Article Per Year (5 Year)
p-Index From 2021 - 2026
0.778
P-Index
This Author published in this journals
All Journal International Journal of Multidisciplinary Sciences and Arts International Journal of Applied Research and Sustainable Sciences (IJARSS) Jurnal Ilmiah Computer Science
Shiwlani, Ashish
Unknown Affiliation
Religion Humanities Chemical Engineering, Chemistry & Bioengineering Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Engineering Languange, Linguistic, Communication & Media

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
BI-RADS Category Prediction from Mammography Images and Mammography Radiology Reports Using Deep Learning: A Systematic Review Shiwlani, Ashish; Ahmad, Ahsan; Umar, Muhammad; Dharejo, Nasrullah; Tahir, Anoosha; Shiwlani, Sheena
Jurnal Ilmiah Computer Science Vol. 3 No. 1 (2024): Volume 3 Number 1 July 2024
Publisher : PT. SNN MEDIA TECH PRESS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58602/jics.v3i1.31

Abstract

Women's health and mortality are significantly threatened by breast cancer, underscoring the importance of timely detection and treatment. Mammograms are an extremely useful and trustworthy diagnostic tool for early detection and screening of breast cancer. Mammograms based CADe systems have helped doctors in predicting BI-RADS categories and make better decisions and have somewhat reduced diagnostic errors. As deep learning algorithms advance, deep learning-based CADe systems become a practical means of resolving these problems and greatly improving the accuracy. The purpose of this review is to discuss the current techniques that have been developed for BI-RADS category classification in the fields of deep learning and convolutional neural networks. Additionally, the paper demonstrates the progression of models introduced in the past ten years. It also discusses the shortcomings of models proposed in the literature for the prediction of BI-RADS categories from mammography radiology reports and mammography images, in addition to summarizing the current challenges. Lastly, it proposes a novel multi-modal approach to predict the BI-RADS categories from radiology reports and mammography images.
Hepatocellular Carcinoma Prediction in HCV Patients using Machine Learning and Deep Learning Techniques Saeed, Fiza; Shiwlani, Ashish; Umar, Muhammad; Jahangir, Zeib; Tahir, Anoosha; Shiwlani, Sheena
Jurnal Ilmiah Computer Science Vol. 3 No. 2 (2025): Volume 3 Number 2 January 2025
Publisher : PT. SNN MEDIA TECH PRESS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58602/jics.v3i2.48

Abstract

Hepatitis C virus is the root cause of 78% of hepato-cellular carcinoma cases. Hepatocellular carcinoma (HCC) represents one of the primary causes of liver cancer mortality and incidence. Clinical prediction of HCC in patients suffering with hepatitis C virus infection (HCV) is challenging due to the diagnostic gold standard, liver biopsy, which is an invasive technique with several limitations. Artificial intelligence (AI) technology is being used in clinical research at a larger rate in recent years, and the field of HCC diagnosis is no exception. Several advanced and light-weight machine learning algorithms combined with less invasive blood tests have promising diagnostic potential to diagnose HCC from HCV. Deep learning algorithms are regarded as best methods for handling and processing complex, unstructured and raw data from various modalities, ranging from routine clinical variables i.e., from EMRs and laboratories to high-resolution medical images. This paper offers a thorough analysis of the most current research that has used machine learning and deep learning to diagnose, prognosticate, treat, and predict HCC risk in patients suffering with HCV.
The Role of Artificial Intelligence in Diagnosing Drug-Induced Hepatitis: A Systematic Review on Differentiation from Viral Hepatitis Hasan, Syed Umer; Kumar , Samesh; Shiwlani, Ashish; Kumar , Sooraj; Shiwlani, Nitasha
International Journal of Multidisciplinary Sciences and Arts Vol. 4 No. 3 (2025): International Journal of Multidisciplinary Sciences and Arts, Article July 2025
Publisher : Information Technology and Science (ITScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/ijmdsa.v4i3.5291

Abstract

DILI presents symptoms like those in viral hepatitis in terms of elevated liver enzymes, jaundice, and liver dysfunction. These make it rather difficult to differentiate between DILI and viral hepatitis through traditional diagnostic methods. DILI is of profound relevance to global morbidity and mortality today. Thus, accurate diagnosis in terms of time and precision is essential. AI offers hope and promises to use improved diagnostics for personalized treatment strategies. After a systematic search on PubMed and Google Scholar, 933 studies were identified, and they concentrated on AI applications in differentiation regarding DILI and viral hepatitis. Only 55 studies were shortlisted for evaluation via a review process that covered diverse AI techniques deployed in diagnosis, including performance metrics. Models, AI have improved how DILI is diagnosed into a paradigm of distinctive biomarkers in a cross-section of clinical data. Machine learning algorithms using clinical data and imaging have very high accuracy in distinguishing DILI from viral hepatitis. It will improve early diagnosis, prognostic predictions, and novel therapeutic target identification by AI with multimodal-data cross-images, laboratory tests, and clinical history. Indeed, AI has the potential to be instrumental in enhancing the diagnosis of DILI and its differentiation from viral hepatitis. With the development of further advanced models, AI could even act as predictive compared to giving the facilities for drug-induced hepatotoxicity and thus enhance patient outcomes while reducing the cost-benefits for richer pharmaceutical processes.
Artificial Intelligence in Stroke Care: Enhancing Diagnostic Accuracy, Personalizing Treatment, and Addressing Implementation Challenges Yahya Abdul Rehman Shah; Qureshi, Sara Mudassir; Hamza Ahmed Qureshi; Saad Ur Rehman Shah; Shiwlani, Ashish; Ahmad, Ahsan
International Journal of Applied Research and Sustainable Sciences Vol. 2 No. 10 (2024): October 2024
Publisher : MultiTech Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59890/ijarss.v2i10.2575

Abstract

Objective: Stroke remains a leading cause of global disability, and with ageing populations, there is a growing need for advanced medical interventions. This literature review aims to assess how Artificial Intelligence (AI) and Machine Learning (ML) technologies have transformed the diagnosis, treatment, and long-term care of stroke patients. Methods: A comprehensive literature review was conducted using databases such as PubMed, IEEE Xplore, and Scopus, covering articles published from January 2018 to August 2024. The review focused on studies related to the application of AI/ML in stroke diagnosis, treatment, and management, including ethical, technical, and regulatory issues. Results: AI and ML technologies have significantly enhanced stroke diagnosis, primarily through advanced deep learning models that analyze imaging data more accurately and rapidly than traditional methods. These AI-based models have demonstrated high precision in detecting ischemic and hemorrhagic strokes, reducing diagnosis time by up to 50% and markedly improving patient outcomes. Predictive models utilizing big data have consistently surpassed traditional risk assessments in forecasting stroke outcomes and customizing treatments. AI-driven decision-support systems have improved patient selection for thrombolysis and mechanical thrombectomy, optimizing treatment strategies. Conclusion: While AI and ML offer substantial advancements in stroke management, including improved diagnosis, personalized therapy, and prognosis, challenges remain. Issues such as data quality, algorithmic transparency, integration into clinical workflows, algorithmic bias, and patient privacy must be addressed. Further research is needed to overcome these technical, ethical, and regulatory obstacles to fully integrate AI and ML into healthcare systems and enhance stroke management and patient outcomes.
Co-Authors Ahmad, Ahsan Dharejo, Nasrullah Hamza Ahmed Qureshi Hasan, Syed Umer Jahangir, Zeib Kumar , Samesh Kumar , Sooraj Muhammad Umar Qureshi, Sara Mudassir Saad Ur Rehman Shah Saeed, Fiza Shiwlani, Nitasha Shiwlani, Sheena Tahir, Anoosha Yahya Abdul Rehman Shah