Computational prediction of diagnosis and feature selection on mesothelioma patient health records

Abstract

BackgroundMesothelioma is a lung cancer that kills thousands of people worldwide annually, especially those with exposure to asbestos. Diagnosis of mesothelioma in patients often requires time-consuming imaging techniques and biopsies. Machine learning can provide for a more effective, cheaper, and faster patient diagnosis and feature selection from clinical data in patient records.Methods and findingsWe analyzed a dataset of health records of 324 patients having mesothelioma symptoms from Turkey. The patients had prior asbestos exposure and displayed symptoms consistent with mesothelioma. We compared probabilistic neural network, perceptron-based neural network, random forest, one rule, and decision tree classifiers to predict diagnosis of the patient records. We measured classifiers’ performance through standard confusion matrix scores such as Matthews correlation coefficient (MCC). Random forest outperformed all models tried, obtaining MCC = +0.37 on the complete imbalanced dataset and MCC = +0.64 on the under-sampled balanced dataset. We then employed random forest feature selection to identify the two most relevant dataset traits associated with mesothelioma: lung side and platelet count. These two risk factors resulted so predictive, that decision tree focusing on them achieved the second top accuracy on the complete dataset diagnosis prediction (MCC = +0.28), outperforming all other methods and even decision tree itself applied to all features.ConclusionsOur results show that machine learning can predict diagnoses of patients having mesothelioma symptoms with high accuracy, sensitivity, and specificity, in few minutes. Additionally, random forest can efficiently select the most important features of this clinical dataset (lung side and platelet count) in few seconds. The importance of pleural plaques in lung sides and blood platelets in mesothelioma diagnosis indicates that physicians should focus on these two features when reading records of patients with mesothelioma symptoms. Moreover, doctors can exploit our machinery to predict patient diagnosis when only lung side and platelet data are available.

Machine learning can predict survival of patients with heart failure from serum creatinine and ejection fraction alone

“…Similarly to what authors did for a dataset of patients having mesothelioma symptoms [92], we decided then to investigate the most important features of the cardiovascular heart disease patients dataset. To this aim, we first performed a traditional univariate biostatistics analysis ("Feature ranking" section), and then employed Random Forests [108], to generate machine learning results.…”

“…Regarding machine learning feature ranking, we focused only on Random Forests [72,91], because as it turned out to be the top performing classifier on the complete dataset ("Feature ranking results" section). Random Forests [72] provides two feature ranking techniques: mean accuracy reduction and Gini impurity reduction [92]. During training, Random Forests generates several random Decision Trees that it applies to data subsets, containing a subsets both of data instances and of features.…”

“…Regarding the final prediction using only the top two selected features, we chose Random Forests because it resulted in being the top performing classifier on the complete feature dataset ("Survival machine learning prediction on all clinical features" section) and it is universally considered an efficient method for feature ranking [92]. We then chose Gradient Boosting and Support Vector Machine with radial Gaussian kernel because both these methods have shown efficient performances in feature ranking with medical informatics data [105,106].…”

Identification of Malignant Mesothelioma Risk Factors through Association Rule Mining

“…The dataset consists of medicinal histories of 324 patients gathered from the University of California (Irvine, CA, USA) machine learning database [29]. There were 96 mesothelioma patients as well as 228 healthy individuals which indicated imbalanced dataset [30]. Regarding with imbalanced dataset, it includes 29.63% patients of mesothelioma and 70.37% healthy individuals.…”

“…The completeness of the dataset is exceptional quality in electronic medical records which enables to make a more exact and precise analysis than different conditions where a few values are missing [32]. The "diagnosis method" attribute has duplicate values to "class of diagnosis" [30] then attribute was removed from the data set.…”