scholarly journals Supervised machine learning enables non-invasive lesion characterization in primary prostate cancer with [68Ga]Ga-PSMA-11 PET/MRI

2020 ◽  
Author(s):  
L. Papp ◽  
C. P. Spielvogel ◽  
B. Grubmüller ◽  
M. Grahovac ◽  
D. Krajnc ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Machine Learning ◽  
Cross Validation ◽  
Prospective Trial ◽  
Specific Antigen ◽  
Tnm Staging ◽  
Risk Classification ◽  
Supervised Machine Learning ◽  
In Vivo Models ◽  
Primary Prostate Cancer

Abstract Purpose Risk classification of primary prostate cancer in clinical routine is mainly based on prostate-specific antigen (PSA) levels, Gleason scores from biopsy samples, and tumor-nodes-metastasis (TNM) staging. This study aimed to investigate the diagnostic performance of positron emission tomography/magnetic resonance imaging (PET/MRI) in vivo models for predicting low-vs-high lesion risk (LH) as well as biochemical recurrence (BCR) and overall patient risk (OPR) with machine learning. Methods Fifty-two patients who underwent multi-parametric dual-tracer [18F]FMC and [68Ga]Ga-PSMA-11 PET/MRI as well as radical prostatectomy between 2014 and 2015 were included as part of a single-center pilot to a randomized prospective trial (NCT02659527). Radiomics in combination with ensemble machine learning was applied including the [68Ga]Ga-PSMA-11 PET, the apparent diffusion coefficient, and the transverse relaxation time-weighted MRI scans of each patient to establish a low-vs-high risk lesion prediction model (MLH). Furthermore, MBCR and MOPR predictive model schemes were built by combining MLH, PSA, and clinical stage values of patients. Performance evaluation of the established models was performed with 1000-fold Monte Carlo (MC) cross-validation. Results were additionally compared to conventional [68Ga]Ga-PSMA-11 standardized uptake value (SUV) analyses. Results The area under the receiver operator characteristic curve (AUC) of the MLH model (0.86) was higher than the AUC of the [68Ga]Ga-PSMA-11 SUVmax analysis (0.80). MC cross-validation revealed 89% and 91% accuracies with 0.90 and 0.94 AUCs for the MBCR and MOPR models respectively, while standard routine analysis based on PSA, biopsy Gleason score, and TNM staging resulted in 69% and 70% accuracies to predict BCR and OPR respectively. Conclusion Our results demonstrate the potential to enhance risk classification in primary prostate cancer patients built on PET/MRI radiomics and machine learning without biopsy sampling.

Preclinical investigation of a small molecule inhibitor of p300/CBP reveals efficacy in patient-derived prostate tumor explants.

2019 ◽  
Vol 37 (15_suppl) ◽  
pp. e16534-e16534 ◽  
Author(s):  
Lisa Butler ◽  
Swati Irani ◽  
Margaret Centenera ◽  
Natalie Ryan ◽  
Neil Pegg ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Cancer Cells ◽  
Small Molecule ◽  
Single Agent ◽  
Specific Antigen ◽  
Resistance Mechanisms ◽  
Prostate Cancer Cells ◽  
In Vivo Models

e16534 Background: Growth and survival of prostate cancer cells are initially dependent upon androgens, and androgen deprivation therapy (ADT) is used to control tumor growth. Unfortunately, resistance to ADT inevitably occurs, and patients relapse with lethal castrate-resistant prostate cancer (CRPC). Increased expression of the androgen receptor (AR) and constitutively active AR variants are hallmarks of CRPC, and treatments targeting aberrant AR signaling are urgently required. CCS1477 is an inhibitor of p300/CBP currently in a Phase I/IIa study for CRPC. CCS1477 enhances degradation of numerous cellular proteins including the AR and AR variants in prostate cancer cells. Our preclinical studies with this compound demonstrated potent single-agent efficacy of CCS1477 using in vitro and in vivo models of prostate cancer and, when used in combination, CCS1477 enhances the efficacy of enzalutamide, a clinical AR antagonist. Understanding the response of clinical tumors to CCS1477, and their potential adaptive evolution, is essential to personalize treatment and predict potential resistance mechanisms. Methods: To assess CCS1477 in human disease, we used a unique model in which clinical prostate tumors from radical prostatectomy are cultured as explants with maintenance of tissue integrity, cell proliferation and androgen signaling. Tumors from 13 patients were cultured in the absence or presence of CCS1477 (10µM) or enzalutamide (10µM) for 48 or 72 hours; micromolar doses were selected to account for altered small molecule uptake and penetration into tissues compared to cell lines, as previously reported. Proliferation, apoptosis and androgen signaling were all analyzed post-culture. Results: Whereas the tumor explants exhibited highly heterogenous proliferative responses to enzalutamide, tumors from all patients exhibited a marked antiproliferative response to CCS1477 (mean reduction in Ki67 immunoreactivity of > 90% compared to vehicle control; p < 0.0005). Culture with CCS1477 was associated with repression of androgen signaling in the prostate tissues, measured by expression and secretion of the clinical biomarker prostate specific antigen (PSA). Conclusions: The consistent and pronounced efficacy of CCS1477 in this patient-derived model would support further investigation of this class of epigenetic agents in the castrate-sensitive prostate cancer setting.

Using longitudinal PSA values and machine learning for predicting progression of early stage prostate cancer in veterans.

2020 ◽  
Vol 38 (15_suppl) ◽  
pp. e17554-e17554
Author(s):  
Ioana Danciu ◽  
Samantha Erwin ◽  
Greeshma Agasthya ◽  
Tate Janet ◽  
Benjamin McMahon ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Machine Learning ◽  
Disease Progression ◽  
Gleason Score ◽  
Prediction Models ◽  
Early Stage ◽  
Treatment Plan ◽  
Specific Antigen ◽  
Machine Learning Algorithms ◽  
Age At Diagnosis

e17554 Background: The ability to understand and predict at the time of diagnosis the trajectories of prostate cancer patients is critical for deciding the appropriate treatment plan. Evidence-based approaches for outcome prediction include predictive machine learning algorithms that harness health record data. Methods: All our analyses used the Veterans Affairs Clinical Data Warehouse (CDW). We included all individuals with a non-metastatic (early stage) prostate cancer diagnosis between 2002 and 2017 as documented in the CDW cancer registry (N = 111351). Our predictors were demographics (age at diagnosis, race), disease staging parameters abstracted at diagnosis ( Stage grouping AJCC, Gleason score, SEER summary stage) and prostate specific antigen (PSA) laboratory values in the last 5 years prior to diagnosis (last value, the value before last, average, minimum, maximum, rate of the change of the last 2 PSAs and density). The predicted outcome was disease progression at 2 years (N = 3469) and 5 years (N = 6325) defined as metastasis - taking either Abiraterone, Sipuleucel-T, Enzalutamide or Radium 223, registry cancer related death or PSA > 50. We used 4 different machine learning classifiers to train prediction models: random forest, k-nearest neighbor, decision trees, and xgboost all with hyper parameter optimization. For testing, we used two approaches: (1) 20% sample held out at the beginning of the study, and (2) stratified test/train split on the remaining data. Results: The table below shows the performance of the best classifier, xgboost. The top five predictors of disease progression were the last PSA, Gleason Score, maximum PSA, age at diagnosis, and SEER summary stage. The last PSA had a significantly higher contribution than the other predictors. More than one PSA value is important for prediction, emphasizing the need for investigating the PSA trajectory in the period before diagnosis. The models are overall very robust going from outcome at 2 years compared to 5 years. Conclusions: A machine learning based xgboost classifier can be integrated in clinical decision support at diagnosis, to robustly predict disease progression at 2 and 5 years. [Table: see text]

scholarly journals Learning predictive models of drug side-effect relationships from distributed representations of literature-derived semantic predications

2018 ◽  
Vol 25 (10) ◽  
pp. 1339-1350 ◽  
Author(s):  
Justin Mower ◽  
Devika Subramanian ◽  
Trevor Cohen
Keyword(s):  
Machine Learning ◽  
Language Processing ◽  
Side Effect ◽  
Cross Validation ◽  
Processing System ◽  
Biomedical Literature ◽  
Supervised Machine Learning ◽  
Machine Learning Techniques ◽  
Drug Side Effect ◽  
Natural Language Processing System

Abstract Objective The aim of this work is to leverage relational information extracted from biomedical literature using a novel synthesis of unsupervised pretraining, representational composition, and supervised machine learning for drug safety monitoring. Methods Using ≈80 million concept-relationship-concept triples extracted from the literature using the SemRep Natural Language Processing system, distributed vector representations (embeddings) were generated for concepts as functions of their relationships utilizing two unsupervised representational approaches. Embeddings for drugs and side effects of interest from two widely used reference standards were then composed to generate embeddings of drug/side-effect pairs, which were used as input for supervised machine learning. This methodology was developed and evaluated using cross-validation strategies and compared to contemporary approaches. To qualitatively assess generalization, models trained on the Observational Medical Outcomes Partnership (OMOP) drug/side-effect reference set were evaluated against a list of ≈1100 drugs from an online database. Results The employed method improved performance over previous approaches. Cross-validation results advance the state of the art (AUC 0.96; F1 0.90 and AUC 0.95; F1 0.84 across the two sets), outperforming methods utilizing literature and/or spontaneous reporting system data. Examination of predictions for unseen drug/side-effect pairs indicates the ability of these methods to generalize, with over tenfold label support enrichment in the top 100 predictions versus the bottom 100 predictions. Discussion and Conclusion Our methods can assist the pharmacovigilance process using information from the biomedical literature. Unsupervised pretraining generates a rich relationship-based representational foundation for machine learning techniques to classify drugs in the context of a putative side effect, given known examples.

scholarly journals Identifying prostate cancer and its clinical risk in asymptomatic men using machine learning of high dimensional peripheral blood flow cytometric natural killer cell subset phenotyping data

eLife ◽  
2020 ◽  
Vol 9 ◽  
Author(s):  
Simon P Hood ◽  
Georgina Cosma ◽  
Gemma A Foulds ◽  
Catherine Johnson ◽  
Stephen Reeder ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Machine Learning ◽  
Natural Killer ◽  
Killer Cell ◽  
Specific Antigen ◽  
Cell Subset ◽  
Cancer Diagnostics ◽  
Peripheral Blood Flow ◽  
Flow Cytometric ◽  
Asymptomatic Men

We demonstrate that prostate cancer can be identified by flow cytometric profiling of blood immune cell subsets. Herein, we profiled natural killer (NK) cell subsets in the blood of 72 asymptomatic men with Prostate-Specific Antigen (PSA) levels < 20 ng ml-1, of whom 31 had benign disease (no cancer) and 41 had prostate cancer. Statistical and computational methods identified a panel of eight phenotypic features (C⁢D⁢56d⁢i⁢m⁢C⁢D⁢16h⁢i⁢g⁢h, C⁢D⁢56+⁢D⁢N⁢A⁢M-1-, C⁢D⁢56+⁢L⁢A⁢I⁢R-1+, C⁢D⁢56+⁢L⁢A⁢I⁢R-1-, C⁢D⁢56b⁢r⁢i⁢g⁢h⁢t⁢C⁢D⁢8+, C⁢D⁢56+⁢N⁢K⁢p⁢30+, C⁢D⁢56+⁢N⁢K⁢p⁢30-, C⁢D⁢56+⁢N⁢K⁢p⁢46+) that, when incorporated into an Ensemble machine learning prediction model, distinguished between the presence of benign prostate disease and prostate cancer. The machine learning model was then adapted to predict the D’Amico Risk Classification using data from 54 patients with prostate cancer and was shown to accurately differentiate between the presence of low-/intermediate-risk disease and high-risk disease without the need for additional clinical data. This simple blood test has the potential to transform prostate cancer diagnostics.

scholarly journals Prediction of Prostate Cancer Disease Aggressiveness Using Bi-Parametric Mri Radiomics

Cancers ◽  
2021 ◽  
Vol 13 (23) ◽  
pp. 6065
Author(s):  
Ana Rodrigues ◽  
João Santinha ◽  
Bernardo Galvão ◽  
Celso Matos ◽  
Francisco M. Couto ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Machine Learning ◽  
Gleason Score ◽  
Feature Selection Method ◽  
Supervised Machine Learning ◽  
Lesion Volume ◽  
Clinical Images ◽  
Gland Volume ◽  
Volume Of Interest ◽  
Cancer Aggressiveness

Prostate cancer is one of the most prevalent cancers in the male population. Its diagnosis and classification rely on unspecific measures such as PSA levels and DRE, followed by biopsy, where an aggressiveness level is assigned in the form of Gleason Score. Efforts have been made in the past to use radiomics coupled with machine learning to predict prostate cancer aggressiveness from clinical images, showing promising results. Thus, the main goal of this work was to develop supervised machine learning models exploiting radiomic features extracted from bpMRI examinations, to predict biological aggressiveness; 288 classifiers were developed, corresponding to different combinations of pipeline aspects, namely, type of input data, sampling strategy, feature selection method and machine learning algorithm. On a cohort of 281 lesions from 183 patients, it was found that (1) radiomic features extracted from the lesion volume of interest were less stable to segmentation than the equivalent extraction from the whole gland volume of interest; and (2) radiomic features extracted from the whole gland volume of interest produced higher performance and less overfitted classifiers than radiomic features extracted from the lesions volumes of interest. This result suggests that the areas surrounding the tumour lesions offer relevant information regarding the Gleason Score that is ultimately attributed to that lesion.

scholarly journals Predicting genes associated with RNA methylation pathways using machine learning

2021 ◽  
Author(s):  
Georgia Tsagkogeorga ◽  
Helena Santos Rosa ◽  
Andrej Alendar ◽  
Dan Leggate ◽  
Oliver Rausch ◽  
...  
Keyword(s):  
Machine Learning ◽  
Cross Validation ◽  
Supervised Machine Learning ◽  
Protein Interaction Data ◽  
Physical Interaction ◽  
Interaction Data ◽  
Rna Methylation ◽  
Protein Protein Interaction ◽  
Predict Gene Function ◽  
Functional Regulation

RNA methylation plays an important role in functional regulation of RNAs, and has thus attracted an increasing interest in biology and drug discovery. Here, we collected and collated transcriptomic, proteomic, structural and physical interaction data from the Harmonizome database, and applied supervised machine learning to predict novel genes associated with RNA methylation pathways in human. We selected five types of classifiers, which we trained and evaluated using cross-validation on multiple training sets. The best models reached 88% accuracy based on cross-validation, and an average 91% accuracy on the test set. Using protein-protein interaction data, we propose six molecular sub-networks linking model predictions to previously known RNA methylation genes, with roles in mRNA methylation, tRNA processing, rRNA processing, but also protein and chromatin modifications. Our study exemplifies how access to large omics datasets joined by machine learning methods can be used to predict gene function.

Sign in / Sign up

Export Citation Format

Share Document