model

PREDICT Prostate is an individualised prognostic model that provides long-term survival estimates for men diagnosed with non-metastatic prostate cancer ( www.prostate.predict.nhs.uk ). In this study clinician estimates of survival were compared against model predictions and its potential value as a clinical tool was assessed. Prostate cancer (PCa) specialists were invited to participate in the study. 190 clinicians (63% urologists, 17% oncologists, 20% other) were randomised into two groups and shown 12 clinical vignettes through an online portal. Each group viewed opposing vignettes with clinical information alone, or alongside PREDICT Prostate estimates. 15-year clinician survival estimates were compared against model predictions and reported treatment recommendations with and without seeing PREDICT estimates were compared. 155 respondents (81.6%) reported counselling new PCa patients at least weekly. Clinician estimates of PCa-specific mortality exceeded PREDICT estimates in 10/12 vignettes. Their estimates for treatment survival benefit at 15 years were over-optimistic in every vignette, with mean clinician estimates more than 5-fold higher than PREDICT Prostate estimates. Concomitantly seeing PREDICT Prostate estimates led to significantly lower reported likelihoods of recommending radical treatment in 7/12 (58%) vignettes, particularly in older patients. These data suggest clinicians overestimate cancer-related mortality and radical treatment benefit. Using an individualised prognostic tool may help reduce overtreatment.