Methodical approach to assess the condition of samples of weapons and military equipment on the basis of algorithmic trees

An effective mechanism for the synthesis of classification trees based on fixed initial information (in the form of a training sample) for the task of recognizing the technical condition of samples of weapons and military equipment. The constructed algorithmic classification tree (model) will unmistakably classify (recognize) the entire training sample (situational objects) according to which the classification scheme is constructed. And have a minimal structure (structural complexity) and consist of components (modules) - autonomous algorithms for classification and recognition as vertices of the structure (attributes of the tree). The developed method of building models of algorithm trees (classification schemes) allows you to work with training samples of a large amount of different types of information (discrete type). Provides high accuracy, speed and economy of hardware resources in the process of generating the final classification scheme, build classification trees (models) with a predetermined accuracy. The approach of synthesis of new algorithms of recognition (classification) on the basis of library (set) of already known algorithms (schemes) and methods is offered. Based on the proposed concept of algorithmic classification trees, a set of models was built, which provided effective classification and prediction of the technical condition of samples. The paper proposes a set of general indicators (parameters), which allows to effectively present the general characteristics of the classification tree model, it is possible to use it to select the most optimal tree of algorithms from a set based on methods of random classification trees. Practical tests have confirmed the efficiency of mathematical software and models of algorithm trees.

Analysis of Indications for Electrotherapy Using Classification Trees

Electrotherapy is a dynamically developing method of treatment of sinus node dysfunction and atrioventricular conduction disturbances. It is an extremely important method used in the treatment of heart failure. The aim of this paper was to use classification trees for the differentiation between patients implanted with one of the three electrotherapy devices, i.e. SC-VVI/AAI, DC-DDD, ICD/CRT. The analysed data concerned 2071 patients who underwent implantation or device replacement procedures in the years 2010–2018, hospitalized in a coronary care unit. CART-type classification trees with 5-fold cross-validation were used for the analysis. The decision concerning the choice of a particular electrotherapy device is always made based on the latest guidelines and the patient’s clinical condition. The used classification trees may enable verification of the state of implementation of guidelines in real-life therapeutic decisions.

Benchmarking in Congenital Heart Surgery Using Machine Learning-Derived Optimal Classification Trees

Background: We have previously shown that the machine learning methodology of optimal classification trees (OCTs) can accurately predict risk after congenital heart surgery (CHS). We have now applied this methodology to define benchmarking standards after CHS, permitting case-adjusted hospital-specific performance evaluation. Methods: The European Congenital Heart Surgeons Association Congenital Database data subset (31 792 patients) who had undergone any of the 10 “benchmark procedure group” primary procedures were analyzed. OCT models were built predicting hospital mortality (HM), and prolonged postoperative mechanical ventilatory support time (MVST) or length of hospital stay (LOS), thereby establishing case-adjusted benchmarking standards reflecting the overall performance of all participating hospitals, designated as the “virtual hospital.” These models were then used to predict individual hospitals’ expected outcomes (both aggregate and, importantly, for risk-matched patient cohorts) for their own specific cases and case-mix, based on OCT analysis of aggregate data from the “virtual hospital.” Results: The raw average rates were HM = 4.4%, MVST = 15.3%, and LOS = 15.5%. Of 64 participating centers, in comparison with each hospital's specific case-adjusted benchmark, 17.0% statistically (under 90% confidence intervals) overperformed and 26.4% underperformed with respect to the predicted outcomes for their own specific cases and case-mix. For MVST and LOS, overperformers were 34.0% and 26.4%, and underperformers were 28.3% and 43.4%, respectively. OCT analyses reveal hospital-specific patient cohorts of either overperformance or underperformance. Conclusions: OCT benchmarking analysis can assess hospital-specific case-adjusted performance after CHS, both overall and patient cohort-specific, serving as a tool for hospital self-assessment and quality improvement.

Robust optimal classification trees under noisy labels

In this paper we propose a novel methodology to construct Optimal Classification Trees that takes into account that noisy labels may occur in the training sample. The motivation of this new methodology is based on the superaditive effect of combining together margin based classifiers and outlier detection techniques. Our approach rests on two main elements: (1) the splitting rules for the classification trees are designed to maximize the separation margin between classes applying the paradigm of SVM; and (2) some of the labels of the training sample are allowed to be changed during the construction of the tree trying to detect the label noise. Both features are considered and integrated together to design the resulting Optimal Classification Tree. We present a Mixed Integer Non Linear Programming formulation for the problem, suitable to be solved using any of the available off-the-shelf solvers. The model is analyzed and tested on a battery of standard datasets taken from UCI Machine Learning repository, showing the effectiveness of our approach. Our computational results show that in most cases the new methodology outperforms both in accuracy and AUC the results of the benchmarks provided by OCT and OCT-H.