Health Care Surveillance Using Machine Learning and Data Analytics - Empirical Study of RBFN Classifiers - Performance Evaluation

Aug 5, 2026

Healthy populations are a vital asset for every country, and strengthening healthcare systems and infrastructure has become a major global priority, especially after recent pandemics. Effective public health surveillance depends on research-driven conclusions and on modern computing tools. This work applies promising machine learning techniques to healthcare surveillance, presenting an empirical investigation of RBFN classifiers. Recall, f-score, accuracy, precision, and false positive rate are used to assess the proposed procedures, showing strong performance with the best accuracy and low time complexity in disease identification.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages8

Reading Time20 min

AccessFree to download

Introduction

Public health surveillance and pandemic context

Motivation and study scope

Literature Review

Machine learning in health challenges

Time series and forecasting

Epidemic modeling (SIR/SEIR)

Pandemic interventions and impacts

Health Care Surveillance Using Machine Learning and Data Analytics. SEEJPH 2024 Posted: 30-06-2024 Health Care Surveillance Using Machine Learning and Data Analytics Ashu Nayak1, Kapesh Subhash Raghatate2 1Assistant Professor, Department of CS & IT, Kalinga University, Raipur, India 2Research Scholar, Department of CS & IT, Kalinga University, Raipur, India. KEYWORDS Health, Machine Learning, Data analytics, classification, RBFN. ABSTRACT Any country's healthy population are a true asset. Both developed and developing nations are spending enormous sums of money to strengthen their "healthcare systems" and the required "health infrastructure. "Globally, only few countries have a proactive approach to healthcare. The pandemic that has been going on recently has taught countries hard lessons about how important it is to have strong healthcare systems. The formulation of effective health policies and initiatives depends heavily on studies on Public Health Surveillance (PHS) and the conclusions that follow. This task has become clearer with the introduction of modern computing techniques and technology. Humanity has always been saved by technology when it is applied correctly. In this context, the most promising machine learning techniques are applied in this work. An empirical investigation of RBFN classifiers is presented in this paper. A variety of performance criteria, including recall, f-score, accuracy, precision, and False Positive Rate (FPR), are used to evaluate the efficacy of the recommended procedures. The RBFN approach has the highest accuracy and the least amount of time complexity in identifying health diseases. 1. Introduction Since 2019, the pandemic has produced a new normal where the age-old lesson "Health is Wealth"may be the ideal one to reconsider. Every study that addresses such a unique health scenario is important to researchers and vital to the welfare of humanity. A society's citizens, and consequently a region or country, find infectious and contagious diseases to be extremely concerning. A pandemic poses a far greater threat, with the majority of nations potentially affected. Pandemic illnesses are extremely infectious and contagious. The majority of the time, infection transmission andretransmission cause disruptions to daily living [1]. This transmission must occur between individuals, or between individuals and a cohort or cluster. Based on historical information, it is suggested that this pandemic occurs once every 100 years on average. Every time a pandemic strike, the effects on human evolution and history are unfathomable. In summary, pandemics are a signpost for humanity's quest for growth. The main obstacle to infection identification is that those in the asymptotic category (infected without symptoms) can remain infected for several days, making it extremely tough to track the spread of the virus in this category [2] . Emergencies in the health and economy happen at the same time. Millions of people contract the infection, become ill, and occasionally develop fatal illnesses. The society's health will be in unanticipated peril. After a while, one's physical and mental well-being are called into doubt. It is necessary to address the state of economic instability. Costs both direct and indirect go up, which raises living expenses. Handling the impact on social, health, and economic issues is nearly impossible [10] . There are limitations on travel and unexpected market closures, which could cause unanticipated disruptions in people's lives and social trauma that needs to be addressed collectively [3] . One most common scenario is high morbidity and mortality; this needs to be treated cautiously. Naturally, one more risk that arises during a pandemic is security on a regional, national, and international scale [7] . In recent times, machine learning techniques have been employed in the design and development of early warning systems. Machine learning techniques are utilised

FAQs

What is the main goal of the Health Care Surveillance study in this document?

To anticipate and support healthcare surveillance by applying machine learning techniques for early warning and prediction during pandemic scenarios.

Which classifier approach is empirically investigated?

The paper presents an empirical investigation of RBFN classifiers for identifying health diseases.

What performance measures are used to evaluate the proposed procedures?

The evaluation includes recall, f-score, accuracy, precision, and false positive rate (FPR).

Aug 5, 2026

Upload by River Wang