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]

Machine Learning Algorithms to Detect Subclinical Keratoconus: Systematic Review (Preprint)

2021 ◽  
Author(s):  
Howard Maile ◽  
Ji-Peng Olivia Li ◽  
Daniel Gore ◽  
Marcello Leucci ◽  
Padraig Mulholland ◽  
...  
Keyword(s):  
Machine Learning ◽  
Disease Progression ◽  
Learning Algorithm ◽  
Early Stage ◽  
Demographic Data ◽  
Learning Algorithms ◽  
Detailed Comparison ◽  
Machine Learning Algorithms ◽  
Machine Learning Algorithm ◽  
Clinical Measures

BACKGROUND Keratoconus is a disorder characterized by progressive thinning and distortion of the cornea. If detected at an early stage corneal collagen cross linking can prevent disease progression and further visual loss. Whilst advanced forms are easily detected, reliably identifying subclinical disease can be problematic. A number of different machine learning algorithms have been used to improve the detection of subclinical keratoconus based on the analysis of single or multiple clinical measures such as corneal imaging, aberrometry, or biomechanical measurements. OBJECTIVE To survey and critically evaluate the literature on algorithmic detection of subclinical keratoconus and equivalent definitions. METHODS We performed a structured search of the following databases: Medical Literature Analysis and Retrieval System Online (MEDLINE), Excerpta Medica Database (EMBASE), Web of Science and Cochrane from Jan 1, 2010 to Oct 31, 2020. We included all full text studies that have used algorithms for the detection of subclinical keratoconus. We excluded studies that did not perform validation. RESULTS We compared the parameters measured and the design of the machine learning algorithms reported in 26 papers that met the inclusion criteria. All salient information required for detailed comparison including diagnostic criteria, demographic data, sample size, acquisition system, validation details, parameter inputs, machine learning algorithm and key results are reported in this study. CONCLUSIONS Machine learning has the potential to improve the detection of subclinical keratoconus or early keratoconus in routine ophthalmic practice. Presently there is no consensus regarding the corneal parameters that should be included for assessment and the optimal design for the machine learning algorithm. We have identified avenues for further research to improve early detection and stratification of patients for early intervention to prevent disease progression. CLINICALTRIAL N/A

scholarly journals Predicting High-Risk Prostate Cancer Using Machine Learning Methods

Data ◽  
2019 ◽  
Vol 4 (3) ◽  
pp. 129 ◽  
Author(s):  
Barlow ◽  
Mao ◽  
Khushi
Keyword(s):  
Prostate Cancer ◽  
Machine Learning ◽  
High Risk ◽  
Specific Antigen ◽  
Rate Of Change ◽  
Machine Learning Algorithms ◽  
Negative Consequences ◽  
Ovarian Cancer Screening ◽  
High Risk Prostate Cancer ◽  
Risk Prostate Cancer

Prostate cancer can be low- or high-risk to the patient’s health. Current screening on the basis of prostate-specific antigen (PSA) levels has a tendency towards both false positives and false negatives, both of which have negative consequences. We obtained a dataset of 35,875 patients from the screening arm of the National Cancer Institute’s Prostate, Lung, Colorectal, and Ovarian Cancer Screening Trial. We segmented the data into instances without prostate cancer, instances with low-risk prostate cancer, and instances with high-risk prostate cancer. We developed a pipeline to deal with imbalanced data and proposed algorithms to perform preprocessing on such datasets. We evaluated the accuracy of various machine learning algorithms in predicting high-risk prostate cancer. An accuracy of 91.5% can be achieved by the proposed pipeline, using standard scaling, SVMSMOTE sampling method, and AdaBoost for machine learning. We then evaluated the contribution of rate of change of PSA, age, BMI, and filtration by race to this model’s accuracy. We identified that including the rate of change of PSA and age in our model increased the area under the curve (AUC) of the model by 6.8%, whereas BMI and race had a minimal effect.

scholarly journals Machine Learning–Based Interpretation and Visualization of Nonlinear Interactions in Prostate Cancer Survival

2020 ◽  
pp. 637-646 ◽  
Author(s):  
Richard Li ◽  
Ashwin Shinde ◽  
An Liu ◽  
Scott Glaser ◽  
Yung Lyou ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Machine Learning ◽  
Gleason Score ◽  
Cancer Survival ◽  
A Priori ◽  
Specific Antigen ◽  
Interaction Effects ◽  
Tree Model ◽  
Prediction Of Mortality ◽  
Staging Systems

PURPOSE Shapley additive explanation (SHAP) values represent a unified approach to interpreting predictions made by complex machine learning (ML) models, with superior consistency and accuracy compared with prior methods. We describe a novel application of SHAP values to the prediction of mortality risk in prostate cancer. METHODS Patients with nonmetastatic, node-negative prostate cancer, diagnosed between 2004 and 2015, were identified using the National Cancer Database. Model features were specified a priori: age, prostate-specific antigen (PSA), Gleason score, percent positive cores (PPC), comorbidity score, and clinical T stage. We trained a gradient-boosted tree model and applied SHAP values to model predictions. Open-source libraries in Python 3.7 were used for all analyses. RESULTS We identified 372,808 patients meeting the inclusion criteria. When analyzing the interaction between PSA and Gleason score, we demonstrated consistency with the literature using the example of low-PSA, high-Gleason prostate cancer, recently identified as a unique entity with a poor prognosis. When analyzing the PPC-Gleason score interaction, we identified a novel finding of stronger interaction effects in patients with Gleason ≥ 8 disease compared with Gleason 6-7 disease, particularly with PPC ≥ 50%. Subsequent confirmatory linear analyses supported this finding: 5-year overall survival in Gleason ≥ 8 patients was 87.7% with PPC < 50% versus 77.2% with PPC ≥ 50% ( P < .001), compared with 89.1% versus 86.0% in Gleason 7 patients ( P < .001), with a significant interaction term between PPC ≥ 50% and Gleason ≥ 8 ( P < .001). CONCLUSION We describe a novel application of SHAP values for modeling and visualizing nonlinear interaction effects in prostate cancer. This ML-based approach is a promising technique with the potential to meaningfully improve risk stratification and staging systems.

scholarly journals A Survey on Cardiovascular Prediction using Variant Machine learning

2021 ◽  
Vol 309 ◽  
pp. 01042
Author(s):  
L. Chandrika ◽  
K. Madhavi ◽  
B. Sindhuja ◽  
M. Arshi
Keyword(s):  
Machine Learning ◽  
Cardiovascular Diseases ◽  
Prediction Models ◽  
Early Stage ◽  
Clustering Algorithms ◽  
Hospital Staff ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Medical Practitioners ◽  
Machine Learning Approach

Prediction of a cardiovascular diseases has always a tedious challenge for doctors and medical practitioners. Most of the practitioners and hospital staff offers expensive medication, care and surgeries to treat the cardiovascular patients. At early-stage of prediction of heart-oriented problems will be giving a chance of survival by taking necessary precautions. Over the years there are different types of methodologies were proposed to predict the cardiovascular diseases one of the best methodologies is a Machine learning approach. These years many scientific advancements take place in the Artificial Intelligence, Machine learning, and Deep learning which gives an extra push up to help and implement the path in the field of medical image processing and medical data analysis. By using the enormous dataset from various medical experts used to help the researchers to predict the coronary problems prior to happening. Many researchers have tried and implemented different machine learning algorithms to automate the prediction analysis using the enormous number of datasets. There are numerous algorithms and procedures to predict the cardiovascular diseases and accessible to be specific Classification methods including Artificial Neural Networks (AI), Decision tree (DT), Support vector machine (SVM), Genetic algorithm (GA), Neural network (NN), Naive Bayes (NB) and Clustering algorithms like K-NN. A few examinations have been done for creating expectation models utilizing singular procedures and additionally concatenating at least two strategies. This paper gives a speedy and simple survey and knowledge of approachable prediction models using different researchers work from 2004 to 2019. The examination indicates the precision of individual experiments done by various researchers.

Risk factors for disease progression after post-prostatectomy salvage radiation: Long-term results of a large institutional experience.

2016 ◽  
Vol 34 (2_suppl) ◽  
pp. 110-110
Author(s):  
Danielle Rodin ◽  
Lars Wiuff Andersen ◽  
Daniela Buscariollo ◽  
Michael Drumm ◽  
Rebecca Helen Clayman ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Risk Factors ◽  
Disease Progression ◽  
Gleason Score ◽  
Doubling Time ◽  
Multivariable Analysis ◽  
Specific Antigen ◽  
Long Term Results ◽  
Recurrent Prostate Cancer ◽  
Cox Regression Analysis

110 Background: Salvage radiotherapy (SRT) has been successfully used to treat recurrent prostate cancer following radical prostatectomy (RP). The objective of this study was to identify risk factors for disease progression post-SRT. Methods: Retrospective review of 719 consecutive patients who had RP and received post-operative radiation (adjuvant/SRT) for recurrent prostate cancer from 1992-2013. Disease progression was defined by a prostate specific antigen (PSA) ≥0.2 ng/ml, local recurrence, nodal failure, or distant metastases. Analysis was restricted to patients treated after 2000, when the PSA detectability threshold decreased to 0.2. Univariable and multivariable Cox regression analysis with backwards selection was performed with the following variables: demographics (age, race), pathological features (Gleason score, positive margins, pT-stage), surgery type, radiation details, hormone therapy, and pre-SRT PSA. Secondarily, we included PSA velocity and doubling-time as continuous variables in the model. Results: 384 patients received SRT after 2000, of which 152 had disease progression, with a median time to recurrence of 6.2 years (95% CI 4.1-7.6 years). Multivariable analysis results are reported in the Table. Gleason score, T-stage, seminal vesicle invasion, and pre-SRT PSA were associated with progression. Pre-SRT PSA ≤ 0.3 conferred the lowest rate of disease progression. In a secondary model, PSA kinetics was evaluated in which doubling-time was associated with progression (HR 0.98 per month increase, 95% CI 0.96-1.00; p=0.03). Conclusions: The lowest rate of disease progression was found amongst patients treated with a PSA ≤ 0.3. A shorter DT may also be a useful predictor of disease progression after SRT. [Table: see text]

Prostate Cancer: Biology, Incidence, Detection Methods, Treatment Methods, and Vaccines

2020 ◽  
Vol 20 (10) ◽  
pp. 847-854
Author(s):  
Ronald Bartzatt
Keyword(s):  
Prostate Cancer ◽  
Cancer Treatment ◽  
Prostate Specific Antigen ◽  
Cancer Biology ◽  
Early Stage ◽  
Specific Antigen ◽  
Detection Methods ◽  
Hormone Refractory Prostate Cancer ◽  
High Risk Prostate Cancer ◽  
Hormone Refractory

Cancer of the prostate are cancers in which most incidences are slow-growing, and in the U.S., a record of 1.2 million new cases of prostate cancer occurred in 2018. The rates of this type of cancer have been increasing in developing nations. The risk factors for prostate cancer include age, family history, and obesity. It is believed that the rate of prostate cancer is correlated with the Western diet. Various advances in methods of radiotherapy have contributed to lowering morbidity. Therapy for hormone- refractory prostate cancer is making progress, for almost all men with metastases will proceed to hormone-refractory prostate cancer. Smoking cigarettes along with the presence of prostate cancer has been shown to cause a higher risk of mortality in prostate cancer. The serious outcome of incontinence and erectile dysfunction result from the cancer treatment of surgery and radiation, particularly for prostate- specific antigen detected cancers that will not cause morbidity or mortality. Families of patients, as well as patients, are profoundly affected following the diagnosis of prostate cancer. Poor communication between spouses during prostate cancer increases the risk for poor adjustment to prostate cancer. The use of serum prostate-specific antigen to screen for prostate cancer has led to a greater detection, in its early stage, of this cancer. Prostate cancer is the most common malignancy in American men, accounting for more than 29% of all diagnosed cancers and about 13% of all cancer deaths. A shortened course of hormonal therapy with docetaxel following radical prostatectomy (or radiation therapy) for high-risk prostate cancer has been shown to be both safe and feasible. Patients treated with docetaxel-estramustine had a prostate-specific antigen response decline of at least 50%. Cancer vaccines are an immune-based cancer treatment that may provide the promise of a non-toxic but efficacious therapeutic alternative for cancer patients. Further studies will elucidate improved methods of detection and treatment.

Development of Prediction Models Using Machine Learning Algorithms for Girls with Suspected Central Precocious Puberty: Retrospective Study (Preprint)

2018 ◽  
Author(s):  
Liyan Pan ◽  
Guangjian Liu ◽  
Xiaojian Mao ◽  
Huixian Li ◽  
Jiexin Zhang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Retrospective Study ◽  
Random Forest ◽  
Precocious Puberty ◽  
Prediction Models ◽  
Central Precocious Puberty ◽  
Machine Learning Algorithms ◽  
Stimulation Test ◽  
Gnrh Analogue ◽  
Prediction Probability

BACKGROUND Central precocious puberty (CPP) in girls seriously affects their physical and mental development in childhood. The method of diagnosis—gonadotropin-releasing hormone (GnRH)–stimulation test or GnRH analogue (GnRHa)–stimulation test—is expensive and makes patients uncomfortable due to the need for repeated blood sampling. OBJECTIVE We aimed to combine multiple CPP–related features and construct machine learning models to predict response to the GnRHa-stimulation test. METHODS In this retrospective study, we analyzed clinical and laboratory data of 1757 girls who underwent a GnRHa test in order to develop XGBoost and random forest classifiers for prediction of response to the GnRHa test. The local interpretable model-agnostic explanations (LIME) algorithm was used with the black-box classifiers to increase their interpretability. We measured sensitivity, specificity, and area under receiver operating characteristic (AUC) of the models. RESULTS Both the XGBoost and random forest models achieved good performance in distinguishing between positive and negative responses, with the AUC ranging from 0.88 to 0.90, sensitivity ranging from 77.91% to 77.94%, and specificity ranging from 84.32% to 87.66%. Basal serum luteinizing hormone, follicle-stimulating hormone, and insulin-like growth factor-I levels were found to be the three most important factors. In the interpretable models of LIME, the abovementioned variables made high contributions to the prediction probability. CONCLUSIONS The prediction models we developed can help diagnose CPP and may be used as a prescreening tool before the GnRHa-stimulation test.

scholarly journals Development of Machine Learning Models for Prediction of Smoking Cessation Outcome

2021 ◽  
Vol 18 (5) ◽  
pp. 2584
Author(s):  
Cheng-Chien Lai ◽  
Wei-Hsin Huang ◽  
Betty Chia-Chen Chang ◽  
Lee-Ching Hwang
Keyword(s):  
Machine Learning ◽  
Smoking Cessation ◽  
Success Rate ◽  
Prediction Models ◽  
Smoking Status ◽  
Medical Center ◽  
Machine Learning Algorithms ◽  
Classification And Regression Tree ◽  
Support Vector ◽  
Smoking Cessation Outcome

Predictors for success in smoking cessation have been studied, but a prediction model capable of providing a success rate for each patient attempting to quit smoking is still lacking. The aim of this study is to develop prediction models using machine learning algorithms to predict the outcome of smoking cessation. Data was acquired from patients underwent smoking cessation program at one medical center in Northern Taiwan. A total of 4875 enrollments fulfilled our inclusion criteria. Models with artificial neural network (ANN), support vector machine (SVM), random forest (RF), logistic regression (LoR), k-nearest neighbor (KNN), classification and regression tree (CART), and naïve Bayes (NB) were trained to predict the final smoking status of the patients in a six-month period. Sensitivity, specificity, accuracy, and area under receiver operating characteristic (ROC) curve (AUC or ROC value) were used to determine the performance of the models. We adopted the ANN model which reached a slightly better performance, with a sensitivity of 0.704, a specificity of 0.567, an accuracy of 0.640, and an ROC value of 0.660 (95% confidence interval (CI): 0.617–0.702) for prediction in smoking cessation outcome. A predictive model for smoking cessation was constructed. The model could aid in providing the predicted success rate for all smokers. It also had the potential to achieve personalized and precision medicine for treatment of smoking cessation.

Sign in / Sign up

Export Citation Format

Share Document