The Influence of Inhomogeneous Input Data from Different Waves on Predictive Model Development for COVID-19 ICU Patients (Preprint)

2021 ◽  
Author(s):  
Sebastian Johannes Fritsch ◽  
Konstantin Sharafutdinov ◽  
Moein Einollahzadeh Samadi ◽  
Gernot Marx ◽  
Andreas Schuppert ◽  
...  
Keyword(s):  
Machine Learning ◽  
Convex Hull ◽  
Prediction Models ◽  
Model Development ◽  
Predictive Performance ◽  
Support Vector ◽  
Good Prediction ◽  
The Impact ◽  
Second Wave ◽  
Over Time

BACKGROUND During the course of the COVID-19 pandemic, a variety of machine learning models were developed to predict different aspects of the disease, such as long-term causes, organ dysfunction or ICU mortality. The number of training datasets used has increased significantly over time. However, these data now come from different waves of the pandemic, not always addressing the same therapeutic approaches over time as well as changing outcomes between two waves. The impact of these changes on model development has not yet been studied. OBJECTIVE The aim of the investigation was to examine the predictive performance of several models trained with data from one wave predicting the second wave´s data and the impact of a pooling of these data sets. Finally, a method for comparison of different datasets for heterogeneity is introduced. METHODS We used two datasets from wave one and two to develop several predictive models for mortality of the patients. Four classification algorithms were used: logistic regression (LR), support vector machine (SVM), random forest classifier (RF) and AdaBoost classifier (ADA). We also performed a mutual prediction on the data of that wave which was not used for training. Then, we compared the performance of models when a pooled dataset from two waves was used. The populations from the different waves were checked for heterogeneity using a convex hull analysis. RESULTS 63 patients from wave one (03-06/2020) and 54 from wave two (08/2020-01/2021) were evaluated. For both waves separately, we found models reaching sufficient accuracies up to 0.79 AUROC (95%-CI 0.76-0.81) for SVM on the first wave and up 0.88 AUROC (95%-CI 0.86-0.89) for RF on the second wave. After the pooling of the data, the AUROC decreased relevantly. In the mutual prediction, models trained on second wave´s data showed, when applied on first wave´s data, a good prediction for non-survivors but an insufficient classification for survivors. The opposite situation (training: first wave, test: second wave) revealed the inverse behaviour with models correctly classifying survivors and incorrectly predicting non-survivors. The convex hull analysis for the first and second wave populations showed a more inhomogeneous distribution of underlying data when compared to randomly selected sets of patients of the same size. CONCLUSIONS Our work demonstrates that a larger dataset is not a universal solution to all machine learning problems in clinical settings. Rather, it shows that inhomogeneous data used to develop models can lead to serious problems. With the convex hull analysis, we offer a solution for this problem. The outcome of such an analysis can raise concerns if the pooling of different datasets would cause inhomogeneous patterns preventing a better predictive performance.

scholarly journals Comparative analysis of machine learning approaches to analyze and predict the COVID-19 outbreak

2021 ◽  
Vol 7 ◽  
pp. e746
Author(s):  
Muhammad Naeem ◽  
Jian Yu ◽  
Muhammad Aamir ◽  
Sajjad Ahmad Khan ◽  
Olayinka Adeleye ◽  
...  
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Comparative Analysis ◽  
Prediction Models ◽  
Mean Absolute Percentage Error ◽  
Percentage Error ◽  
Support Vector ◽  
Absolute Percentage Error ◽  
Statistical Measures ◽  
The Impact

Background Forecasting the time of forthcoming pandemic reduces the impact of diseases by taking precautionary steps such as public health messaging and raising the consciousness of doctors. With the continuous and rapid increase in the cumulative incidence of COVID-19, statistical and outbreak prediction models including various machine learning (ML) models are being used by the research community to track and predict the trend of the epidemic, and also in developing appropriate strategies to combat and manage its spread. Methods In this paper, we present a comparative analysis of various ML approaches including Support Vector Machine, Random Forest, K-Nearest Neighbor and Artificial Neural Network in predicting the COVID-19 outbreak in the epidemiological domain. We first apply the autoregressive distributed lag (ARDL) method to identify and model the short and long-run relationships of the time-series COVID-19 datasets. That is, we determine the lags between a response variable and its respective explanatory time series variables as independent variables. Then, the resulting significant variables concerning their lags are used in the regression model selected by the ARDL for predicting and forecasting the trend of the epidemic. Results Statistical measures—Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and Symmetric Mean Absolute Percentage Error (SMAPE)—are used for model accuracy. The values of MAPE for the best-selected models for confirmed, recovered and deaths cases are 0.003, 0.006 and 0.115, respectively, which falls under the category of highly accurate forecasts. In addition, we computed 15 days ahead forecast for the daily deaths, recovered, and confirm patients and the cases fluctuated across time in all aspects. Besides, the results reveal the advantages of ML algorithms for supporting the decision-making of evolving short-term policies.

Prediction of Dansgaard-Oeschger events using machine learning

2021 ◽  
Author(s):  
Nuno Moniz ◽  
Susana Barbosa
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Prediction Models ◽  
Learning Algorithms ◽  
Ice Core ◽  
Model Performance ◽  
Predictive Performance ◽  
Oxygen Isotopic Composition ◽  
Machine Learning Algorithms ◽  
Support Vector

<p>The Dansgaard-Oeschger (DO) events are one of the most striking examples of abrupt climate change in the Earth's history, representing temperature oscillations of about 8 to 16 degrees Celsius within a few decades. DO events have been studied extensively in paleoclimatic records, particularly in ice core proxies. Examples include the Greenland NGRIP record of oxygen isotopic composition.<br>This work addresses the anticipation of DO events using machine learning algorithms. We consider the NGRIP time series from 20 to 60 kyr b2k with the GICC05 timescale and 20-year temporal resolution. Forecasting horizons range from 0 (nowcasting) to 400 years. We adopt three different machine learning algorithms (random forests, support vector machines, and logistic regression) in training windows of 5 kyr. We perform validation on subsequent test windows of 5 kyr, based on timestamps of previous DO events' classification in Greenland by Rasmussen et al. (2014). We perform experiments with both sliding and growing windows.<br>Results show that predictions on sliding windows are better overall, indicating that modelling is affected by non-stationary characteristics of the time series. The three algorithms' predictive performance is similar, with a slightly better performance of random forest models for shorter forecast horizons. The prediction models' predictive capability decreases as the forecasting horizon grows more extensive but remains reasonable up to 120 years. Model performance deprecation is mostly related to imprecision in accurately determining the start and end time of events and identifying some periods as DO events when such is not valid.</p>

Machine learning for air quality prediction using meteorological and traffic related features

2020 ◽  
Vol 12 (5) ◽  
pp. 379-391
Author(s):  
Ihsane Gryech ◽  
Mounir Ghogho ◽  
Hajar Elhammouti ◽  
Nada Sbihi ◽  
Abdellatif Kobbane
Keyword(s):  
Machine Learning ◽  
Air Quality ◽  
Linear Models ◽  
Prediction Models ◽  
Road Traffic ◽  
Support Vector ◽  
Air Quality Prediction ◽  
Monitoring Process ◽  
Non Linear ◽  
The Impact

The presence of pollutants in the air has a direct impact on our health and causes detrimental changes to our environment. Air quality monitoring is therefore of paramount importance. The high cost of the acquisition and maintenance of accurate air quality stations implies that only a small number of these stations can be deployed in a country. To improve the spatial resolution of the air monitoring process, an interesting idea is to develop data-driven models to predict air quality based on readily available data. In this paper, we investigate the correlations between air pollutants concentrations and meteorological and road traffic data. Using machine learning, regression models are developed to predict pollutants concentration. Both linear and non-linear models are investigated in this paper. It is shown that non-linear models, namely Random Forest (RF) and Support Vector Regression (SVR), better describe the impact of traffic flows and meteorology on the concentrations of pollutants in the atmosphere. It is also shown that more accurate prediction models can be obtained when including some pollutants’ concentration as predictors. This may be used to infer the concentrations of some pollutants using those of other pollutants, thereby reducing the number of air pollution sensors.

MACHINE LEARNING APPLICATIONS IN CONSTRUCTION SAFETY LITERATURE

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Kerim Koc ◽  
Asli Pelin Gurgun
Keyword(s):  
Machine Learning ◽  
Literature Review ◽  
Management Practices ◽  
Prediction Models ◽  
Safety Management ◽  
Model Development ◽  
Construction Safety ◽  
Future Research ◽  
Support Vector ◽  
Construction Accidents

Despite significant improvements in safety management practices, the construction industry remains among the most unsafe industries. Thus, it is an essential need to reduce the number of construction accidents through prediction models. In this context, machine learning (ML) methods are extensively used in construction safety literature to predict several outcomes of construction accidents. This study provides a literature review in ML applications in construction safety literature to illustrate research directions for future research. Based on the literature review, 43 journal articles were deeply investigated, and distribution of the articles were classified based on six features: journal, year, adopted machine learning methods, model development approach, utilized dataset, and sub-topics. The findings show that the prediction models in construction safety have taken considerable attention recently. Besides, linear regression and logistic regression were used as a benchmark model, while support vector machine and decision tree were the most frequently implemented ML methods. The number of publications that considered classification problem is two times higher than those adopted regression models. Utilized data were mainly captured from national databases or construction companies. Severity evaluation of construction accidents was the most widely investigated sub-topic, while there is a gap in the literature related to effects of culture on accident outcome and conflict, claim and nonconformance. The findings of this study can provide valuable information for researchers with trends in construction safety literature.

scholarly journals Development of Childhood Asthma Prediction Models using Machine Learning Approaches

2021 ◽  
Author(s):  
Dilini M Kothalawala ◽  
Clare Murray ◽  
Angela Simpson ◽  
Adnan Custovic ◽  
William J Tapper ◽  
...  
Keyword(s):  
Machine Learning ◽  
Childhood Asthma ◽  
Early Life ◽  
Prediction Models ◽  
Predictive Performance ◽  
Preschool Age ◽  
Receiver Operating Curve ◽  
Support Vector ◽  
School Age ◽  
Learning Approaches

Background: Wheeze is common in early life and often transient. It is difficult to identify which children will experience persistent symptoms and subsequently develop asthma. Machine learning approaches have the potential for better predictive performance and generalisability over existing childhood asthma prediction models. Objective: To apply machine learning approaches for predicting school-age asthma (age 10) in early life (Childhood Asthma Prediction in Early life, CAPE model) and at preschool age (Childhood Asthma Prediction at Preschool age, CAPP model). Methods: Data on clinical symptoms and environmental exposures were collected from children enrolled in the Isle of Wight Birth Cohort (N=1368, ~15% asthma prevalence). Recursive Feature Elimination (RFE) identified the optimal subset of features predictive of school-age asthma for each model. Seven state-of-the-art machine learning classification algorithms were used to develop the models and the results were compared. To optimize the models, training was performed by applying 5-fold cross-validation, imputation and resampling. Predictive performances were evaluated on the test set and externally validated in the Manchester Asthma and Allergy Study (MAAS) cohort. Results: RFE identified eight and 12 predictors for the CAPE and CAPP models, respectively. The best predictive performance was demonstrated by a Support Vector Machine (SVM) algorithm for both the CAPE model (area under the receiver operating curve, AUC=0.71) and CAPP model (AUC=0.82). Both models demonstrated good generalisability in MAAS (CAPE 8YR=0.71, 11YR=0.71, CAPP 8YR=0.83, 11YR=0.79). Conclusion: Using machine learning approaches improved upon the predictive performance of existing regression-based models, with good generalisability and ability to rule in asthma.

scholarly journals Predicting Colorectal Cancer Recurrence and Patient Survival Using Supervised Machine Learning Approach: A South African Population-Based Study

2021 ◽  
Vol 9 ◽  
Author(s):  
Okechinyere J. Achilonu ◽  
June Fabian ◽  
Brendan Bebington ◽  
Elvira Singh ◽  
M. J. C. Eijkemans ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Machine Learning ◽  
South African ◽  
Patient Survival ◽  
Information Gain ◽  
Model Development ◽  
Predictive Performance ◽  
Sub Saharan Africa ◽  
Supervised Machine Learning ◽  
Support Vector

Background: South Africa (SA) has the highest incidence of colorectal cancer (CRC) in Sub-Saharan Africa (SSA). However, there is limited research on CRC recurrence and survival in SA. CRC recurrence and overall survival are highly variable across studies. Accurate prediction of patients at risk can enhance clinical expectations and decisions within the South African CRC patients population. We explored the feasibility of integrating statistical and machine learning (ML) algorithms to achieve higher predictive performance and interpretability in findings.Methods: We selected and compared six algorithms:- logistic regression (LR), naïve Bayes (NB), C5.0, random forest (RF), support vector machine (SVM) and artificial neural network (ANN). Commonly selected features based on OneR and information gain, within 10-fold cross-validation, were used for model development. The validity and stability of the predictive models were further assessed using simulated datasets.Results: The six algorithms achieved high discriminative accuracies (AUC-ROC). ANN achieved the highest AUC-ROC for recurrence (87.0%) and survival (82.0%), and other models showed comparable performance with ANN. We observed no statistical difference in the performance of the models. Features including radiological stage and patient's age, histology, and race are risk factors of CRC recurrence and patient survival, respectively.Conclusions: Based on other studies and what is known in the field, we have affirmed important predictive factors for recurrence and survival using rigorous procedures. Outcomes of this study can be generalised to CRC patient population elsewhere in SA and other SSA countries with similar patient profiles.

scholarly journals Prediction of Allogeneic HSCT Related Mortality in Acute Leukemia: Exploring Boundaries of Prediction through Machine Learning Based Modeling. a Data Mining Study from the Acute Leukemia Working Party (ALWP) of the EBMT

Blood ◽  
2014 ◽  
Vol 124 (21) ◽  
pp. 2568-2568
Author(s):  
Roni Shouval ◽  
Myriam Labopin ◽  
Ron Unger ◽  
Sebastian Giebel ◽  
Fabio Ciceri ◽  
...  
Keyword(s):  
Machine Learning ◽  
Data Mining ◽  
Acute Leukemia ◽  
Outcome Prediction ◽  
Prediction Models ◽  
Model Development ◽  
Predictive Performance ◽  
Computational Approach ◽  
Optimal Prediction ◽  
Related Mortality

Abstract Background: Allogeneic hematopoietic stem cell transplantation (allo-HSCT) has been shown to increase survival and induce cure of acute leukemia (AL). Unfortunately, transplant related mortality (TRM) remains high. Risk scores, based on a conventional statistical approach, have been developed for TRM prediction. These have been well validated. Nevertheless, predictive performance is sub-optimal; thus, limiting clinical utility. Factors impeding prediction might be attributed to the statistical methodology, number and quality of features collected, or simply the size of the population analyzed. We set to explore these factors, using a novel computational approach, based on machine learning algorithms (ML). ML is a subfield of computer science and artificial intelligence that deals with the construction and study of systems that can learn from data, rather than follow only explicitly programmed instructions. Commonly applied in complex data scenarios, such as financial and technological settings, it may be suitable for outcome prediction if the field of HSCT. Study design: Using a cohort of 28,236 adult allo-HSCT recipients from the ALWP registry of the EBMT, transplanted between 2000-2011, owing to Acute Myeloid Leukemia or Acute Lymphoblastic Leukemia, and containing 24 variables (i.e., patient, leukemia, donor, and transplant characteristics) we devised a two phase data mining study 1) Development of ML based prediction models for day 100 TRM; 2) In- silico analysis (i.e., performed through a computerized simulation) of the developed models. Factors necessary for optimal prediction were explored: type of model, size of data set, number of necessary variables, and performance in specific subpopulations; Model development and analysis were performed with "WEKA" a data mining suite. The area under the receiver operating characteristic curve (AUC) is a commonly used evaluation method for binary choice problems, which involve classifying an instance as either positive or negative. A perfect model will score an AUC of 1, while random guessing will score an AUC of around of 0.5. The AUC was used as measure of predictive performance for the developed models. Results: We developed six machine learning based prediction models for TRM at day 100. Optimal AUCs ranged from 0.65-0.68. Predictive performance plateaued for a population size ranging from n=5647-8471, depending on the algorithm (Figure 1). A feature selection algorithm ranked variables according to importance. Provided with the ranked variable data, we discovered that a range of 6-12 ranked variables were necessary for optimal prediction, depending on the algorithm (Figure 2). Predictive performance of models developed for specific subpopulations, ranged from an average of 0.59 to 0.67 for patient in second complete remission and patients receiving reduced intensity conditioning respectively. Conclusions: We present a novel computational approach for prediction model development and analysis in the field of HSCT. Using data commonly collected on transplant patients, our simulation elucidate outcome prediction limiting factors. Regardless of the methodology applied, predictive performance converged when sampling more than 5000 patients. Few variables (approximately 6-12), "carry the weight" with regard to predictive influence. In summary, the presented findings describe a phenomenon of predictive saturation, with data traditionally collected. Improving the current performance will likely require additional types of input like genetic, biologic and procedural factors. Figure 1 Figure 1. Figure 2 Figure 2. Disclosures No relevant conflicts of interest to declare.

In silico Prediction of Inhibitory Constant of Thrombin Inhibitors Using Machine Learning

2019 ◽  
Vol 21 (9) ◽  
pp. 662-669 ◽  
Author(s):  
Junnan Zhao ◽  
Lu Zhu ◽  
Weineng Zhou ◽  
Lingfeng Yin ◽  
Yuchen Wang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Prediction Models ◽  
Regression Tree ◽  
Large Data ◽  
Thrombin Inhibitors ◽  
Coagulation Cascade ◽  
Gradient Boosting ◽  
Support Vector ◽  
Data Set ◽  
Descriptor Selection

Background: Thrombin is the central protease of the vertebrate blood coagulation cascade, which is closely related to cardiovascular diseases. The inhibitory constant Ki is the most significant property of thrombin inhibitors. Method: This study was carried out to predict Ki values of thrombin inhibitors based on a large data set by using machine learning methods. Taking advantage of finding non-intuitive regularities on high-dimensional datasets, machine learning can be used to build effective predictive models. A total of 6554 descriptors for each compound were collected and an efficient descriptor selection method was chosen to find the appropriate descriptors. Four different methods including multiple linear regression (MLR), K Nearest Neighbors (KNN), Gradient Boosting Regression Tree (GBRT) and Support Vector Machine (SVM) were implemented to build prediction models with these selected descriptors. Results: The SVM model was the best one among these methods with R2=0.84, MSE=0.55 for the training set and R2=0.83, MSE=0.56 for the test set. Several validation methods such as yrandomization test and applicability domain evaluation, were adopted to assess the robustness and generalization ability of the model. The final model shows excellent stability and predictive ability and can be employed for rapid estimation of the inhibitory constant, which is full of help for designing novel thrombin inhibitors.

scholarly journals Machine Learning Methods Applied to the Prediction of Pseudo-nitzschia spp. Blooms in the Galician Rias Baixas (NW Spain)

2021 ◽  
Vol 10 (4) ◽  
pp. 199
Author(s):  
Francisco M. Bellas Aláez ◽  
Jesus M. Torres Palenzuela ◽  
Evangelos Spyrakos ◽  
Luis González Vilas
Keyword(s):  
Machine Learning ◽  
Performance Metrics ◽  
Prediction Models ◽  
Support Vector ◽  
False Alarms ◽  
Learning Approaches ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Rías Baixas ◽  
New Algorithms

This work presents new prediction models based on recent developments in machine learning methods, such as Random Forest (RF) and AdaBoost, and compares them with more classical approaches, i.e., support vector machines (SVMs) and neural networks (NNs). The models predict Pseudo-nitzschia spp. blooms in the Galician Rias Baixas. This work builds on a previous study by the authors (doi.org/10.1016/j.pocean.2014.03.003) but uses an extended database (from 2002 to 2012) and new algorithms. Our results show that RF and AdaBoost provide better prediction results compared to SVMs and NNs, as they show improved performance metrics and a better balance between sensitivity and specificity. Classical machine learning approaches show higher sensitivities, but at a cost of lower specificity and higher percentages of false alarms (lower precision). These results seem to indicate a greater adaptation of new algorithms (RF and AdaBoost) to unbalanced datasets. Our models could be operationally implemented to establish a short-term prediction system.

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