scholarly journals Machine learning algorithm for early mortality prediction in patients with advanced penile cancer

2020 ◽  
Author(s):  
Robert Chen ◽  
Matthew R Kudelka ◽  
Aaron M Rosado ◽  
James Zhang
Keyword(s):  
Machine Learning ◽  
Overall Survival ◽  
Penile Cancer ◽  
Learning Algorithm ◽  
Stage Iv ◽  
The United States ◽  
Lymph Node Biopsy ◽  
Mortality Prediction ◽  
Early Mortality ◽  
Multivariate Logistic Regression Model

ABSTRACTPenile cancer remains a rare cancer with an annual incidence of 1 in 100,000 men in the United States, accounting for 0.4-0.6% of all malignancies. Furthermore, to date there are no predictive models of early mortality in penile cancer. Meanwhile, machine learning has potential to serve as a prognostic tool for patients with advanced disease.We developed a machine learning model for predicting early mortality in penile cancer (survival less than 11 months after initial diagnosis. A cohort of 88 patients with advanced penile cancer was extracted from the Surveillance, Epidemiology and End Results (SEER) program. In the cohort, patients with advanced penile cancer exhibited a median overall survival of 21 months, with the 25th percentile of overall survival being 11 months. We constructed predictive features based on patient demographics, staging, metastasis, lymph node biopsy criteria, and metastatic sites. We trained a multivariate logistic regression model, tuning parameters with respect to regularization, and feature selection criteria.Upon evaluation with 5-fold cross validation, our model achieved 68.2% accuracy with AUC 0.696. Criteria for advanced staging (T4, group stage IV), as well as higher age, white race and squamous cell histology, were the most predictive of early mortality. Tumor size was the strongest negative predictor of early mortality.Our study showcases the first known predictive model for early mortality in patients with advanced penile cancer and should serve as a framework for approaching the clinical problem in future studies. Future work should aim to incorporate other data sources such as genomic and metabolomic data, increase patient counts, incorporate clinical characteristics such as ECOG and RECIST criteria, and assess the performance of the model in a prospective fashion.

Personalized stratification of back to work risk amidst COVID-19: A machine learning approach (Preprint)

2020 ◽  
Author(s):  
Carson Lam ◽  
Jacob Calvert ◽  
Gina Barnes ◽  
Emily Pellegrini ◽  
Anna Lynn-Palevsky ◽  
...  
Keyword(s):  
Machine Learning ◽  
High Risk ◽  
Learning Algorithm ◽  
Severe Disease ◽  
High Specificity ◽  
Population Level ◽  
The United States ◽  
Health Condition ◽  
Available P ◽  
Severe Illness

BACKGROUND In the wake of COVID-19, the United States has developed a three stage plan to outline the parameters to determine when states may reopen businesses and ease travel restrictions. The guidelines also identify subpopulations of Americans that should continue to stay at home due to being at high risk for severe disease should they contract COVID-19. These guidelines were based on population level demographics, rather than individual-level risk factors. As such, they may misidentify individuals at high risk for severe illness and who should therefore not return to work until vaccination or widespread serological testing is available. OBJECTIVE This study evaluated a machine learning algorithm for the prediction of serious illness due to COVID-19 using inpatient data collected from electronic health records. METHODS The algorithm was trained to identify patients for whom a diagnosis of COVID-19 was likely to result in hospitalization, and compared against four U.S policy-based criteria: age over 65, having a serious underlying health condition, age over 65 or having a serious underlying health condition, and age over 65 and having a serious underlying health condition. RESULTS This algorithm identified 80% of patients at risk for hospitalization due to COVID-19, versus at most 62% that are identified by government guidelines. The algorithm also achieved a high specificity of 95%, outperforming government guidelines. CONCLUSIONS This algorithm may help to enable a broad reopening of the American economy while ensuring that patients at high risk for serious disease remain home until vaccination and testing become available.

scholarly journals Gastric Cancer Treatments and Survival Trends in the United States

2020 ◽  
Vol 28 (1) ◽  
pp. 138-151
Author(s):  
Kelly A. Stahl ◽  
Elizabeth J. Olecki ◽  
Matthew E. Dixon ◽  
June S. Peng ◽  
Madeline B. Torres ◽  
...  
Keyword(s):  
Gastric Cancer ◽  
Overall Survival ◽  
Stage Iv ◽  
The United States ◽  
Current Treatment ◽  
Stage I ◽  
Stage Ii ◽  
Chi Square ◽  
Specific Guideline ◽  
Kaplan Meier

Gastric cancer is the third most common cause of cancer deaths worldwide. Despite evidence-based recommendation for treatment, the current treatment patterns for all stages of gastric cancer remain largely unexplored. This study investigates trends in the treatments and survival of gastric cancer. The National Cancer Database was used to identify gastric adenocarcinoma patients from 2004–2016. Chi-square tests were used to examine subgroup differences between disease stages: Stage I, II/III and IV. Multivariate analyses identified factors associated with the receipt of guideline concordant care. The Kaplan–Meier method was used to assess three-year overall survival. The final cohort included 108,150 patients: 23,584 Stage I, 40,216 Stage II/III, and 44,350 Stage IV. Stage specific guideline concordant care was received in only 73% of patients with Stage I disease and 51% of patients with Stage II/III disease. Patients who received guideline consistent care had significantly improved survival compared to those who did not. Overall, we found only moderate improvement in guideline adherence and three-year overall survival during the 13-year study time period. This study showed underutilization of stage specific guideline concordant care for stage I and II/III disease.

scholarly journals Machine learning based predictive model of early mortality in stage III and IV prostate cancer

2020 ◽  
Author(s):  
Robert Chen
Keyword(s):  
Prostate Cancer ◽  
Machine Learning ◽  
Cancer Survival ◽  
Stage Iv ◽  
Clinical Decision ◽  
Early Mortality ◽  
Stage Iii ◽  
Clinical Endpoints ◽  
Metabolomic Data ◽  
Metastatic Sites

AbstractProstate cancer remains the third highest cause of cancer-related deaths. Metastatic prostate cancer could yield poor prognosis, however there is limited work on predictive models for clinical decision support in stage III and IV prostate cancer.We developed a machine learning model for predicting early mortality in prostate cancer (survival less than 21 months after initial diagnosis). A cohort of 10,303 patients was extracted from the Surveillance, Epidemiology and End Results (SEER) program. Features were constructed in several domains including demographics, histology of primary tumor, and metastatic sites. Feature selection was performed followed by regularized logistic regression. The model was evaluated using 5-fold cross validation and achieved 75.2% accuracy with AUC 0.649. Of the 19 most predictive features, all of them were validated to be clinically meaningful for prediction of early mortality.Our study serves as a framework for prediction of early mortality in patients with stage II and stage IV prostate cancer, and can be generalized to predictive modeling problems for other relevant clinical endpoints. Future work should involve integration of other data sources such as electronic health record and genomic or metabolomic data.

scholarly journals Clinicopathological Features, Staging, and Current Approaches to Treatment in High-Risk Resectable Melanoma

2020 ◽  
Vol 112 (9) ◽  
pp. 875-885 ◽  
Author(s):  
Emily Z Keung ◽  
Jeffrey E Gershenwald
Keyword(s):  
Lymph Node ◽  
High Risk ◽  
Regional Lymph Node ◽  
Stage Iv ◽  
Staging System ◽  
The United States ◽  
Immune Checkpoint Blockade ◽  
Lymph Node Biopsy ◽  
Clinicopathological Features ◽  
Disease Stage

Abstract The incidence of melanoma in the United States has been increasing over the past several decades. Prognosis largely depends on disease stage, with 5-year melanoma-specific survival ranging from as high as 99% in patients with stage I disease to less than 10% for some patients with stage IV (distant metastatic) disease. Fortunately, in the last 5–10 years, there have been remarkable treatment advances for patients with high-risk resectable melanoma, including approval of targeted and immune checkpoint blockade therapies. In addition, results of recent clinical trials have confirmed the importance of sentinel lymph node biopsy and continue to refine the approach to regional lymph node basin management. Lastly, the melanoma staging system was revised in the eighth edition AJCC Cancer Staging Manual, which was implemented on January 1, 2018. Here we discuss these changes and the clinicopathological features that confer high risk for locoregional and distant disease relapse and poor survival. Implications regarding the management of melanoma in the metastatic and adjuvant settings are discussed, as are future directions for neoadjuvant therapies.

Immunotherapy disparities in metastatic melanoma.

2019 ◽  
Vol 37 (15_suppl) ◽  
pp. 9525-9525 ◽  
Author(s):  
Thomas Oliver ◽  
Todd A. Pezzi ◽  
Ashley E. Pezzi ◽  
Amanda Shreders ◽  
Henry Dao ◽  
...  
Keyword(s):  
Overall Survival ◽  
Metastatic Melanoma ◽  
Median Overall Survival ◽  
Stage Iv ◽  
Therapy Response ◽  
Subsequent Development ◽  
The United States ◽  
Community Practice ◽  
Term Survival ◽  
Dismal Prognosis

9525 Background: Historically, patients with advanced malignant melanoma had a dismal prognosis with an estimated median overall survival of nine months. Therapy response rates and long-term survival have significantly improved with the advent of immunotherapies and targeted chemotherapies. First approved in 2011, there has been subsequent development of more advanced immunotherapeutic agents and targeted chemotherapies, with continued improvement in median overall survival. We examined patterns in the use of immunotherapy and other systemic therapies for metastatic melanoma, as well as the demographic and socioeconomic predictors for the use of these therapies, in order to identify and understand potential barriers to access in the United States. Methods: We used the NCDB for all patients aged 18-years and older who were diagnosed with metastatic melanoma of cutaneous origin from 2004-2014. Patients were included if they had distant metastases or American Joint Committee on Cancer (AJCC) Stage IV. Sociodemographic data, including race, age, insurance status, facility providing care, Charlson/Deyo comorbidity score11, and education by patient’s zip code, were collected. Results: In patients under age 65 with a Charlson-Deyo score of zero, immunotherapy utilization ranged between 8.5–13.4% during 2004 to 2010. In 2011, the usage increased to 16.5% and rose every subsequent year to 29.6% in 2014. Patients were less likely to receive immunotherapy if they had no insurance, were of older age, or received care at a community practice rather than an academic center. Those who received immunotherapy had greater overall survival compared with those who did not. Conclusions: Immunotherapy and targeted agents have become standard of care in those with metastatic melanoma. Adoption of immunotherapy use for metastatic melanoma has been relatively slow despite evidence showing an overall survival benefit; our analysis suggests this is explained in part by socioeconomic barriers.

Racial disparities in the outcomes of transitional cell carcinoma of the bladder: A population-based analysis.

2020 ◽  
Vol 38 (6_suppl) ◽  
pp. 577-577
Author(s):  
Firas Baidoun ◽  
Inas A. Ruhban ◽  
Anas M. Saad ◽  
Mohamed M. Gad ◽  
Khalid Jazieh ◽  
...  
Keyword(s):  
Overall Survival ◽  
Bladder Cancer ◽  
Transitional Cell Carcinoma ◽  
Racial Disparities ◽  
Cell Carcinoma ◽  
Transitional Cell ◽  
Stage Iv ◽  
The United States ◽  
Pacific Islanders ◽  
The Us

577 Background: Bladder cancer is the most common type of genitourinary malignancy and is the fourth most common cancer in men in the US. Transitional cell carcinoma (TCC) of the bladder accounts for most bladder cancer cases. Previous studies have observed racial disparities in the prognosis between white and black populations with very little mentioned about other ethnicities and race groups that are part of the United States population. We hereby, present a detailed and comprehensive analysis of racial disparities in TCC survival in the US. Methods: Using the data from surveillance Epidemiology and End results (SEER) database, we identified patients with TCC between 1992 and 2015. We used multivariable covariate-adjusted Cox models to analyze the overall and TCC-specific survival of patients according to their race. Results: We evaluated 176,388 patients with TCC and after we adjusted for age, sex, race, stage, grade, and undergoing cancer-targeted surgery, we found that Asians/Pacific Islanders and Hispanics had a better overall survival when compared to whites (HR= 0.792, 95% CI [0.761-0.824], P<.001 and HR = 0.941, 95% CI [0.909-0.974], P = .001, respectively). Asians/Pacific Islanders also showed better TCC specific survival (HR = 0.843, 95% CI [0.759-0.894], P<.001). Blacks had worse overall survival and TCC-specific survival (HR =1.221, 95% CI [1.181-1.262], P <.001 and HR =1.325, 95% CI [1.268- 1.384], P <.001, respectively). When stage IV TCC was analyzed separately, only Hispanics showed better overall and TCC specific survival when compared to whites (HR = 0.896, 95% CI [0.806-0.997], P = 0.044 and HR = 0.891, 95% CI [0.797-0.996], P = 0.42). Conclusions: Asians/Pacific Islanders have better overall and TCC-specific outcome while blacks have the worst outcome compared to whites. Hispanics have better overall and cancer specific survival in stage IV TCC. These disparities likely related to different and complex factors from lifestyle and chemical exposure to genetic factors. Further studies can help us more in understanding and approaching this malignancy in different race groups.

Machine learning based early mortality prediction in the emergency department

2021 ◽  
pp. 104570
Author(s):  
Cong Li ◽  
Zhuo Zhang ◽  
Yazhou Ren ◽  
Hu Nie ◽  
Yuqing Lei ◽  
...  
Keyword(s):  
Machine Learning ◽  
Emergency Department ◽  
Mortality Prediction ◽  
Early Mortality

scholarly journals Early mortality of stage IV non-small cell lung cancer in the United States

2019 ◽  
Vol 58 (8) ◽  
pp. 1095-1101 ◽  
Author(s):  
Arya Amini ◽  
Vivek Verma ◽  
Scott M. Glaser ◽  
Ashwin Shinde ◽  
Sagus Sampath ◽  
...  
Keyword(s):  
United States ◽  
Lung Cancer ◽  
Small Cell Lung Cancer ◽  
Cell Lung Cancer ◽  
Stage Iv ◽  
The United States ◽  
Small Cell ◽  
Early Mortality ◽  
Small Cell Lung

scholarly journals Predicting in-Hospital Mortality of Patients with COVID-19 Using Machine Learning Techniques

2021 ◽  
Vol 11 (5) ◽  
pp. 343
Author(s):  
Fabiana Tezza ◽  
Giulia Lorenzoni ◽  
Danila Azzolina ◽  
Sofia Barbar ◽  
Lucia Anna Carmela Leone ◽  
...  
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Hospital Mortality ◽  
Learning Algorithm ◽  
Vital Signs ◽  
Mortality Prediction ◽  
Machine Learning Techniques ◽  
Gradient Boosting ◽  
Support Vector ◽  
Learning Techniques

The present work aims to identify the predictors of COVID-19 in-hospital mortality testing a set of Machine Learning Techniques (MLTs), comparing their ability to predict the outcome of interest. The model with the best performance will be used to identify in-hospital mortality predictors and to build an in-hospital mortality prediction tool. The study involved patients with COVID-19, proved by PCR test, admitted to the “Ospedali Riuniti Padova Sud” COVID-19 referral center in the Veneto region, Italy. The algorithms considered were the Recursive Partition Tree (RPART), the Support Vector Machine (SVM), the Gradient Boosting Machine (GBM), and Random Forest. The resampled performances were reported for each MLT, considering the sensitivity, specificity, and the Receiving Operative Characteristic (ROC) curve measures. The study enrolled 341 patients. The median age was 74 years, and the male gender was the most prevalent. The Random Forest algorithm outperformed the other MLTs in predicting in-hospital mortality, with a ROC of 0.84 (95% C.I. 0.78–0.9). Age, together with vital signs (oxygen saturation and the quick SOFA) and lab parameters (creatinine, AST, lymphocytes, platelets, and hemoglobin), were found to be the strongest predictors of in-hospital mortality. The present work provides insights for the prediction of in-hospital mortality of COVID-19 patients using a machine-learning algorithm.

scholarly journals Development of an electronic frailty index for predicting mortality in patients undergoing transcatheter aortic valve replacement using machine learning

2020 ◽  
Author(s):  
Yiyi Chen ◽  
Jiandong Zhou ◽  
Sharen Lee ◽  
Tong Liu ◽  
Sandeep S Hothi ◽  
...  
Keyword(s):  
Machine Learning ◽  
Cox Regression ◽  
Learning Algorithm ◽  
Frailty Index ◽  
Mortality Prediction ◽  
Frailty Models ◽  
Gradient Boosting ◽  
Cumulative Number ◽  
Analysis Model ◽  
All Cause Mortality

AbstractBackgroundElectronic frailty indices can be useful surrogate measures of frailty. We assessed the role of machine learning to develop an electronic frailty index, incorporating demographics, baseline comorbidities, healthcare utilization characteristics, electrocardiographic measurements, and laboratory examinations, and used this to predict all-cause mortality in patients undergoing transaortic valvular replacement (TAVR).MethodsThis was a multi-centre retrospective observational study of patients undergoing for TAVR. Significant univariate and multivariate predictors of all-cause mortality were identified using Cox regression. Importance ranking of variables was obtained with a gradient boosting survival tree (GBST) model, a supervised sequential ensemble learning algorithm, and used to build the frailty models. Comparisons were made between multivariate Cox, GBST and random survival forest models.ResultsA total of 450 patients (49% females; median age at procedure 82.3 (interquartile range, IQR 79.0-86.0)) were included, of which 22 died during follow-up. A machine learning survival analysis model found that the most important predictors of mortality were APTT, followed by INR, severity of tricuspid regurgitation, cumulative hospital stays, cumulative number of readmissions, creatinine, urate, ALP, and QTc/QT intervals. GBST significantly outperformed random survival forests and multivariate Cox regression (precision: 0.91, recall: 0.89, AUC: 0.93, C-index: 0.96, and KS-index: 0.50) for mortality prediction.ConclusionsAn electronic frailty index incorporating multi-domain data can efficiently predict all-cause mortality in patients undergoing TAVR. A machine learning survival learning model significantly improves the risk prediction performance of the frailty models.

Sign in / Sign up

Export Citation Format

Share Document