Study of Complex-valued Learning algorithms for Post-surgery survival prediction

2016 ◽  
Author(s):  
Sivachitra Muthusamy ◽  
Savitha Ramasamy
Keyword(s):  
Learning Algorithms ◽  
Survival Prediction ◽  
Post Surgery ◽  
Complex Valued

scholarly journals A Machine Learning Tool to Predict the Response to Neoadjuvant Chemotherapy in Patients with Locally Advanced Cervical Cancer

2021 ◽  
Vol 11 (2) ◽  
pp. 823
Author(s):  
Francesca Arezzo ◽  
Daniele La Forgia ◽  
Vincenzo Venerito ◽  
Marco Moschetta ◽  
Alberto Stefano Tagliafico ◽  
...  
Keyword(s):  
Machine Learning ◽  
Cervical Cancer ◽  
Neoadjuvant Chemotherapy ◽  
Learning Algorithms ◽  
Locally Advanced ◽  
Machine Learning Algorithms ◽  
Advanced Cervical Cancer ◽  
Locally Advanced Cervical Cancer ◽  
Post Surgery ◽  
Core Set

Despite several studies having identified factors associated with successful treatment outcomes in locally advanced cervical cancer, there is the lack of accurate predictive modeling for progression-free survival (PFS) in patients who undergo radical hysterectomy after neoadjuvant chemotherapy (NACT). Here we investigated whether machine learning (ML) may have the potential to provide a tool to predict neoadjuvant treatment response as PFS. In this retrospective observational study, we analyzed patients with locally advanced cervical cancer (FIGO stages IB2, IB3, IIA1, IIA2, IIB, and IIIC1) who were followed in a tertiary center from 2010 to 2018. Demographic and clinical characteristics were collected at either treatment baseline or at 24-month follow-up. Furthermore, we recorded data about magnetic resonance imaging (MRI) examinations and post-surgery histopathology. Proper feature selection was used to determine an attribute core set. Three different machine learning algorithms, namely Logistic Regression (LR), Random Forest (RFF), and K-nearest neighbors (KNN), were then trained and validated with 10-fold cross-validation to predict 24-month PFS. Our analysis included n. 92 patients. The attribute core set used to train machine learning algorithms included the presence/absence of fornix infiltration at pre-treatment MRI as well as of either parametrium invasion and lymph nodes involvement at post-surgery histopathology. RFF showed the best performance (accuracy 82.4%, precision 83.4%, recall 96.2%, area under receiver operating characteristic curve (AUROC) 0.82). We developed an accurate ML model to predict 24-month PFS.

scholarly journals A Machine Learning-Based Investigation of Gender-Specific Prognosis of Lung Cancers

Medicina ◽  
2021 ◽  
Vol 57 (2) ◽  
pp. 99
Author(s):  
Yueying Wang ◽  
Shuai Liu ◽  
Zhao Wang ◽  
Yusi Fan ◽  
Jingxuan Huang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Lung Cancer ◽  
Learning Algorithms ◽  
Primary Lung Cancer ◽  
Machine Learning Algorithms ◽  
Survival Prediction ◽  
Cancer Type ◽  
Lung Cancers ◽  
One Year ◽  
Gender Specific

Background and Objective: Primary lung cancer is a lethal and rapidly-developing cancer type and is one of the most leading causes of cancer deaths. Materials and Methods: Statistical methods such as Cox regression are usually used to detect the prognosis factors of a disease. This study investigated survival prediction using machine learning algorithms. The clinical data of 28,458 patients with primary lung cancers were collected from the Surveillance, Epidemiology, and End Results (SEER) database. Results: This study indicated that the survival rate of women with primary lung cancer was often higher than that of men (p < 0.001). Seven popular machine learning algorithms were utilized to evaluate one-year, three-year, and five-year survival prediction The two classifiers extreme gradient boosting (XGB) and logistic regression (LR) achieved the best prediction accuracies. The importance variable of the trained XGB models suggested that surgical removal (feature “Surgery”) made the largest contribution to the one-year survival prediction models, while the metastatic status (feature “N” stage) of the regional lymph nodes was the most important contributor to three-year and five-year survival prediction. The female patients’ three-year prognosis model achieved a prediction accuracy of 0.8297 on the independent future samples, while the male model only achieved the accuracy 0.7329. Conclusions: This data suggested that male patients may have more complicated factors in lung cancer than females, and it is necessary to develop gender-specific diagnosis and prognosis models.

scholarly journals Survival prediction for bladder cancer using machine learning: development of BlaCaSurv online survival prediction application

2020 ◽  
Author(s):  
Ashis Kumar Das ◽  
Shiba Mishra ◽  
Devi Kalyan Mishra ◽  
Saji Saraswathy Gopalan
Keyword(s):  
Machine Learning ◽  
Bladder Cancer ◽  
Cancer Patients ◽  
Web Application ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Gradient Boosting ◽  
Support Vector ◽  
Survival Prediction ◽  
Common Cause

AbstractBackgroundBladder cancer is the most common cancer of the urinary system among the American population and it is the fourth most common cause of cancer morbidity and the eight most common cause of cancer mortality among men. Using machine learning algorithms, we predict the five-year survival among bladder cancer patients and deploy the best performing algorithm as a web application for survival prediction.MethodsMicroscopically confirmed adult bladder cancer patients were included from the Surveillance Epidemiology and End Results (SEER) database (2000-2017) and randomly split into training and test datasets (70/30 ratio). Five machine learning algorithms (logistic regression, support vector machine, gradient boosting, random forest, and K nearest neighbor) were trained on features to predict five-year survival. The algorithms were compared with performance metrics and the best performing algorithm was deployed as a web application.ResultsA total of 52,529 patients were included in our study. The gradient boosting algorithm was the best performer in terms of predictive ability and discrimination. It was deployed as the survival prediction web application named BlaCaSurv (https://blacasurv.herokuapp.com/).ConclusionsWe tested several machine learning algorithms and developed a web application for predicting five-year survival for bladder cancer patients. This application can be used as a supplementary prognostic tool to clinical decision making.

scholarly journals Patient Survival Prediction with Machine Learning Algorithms

2020 ◽  
pp. 93-96
Author(s):  
Mustafa Berkant Selek ◽  
Saadet Sena Egeli ◽  
Yalcin Isler
Keyword(s):  
Machine Learning ◽  
Intensive Care ◽  
Cross Validation ◽  
Patient Survival ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Survival Prediction ◽  
Accuracy Rate ◽  
Intensive Care Patients ◽  
One Year

In this study, the intensive care unit patient survival is predicted by machine learning algorithms according to the examinations performed in the first 24 hours. The data of intensive care patients collected from approximately two hundred hospitals over a period of one year were used. Algorithms are run in Python environment. Machine learning models were compared with the Cross-Validation method, and the random forest algorithm is used. The model made the prediction with 92,53% accuracy rate.

scholarly journals An Online Calculator for the Prediction of Survival in Glioblastoma Patients Using Classical Statistics and Machine Learning

Neurosurgery ◽  
2019 ◽  
Vol 86 (2) ◽  
pp. E184-E192 ◽  
Author(s):  
Joeky T Senders ◽  
Patrick Staples ◽  
Alireza Mehrtash ◽  
David J Cote ◽  
Martin J B Taphoorn ◽  
...  
Keyword(s):  
Machine Learning ◽  
Computational Efficiency ◽  
Failure Time ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Superior Performance ◽  
Accelerated Failure Time Model ◽  
Survival Prediction ◽  
Prediction Tools ◽  
Classical Statistics

Abstract BACKGROUND Although survival statistics in patients with glioblastoma multiforme (GBM) are well-defined at the group level, predicting individual patient survival remains challenging because of significant variation within strata. OBJECTIVE To compare statistical and machine learning algorithms in their ability to predict survival in GBM patients and deploy the best performing model as an online survival calculator. METHODS Patients undergoing an operation for a histopathologically confirmed GBM were extracted from the Surveillance Epidemiology and End Results (SEER) database (2005-2015) and split into a training and hold-out test set in an 80/20 ratio. Fifteen statistical and machine learning algorithms were trained based on 13 demographic, socioeconomic, clinical, and radiographic features to predict overall survival, 1-yr survival status, and compute personalized survival curves. RESULTS In total, 20 821 patients met our inclusion criteria. The accelerated failure time model demonstrated superior performance in terms of discrimination (concordance index = 0.70), calibration, interpretability, predictive applicability, and computational efficiency compared to Cox proportional hazards regression and other machine learning algorithms. This model was deployed through a free, publicly available software interface (https://cnoc-bwh.shinyapps.io/gbmsurvivalpredictor/). CONCLUSION The development and deployment of survival prediction tools require a multimodal assessment rather than a single metric comparison. This study provides a framework for the development of prediction tools in cancer patients, as well as an online survival calculator for patients with GBM. Future efforts should improve the interpretability, predictive applicability, and computational efficiency of existing machine learning algorithms, increase the granularity of population-based registries, and externally validate the proposed prediction tool.

scholarly journals Prognostic value of the dynamic change of platelets to lymphocytes ratio and neutrophil to lymphocyte ratio for gastric cancer patients receiving curative surgery.

2020 ◽  
Author(s):  
Shiva Basnet ◽  
Nan Liu ◽  
Qixin Jiang ◽  
Hai Dan Lan ◽  
Mamata Khadka ◽  
...  
Keyword(s):  
Gastric Cancer ◽  
Prognostic Factors ◽  
Categorical Data ◽  
Neutrophil To Lymphocyte Ratio ◽  
Receiver Operating Curve ◽  
P Value ◽  
Survival Prediction ◽  
Cox Regression Analysis ◽  
Lymphocyte Ratio ◽  
Post Surgery

Abstract Background: The inflammatory biomarkers play a prominent role in tumorigenesis and progression of gastric cancer. Inflammatory response has shown to be promising candidate for monitoring the survival prediction in various cancer. Certain percent of cancer related deaths are closely associated with chronic inflammation. Our study aims to focus a precise estimation on the prognostic significance of preoperative Neutrophil to Lymphocyte ratio (NLR), Platelets to Lymphocyte ratio (PLR), derived Neutrophil to Lymphocyte ratio (ΔNLR) and derived Platelet to Lymphocyte ratio (ΔPLR) following gastric cancer.Methods: A retrospective analysis was conducted in patients with gastric cancer in Shanghai East Hospital affiliated with Tong ji University between December 2012 and June 2015, and total 145 patients were identified eligible. NLR, PLR, Δ NLR and ΔPLR values were calculated from peripheral blood cell count taken before surgery and 6-month post-surgery. Optimal cutoff value was determined by Receiver operating curve (ROC). Kaplan-Meier analysis was used to calculate the overall survival (OS) and Recurrence Free Survival (RFS). Cox regression analysis was performed to assess the prognostic factors. Continuous data with normal distribution was presented as mean ± standard deviation, and non-parametrical data were presented as median with interquartile range (IQR). Categorical data was described by frequency. The Student’s t test or one-way ANOVA (Analysis of Variance) was used for comparing continuous variables whereas Fisher’s exact test or χ2 test was used for categorical dataResults: The median follow-up duration was 26 months (IQR, 17–35). Patients were stratified in two groups by NLR (≤ 2.9,>2.9) and PLR (≤ 147,>147).3 years RFS of low ΔNLR and high ΔNLR is 59.0% and 76.7% respectively. Similarly, RFS of low ΔPLR and high ΔPLR group is 58.0% and 76.2%respectively. Multivariate analysis reviled elevated PLR [HR = 1.008,95%CI = 1.002–1.014, P-value = 0.011, for OS and HR = 1.009,95%CI = 1.004–1.014, P-value = 0.001, for RFS] and ΔPLR [HR = .994,95%CI = 0.990–0.999, P-value = 0.016 for OS and HR = 0.991 95%CI = 0.987–0.996 P-value = < 0.001 for RFS] were significantly associated with OS and RFS.Conclusions: Pre-operative PLR and derived(ΔPLR) are independent prognostic factors of OS and RFS in Gastric Cancer (GC) patients undergoing radical gastrectomy. The reduction of PLR and NLR after surgery might be helpful to predict cancer recurrence in patients who have undergone gastrectomy.

Sign in / Sign up

Export Citation Format

Share Document