arXiv subjects

Georgi Nalbantov

Publications and source records attributed to Georgi Nalbantov.

5 recordsLinked to original sources

arXiv2026

Routine Blood Tests Outperform CRP for Distinguishing Bacterial From Viral Infection in Children

Acute infectious diseases are among the leading causes of medical consultations and hospitalizations in children worldwide. These infections are predominantly caused by viruses or bacteria, yet differentiating between the two remains a common clinical challenge. As a result, pediatricians often default to the safer option of prescribing antibiotics contributing to the growing problem of antimicrobial resistance. The objective is to assess the additional predictive value of CBC towards determining the current infection. This retrospective study used data from 906 pediatric patients aged between 2 and 14 years who were tested positive either for viral or bacterial infection between 2022 and 2026. Inclusion criteria further required availability of CBC results and CRP level measurements. These laboratory parameters as well as age were used as input features for several supervised classification models. Model performance was evaluated using AUC, sensitivity and specificity. The best performing model is XGBoost, which included all features, achieving out of-sample performance of AUC of 81.7% and sensitivity of 70.8%, specificity of 79.2%. All trained models outperform a CRP-based only decision-rule model in terms of AUC. We suggest that the decision to prescribe antibiotics should be based on a number of factors, including but not limited to CBC, some of which are not currently incorporated into routine practice.

cs.LG↗

arXiv2021

Predictive Maintenance Tool for Non-Intrusive Inspection Systems

Cross-border security is of topmost priority for societies. Economies lose billions each year due to counterfeiters and other threats. Security checkpoints equipped with X-ray Security Systems (NIIS-Non-Intrusive Inspection Systems) like airports, ports, border control and customs authorities tackle the myriad of threats by using NIIS to inspect bags, air, land, sea and rail cargo, and vehicles. The reliance on the X-ray scanning systems necessitates their continuous 24/7 functioning being provided for. Hence the need for their working condition being closely monitored and preemptive actions being taken to reduce the overall X-ray systems downtime. In this paper, we present a predictive maintenance decision support system, abbreviated as PMT4NIIS (Predictive Maintenance Tool for Non-Intrusive Inspection Systems), which is a kind of augmented analytics platforms that provides real-time AI-generated warnings for upcoming risk of system malfunctioning leading to possible downtime. The industrial platform is the basis of a 24/7 Service Desk and Monitoring center for the working condition of various X-ray Security Systems.

cs.LG↗

arXiv2021

Optimal Linear Combination of Classifiers

The question of whether to use one classifier or a combination of classifiers is a central topic in Machine Learning. We propose here a method for finding an optimal linear combination of classifiers derived from a bias-variance framework for the classification task.

cs.LG↗

arXiv2019

Tutorial on Implied Posterior Probability for SVMs

Implied posterior probability of a given model (say, Support Vector Machines (SVM)) at a point $\bf{x}$ is an estimate of the class posterior probability pertaining to the class of functions of the model applied to a given dataset. It can be regarded as a score (or estimate) for the true posterior probability, which can then be calibrated/mapped onto expected (non-implied by the model) posterior probability implied by the underlying functions, which have generated the data. In this tutorial we discuss how to compute implied posterior probabilities of SVMs for the binary classification case as well as how to calibrate them via a standard method of isotonic regression.

cs.LG↗

arXiv2019

A Note on Posterior Probability Estimation for Classifiers

One of the central themes in the classification task is the estimation of class posterior probability at a new point $\bf{x}$. The vast majority of classifiers output a score for $\bf{x}$, which is monotonically related to the posterior probability via an unknown relationship. There are many attempts in the literature to estimate this latter relationship. Here, we provide a way to estimate the posterior probability without resorting to using classification scores. Instead, we vary the prior probabilities of classes in order to derive the ratio of pdf's at point $\bf{x}$, which is directly used to determine class posterior probabilities. We consider here the binary classification problem.

cs.LG↗