Machine Learning Models of Survival Prediction in Trauma Patients

Background: We aimed to build a model using machine learning for the prediction of survival in trauma patients and compared these model predictions to those predicted by the most commonly used algorithm, the Trauma and Injury Severity Score (TRISS). Methods: Enrolled hospitalized trauma patients from 2009 to 2016 were divided into a training dataset (70% of the original data set) for generation of a plausible model under supervised classification, and a test dataset (30% of the original data set) to test the performance of the model. The training and test datasets comprised 13,208 (12,871 survival and 337 mortality) and 5603 (5473 survival and 130 mortality) patients, respectively. With the provision of additional information such as pre-existing comorbidity status or laboratory data, logistic regression (LR), support vector machine (SVM), and neural network (NN) (with the Stuttgart Neural Network Simulator (RSNNS)) were used to build models of survival prediction and compared to the predictive performance of TRISS. Predictive performance was evaluated by accuracy, sensitivity, and specificity, as well as by area under the curve (AUC) measures of receiver operating characteristic curves. Results: In the validation dataset, NN and the TRISS presented the highest score (82.0%) for balanced accuracy, followed by SVM (75.2%) and LR (71.8%) models. In the test dataset, NN had the highest balanced accuracy (75.1%), followed by the TRISS (70.2%), SVM (70.6%), and LR (68.9%) models. All four models (LR, SVM, NN, and TRISS) exhibited a high accuracy of more than 97.5% and a sensitivity of more than 98.6%. However, NN exhibited the highest specificity (51.5%), followed by the TRISS (41.5%), SVM (40.8%), and LR (38.5%) models. Conclusions: These four models (LR, SVM, NN, and TRISS) exhibited a similar high accuracy and sensitivity in predicting the survival of the trauma patients. In the test dataset, the NN model had the highest balanced accuracy and predictive specificity.

Download Full-text

A machine learning-based predictor for the identification of the recurrence of patients with gastric cancer after operation

Scientific Reports ◽

10.1038/s41598-021-81188-6 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Chengmao Zhou ◽

Junhong Hu ◽

Ying Wang ◽

Mu-Huo Ji ◽

Jianhua Tong ◽

...

Keyword(s):

Machine Learning ◽

Gastric Cancer ◽

Learning Algorithms ◽

Test Group ◽

Operation Time ◽

Predictive Performance ◽

Original Data ◽

Postoperative Recurrence ◽

Machine Learning Algorithms ◽

Gastric Cancer Patients

AbstractTo explore the predictive performance of machine learning on the recurrence of patients with gastric cancer after the operation. The available data is divided into two parts. In particular, the first part is used as a training set (such as 80% of the original data), and the second part is used as a test set (the remaining 20% of the data). And we use fivefold cross-validation. The weight of recurrence factors shows the top four factors are BMI, Operation time, WGT and age in order. In training group:among the 5 machine learning models, the accuracy of gbm was 0.891, followed by gbm algorithm was 0.876; The AUC values of the five machine learning algorithms are from high to low as forest (0.962), gbm (0.922), GradientBoosting (0.898), DecisionTree (0.790) and Logistic (0.748). And the precision of the forest is the highest 0.957, followed by the GradientBoosting algorithm (0.878). At the same time, in the test group is as follows: the highest accuracy of Logistic was 0.801, followed by forest algorithm and gbm; the AUC values of the five algorithms are forest (0.795), GradientBoosting (0.774), DecisionTree (0.773), Logistic (0.771) and gbm (0.771), from high to low. Among the five machine learning algorithms, the highest precision rate of Logistic is 1.000, followed by the gbm (0.487). Machine learning can predict the recurrence of gastric cancer patients after an operation. Besides, the first four factors affecting postoperative recurrence of gastric cancer were BMI, Operation time, WGT and age.

Download Full-text

Nowcasting heavy precipitation over the Netherlands using a 13-year radar archive: a machine learning approach

10.5194/egusphere-egu21-12814 ◽

2021 ◽

Author(s):

Eva van der Kooij ◽

Marc Schleiss ◽

Riccardo Taormina ◽

Francesco Fioranelli ◽

Dorien Lugt ◽

...

Keyword(s):

Machine Learning ◽

The Netherlands ◽

Heavy Rainfall ◽

Predictive Performance ◽

Heavy Precipitation ◽

Early Warning Systems ◽

Training Data ◽

Short Term ◽

Data Set ◽

Radar Images

Accurate short-term forecasts, also known as nowcasts, of heavy precipitation are desirable for creating early warning systems for extreme weather and its consequences, e.g. urban flooding. In this research, we explore the use of machine learning for short-term prediction of heavy rainfall showers in the Netherlands.We assess the performance of a recurrent, convolutional neural network (TrajGRU) with lead times of 0 to 2 hours. The network is trained on a 13-year archive of radar images with 5-min temporal and 1-km spatial resolution from the precipitation radars of the Royal Netherlands Meteorological Institute (KNMI). We aim to train the model to predict the formation and dissipation of dynamic, heavy, localized rain events, a task for which traditional Lagrangian nowcasting methods still come up short.We report on different ways to optimize predictive performance for heavy rainfall intensities through several experiments. The large dataset available provides many possible configurations for training. To focus on heavy rainfall intensities, we use different subsets of this dataset through using different conditions for event selection and varying the ratio of light and heavy precipitation events present in the training data set and change the loss function used to train the model.To assess the performance of the model, we compare our method to current state-of-the-art Lagrangian nowcasting system from the pySTEPS library, like S-PROG, a deterministic approximation of an ensemble mean forecast. The results of the experiments are used to discuss the pros and cons of machine-learning based methods for precipitation nowcasting and possible ways to further increase performance.

Download Full-text

Comparing predictive performance of general regression neural network (GRNN) and hedonic regression model for factors affecting housing prices in “Pune-India”

International Journal of Housing Markets and Analysis ◽

10.1108/ijhma-01-2021-0003 ◽

2021 ◽

Vol ahead-of-print (ahead-of-print) ◽

Author(s):

Abhijat Arun Abhyankar ◽

Harish Kumar Singla

Keyword(s):

Neural Network ◽

Regression Model ◽

Multivariate Regression ◽

Housing Prices ◽

Predictive Performance ◽

General Regression Neural Network ◽

Multivariate Regression Model ◽

Data Set ◽

Content Type ◽

General Regression

Purpose The purpose of this study is to compare the predictive performance of the hedonic multivariate regression model with the probabilistic neural network (PNN)-based general regression neural network (GRNN) model of housing prices in “Pune-India.” Design/methodology/approach Data on 211 properties across “Pune city-India” is collected. The price per square feet is considered as a dependent variable whereas distances from important landmarks such as railway station, fort, university, airport, hospital, temple, parks, solid waste site and stadium are considered as independent variables along with a dummy for amenities. The data is analyzed using a hedonic type multivariate regression model and GRNN. The GRNN divides the entire data set into two sets, namely, training set and testing set and establishes a functional relationship between the dependent and target variables based on the probability density function of the training data (Alomair and Garrouch, 2016). Findings While comparing the performance of the hedonic multivariate regression model and PNN-based GRNN, the study finds that the output variable (i.e. price) has been accurately predicted by the GRNN model. All the 42 observations of the testing set are correctly classified giving an accuracy rate of 100%. According to Cortez (2015), a value close to 100% indicates that the model can correctly classify the test data set. Further, the root mean square error (RMSE) value for the final testing for the GRNN model is 0.089 compared to 0.146 for the hedonic multivariate regression model. A lesser value of RMSE indicates that the model contains smaller errors and is a better fit. Therefore, it is concluded that GRNN is a better model to predict the housing price functions. The distance from the solid waste site has the highest degree of variable senstivity impact on the housing prices (22.59%) followed by distance from university (17.78%) and fort (17.73%). Research limitations/implications The study being a “case” is restricted to a particular geographic location hence, the findings of the study cannot be generalized. Further, as the objective of the study is restricted to just to compare the predictive performance of two models, it is felt appropriate to restrict the scope of work by focusing only on “location specific hedonic factors,” as determinants of housing prices. Practical implications The study opens up a new dimension for scholars working in the field of housing prices/valuation. Authors do not rule out the use of traditional statistical techniques such as ordinary least square regression but strongly recommend that it is high time scholars use advanced statistical methods to develop the domain. The application of GRNN, artificial intelligence or other techniques such as auto regressive integrated moving average and vector auto regression modeling helps analyze the data in a much more sophisticated manner and help come up with more robust and conclusive evidence. Originality/value To the best of the author’s knowledge, it is the first case study that compares the predictive performance of the hedonic multivariate regression model with the PNN-based GRNN model for housing prices in India.

Download Full-text

Deep Learning for Caries Detection and Classification

Diagnostics ◽

10.3390/diagnostics11091672 ◽

2021 ◽

Vol 11 (9) ◽

pp. 1672

Author(s):

Luya Lian ◽

Tianer Zhu ◽

Fudong Zhu ◽

Haihua Zhu

Keyword(s):

Neural Network ◽

Deep Learning ◽

Disease Diagnosis ◽

Validation Dataset ◽

Reference Dataset ◽

Dice Coefficient ◽

Learning Methods ◽

Test Dataset ◽

The Impact ◽

Caries Lesions

Objectives: Deep learning methods have achieved impressive diagnostic performance in the field of radiology. The current study aimed to use deep learning methods to detect caries lesions, classify different radiographic extensions on panoramic films, and compare the classification results with those of expert dentists. Methods: A total of 1160 dental panoramic films were evaluated by three expert dentists. All caries lesions in the films were marked with circles, whose combination was defined as the reference dataset. A training and validation dataset (1071) and a test dataset (89) were then established from the reference dataset. A convolutional neural network, called nnU-Net, was applied to detect caries lesions, and DenseNet121 was applied to classify the lesions according to their depths (dentin lesions in the outer, middle, or inner third D1/2/3 of dentin). The performance of the test dataset in the trained nnU-Net and DenseNet121 models was compared with the results of six expert dentists in terms of the intersection over union (IoU), Dice coefficient, accuracy, precision, recall, negative predictive value (NPV), and F1-score metrics. Results: nnU-Net yielded caries lesion segmentation IoU and Dice coefficient values of 0.785 and 0.663, respectively, and the accuracy and recall rate of nnU-Net were 0.986 and 0.821, respectively. The results of the expert dentists and the neural network were shown to be no different in terms of accuracy, precision, recall, NPV, and F1-score. For caries depth classification, DenseNet121 showed an overall accuracy of 0.957 for D1 lesions, 0.832 for D2 lesions, and 0.863 for D3 lesions. The recall results of the D1/D2/D3 lesions were 0.765, 0.652, and 0.918, respectively. All metric values, including accuracy, precision, recall, NPV, and F1-score values, were proven to be no different from those of the experienced dentists. Conclusion: In detecting and classifying caries lesions on dental panoramic radiographs, the performance of deep learning methods was similar to that of expert dentists. The impact of applying these well-trained neural networks for disease diagnosis and treatment decision making should be explored.

Download Full-text

Toward Optimal Heparin Dosing by Comparing Multiple Machine Learning Methods: Retrospective Study (Preprint)

10.2196/preprints.17648 ◽

2019 ◽

Author(s):

Longxiang Su ◽

Chun Liu ◽

Dongkai Li ◽

Jie He ◽

Fanglan Zheng ◽

...

Keyword(s):

Neural Network ◽

Machine Learning ◽

Intensive Care Unit ◽

Intensive Care ◽

Data Set ◽

Machine Learning Methods ◽

Heparin Treatment ◽

Neural Network Algorithm ◽

Mimic Iii ◽

Machine Learning Models

BACKGROUND Heparin is one of the most commonly used medications in intensive care units. In clinical practice, the use of a weight-based heparin dosing nomogram is standard practice for the treatment of thrombosis. Recently, machine learning techniques have dramatically improved the ability of computers to provide clinical decision support and have allowed for the possibility of computer generated, algorithm-based heparin dosing recommendations. OBJECTIVE The objective of this study was to predict the effects of heparin treatment using machine learning methods to optimize heparin dosing in intensive care units based on the predictions. Patient state predictions were based upon activated partial thromboplastin time in 3 different ranges: subtherapeutic, normal therapeutic, and supratherapeutic, respectively. METHODS Retrospective data from 2 intensive care unit research databases (Multiparameter Intelligent Monitoring in Intensive Care III, MIMIC-III; e–Intensive Care Unit Collaborative Research Database, eICU) were used for the analysis. Candidate machine learning models (random forest, support vector machine, adaptive boosting, extreme gradient boosting, and shallow neural network) were compared in 3 patient groups to evaluate the classification performance for predicting the subtherapeutic, normal therapeutic, and supratherapeutic patient states. The model results were evaluated using precision, recall, F1 score, and accuracy. RESULTS Data from the MIMIC-III database (n=2789 patients) and from the eICU database (n=575 patients) were used. In 3-class classification, the shallow neural network algorithm performed the best (F1 scores of 87.26%, 85.98%, and 87.55% for data set 1, 2, and 3, respectively). The shallow neural network algorithm achieved the highest F1 scores within the patient therapeutic state groups: subtherapeutic (data set 1: 79.35%; data set 2: 83.67%; data set 3: 83.33%), normal therapeutic (data set 1: 93.15%; data set 2: 87.76%; data set 3: 84.62%), and supratherapeutic (data set 1: 88.00%; data set 2: 86.54%; data set 3: 95.45%) therapeutic ranges, respectively. CONCLUSIONS The most appropriate model for predicting the effects of heparin treatment was found by comparing multiple machine learning models and can be used to further guide optimal heparin dosing. Using multicenter intensive care unit data, our study demonstrates the feasibility of predicting the outcomes of heparin treatment using data-driven methods, and thus, how machine learning–based models can be used to optimize and personalize heparin dosing to improve patient safety. Manual analysis and validation suggested that the model outperformed standard practice heparin treatment dosing.

Download Full-text

Methodology for Neural Network-Based Material Card Calibration Using LS-DYNA MAT_187_SAMP-1 Considering Failure with GISSMO

Materials ◽

10.3390/ma15020643 ◽

2022 ◽

Vol 15 (2) ◽

pp. 643

Author(s):

Paul Meißner ◽

Jens Winter ◽

Thomas Vietor

Keyword(s):

Neural Network ◽

Machine Learning ◽

Rate Dependency ◽

Material Parameter Identification ◽

General Applicability ◽

Time Saving ◽

Test Dataset ◽

The Common ◽

Computationally Intensive ◽

Tension Compression Asymmetry

A neural network (NN)-based method is presented in this paper which allows the identification of parameters for material cards used in Finite Element simulations. Contrary to the conventionally used computationally intensive material parameter identification (MPI) by numerical optimization with internal or commercial software, a machine learning (ML)-based method is time saving when used repeatedly. Within this article, a self-developed ML-based Python framework is presented, which offers advantages, especially in the development of structural components in early development phases. In this procedure, different machine learning methods are used and adapted to the specific MPI problem considered herein. Using the developed NN-based and the common optimization-based method with LS-OPT, the material parameters of the LS-DYNA material card MAT_187_SAMP-1 and the failure model GISSMO were exemplarily calibrated for a virtually generated test dataset. Parameters for the description of elasticity, plasticity, tension–compression asymmetry, variable plastic Poisson’s ratio (VPPR), strain rate dependency and failure were taken into account. The focus of this paper is on performing a comparative study of the two different MPI methods with varying settings (algorithms, hyperparameters, etc.). Furthermore, the applicability of the NN-based procedure for the specific usage of both material cards was investigated. The studies reveal the general applicability for the calibration of a complex material card by the example of the used MAT_187_SAMP-1.

Download Full-text

NEURAL NETWORK ANALYSIS FOR TUMOR INVESTIGATION AND CANCER PREDICTION

Journal of Electronics and Informatics - September 2019 ◽

10.36548/jei.2019.2.004 ◽

2019 ◽

Vol 2019 (02) ◽

pp. 89-98

Author(s):

Vijayakumar T

Keyword(s):

Neural Network ◽

Neural Networks ◽

Early Stage ◽

Original Data ◽

Data Set ◽

Cancer Prediction ◽

The Neural Network ◽

Feed Forward Neural Networks ◽

The Neural Networks ◽

Human Nervous System

Predicting the category of tumors and the types of the cancer in its early stage remains as a very essential process to identify depth of the disease and treatment available for it. The neural network that functions similar to the human nervous system is widely utilized in the tumor investigation and the cancer prediction. The paper presents the analysis of the performance of the neural networks such as the, FNN (Feed Forward Neural Networks), RNN (Recurrent Neural Networks) and the CNN (Convolutional Neural Network) investigating the tumors and predicting the cancer. The results obtained by evaluating the neural networks on the breast cancer Wisconsin original data set shows that the CNN provides 43 % better prediction than the FNN and 25% better prediction than the RNN.

Download Full-text

Convolutional Neural Network for Iris Recognition

10.21203/rs.3.rs-244624/v1 ◽

2021 ◽

Author(s):

Wael Alnahari

Keyword(s):

Neural Network ◽

Machine Learning ◽

Neural Networks ◽

Deep Learning ◽

Convolutional Neural Network ◽

Iris Recognition ◽

Recognition System ◽

High Accuracy ◽

Accuracy Rate

Abstract In this paper, I proposed an iris recognition system by using deep learning via neural networks (CNN). Although CNN is used for machine learning, the recognition is achieved by building a non-trained CNN network with multiple layers. The main objective of the code the test pictures’ category (aka person name) with a high accuracy rate after having extracted enough features from training pictures of the same category which are obtained from a that I added to the code. I used IITD iris which included 10 iris pictures for 223 people.

Download Full-text

Machine Learning-Based Estimation of Ground Reaction Forces and Knee Joint Kinetics from Inertial Sensors While Performing a Vertical Drop Jump

Sensors ◽

10.3390/s21227709 ◽

2021 ◽

Vol 21 (22) ◽

pp. 7709

Author(s):

Serena Cerfoglio ◽

Manuela Galli ◽

Marco Tarabini ◽

Filippo Bertozzi ◽

Chiarella Sforza ◽

...

Keyword(s):

Neural Network ◽

Machine Learning ◽

Knee Joint ◽

Field Analysis ◽

Ground Reaction Forces ◽

Drop Jump ◽

Joint Moments ◽

Data Set ◽

Joint Kinetics ◽

Reaction Forces

Nowadays, the use of wearable inertial-based systems together with machine learning methods opens new pathways to assess athletes’ performance. In this paper, we developed a neural network-based approach for the estimation of the Ground Reaction Forces (GRFs) and the three-dimensional knee joint moments during the first landing phase of the Vertical Drop Jump. Data were simultaneously recorded from three commercial inertial units and an optoelectronic system during the execution of 112 jumps performed by 11 healthy participants. Data were processed and sorted to obtain a time-matched dataset, and a non-linear autoregressive with external input neural network was implemented in Matlab. The network was trained through a train-test split technique, and performance was evaluated in terms of Root Mean Square Error (RMSE). The network was able to estimate the time course of GRFs and joint moments with a mean RMSE of 0.02 N/kg and 0.04 N·m/kg, respectively. Despite the comparatively restricted data set and slight boundary errors, the results supported the use of the developed method to estimate joint kinetics, opening a new perspective for the development of an in-field analysis method.

Download Full-text

Abstract 16588: Using Machine Learning to Improve Survival Prediction After Heart Transplantation

Circulation ◽

10.1161/circ.142.suppl_3.16588 ◽

2020 ◽

Vol 142 (Suppl_3) ◽

Author(s):

Brian Ayers ◽

Toumas Sandhold ◽

Igor Gosev ◽

Sunil Prasad ◽

Arman Kilic

Keyword(s):

Machine Learning ◽

Logistic Regression ◽

Heart Transplantation ◽

Risk Prediction ◽

Predictive Analytics ◽

Predictive Performance ◽

Orthotopic Heart Transplantation ◽

Survival Prediction ◽

One Year ◽

Testing Set

Introduction: Prior risk models for predicting survival after orthotopic heart transplantation (OHT) have displayed only modest discriminatory capability. With increasing interest in the application of machine learning (ML) to predictive analytics in clinical medicine, this study aimed to evaluate whether modern ML techniques could improve risk prediction in OHT. Methods: Data from the United Network for Organ Sharing registry was collected for all adult patients that underwent OHT from 2000 through 2019. The primary outcome was one-year post-transplant mortality. Dimensionality reduction and data re-sampling were employed during training. The final ensemble model was created from 100 different models of each algorithm: deep neural network, logistic regression, adaboost, and random forest. Discriminatory capability was assessed using area under receiver-operating-characteristic curve (AUROC), net reclassification index (NRI), and decision curve analysis (DCA). Results: Of the 33,657 study patients, 26,926 (80%) were randomly selected for the training set and 6,731 (20%) as a separate testing set. One-year mortality was balanced between cohorts (11.0% vs 11.3%). The optimal model performance was a final ensemble ML model. This model demonstrated an improved AUROC of 0.764 (95% CI, 0.745-0.782) in the testing set as compared to the other models (Figure). Additionally, the final model demonstrated an improvement of 72.9% ±3.8% (p<0.001) in predictive performance as assessed by NRI compared to logistic regression. The DCA showed the final ensemble method improved risk prediction across the entire spectrum of predicted risk as compared to all other models (p<0.001). Conclusions: An ensemble ML model was able to achieve greater predictive performance as compared to individual ML models as well as logistic regression for predicting survival after OHT. This analysis demonstrates the promise of ML techniques in risk prediction in OHT.

Download Full-text