An Online Calculator for the Prediction of Survival in Glioblastoma Patients Using Classical Statistics and Machine Learning.
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.
Project description:BACKGROUND:Osteoarthritis (OA) is the most common disease of arthritis. Analgesics are widely used in the treat of arthritis, which may increase the risk of cardiovascular diseases by 20% to 50% overall.There are few studies on the side effects of OA medication, especially the risk prediction models on side effects of analgesics. In addition, most prediction models do not provide clinically useful interpretable rules to explain the reasoning process behind their predictions. In order to assist OA patients, we use the eXtreme Gradient Boosting (XGBoost) method to balance the accuracy and interpretability of the prediction model. RESULTS:In this study we used the XGBoost model as a classifier, which is a supervised machine learning method and can predict side effects of analgesics for OA patients and identify high-risk features (RFs) of cardiovascular diseases caused by analgesics. The Electronic Medical Records (EMRs), which were derived from public knee OA studies, were used to train the model. The performance of the XGBoost model is superior to four well-known machine learning algorithms and identifies the risk features from the biomedical literature. In addition the model can provide decision support for using analgesics in OA patients. CONCLUSION:Compared with other machine learning methods, we used XGBoost method to predict side effects of analgesics for OA patients from EMRs, and selected the individual informative RFs. The model has good predictability and interpretability, this is valuable for both medical researchers and patients.
Project description:Herein, we aim to assess mortality risk prediction in peritoneal dialysis patients using machine-learning algorithms for proper prognosis prediction. A total of 1,730 peritoneal dialysis patients in the CRC for ESRD prospective cohort from 2008 to 2014 were enrolled in this study. Classification algorithms were used for prediction of N-year mortality including neural network. The survival hazard ratio was presented by machine-learning algorithms using survival statistics and was compared to conventional algorithms. A survival-tree algorithm presented the most accurate prediction model and outperformed a conventional method such as Cox regression (concordance index 0.769 vs 0.745). Among various survival decision-tree models, the modified Charlson Comorbidity index (mCCI) was selected as the best predictor of mortality. If peritoneal dialysis patients with high mCCI (>4) were aged ?70.5 years old, the survival hazard ratio was predicted as 4.61 compared to the overall study population. Among the various algorithm using longitudinal data, the AUC value of logistic regression was augmented at 0.804. In addition, the deep neural network significantly improved performance to 0.841. We propose machine learning-based final model, mCCI and age were interrelated as notable risk factors for mortality in Korean peritoneal dialysis patients.
Project description:Understanding the relationship between the genome of a cell and its phenotype is a central problem in precision medicine. Nonetheless, genotype-to-phenotype prediction comes with great challenges for machine learning algorithms that limit their use in this setting. The high dimensionality of the data tends to hinder generalization and challenges the scalability of most learning algorithms. Additionally, most algorithms produce models that are complex and difficult to interpret. We alleviate these limitations by proposing strong performance guarantees, based on sample compression theory, for rule-based learning algorithms that produce highly interpretable models. We show that these guarantees can be leveraged to accelerate learning and improve model interpretability. Our approach is validated through an application to the genomic prediction of antimicrobial resistance, an important public health concern. Highly accurate models were obtained for 12 species and 56 antibiotics, and their interpretation revealed known resistance mechanisms, as well as some potentially new ones. An open-source disk-based implementation that is both memory and computationally efficient is provided with this work. The implementation is turnkey, requires no prior knowledge of machine learning, and is complemented by comprehensive tutorials.
Project description:Amyloid-?(A?) PET positivity in patients with suspected cerebral amyloid angiopathy (CAA) MRI markers is predictive of a worse cognitive trajectory, and it provides insights into the underlying vascular pathology (CAA vs. hypertensive angiopathy) to facilitate prognostic prediction and appropriate treatment decisions. In this study, we applied two interpretable machine learning algorithms, gradient boosting machine (GBM) and random forest (RF), to predict A? PET positivity in patients with CAA MRI markers. In the GBM algorithm, the number of lobar cerebral microbleeds (CMBs), deep CMBs, lacunes, CMBs in dentate nuclei, and age were ranked as the most influential to predict A? positivity. In the RF algorithm, the absence of diabetes was additionally chosen. Cut-off values of the above variables predictive of A? positivity were as follows: (1) the number of lobar CMBs?>?16.4(GBM)/14.3(RF), (2) no deep CMBs(GBM/RF), (3) the number of lacunes?>?7.4(GBM/RF), (4) age?>?74.3(GBM)/64(RF), (5) no CMBs in dentate nucleus(GBM/RF). The classification performances based on the area under the receiver operating characteristic curve were 0.83 in GBM and 0.80 in RF. Our study demonstrates the utility of interpretable machine learning in the clinical setting by quantifying the relative importance and cutoff values of predictive variables for A? positivity in patients with suspected CAA markers.
Project description:Objective:Machine learning methods may have better or comparable predictive ability than traditional analysis. We explore machine learning methods to predict the likelihood of acute kidney injury after liver cancer resection. Methods:This is a secondary analysis cohort study. We reviewed data from patients who had undergone resection of primary hepatocellular carcinoma between January 2008 and October 2015. Results:The analysis included 1,173 hepatectomy patients, 77 (6.6%) of whom had AKI and 1,096 (93.4%) who did not. The importance matrix for the Gbdt algorithm model shows that age, cholesterol, tumor size, surgery duration and PLT were the five most important parameters. Figure 1 shows that Age, tumor size and surgery duration had weak positive correlations with AKI. Cholesterol and PLT also had weak negative correlations with AKI. The models constructed by the four machine learning algorithms in the training group were compared. Among the four machine learning algorithms, random forest and gbm had the highest accuracy, 0.989 and 0.970 respectively. The precision of four of the five algorithms was 1, random forest being the exception. Among the test group, gbm had the highest accuracy (0.932). Random forest and gbm had the highest precision, both being 0.333. The AUC values for the four algorithms were: Gbdt (0.772), gbm (0.725), forest (0.662) and DecisionTree (0.628). Conclusions:Machine learning technology can predict acute kidney injury after hepatectomy. Age, cholesterol, tumor size, surgery duration and PLT influence the likelihood and development of postoperative acute kidney injury.
Project description:The aim of this study is to explore the feasibility of using machine learning (ML) technology to predict postoperative recurrence risk among stage IV colorectal cancer patients. Four basic ML algorithms were used for prediction-logistic regression, decision tree, GradientBoosting and lightGBM. The research samples were randomly divided into a training group and a testing group at a ratio of 8:2. 999 patients with stage 4 colorectal cancer were included in this study. In the training group, the GradientBoosting model's AUC value was the highest, at 0.881. The Logistic model's AUC value was the lowest, at 0.734. The GradientBoosting model had the highest F1_score (0.912). In the test group, the AUC Logistic model had the lowest AUC value (0.692). The GradientBoosting model's AUC value was 0.734, which can still predict cancer progress. However, the gbm model had the highest AUC value (0.761), and the gbm model had the highest F1_score (0.974). The GradientBoosting model and the gbm model performed better than the other two algorithms. The weight matrix diagram of the GradientBoosting algorithm shows that chemotherapy, age, LogCEA, CEA and anesthesia time were the five most influential risk factors for tumor recurrence. The four machine learning algorithms can each predict the risk of tumor recurrence in patients with stage IV colorectal cancer after surgery. Among them, GradientBoosting and gbm performed best. Moreover, the GradientBoosting weight matrix shows that the five most influential variables accounting for postoperative tumor recurrence are chemotherapy, age, LogCEA, CEA and anesthesia time.
Project description:This study aims to demonstrate the use of the tree-based machine learning algorithms to predict the 3- and 5-year disease-specific survival of oral and pharyngeal cancers (OPCs) and compare their performance with the traditional Cox regression. A total of 21,154 individuals diagnosed with OPCs between 2004 and 2009 were obtained from the Surveillance, Epidemiology, and End Results (SEER) database. Three tree-based machine learning algorithms (survival tree (ST), random forest (RF) and conditional inference forest (CF)), together with a reference technique (Cox proportional hazard models (Cox)), were used to develop the survival prediction models. To handle the missing values in predictors, we applied the substantive model compatible version of the fully conditional specification imputation approach to the Cox model, whereas we used RF to impute missing data for the ST, RF and CF models. For internal validation, we used 10-fold cross-validation with 50 iterations in the model development datasets. Following this, model performance was evaluated using the C-index, integrated Brier score (IBS) and calibration curves in the test datasets. For predicting the 3-year survival of OPCs with the complete cases, the C-index in the development sets were 0.77 (0.77, 0.77), 0.70 (0.70, 0.70), 0.83 (0.83, 0.84) and 0.83 (0.83, 0.86) for Cox, ST, RF and CF, respectively. Similar results were observed in the 5-year survival prediction models, with C-index for Cox, ST, RF and CF being 0.76 (0.76, 0.76), 0.69 (0.69, 0.70), 0.83 (0.83, 0.83) and 0.85 (0.84, 0.86), respectively, in development datasets. The prediction error curves based on IBS showed a similar pattern for these models. The predictive performance remained unchanged in the analyses with imputed data. Additionally, a free web-based calculator was developed for potential clinical use. In conclusion, compared to Cox regression, ST had a lower and RF and CF had a higher predictive accuracy in predicting the 3- and 5-year OPCs survival using SEER data. The RF and CF algorithms provide non-parametric alternatives to Cox regression to be of clinical use for estimating the survival probability of OPCs patients.
Project description:Deep learning is a class of machine learning algorithms that are popular for building risk prediction models. When observations are censored, the outcomes are only partially observed and standard deep learning algorithms cannot be directly applied. We develop a new class of deep learning algorithms for outcomes that are potentially censored. To account for censoring, the unobservable loss function used in the absence of censoring is replaced by a censoring unbiased transformation. The resulting class of algorithms can be used to estimate both survival probabilities and restricted mean survival. We show how the deep learning algorithms can be implemented by adapting software for uncensored data by using a form of response transformation. We provide comparisons of the proposed deep learning algorithms to existing risk prediction algorithms for predicting survival probabilities and restricted mean survival through both simulated datasets and analysis of data from breast cancer patients.
Project description:Machine learning algorithms that are both interpretable and accurate are essential in applications such as medicine where errors can have a dire consequence. Unfortunately, there is currently a tradeoff between accuracy and interpretability among state-of-the-art methods. Decision trees are interpretable and are therefore used extensively throughout medicine for stratifying patients. Current decision tree algorithms, however, are consistently outperformed in accuracy by other, less-interpretable machine learning models, such as ensemble methods. We present MediBoost, a novel framework for constructing decision trees that retain interpretability while having accuracy similar to ensemble methods, and compare MediBoost's performance to that of conventional decision trees and ensemble methods on 13 medical classification problems. MediBoost significantly outperformed current decision tree algorithms in 11 out of 13 problems, giving accuracy comparable to ensemble methods. The resulting trees are of the same type as decision trees used throughout clinical practice but have the advantage of improved accuracy. Our algorithm thus gives the best of both worlds: it grows a single, highly interpretable tree that has the high accuracy of ensemble methods.
Project description:BACKGROUND:This study aimed to examine multi-dimensional MRI features' predictability on survival outcome and associations with differentially expressed Genes (RNA Sequencing) in groups of glioblastoma multiforme (GBM) patients. METHODS:Radiomics features were extracted from segmented lesions of T2-FLAIR MRI data of 137 GBM patients. Radiomics features include intensity, shape and textural features in seven classes were included in the analysis. Patients were divided into two groups depending on their survival time (shorter or longer than 1-year survival). Four different machine learning algorithms were implemented to construct the prediction models. Features with top importance (importance >0.04) were selected to construct the prediction model using the model with the best performance. The interactions between image features and genomics were then analysed with Pearson's correlation analysis. RESULTS:The GBDT model with 72 features with highest importance had the highest accuracy of 0.81 on both short and long survival time classes, and the area under the curve (AUC) of the receiver operative characteristic (ROC) of the short and long survival time class were 0.79 and 0.81. Six metagenes showed significant interactive effect (P < 0.05), and Pearson's correlation analysis revealed that three of these metagenes (TIMP1, ROS1 EREG) showed moderate (0.3 < |r| < 0.5) or high correlation (|r| > 0.5) with image features. CONCLUSION:Radiogenomics analysis shows that MRI features are predictive of survival outcomes, and image features are highly associated with selective metagenes. Radiogenomics analysis is a useful method for optimizing clinical diagnosis and selecting effective treatments.