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

Lee, Changhee; Light, Alexander; Alaa, Ahmed M.; Thurtle, David; Schaar, Mihaela van der; Gnanapragasam, Vincent

doi:10.1016/s2589-7500(20)30314-9

Cited by 79 publications

(66 citation statements)

References 30 publications

(52 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DCA was performed for four machine learning models in the testing data set to compare the net benefit of the best model and alternative approaches for clinical decision-making. Clinical net benefit is defined as the minimum probability of disease, when further intervention would be warranted [ 28 ]. The plot measures the net benefit at different threshold probabilities.…”

Section: Resultsmentioning

confidence: 99%

Predicting Mortality in Intensive Care Unit Patients With Heart Failure Using an Interpretable Machine Learning Model: Retrospective Cohort Study

Li¹,

Liu²,

Hu³

et al. 2022

J Med Internet Res

View full text Add to dashboard Cite

Background Heart failure (HF) is a common disease and a major public health problem. HF mortality prediction is critical for developing individualized prevention and treatment plans. However, due to their lack of interpretability, most HF mortality prediction models have not yet reached clinical practice. Objective We aimed to develop an interpretable model to predict the mortality risk for patients with HF in intensive care units (ICUs) and used the SHapley Additive exPlanation (SHAP) method to explain the extreme gradient boosting (XGBoost) model and explore prognostic factors for HF. Methods In this retrospective cohort study, we achieved model development and performance comparison on the eICU Collaborative Research Database (eICU-CRD). We extracted data during the first 24 hours of each ICU admission, and the data set was randomly divided, with 70% used for model training and 30% used for model validation. The prediction performance of the XGBoost model was compared with three other machine learning models by the area under the curve. We used the SHAP method to explain the XGBoost model. Results A total of 2798 eligible patients with HF were included in the final cohort for this study. The observed in-hospital mortality of patients with HF was 9.97%. Comparatively, the XGBoost model had the highest predictive performance among four models with an area under the curve (AUC) of 0.824 (95% CI 0.7766-0.8708), whereas support vector machine had the poorest generalization ability (AUC=0.701, 95% CI 0.6433-0.7582). The decision curve showed that the net benefit of the XGBoost model surpassed those of other machine learning models at 10%~28% threshold probabilities. The SHAP method reveals the top 20 predictors of HF according to the importance ranking, and the average of the blood urea nitrogen was recognized as the most important predictor variable. Conclusions The interpretable predictive model helps physicians more accurately predict the mortality risk in ICU patients with HF, and therefore, provides better treatment plans and optimal resource allocation for their patients. In addition, the interpretable framework can increase the transparency of the model and facilitate understanding the reliability of the predictive model for the physicians.

show abstract

Section: Resultsmentioning

confidence: 99%

Predicting Mortality in Intensive Care Unit Patients With Heart Failure Using an Interpretable Machine Learning Model: Retrospective Cohort Study

Li¹,

Liu²,

Hu³

et al. 2022

J Med Internet Res

View full text Add to dashboard Cite

show abstract

“…In this model (Survival Quilts), an algorithm automatically tunes and selects ensembles of survival models based on clinical-pathological parameters using the Surveillance, Epidemiology, and End Results (SEER) datasheet. Data have been collected from (approximately) 30% of the US population, especially from men aged 35–95 years ( Adamo et al, 2016 ; Lee et al, 2021 ). Survival Quilts is open-source software designed to mechanize the operation of machine learning in estimating survival rates.…”

Section: Natural Products For the Treatment Management Of Castration-resistant Prostate Cancermentioning

confidence: 99%

Natural Product-Based Studies for the Management of Castration-Resistant Prostate Cancer: Computational to Clinical Studies

Singla

Sharma

Dubey³

et al. 2021

Front. Pharmacol.

View full text Add to dashboard Cite

Background: With prostate cancer being the fifth-greatest cause of cancer mortality in 2020, there is a dire need to expand the available treatment options. Castration-resistant prostate cancer (CRPC) progresses despite androgen depletion therapy. The mechanisms of resistance are yet to be fully discovered. However, it is hypothesized that androgens depletion enables androgen-independent cells to proliferate and recolonize the tumor.Objectives: Natural bioactive compounds from edible plants and herbal remedies might potentially address this need. This review compiles the available cheminformatics-based studies and the translational studies regarding the use of natural products to manage CRPC.Methods: PubMed and Google Scholar searches for preclinical studies were performed, while ClinicalTrials.gov and PubMed were searched for clinical updates. Studies that were not in English and not available as full text were excluded. The period of literature covered was from 1985 to the present.Results and Conclusion: Our analysis suggested that natural compounds exert beneficial effects due to their broad-spectrum molecular disease-associated targets. In vitro and in vivo studies revealed several bioactive compounds, including rutaecarpine, berberine, curcumin, other flavonoids, pentacyclic triterpenoids, and steroid-based phytochemicals. Molecular modeling tools, including machine and deep learning, have made the analysis more comprehensive. Preclinical and clinical studies on resveratrol, soy isoflavone, lycopene, quercetin, and gossypol have further validated the translational potential of the natural products in the management of prostate cancer.

show abstract

“…This discovery aids in detecting a person's risk of cancer at such an initial phase of treatment. Changhee et al [8] developed a better prognosis model based on machine learning named Survival Quilts. This model is being developed on the 10-year data of US prostate cancer patients to predict their mortality rate.…”

Section: Related Research Workmentioning

confidence: 99%

Comparative Analysis of Data Mining Algorithms for Cancer Gene Expression Data

Thareja¹,

Chhillar²

2021

IJACSA

View full text Add to dashboard Cite

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

Cited by 79 publications

References 30 publications

Predicting Mortality in Intensive Care Unit Patients With Heart Failure Using an Interpretable Machine Learning Model: Retrospective Cohort Study

Predicting Mortality in Intensive Care Unit Patients With Heart Failure Using an Interpretable Machine Learning Model: Retrospective Cohort Study

Natural Product-Based Studies for the Management of Castration-Resistant Prostate Cancer: Computational to Clinical Studies

Comparative Analysis of Data Mining Algorithms for Cancer Gene Expression Data

Contact Info

Product

Resources

About