CORTEXA
← Browse
openalexZenodo (CERN European Organization for Nuclear Research)2026-07-23Cited by 0

Machine Learning Classification of COVID-19 Test Outcomes Using Symptom and Testing-Context Features

Edward Okhumaile

This preprint presents a reproducible machine-learning study of COVID-19 test outcome classification using symptom and testing-context features from a public 2020-2021 dataset. The study compares seven supervised learning algorithms and examines whether apparent model performance is maintained under stricter temporal validation. The original comparison used the first 1,000,000 records, while the corrected secondary analysis used all 5,861,480 records with separate development, validation and untouched temporal-holdout periods. Calibration and threshold selection were restricted to validation data. The findings show that random-split performance did not translate reliably to later records. In the corrected temporal holdout, ROC-AUC fell to 0.694 and precision to 0.136, demonstrating substantial temporal degradation. The manuscript is therefore presented as a reproducible validation-design and machine-learning case study, not as a clinically deployable diagnostic model. The source code and workflow are available at:https://github.com/Edy-King/covid-19-ml-workflow This manuscript has not been peer reviewed.

View free PDFSource page

Related papers

openalexZenodo (CERN European Organization for Nuclear Research)2026-07-25

Intelligent Classification of Respiratory Diseases Using Machine Learning-Based Lung Sound Analysis

Tara V K, Varsha S

Respiratory diseases such as asthma, chronic obstructive pulmonary disease (COPD), pneumonia, bronchiectasis, bronchiolitis and upper respiratory tract infection (URTI) remain among the leading causes of illness and death worldwide. Conventional diagnosis relies heavily on auscul…

View free PDFSource page
openalexZenodo (CERN European Organization for Nuclear Research)2026-07-25

Event-Based Prediction of Liquidity Sweep Dynamics in XAUUSD Using Machine Learning

Vanshvardhan Sharma

This paper develops a machine learning framework for detecting and predicting liquidity sweep events in XAUUSD using event-based market microstructure analysis. Using 15-minute data from 2014–2024, the study formalizes liquidity sweeps as a binary classification problem evaluated…

View free PDFSource page
openalexZenodo (CERN European Organization for Nuclear Research)2026-07-26

Comparative Analysis of Machine Learning Classification Algorithms and Hybrid Models for Student Performance Prediction

Ms. Pooja C. Soni, Dr. Hetal R. Modi, PC Negi

This study focuses on the analysis and comparison of machine learning classification algorithms and hybrid machine learning models for predicting student academic performance. Educational Data Mining techniques are used to extract meaningful insights from student datasets. Variou…

View free PDFSource page
openalexZenodo (CERN European Organization for Nuclear Research)2026-07-25

Suspicious Activity Detection Using Machine Learning

Jyoti Neeli, S V Shwetha, H M Rakshitha, Nuthan

Abstract: Video surveillance has become a critical component in today's world. With developments in advanced systems have been developed as a result of the precision and efficacy of deep learning, machine learning, and artificial intelligence to identify and identify questionable…

View free PDFSource page
openalexZenodo (CERN European Organization for Nuclear Research)2026-07-24

Resume Ranking Engine Using Machine Learning and Natural Language Processing for Automated Candidate Screening

V. Satish Mantripragada Akshaya Pranathi

Organizations often receive hundreds of resumes for a single job opening, making manual candidate screening slow and difficult to manage. Conventional recruitment methods generally depend on keyword matching or manual evaluation, both of which may overlook qualified applicants be…

View free PDFSource page
openalexZenodo (CERN European Organization for Nuclear Research)2026-07-24

PromptShield AI: A Multi-Agent Architecture for Intelligent Prompt Injection and Jailbreak Attack Detection Using Machine Learning

Jahnavi Somaraju, N. Sree Charan, M. Mythili, T. Reddy Bhargavi, K. Navya Sree

Large language models (LLMs) are increasingly deployed in user-facing applications, which exposes them to prompt injection and jailbreak attacks that override system instructions, exfiltrate data, or elicit disallowed behaviour. Existing defences are largely single-mechanism: a r…

View free PDFSource page