Early detection of prostate cancer in African-American men through use of multiple biomarkers: human kallikrein 2 (hK2), prostate-specific antigen (PSA), and free PSA (fPSA)

Application of tree-based machine learning classification methods to detect signals of fluoroquinolones using the Korea Adverse Event Reporting System (KAERS) database

BACKGROUND

Safety issues for fluoroquinolones have been provided by regulatory agencies. This study was conducted to identify signals of fluoroquinolones reported in the Korea Adverse Event Reporting System (KAERS) using tree-based machine learning (ML) methods.

RESEARCH DESIGN AND METHODS

All adverse events (AEs) associated with the target drugs reported in the KAERS from 2013 to 2017 were matched with drug label information. A dataset containing label-positive and -negative AEs was arbitrarily divided into training and test sets. Decision tree, random forest (RF), bagging, and gradient boosting machine (GBM) were fitted on the training set with hyperparameters tuned using five-fold cross-validation and applied to the test set. The ML method with the highest area under the curve (AUC) scores was selected as the final ML model.

RESULTS

Bagging was selected as the final ML model for gemifloxacin (AUC score: 1) and levofloxacin (AUC: 0.9987). RF was selected in ciprofloxacin, moxifloxacin, and ofloxacin (AUC scores: 0.9859, 0.9974, and 0.9999 respectively). We found that the final ML methods detected additional signals that were not detected using the disproportionality analysis (DPA) methods.

CONCLUSIONS

The bagging-or-RF-based ML methods performed better than DPA and detected novel AE signals previously unidentified using the DPA methods.

Machine Learning for Detection of Safety Signals From Spontaneous Reporting System Data: Example of Nivolumab and Docetaxel

Introduction: Various methods have been implemented to detect adverse drug reaction (ADR) signals. However, the applicability of machine learning methods has not yet been fully evaluated.

Objective: To evaluate the feasibility of machine learning algorithms in detecting ADR signals of nivolumab and docetaxel, new and old anticancer agents.

Methods: We conducted a safety surveillance study of nivolumab and docetaxel using the Korea national spontaneous reporting database from 2009 to 2018. We constructed a novel input dataset for each study drug comprised of known ADRs that were listed in the drug labels and unknown ADRs. Given the known ADRs, we trained machine learning algorithms and evaluated predictive performance in generating safety signals of machine learning algorithms (gradient boosting machine [GBM] and random forest [RF]) compared with traditional disproportionality analysis methods (reporting odds ratio [ROR] and information component [IC]) by using the area under the curve (AUC). Each method then was implemented to detect new safety signals from the unknown ADR datasets.

Results: Of all methods implemented, GBM achieved the best average predictive performance (AUC: 0.97 and 0.93 for nivolumab and docetaxel). The AUC achieved by each method was 0.95 and 0.92 (RF), 0.55 and 0.51 (ROR), and 0.49 and 0.48 (IC) for respective drug. GBM detected additional 24 and nine signals for nivolumab and 82 and 76 for docetaxel compared to ROR and IC, respectively, from the unknown ADR datasets.

Conclusion: Machine learning algorithm based on GBM performed better and detected more new ADR signals than traditional disproportionality analysis methods.

Chemoprevention in African American Men With Prostate Cancer

BACKGROUND

Recommendations for cancer screening are uncertain for the early detection or prevention of prostate cancer in African American men. Thus, chemoprevention strategies are needed to specifically target African American men.

METHODS

The evidence was examined on the biological etiology of disparities in African Americans related to prostate cancer. Possible chemopreventive agents and biomarkers critical to prostate cancer in African American men were also studied.

RESULTS

High-grade prostatic intraepithelial neoplasia may be more prevalent in African American men, even after controlling for age, prostate-specific antigen (PSA) level, abnormal results on digital rectal examination, and prostate volume. Prostate cancer in African American men can lead to the overexpression of signaling receptors that may mediate increased proliferation, angiogenesis, and decreased apoptosis. Use of chemopreventive agents may be useful for select populations of men.

CONCLUSIONS

Green tea catechins are able to target multiple pathways to address the underlying biology of prostate carcinogenesis in African American men, so they may be ideal as a chemoprevention agent in these men diagnosed with high-grade prostatic intraepithelial neoplasia.

Novel biomarkers for the detection of prostate cancer

Prostate-specific antigen (PSA) is widely used as a biomarker in the detection of prostate cancer and for decision making regarding treatment options, response to therapy, and clinical follow-up. Despite its widespread use, it is well recognised that PSA has suboptimal performance as a screening tool due to poor specificity, resulting in high negative biopsy rates and potential ‘over-diagnosis’ and ‘over-treatment’ of clinically insignificant cancers. In particular, PSA does not reliably distinguish either cancer from benign prostatic conditions, or ‘clinically significant’ from ‘indolent cancers’, and it is inaccurate in predicting disease burden and response to treatment. There is an urgent demand for novel biomarkers to address these clinical needs. This article provides an update on the novel candidate biomarkers in development, which have shown potential for improving the detection of clinically significant cases of this malignancy.

Human Kallikrein-2, Prostate Specific Antigen and Free- Prostate Specific Antigen in Combination to Discriminate Prostate Cancer from Benign Diseases in Syrian Patients

BACKGROUND

The high incidence of prostate cancer as the most common malignancy in males in many countries raises the question of developing reliable detection tests. The prostate specific antigen (PSA) test is the most widely used for screening for prostate cancer; however, its low specificity elevates the number of unnecessarily biopsies. Serum human kallikrein-2 (hK2) is considered as a promising marker, and especially its ratio to fPSA, for predicting the presence of malignancy to select the best choice referring to biopsy or surveillance. In this study, we investigated the role of hK2 and its combinations with other markers to discriminate prostate cancer from benign diseases in Syrian patients.

MATERIALS AND METHODS

In this prospective oriented cross-sectional cohort study, serum samples were collected from patients referred to many Hospitals in Damascus, Syria, between May 2011 and March 2012, and diagnosed with biopsy proven benign prostate hyperplasia (BPH) or prostate cancer (PCa). Serum was analyzed for hK2, PSA and fPSA, and the ratios of fPSA/PSA and hK2/fPSA were calculated.

RESULTS

We found that mean hK2/fPSA ratios were significantly higher (P=0.01) in prostate cancer patients than in the BPH or control groups. Also the ratio hk2/fPSA gave the largest area under the curve (AUC:0.96) which was significantly larger than for fPSA/PSA (AUC:0.41) indicative of higher specificity.

CONCLUSIONS

Our results demonstrate that the ratio of hK2/fPSA might be superior to the use of fPSA/PSA alone. The hK2 could be shown to enhance the early detection of prostate cancer; especially the ratio hK2/fPSA improves specificity and hence may reduce the number of negative biopsies.

Biomarker detection technologies and future directions

Biomarkers play a vital role in disease detection and treatment follow-up. It is important to note that diseases in the early stage are typically treated with the greatest probability of success. However, due to various technical difficulties in current technologies for the detection of biomarkers, the potential of biomarkers is not explored completely. Therefore, the developments of technologies, which can enable the accurate detection of prostate cancer at an early stage with simple, experimental protocols are highly inevitable. This critical review evaluates the current methods and technologies used in the detection of biomarkers. The aim of this article is to provide a comprehensive review covering the advantages and disadvantages of the biomarker detection methods. Future directions for the development of technologies to achieve highly selective and sensitive detection of biomarkers for point-of-care applications are also commented on.

Empirical performance of a new user cohort method: lessons for developing a risk identification and analysis system

BACKGROUND

Observational healthcare data offer the potential to enable identification of risks of medical products, but appropriate methodology has not yet been defined. The new user cohort method, which compares the post-exposure rate among the target drug to a referent comparator group, is the prevailing approach for many pharmacoepidemiology evaluations and has been proposed as a promising approach for risk identification but its performance in this context has not been fully assessed.

OBJECTIVES

To evaluate the performance of the new user cohort method as a tool for risk identification in observational healthcare data.

RESEARCH DESIGN

The method was applied to 399 drug-outcome scenarios (165 positive controls and 234 negative controls across 4 health outcomes of interest) in 5 real observational databases (4 administrative claims and 1 electronic health record) and in 6 simulated datasets with no effect and injected relative risks of 1.25, 1.5, 2, 4, and 10, respectively.

MEASURES

Method performance was evaluated through Area Under ROC Curve (AUC), bias, and coverage probability.

RESULTS

The new user cohort method achieved modest predictive accuracy across the outcomes and databases under study, with the top-performing analysis near AUC >0.70 in most scenarios. The performance of the method was particularly sensitive to the choice of comparator population. For almost all drug-outcome pairs there was a large difference, either positive or negative, between the true effect size and the estimate produced by the method, although this error was near zero on average. Simulation studies showed that in the majority of cases, the true effect estimate was not within the 95 % confidence interval produced by the method.

CONCLUSION

The new user cohort method can contribute useful information toward a risk identification system, but should not be considered definitive evidence given the degree of error observed within the effect estimates. Careful consideration of the comparator selection and appropriate calibration of the effect estimates is required in order to properly interpret study findings.

Emerging PSA-based tests to improve screening

This article updates advances in prostate cancer screening based on prostate-specific antigen, its derivatives, and human kallikrein markers. Many men are diagnosed with indolent disease not requiring treatment. Although there is evidence of a survival benefit from screening, the numbers needed to screen and treat remain high. There is risk of exposing men to the side effects of treatment for nonthreatening disease. A screening test is needed with sufficiently good performance characteristics to detect disease at an early stage so treatment may be offered with curative intent, while reducing the number of negative or unnecessary biopsies.

The Kallikrein Panel for prostate cancer screening: its economic impact

BACKGROUND

Current diagnostic testing for prostate cancer results in numerous unnecessary biopsy procedures and creates a substantial financial burden. A statistical prediction model for prostate cancer has been developed, based on four Kallikrein markers in blood. This systematic review and meta-analysis examines the aggregated results from published studies of the Kallikrein Panel.

METHODS

Literature searches to identify relevant studies were conducted. A meta-analysis of the results was performed using inverse variance, mean difference with corresponding 95% confidence intervals (CI). The results of the meta-analysis were used to assess the Kallikrein Panel's effect on healthcare costs.

RESULTS

The Kallikrein Panel has been evaluated in more than 8,500 patients (2,780 with prostate cancer and 598 with high grade prostate cancer). Meta-analysis demonstrates a statistically significant improvement of 8-10% in predictive accuracy. In addition, 48% to 56% of current prostate biopsies could be avoided. Use of the Kallikrein Panel could result in annual US savings approaching $1 billion.

CONCLUSIONS

The Kallikrein Panel has the potential to improve patient outcomes and reduce costs. The panel provides significantly improved specificity. Because the Kallikrein Panel has been studied in a range of clinical settings, it is a test that could be readily and widely used in practice.

The Eastland Prostate Cancer Survey: instrument development and psychometric testing

African-American (AA) women could be instrumental in communicating positive prostate screening behavior to the significant males in their lives. However, little is known about AA women's prostate cancer attitudes, perceived behavioral control, subjective norms, intentions, behaviors, and knowledge regarding prostate cancer screening. This study describes the development and psychometric testing of the Eastland Prostate Cancer Survey (EPCS). A nonexperimental, correlational study with 200 AA women was used to test the psychometric properties of the six-subscale EPCS with 66 items. Construct validity, internal consistency, and test-retest reliability for the EPCS were acceptable and resulted in an eight-subscale EPCS with 56 items. Cronbach's alphas for the subscales ranged from 0.69 to 0.92. The EPCS is a culturally sensitive, gender-relevant instrument that could be used by community health providers to develop community health programs aimed at engaging AA women in the promotion of prostate cancer screening for AA men.

Performance of pharmacovigilance signal-detection algorithms for the FDA adverse event reporting system

Signal-detection algorithms (SDAs) are recognized as vital tools in pharmacovigilance. However, their performance characteristics are generally unknown. By leveraging a unique gold standard recently made public by the Observational Medical Outcomes Partnership (OMOP) and by conducting a unique systematic evaluation, we provide new insights into the diagnostic potential and characteristics of SDAs that are routinely applied to the US Food and Drug Administration (FDA) Adverse Event Reporting System (AERS). We find that SDAs can attain reasonable predictive accuracy in signaling adverse events. Two performance classes emerge, indicating that the class of approaches that address confounding and masking effects benefits safety surveillance. Our study shows that not all events are equally detectable, suggesting that specific events might be monitored more effectively using other data sources. We provide performance guidelines for several operating scenarios to inform the trade-off between sensitivity and specificity for specific use cases. We also propose an approach and demonstrate its application in identifying optimal signaling thresholds, given specific misclassification tolerances.

Empirical assessment of methods for risk identification in healthcare data: results from the experiments of the Observational Medical Outcomes Partnership

BACKGROUND

Expanded availability of observational healthcare data (both administrative claims and electronic health records) has prompted the development of statistical methods for identifying adverse events associated with medical products, but the operating characteristics of these methods when applied to the real-world data are unknown.

METHODS

We studied the performance of eight analytic methods for estimating of the strength of association-relative risk (RR) and associated standard error of 53 drug-adverse event outcome pairs, both positive and negative controls. The methods were applied to a network of ten observational healthcare databases, comprising over 130 million lives. Performance measures included sensitivity, specificity, and positive predictive value of methods at RR thresholds achieving statistical significance of p < 0.05 or p < 0.001 and with absolute threshold RR > 1.5, as well as threshold-free measures such as area under receiver operating characteristic curve (AUC).

RESULTS

Although no specific method demonstrated superior performance, the aggregate results provide a benchmark and baseline expectation for risk identification method performance. At traditional levels of statistical significance (RR > 1, p < 0.05), all methods have a false positive rate >18%, with positive predictive value <38%. The best predictive model, high-dimensional propensity score, achieved an AUC  =  0.77. At 50% sensitivity, false positive rate ranged from 16% to 30%. At 10% false positive rate, sensitivity of the methods ranged from 9% to 33%.

CONCLUSIONS

Systematic processes for risk identification can provide useful information to supplement an overall safety assessment, but assessment of methods performance suggests a substantial chance of identifying false positive associations.

A four-kallikrein panel predicts prostate cancer in men with recent screening: data from the European Randomized Study of Screening for Prostate Cancer, Rotterdam

PURPOSE

We have developed a statistical prediction model for prostate cancer based on four kallikrein markers in blood: total, free, and intact prostate-specific antigen (PSA), and kallikrein-related peptidase 2 (hK2). Although this model accurately predicts the result of biopsy in unscreened men, its properties for men with a history of PSA screening have not been fully characterized.

EXPERIMENTAL DESIGN

A total of 1,501 previously screened men with elevated PSA underwent initial biopsy during rounds 2 and 3 of the European Randomized Study of Screening for Prostate Cancer, Rotterdam, with 388 cancers diagnosed. Biomarker levels were measured in serum samples taken before biopsy. The prediction model developed on the unscreened cohort was then applied and predictions compared with biopsy outcome.

RESULTS

The previously developed four-kallikrein prediction model had much higher predictive accuracy than PSA and age alone (area under the curve of 0.711 versus 0.585, and 0.713 versus 0.557 with and without digital rectal exam, respectively; both P < 0.001). Similar statistically significant enhancements were seen for high-grade cancer. Applying the model with a cutoff of 20% cancer risk as the criterion for biopsy would reduce the biopsy rate by 362 for every 1,000 men with elevated PSA. Although diagnosis would be delayed for 47 cancers, these would be predominately low-stage and low-grade (83% Gleason 6 T(1c)).

CONCLUSIONS

A panel of four kallikreins can help predict the result of initial biopsy in previously screened men with elevated PSA. Use of a statistical model based on the panel would substantially decrease rates of unnecessary biopsy.

Real-time quantitative RT-PCR assessment of PIM-1 and hK2 mRNA expression in benign prostate hyperplasia and prostate cancer

To investigate the expressions of PIM-1 and hK2 mRNA in normal prostate, benign prostatic glandular hyperplasia (BPH), and prostate cancer (PCa), and to explore the association of PIM-1 and hK2 expressions with PCa progression. The samples were harvested from 37 patients with BPH, 23 patients with PCa, and three with normal prostate tissues. Total RNA was extracted from their prostate tissues and analyzed for PIM-1 and hK2 mRNA levels using SYBR green I-based quantitative real-time RT-PCR (QRT-PCR) assays and Southern blot analysis. The differences of gene expressions were calculated based on standard curve. Quantitative expressions of PIM-1 and hK2 mRNA in normal prostate, BPH, and PCa were 1.05 +/- 0.04, 2.57 +/- 0.74, 4.45 +/- 0.63, and 1.02 +/- 0.03, 2.264 +/- 0.46, 5.905 +/- 0.78, respectively. PIM-1 and hK2 were expressed higher in PCa than those in BPH and normal prostate tissues, the differences among which had statistic significance (P < 0.05). Our results support the hypothesis that PIM-1 and hK2 play a significant role in the growth of PCa and the detection of PIM-1 and hK2 mRNA expressions by QRT-PCR provided more reliable and helpful information on diagnosis, treatment, and prognosis of PCa.

A panel of kallikrein markers can reduce unnecessary biopsy for prostate cancer: data from the European Randomized Study of Prostate Cancer Screening in Göteborg, Sweden

BACKGROUND

Prostate-specific antigen (PSA) is widely used to detect prostate cancer. The low positive predictive value of elevated PSA results in large numbers of unnecessary prostate biopsies. We set out to determine whether a multivariable model including four kallikrein forms (total, free, and intact PSA, and human kallikrein 2 (hK2)) could predict prostate biopsy outcome in previously unscreened men with elevated total PSA.

METHODS

The study cohort comprised 740 men in Göteborg, Sweden, undergoing biopsy during the first round of the European Randomized study of Screening for Prostate Cancer. We calculated the area-under-the-curve (AUC) for predicting prostate cancer at biopsy. AUCs for a model including age and PSA (the 'laboratory' model) and age, PSA and digital rectal exam (the 'clinical' model) were compared with those for models that also included additional kallikreins.

RESULTS

Addition of free and intact PSA and hK2 improved AUC from 0.68 to 0.83 and from 0.72 to 0.84, for the laboratory and clinical models respectively. Using a 20% risk of prostate cancer as the threshold for biopsy would have reduced the number of biopsies by 424 (57%) and missed only 31 out of 152 low-grade and 3 out of 40 high-grade cancers.

CONCLUSION

Multiple kallikrein forms measured in blood can predict the result of biopsy in previously unscreened men with elevated PSA. A multivariable model can determine which men should be advised to undergo biopsy and which might be advised to continue screening, but defer biopsy until there was stronger evidence of malignancy.

Proteomic analysis of conditioned media from the PC3, LNCaP, and 22Rv1 prostate cancer cell lines: discovery and validation of candidate prostate cancer biomarkers

Early detection of prostate cancer is problematic due to the lack of a marker that has high diagnostic sensitivity and specificity. The prostate specific antigen (PSA) test, in combination with digital rectal examination, is the gold standard for prostate cancer diagnosis. However, this modality suffers from low specificity. Therefore, specific markers for clinically relevant prostate cancer are needed. Our objective was to proteomically characterize the conditioned media from three human prostate cancer cell lines of differing origin [PC3 (bone metastasis), LNCaP (lymph node metastasis), and 22Rv1 (localized to prostate)] to identify secreted proteins that could serve as novel prostate cancer biomarkers. Each cell line was cultured in triplicate, followed by a bottom-up analysis of the peptides by two-dimensional chromatography and tandem mass spectrometry. Approximately, 12% (329) of the proteins identified were classified as extracellular and 18% (504) as membrane-bound among which were known prostate cancer biomarkers such as PSA and KLK2. To select the most promising candidates for further investigation, tissue specificity, biological function, disease association based on literature searches, and comparison of protein overlap with the proteome of seminal plasma and serum were examined. On the basis of this, four novel candidates, follistatin, chemokine (C-X-C motif) ligand 16, pentraxin 3 and spondin 2, were validated in the serum of patients with and without prostate cancer. The proteins presented in this study represent a comprehensive sampling of the secreted and shed proteins expressed by prostate cancer cells, which may be useful as diagnostic, prognostic or predictive serological markers for prostate cancer.

Use of prostate-specific antigen (PSA) isoforms for the detection of prostate cancer in men with a PSA level of 2-10 ng/ml: systematic review and meta-analysis

OBJECTIVE

Measurement of serum prostate-specific antigen (PSA) for the detection of prostate cancer has poor specificity in men with PSA levels between 2 and 10 ng/ml. It has been suggested that measurement of the ratio of free to total PSA (f/tPSA) or complexed PSA (cPSA) might offer an improvement. We performed a systematic review and meta-analysis to evaluate the diagnostic performance of these tests among men with PSA levels between 2 and 10 ng/ml.

METHODS

Data on sensitivity and specificity were extracted from 66 eligible studies. Likelihood ratios and summary receiver operating characteristic curves were estimated and possible sources of heterogeneity between studies examined.

RESULTS

Use of the f/tPSA or the cPSA test improved diagnostic performance among men with a total PSA (tPSA) of 2-4 or 4-10 ng/ml compared to tPSA alone. The diagnostic performance of the f/tPSA test was significantly higher in the tPSA range of 4-10 ng/ml compared to a tPSA range of 2-4 ng/ml (p < 0.01); at a sensitivity of 95%, the specificity was 18% in the 4-10 ng/ml tPSA range and 6% in the 2-4 ng/ml tPSA range. Among studies that measured both isoforms, the diagnostic performance of the f/tPSA test and the cPSA was equivalent in both PSA ranges.

CONCLUSIONS

The use of the f/tPSA or cPSA test among men with PSA levels between 2 and 10 ng/ml can reduce the number of unnecessary biopsies whilst maintaining a high cancer detection rate.