Mehak Rana

Mehak Rana

Auto-generated profile, based on publicly available information

Mehak Rana

The University of Faisalabad, Pakistan

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 February 2026 in VAWKUM Transactions on Computer Sciences
Verified
Journal Article
Closed access
MRMehak Rana
Mehak Rana
NKNaeem Akhtar Khan
Naeem Akhtar Khan
MHMajid Hussain
Majid Hussain
The term “black box” is used in the field of artificial intelligence to describe the lack of transparency between the model and its users. This work proposes the Explainable AI classifier, a major model for detecting COVID-19 using X-ray pictures, a topic that is at the cutting edge of research in the area of medical image analysis. The purpose of this research is to look at the process by which a model diagnoses a disease based on X-ray pictures. Create a COVID-19 radiography dataset, which includes evaluated lung images of 3616 COVID-19-positive cases and 10192 normal cases that can be accessed by the public. Which features of the image influence the results are identified with the help of the LIME method. The superpixels are categorized by the model and then shown with the help of the LimeImageExplainer function. It's very apparent how the model arrives at its results. With 97% accuracy, 94% precision, and 99.9% recall, the proposed approach exceeds the state-of-the-art model.

2 May 2026
Verified
Book Chapter
Closed access
MRMehak Rana
Mehak Rana
MJMuqadsa Jabeen
Muqadsa Jabeen
MHMajid Hussain
Majid Hussain
MSMuhammad Seed
Muhammad Seed
SHShoaib Hassan
Shoaib Hassan
Artificial intelligence (AI) is disrupting healthcare in the form of disease diagnostics, clinical decision support, and remote patient monitoring. Nevertheless, such developments raise many ethical issues regarding patient safety, data sensitivity, and fair access. This chapter focuses on AI in healthcare as a process that is guided by the principles of clinical validation, transparency, and constant monitoring to avoid diagnostic mistakes and algorithmic bias. It discusses privacy-protective solutions like blockchain governance, federated learning, and differential privacy to ensure sensitive health information is not leaked. Moreover, it states that inclusive datasets and models of fairness are essential to providing equitable access, especially in low- and middle-income countries. Based on the case studies of NHS AI Lab (UK), Mayo Clinic (USA) and AIoT-based diabetes monitoring (Singapore), the chapter suggests an ethical AI implementation system that considers both innovation and trust to provide safe, confidential, and equity healthcare to all populations.