scholarly journals Machine Learning for Prediction of Survival Outcomes with Immune-Checkpoint Inhibitors in Urothelial Cancer

Cancers ◽  
2021 ◽  
Vol 13 (9) ◽  
pp. 2001
Author(s):  
Ahmad Y. Abuhelwa ◽  
Ganessan Kichenadasse ◽  
Ross A. McKinnon ◽  
Andrew Rowland ◽  
Ashley M. Hopkins ◽  
...  
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Urothelial Cancer ◽  
Prediction Models ◽  
Checkpoint Inhibitors ◽  
External Validation ◽  
Model Performance ◽  
Progression Free Survival ◽  
Survival Outcomes ◽  
Forest C

Machine learning (ML) may enhance the efficiency of developing accurate prediction models for survival, which is critical in informing disease prognosis and care planning. This study aimed to develop an ML prediction model for survival outcomes in patients with urothelial cancer-initiating atezolizumab and to compare model performances when built using an expert-selected (curated) versus an all-in list (uncurated) of variables. Gradient-boosted machine (GBM), random forest, Cox-boosted, and penalised, generalised linear models (GLM) were evaluated for predicting overall survival (OS) and progression-free survival (PFS) outcomes. C-statistic (c) was utilised to evaluate model performance. The atezolizumab cohort in IMvigor210 was used for model training, and IMvigor211 was used for external model validation. The curated list consisted of 23 pretreatment factors, while the all-in list consisted of 75. Using the best-performing model, patients were stratified into risk tertiles. Kaplan–Meier analysis was used to estimate survival probabilities. On external validation, the curated list GBM model provided slightly higher OS discrimination (c = 0.71) than that of the random forest (c = 0.70), CoxBoost (c = 0.70), and GLM (c = 0.69) models. All models were equivalent in predicting PFS (c = 0.62). Expansion to the uncurated list was associated with worse OS discrimination (GBM c = 0.70; random forest c = 0.69; CoxBoost c = 0.69, and GLM c = 0.69). In the atezolizumab IMvigor211 cohort, the curated list GBM model discriminated 1-year OS probabilities for the low-, intermediate-, and high-risk groups at 66%, 40%, and 12%, respectively. The ML model discriminated urothelial-cancer patients with distinctly different survival risks, with the GBM applied to a curated list attaining the highest performance. Expansion to an all-in approach may harm model performance.

scholarly journals Classification models using circulating neutrophil transcripts can detect unruptured intracranial aneurysm

2020 ◽  
Vol 18 (1) ◽  
Author(s):  
Kerry E. Poppenberg ◽  
Vincent M. Tutino ◽  
Lu Li ◽  
Muhammad Waqas ◽  
Armond June ◽  
...  
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Prediction Models ◽  
Model Performance ◽  
Supervised Machine Learning ◽  
Support Vector ◽  
Learning Methods ◽  
Training Cohort ◽  
Network Analyses ◽  
Machine Learning Methods

Abstract Background Intracranial aneurysms (IAs) are dangerous because of their potential to rupture. We previously found significant RNA expression differences in circulating neutrophils between patients with and without unruptured IAs and trained machine learning models to predict presence of IA using 40 neutrophil transcriptomes. Here, we aim to develop a predictive model for unruptured IA using neutrophil transcriptomes from a larger population and more robust machine learning methods. Methods Neutrophil RNA extracted from the blood of 134 patients (55 with IA, 79 IA-free controls) was subjected to next-generation RNA sequencing. In a randomly-selected training cohort (n = 94), the Least Absolute Shrinkage and Selection Operator (LASSO) selected transcripts, from which we constructed prediction models via 4 well-established supervised machine-learning algorithms (K-Nearest Neighbors, Random Forest, and Support Vector Machines with Gaussian and cubic kernels). We tested the models in the remaining samples (n = 40) and assessed model performance by receiver-operating-characteristic (ROC) curves. Real-time quantitative polymerase chain reaction (RT-qPCR) of 9 IA-associated genes was used to verify gene expression in a subset of 49 neutrophil RNA samples. We also examined the potential influence of demographics and comorbidities on model prediction. Results Feature selection using LASSO in the training cohort identified 37 IA-associated transcripts. Models trained using these transcripts had a maximum accuracy of 90% in the testing cohort. The testing performance across all methods had an average area under ROC curve (AUC) = 0.97, an improvement over our previous models. The Random Forest model performed best across both training and testing cohorts. RT-qPCR confirmed expression differences in 7 of 9 genes tested. Gene ontology and IPA network analyses performed on the 37 model genes reflected dysregulated inflammation, cell signaling, and apoptosis processes. In our data, demographics and comorbidities did not affect model performance. Conclusions We improved upon our previous IA prediction models based on circulating neutrophil transcriptomes by increasing sample size and by implementing LASSO and more robust machine learning methods. Future studies are needed to validate these models in larger cohorts and further investigate effect of covariates.

scholarly journals Machine Learning Approach Using Routine Immediate Postoperative Laboratory Values for Predicting Postoperative Mortality

2021 ◽  
Vol 11 (12) ◽  
pp. 1271
Author(s):  
Jaehyeong Cho ◽  
Jimyung Park ◽  
Eugene Jeong ◽  
Jihye Shin ◽  
Sangjeong Ahn ◽  
...  
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Prediction Models ◽  
External Validation ◽  
Model Development ◽  
Postoperative Mortality ◽  
Random Forest Model ◽  
Forest Model ◽  
Laboratory Values ◽  
Increased Risk

Background: Several prediction models have been proposed for preoperative risk stratification for mortality. However, few studies have investigated postoperative risk factors, which have a significant influence on survival after surgery. This study aimed to develop prediction models using routine immediate postoperative laboratory values for predicting postoperative mortality. Methods: Two tertiary hospital databases were used in this research: one for model development and another for external validation of the resulting models. The following algorithms were utilized for model development: LASSO logistic regression, random forest, deep neural network, and XGBoost. We built the models on the lab values from immediate postoperative blood tests and compared them with the SASA scoring system to demonstrate their efficacy. Results: There were 3817 patients who had immediate postoperative blood test values. All models trained on immediate postoperative lab values outperformed the SASA model. Furthermore, the developed random forest model had the best AUROC of 0.82 and AUPRC of 0.13, and the phosphorus level contributed the most to the random forest model. Conclusions: Machine learning models trained on routine immediate postoperative laboratory values outperformed previously published approaches in predicting 30-day postoperative mortality, indicating that they may be beneficial in identifying patients at increased risk of postoperative death.

scholarly journals On Missingness Features in Machine Learning Models for Critical Care: Observational Study (Preprint)

2020 ◽  
Author(s):  
Janmajay Singh ◽  
Masahiro Sato ◽  
Tomoko Ohkuma
Keyword(s):  
Machine Learning ◽  
Length Of Stay ◽  
Electronic Health Records ◽  
Prediction Models ◽  
External Validation ◽  
Model Performance ◽  
Learning Models ◽  
Health Records ◽  
Electronic Health ◽  
Machine Learning Models

BACKGROUND Missing data in electronic health records is inevitable and considered to be nonrandom. Several studies have found that features indicating missing patterns (missingness) encode useful information about a patient’s health and advocate for their inclusion in clinical prediction models. But their effectiveness has not been comprehensively evaluated. OBJECTIVE The goal of the research is to study the effect of including informative missingness features in machine learning models for various clinically relevant outcomes and explore robustness of these features across patient subgroups and task settings. METHODS A total of 48,336 electronic health records from the 2012 and 2019 PhysioNet Challenges were used, and mortality, length of stay, and sepsis outcomes were chosen. The latter dataset was multicenter, allowing external validation. Gated recurrent units were used to learn sequential patterns in the data and classify or predict labels of interest. Models were evaluated on various criteria and across population subgroups evaluating discriminative ability and calibration. RESULTS Generally improved model performance in retrospective tasks was observed on including missingness features. Extent of improvement depended on the outcome of interest (area under the curve of the receiver operating characteristic [AUROC] improved from 1.2% to 7.7%) and even patient subgroup. However, missingness features did not display utility in a simulated prospective setting, being outperformed (0.9% difference in AUROC) by the model relying only on pathological features. This was despite leading to earlier detection of disease (true positives), since including these features led to a concomitant rise in false positive detections. CONCLUSIONS This study comprehensively evaluated effectiveness of missingness features on machine learning models. A detailed understanding of how these features affect model performance may lead to their informed use in clinical settings especially for administrative tasks like length of stay prediction where they present the greatest benefit. While missingness features, representative of health care processes, vary greatly due to intra- and interhospital factors, they may still be used in prediction models for clinically relevant outcomes. However, their use in prospective models producing frequent predictions needs to be explored further.

scholarly journals On Missingness Features in Machine Learning Models for Critical Care: Observational Study

10.2196/25022 ◽  
2021 ◽  
Vol 9 (12) ◽  
pp. e25022
Author(s):  
Janmajay Singh ◽  
Masahiro Sato ◽  
Tomoko Ohkuma
Keyword(s):  
Machine Learning ◽  
Length Of Stay ◽  
Electronic Health Records ◽  
Prediction Models ◽  
External Validation ◽  
Model Performance ◽  
Learning Models ◽  
Health Records ◽  
Electronic Health ◽  
Machine Learning Models

Background Missing data in electronic health records is inevitable and considered to be nonrandom. Several studies have found that features indicating missing patterns (missingness) encode useful information about a patient’s health and advocate for their inclusion in clinical prediction models. But their effectiveness has not been comprehensively evaluated. Objective The goal of the research is to study the effect of including informative missingness features in machine learning models for various clinically relevant outcomes and explore robustness of these features across patient subgroups and task settings. Methods A total of 48,336 electronic health records from the 2012 and 2019 PhysioNet Challenges were used, and mortality, length of stay, and sepsis outcomes were chosen. The latter dataset was multicenter, allowing external validation. Gated recurrent units were used to learn sequential patterns in the data and classify or predict labels of interest. Models were evaluated on various criteria and across population subgroups evaluating discriminative ability and calibration. Results Generally improved model performance in retrospective tasks was observed on including missingness features. Extent of improvement depended on the outcome of interest (area under the curve of the receiver operating characteristic [AUROC] improved from 1.2% to 7.7%) and even patient subgroup. However, missingness features did not display utility in a simulated prospective setting, being outperformed (0.9% difference in AUROC) by the model relying only on pathological features. This was despite leading to earlier detection of disease (true positives), since including these features led to a concomitant rise in false positive detections. Conclusions This study comprehensively evaluated effectiveness of missingness features on machine learning models. A detailed understanding of how these features affect model performance may lead to their informed use in clinical settings especially for administrative tasks like length of stay prediction where they present the greatest benefit. While missingness features, representative of health care processes, vary greatly due to intra- and interhospital factors, they may still be used in prediction models for clinically relevant outcomes. However, their use in prospective models producing frequent predictions needs to be explored further.

scholarly journals Classification Models using Circulating Neutrophil Transcripts Can Detect Unruptured Intracranial Aneurysm

2020 ◽  
Author(s):  
Kerry E Poppenberg ◽  
Vincent M Tutino ◽  
Lu Li ◽  
Muhammad Waqas ◽  
Armond June ◽  
...  
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Prediction Models ◽  
Model Performance ◽  
Supervised Machine Learning ◽  
Support Vector ◽  
Learning Methods ◽  
Training Cohort ◽  
Network Analyses ◽  
Machine Learning Methods

Abstract Background: Intracranial aneurysms (IAs) are dangerous because of their potential to rupture. We previously found significant RNA expression differences in circulating neutrophils between patients with and without unruptured IAs and trained machine learning models to predict presence of IA using 40 neutrophil transcriptomes. Here, we aim to develop a predictive model for unruptured IA using neutrophil transcriptomes from a larger population and more robust machine learning methods. Methods: Neutrophil RNA extracted from the blood of 134 patients (55 with IA, 79 IA-free controls) was subjected to next-generation RNA sequencing. In a randomly-selected training cohort (n=94), the Least Absolute Shrinkage and Selection Operator (LASSO) selected transcripts, from which we constructed prediction models via 4 well-established supervised machine-learning algorithms (K-Nearest Neighbors, Random Forest, and Support Vector Machines with Gaussian and cubic kernels). We tested the models in the remaining samples (n=40) and assessed model performance by receiver-operating-characteristic (ROC) curves. Real-time quantitative polymerase chain reaction (RT-qPCR) of 9 IA-associated genes was used to verify gene expression in a subset of 49 neutrophil RNA samples. We also examined the potential influence of demographics and comorbidities on model prediction. Results: Feature selection using LASSO in the training cohort identified 37 IA-associated transcripts. Models trained using these transcripts had a maximum accuracy of 90% in the testing cohort. The testing performance across all methods had an average area under ROC curve (AUC)=0.97, an improvement over our previous models. The Random Forest model performed best across both training and testing cohorts. RT-qPCR confirmed expression differences in 7 of 9 genes tested. Gene ontology and IPA network analyses performed on the 37 model genes reflected dysregulated inflammation, cell signaling, and apoptosis processes. In our data, demographics and comorbidities did not affect model performance. Conclusions: We improved upon our previous IA prediction models based on circulating neutrophil transcriptomes by increasing sample size and by implementing LASSO and more robust machine learning methods. Future studies are needed to validate these models in larger cohorts and further investigate effect of covariates.

scholarly journals Classification Models using Circulating Neutrophil Transcripts Can Detect Unruptured Intracranial Aneurysm

2020 ◽  
Author(s):  
Kerry E Poppenberg ◽  
Vincent M Tutino ◽  
Lu Li ◽  
Muhammad Waqas ◽  
Armond June ◽  
...  
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Prediction Models ◽  
Model Performance ◽  
Supervised Machine Learning ◽  
Support Vector ◽  
Learning Methods ◽  
Training Cohort ◽  
Network Analyses ◽  
Machine Learning Methods

Abstract Background Intracranial aneurysms (IAs) are dangerous because of their potential to rupture. We previously found significant RNA expression differences in circulating neutrophils between patients with and without unruptured IAs and trained machine learning models to predict presence of IA using 40 neutrophil transcriptomes. Here, we aim to develop a predictive model for unruptured IA using neutrophil transcriptomes from a larger population and more robust machine learning methods. Methods Neutrophil RNA extracted from the blood of 134 patients (55 with IA, 79 IA-free controls) was subjected to next-generation RNA sequencing. In a randomly-selected training cohort (n=94), the Least Absolute Shrinkage and Selection Operator (LASSO) selected transcripts, from which we constructed prediction models via 4 well-established supervised machine-learning algorithms (K-Nearest Neighbors, Random Forest, and Support Vector Machines with Gaussian and cubic kernels). We tested the models in the remaining samples (n=40) and assessed model performance by receiver-operating-characteristic (ROC) curves. Real-time quantitative polymerase chain reaction (RT-qPCR) of 10 IA-associated genes was used to verify gene expression in a subset of 50 neutrophil RNA samples. We also examined the potential influence of demographics and comorbidities on model prediction. Results Feature selection using LASSO in the training cohort identified 37 IA-associated transcripts. Models trained using these transcripts had a maximum accuracy of 90% in the testing cohort. The testing performance across all methods had an average area under ROC curve (AUC)=0.97, an improvement over our previous models. The Random Forest model performed best across both training and testing cohorts. RT-qPCR confirmed expression differences in 8 of 10 genes tested. Gene ontology and IPA network analyses performed on the 37 model genes reflected dysregulated inflammation, cell signaling, and apoptosis processes. In our data, demographics and comorbidities did not affect model performance. Conclusions We improved upon our previous IA prediction models based on circulating neutrophil transcriptomes by increasing sample size and by implementing LASSO and more robust machine learning methods. Future studies are needed to validate these models in larger cohorts and further investigate effect of covariates.

Development of Prediction Models Using Machine Learning Algorithms for Girls with Suspected Central Precocious Puberty: Retrospective Study (Preprint)

2018 ◽  
Author(s):  
Liyan Pan ◽  
Guangjian Liu ◽  
Xiaojian Mao ◽  
Huixian Li ◽  
Jiexin Zhang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Retrospective Study ◽  
Random Forest ◽  
Precocious Puberty ◽  
Prediction Models ◽  
Central Precocious Puberty ◽  
Machine Learning Algorithms ◽  
Stimulation Test ◽  
Gnrh Analogue ◽  
Prediction Probability

BACKGROUND Central precocious puberty (CPP) in girls seriously affects their physical and mental development in childhood. The method of diagnosis—gonadotropin-releasing hormone (GnRH)–stimulation test or GnRH analogue (GnRHa)–stimulation test—is expensive and makes patients uncomfortable due to the need for repeated blood sampling. OBJECTIVE We aimed to combine multiple CPP–related features and construct machine learning models to predict response to the GnRHa-stimulation test. METHODS In this retrospective study, we analyzed clinical and laboratory data of 1757 girls who underwent a GnRHa test in order to develop XGBoost and random forest classifiers for prediction of response to the GnRHa test. The local interpretable model-agnostic explanations (LIME) algorithm was used with the black-box classifiers to increase their interpretability. We measured sensitivity, specificity, and area under receiver operating characteristic (AUC) of the models. RESULTS Both the XGBoost and random forest models achieved good performance in distinguishing between positive and negative responses, with the AUC ranging from 0.88 to 0.90, sensitivity ranging from 77.91% to 77.94%, and specificity ranging from 84.32% to 87.66%. Basal serum luteinizing hormone, follicle-stimulating hormone, and insulin-like growth factor-I levels were found to be the three most important factors. In the interpretable models of LIME, the abovementioned variables made high contributions to the prediction probability. CONCLUSIONS The prediction models we developed can help diagnose CPP and may be used as a prescreening tool before the GnRHa-stimulation test.

scholarly journals Machine Learning in Aging: An Example of Developing Prediction Models for Serious Fall Injury in Older Adults

2020 ◽  
Vol 4 (Supplement_1) ◽  
pp. 268-269
Author(s):  
Jaime Speiser ◽  
Kathryn Callahan ◽  
Jason Fanning ◽  
Thomas Gill ◽  
Anne Newman ◽  
...  
Keyword(s):  
Machine Learning ◽  
Older Adults ◽  
Random Forest ◽  
Decision Tree ◽  
Prediction Models ◽  
Receiver Operating Curve ◽  
Learning Methods ◽  
Life Study ◽  
Fall Injury ◽  
Machine Learning Methods

Abstract Advances in computational algorithms and the availability of large datasets with clinically relevant characteristics provide an opportunity to develop machine learning prediction models to aid in diagnosis, prognosis, and treatment of older adults. Some studies have employed machine learning methods for prediction modeling, but skepticism of these methods remains due to lack of reproducibility and difficulty understanding the complex algorithms behind models. We aim to provide an overview of two common machine learning methods: decision tree and random forest. We focus on these methods because they provide a high degree of interpretability. We discuss the underlying algorithms of decision tree and random forest methods and present a tutorial for developing prediction models for serious fall injury using data from the Lifestyle Interventions and Independence for Elders (LIFE) study. Decision tree is a machine learning method that produces a model resembling a flow chart. Random forest consists of a collection of many decision trees whose results are aggregated. In the tutorial example, we discuss evaluation metrics and interpretation for these models. Illustrated in data from the LIFE study, prediction models for serious fall injury were moderate at best (area under the receiver operating curve of 0.54 for decision tree and 0.66 for random forest). Machine learning methods may offer improved performance compared to traditional models for modeling outcomes in aging, but their use should be justified and output should be carefully described. Models should be assessed by clinical experts to ensure compatibility with clinical practice.

scholarly journals Machine Learning-Based Prediction of Air Quality

2020 ◽  
Vol 10 (24) ◽  
pp. 9151
Author(s):  
Yun-Chia Liang ◽  
Yona Maimury ◽  
Angela Hsiang-Ling Chen ◽  
Josue Rodolfo Cuevas Juarez
Keyword(s):  
Machine Learning ◽  
Air Quality ◽  
Random Forest ◽  
Prediction Models ◽  
Superior Performance ◽  
Support Vector ◽  
Economic Activities ◽  
Adaptive Boosting ◽  
Series Of Experiments ◽  
Artificial Neural Network Ann

Air, an essential natural resource, has been compromised in terms of quality by economic activities. Considerable research has been devoted to predicting instances of poor air quality, but most studies are limited by insufficient longitudinal data, making it difficult to account for seasonal and other factors. Several prediction models have been developed using an 11-year dataset collected by Taiwan’s Environmental Protection Administration (EPA). Machine learning methods, including adaptive boosting (AdaBoost), artificial neural network (ANN), random forest, stacking ensemble, and support vector machine (SVM), produce promising results for air quality index (AQI) level predictions. A series of experiments, using datasets for three different regions to obtain the best prediction performance from the stacking ensemble, AdaBoost, and random forest, found the stacking ensemble delivers consistently superior performance for R2 and RMSE, while AdaBoost provides best results for MAE.

Sign in / Sign up

Export Citation Format

Share Document