ترغب بنشر مسار تعليمي؟ اضغط هنا

Limitations of ROC on Imbalanced Data: Evaluation of LVAD Mortality Risk Scores

141   0   0.0 ( 0 )
 نشر من قبل Faezeh Movahedi
 تاريخ النشر 2020
والبحث باللغة English




اسأل ChatGPT حول البحث

Objective: This study illustrates the ambiguity of ROC in evaluating two classifiers of 90-day LVAD mortality. This paper also introduces the precision recall curve (PRC) as a supplemental metric that is more representative of LVAD classifiers performance in predicting the minority class. Background: In the LVAD domain, the receiver operating characteristic (ROC) is a commonly applied metric of performance of classifiers. However, ROC can provide a distorted view of classifiers ability to predict short-term mortality due to the overwhelmingly greater proportion of patients who survive, i.e. imbalanced data. Methods: This study compared the ROC and PRC for the outcome of two classifiers for 90-day LVAD mortality for 800 patients (test group) recorded in INTERMACS who received a continuous-flow LVAD between 2006 and 2016 (mean age of 59 years; 146 females vs. 654 males) in which mortality rate is only %8 at 90-day (imbalanced data). The two classifiers were HeartMate Risk Score (HMRS) and a Random Forest (RF). Results: The ROC indicates fairly good performance of RF and HRMS classifiers with Area Under Curves (AUC) of 0.77 vs. 0.63, respectively. This is in contrast with their PRC with AUC of 0.43 vs. 0.16 for RF and HRMS, respectively. The PRC for HRMS showed the precision rapidly dropped to only 10% with slightly increasing sensitivity. Conclusion: The ROC can portray an overly-optimistic performance of a classifier or risk score when applied to imbalanced data. The PRC provides better insight about the performance of a classifier by focusing on the minority class.



قيم البحث

اقرأ أيضاً

COVID-19 pandemic has created an extreme pressure on the global healthcare services. Fast, reliable and early clinical assessment of the severity of the disease can help in allocating and prioritizing resources to reduce mortality. In order to study the important blood biomarkers for predicting disease mortality, a retrospective study was conducted on 375 COVID-19 positive patients admitted to Tongji Hospital (China) from January 10 to February 18, 2020. Demographic and clinical characteristics, and patient outcomes were investigated using machine learning tools to identify key biomarkers to predict the mortality of individual patient. A nomogram was developed for predicting the mortality risk among COVID-19 patients. Lactate dehydrogenase, neutrophils (%), lymphocyte (%), high sensitive C-reactive protein, and age - acquired at hospital admission were identified as key predictors of death by multi-tree XGBoost model. The area under curve (AUC) of the nomogram for the derivation and validation cohort were 0.961 and 0.991, respectively. An integrated score (LNLCA) was calculated with the corresponding death probability. COVID-19 patients were divided into three subgroups: low-, moderate- and high-risk groups using LNLCA cut-off values of 10.4 and 12.65 with the death probability less than 5%, 5% to 50%, and above 50%, respectively. The prognostic model, nomogram and LNLCA score can help in early detection of high mortality risk of COVID-19 patients, which will help doctors to improve the management of patient stratification.
Biomedical data are widely accepted in developing prediction models for identifying a specific tumor, drug discovery and classification of human cancers. However, previous studies usually focused on different classifiers, and overlook the class imbal ance problem in real-world biomedical datasets. There are a lack of studies on evaluation of data pre-processing techniques, such as resampling and feature selection, on imbalanced biomedical data learning. The relationship between data pre-processing techniques and the data distributions has never been analysed in previous studies. This article mainly focuses on reviewing and evaluating some popular and recently developed resampling and feature selection methods for class imbalance learning. We analyse the effectiveness of each technique from data distribution perspective. Extensive experiments have been done based on five classifiers, four performance measures, eight learning techniques across twenty real-world datasets. Experimental results show that: (1) resampling and feature selection techniques exhibit better performance using support vector machine (SVM) classifier. However, resampling and Feature Selection techniques perform poorly when using C4.5 decision tree and Linear discriminant analysis classifiers; (2) for datasets with different distributions, techniques such as Random undersampling and Feature Selection perform better than other data pre-processing methods with T Location-Scale distribution when using SVM and KNN (K-nearest neighbours) classifiers. Random oversampling outperforms other methods on Negative Binomial distribution using Random Forest classifier with lower level of imbalance ratio; (3) Feature Selection outperforms other data pre-processing methods in most cases, thus, Feature Selection with SVM classifier is the best choice for imbalanced biomedical data learning.
Background: Providing appropriate care for people suffering from COVID-19, the disease caused by the pandemic SARS-CoV-2 virus is a significant global challenge. Many individuals who become infected have pre-existing conditions that may interact with COVID-19 to increase symptom severity and mortality risk. COVID-19 patient comorbidities are likely to be informative about individual risk of severe illness and mortality. Accurately determining how comorbidities are associated with severe symptoms and mortality would thus greatly assist in COVID-19 care planning and provision. Methods: To assess the interaction of patient comorbidities with COVID-19 severity and mortality we performed a meta-analysis of the published global literature, and machine learning predictive analysis using an aggregated COVID-19 global dataset. Results: Our meta-analysis identified chronic obstructive pulmonary disease (COPD), cerebrovascular disease (CEVD), cardiovascular disease (CVD), type 2 diabetes, malignancy, and hypertension as most significantly associated with COVID-19 severity in the current published literature. Machine learning classification using novel aggregated cohort data similarly found COPD, CVD, CKD, type 2 diabetes, malignancy and hypertension, as well as asthma, as the most significant features for classifying those deceased versus those who survived COVID-19. While age and gender were the most significant predictor of mortality, in terms of symptom-comorbidity combinations, it was observed that Pneumonia-Hypertension, Pneumonia-Diabetes and Acute Respiratory Distress Syndrome (ARDS)-Hypertension showed the most significant effects on COVID-19 mortality. Conclusions: These results highlight patient cohorts most at risk of COVID-19 related severe morbidity and mortality which have implications for prioritization of hospital resources.
Many in-hospital mortality risk prediction scores dichotomize predictive variables to simplify the score calculation. However, hard thresholding in these additive stepwise scores of the form add x points if variable v is above/below threshold t may l ead to critical failures. In this paper, we seek to develop risk prediction scores that preserve clinical knowledge embedded in features and structure of the existing additive stepwise scores while addressing limitations caused by variable dichotomization. To this end, we propose a novel score structure that relies on a transformation of predictive variables by means of nonlinear logistic functions facilitating smooth differentiation between critical and normal values of the variables. We develop an optimization framework for inferring parameters of the logistic functions for a given patient population via cyclic block coordinate descent. The parameters may readily be updated as the patient population and standards of care evolve. We tested the proposed methodology on two populations: (1) brain trauma patients admitted to the intensive care unit of the Dell Childrens Medical Center of Central Texas between 2007 and 2012, and (2) adult ICU patient data from the MIMIC II database. The results are compared with those obtained by the widely used PRISM III and SOFA scores. The prediction power of a score is evaluated using area under ROC curve, Youdens index, and precision-recall balance in a cross-validation study. The results demonstrate that the new framework enables significant performance improvements over PRISM III and SOFA in terms of all three criteria.
Surgical risk increases significantly when patients present with comorbid conditions. This has resulted in the creation of numerous risk stratification tools with the objective of formulating associated surgical risk to assist both surgeons and patie nts in decision-making. The Surgical Outcome Risk Tool (SORT) is one of the tools developed to predict mortality risk throughout the entire perioperative period for major elective in-patient surgeries in the UK. In this study, we enhance the original SORT prediction model (UK SORT) by addressing the class imbalance within the dataset. Our proposed method investigates the application of diversity-based selection on top of common re-sampling techniques to enhance the classifiers capability in detecting minority (mortality) events. Diversity amongst training datasets is an essential factor in ensuring re-sampled data keeps an accurate depiction of the minority/majority class region, thereby solving the generalization problem of mainstream sampling approaches. We incorporate the use of the Solow-Polasky measure as a drop-in functionality to evaluate diversity, with the addition of greedy algorithms to identify and discard subsets that share the most similarity. Additionally, through empirical experiments, we prove that the performance of the classifier trained over diversity-based dataset outperforms the original classifier over ten external datasets. Our diversity-based re-sampling method elevates the performance of the UK SORT algorithm by 1.4$.

الأسئلة المقترحة

التعليقات
جاري جلب التعليقات جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا