Book a Demo
Shivam Patel
Gray shield icon
Is this you?
Claim your profile.

Shivam Patel

AS SEEN ON
Hackerlap, umtoday.ca

Twitter bio

Journalist @Reuters, formerly @IndianExpress and @the_hindu

Geo Focus

Coverage Attributes:

Beta
Informative: 50 %
Events: 11 %
Data Driven: 10 %
Evolving Stories: 8 %
Breaking News: 8 %

Themes Covered:

Not enough data icon

Not enough data

Most Recent Topics:

  • Asia
  • Drone Technology
  • United States

Pitching Insights

Shivam Patel's coverage primarily focuses on government announcements, evolving stories, and breaking news related to international relations, India, air pollution, public health, and crime. Given the significant percentage of topics related to government & politics and international relations in his coverage attributes and themes covered, pitches should offer insights into geopolitical developments involving India or other relevant countries.

For evolving stories like the rescue of India tunnel workers or regulatory orders on cough syrup ingredients that are also part of his coverage attributes and themes covered; consider providing expert commentary from engineers for technical aspects or medical professionals for public health issues.

This information evolves through artificial intelligence and human feedback. Improve this profile .

Journalists With Similar Coverage:

Based on similarity of content.
Amiti Sen

Amiti Sen

Associate Editor
*******en@***********.in
Publications
businessline
Most recent topics
Not enough data
Rakesh Sharma

Rakesh Sharma

Senior Video Editor
Publications
Bloomberg News, ThePrint, Walla Walla Union-Bulletin, Derrick Publishing Co, The Boston Globe
Most recent topics
Not enough data
Huma Siddiqui

Huma Siddiqui

Senior Correspondent
Publications
StratNewsGlobal
Most recent topics
Not enough data
Archis Mohan

Archis Mohan

National Affairs/Political Editor
**********an@**************o.in
Publications
Business Standard, Rediff.com India Ltd., Magzter
Most recent topics
Not enough data
Sudhi Ranjan Sen

Sudhi Ranjan Sen

Bloomberg
Publications
Bloomberg News, ThePrint, Walla Walla Union-Bulletin, The Guam Daily Post, Moneyweb
Most recent topics
Not enough data
Yeshi Seli

Yeshi Seli

Publications
Business India
Most recent topics
Not enough data

Articles

Cureus Journal of Medical Science

Evaluating AI Models for Pneumothorax Detection on Chest Radiographs: Diagnostic Accuracy and Clinical Trade-Offs

Evaluating AI Models for Pneumothorax Detection on Chest Radiographs: Diagnostic Accuracy and Clinical Trade-Offs

By: Andrew Bouras, Nitin Chetla, Luis Rodriguez, Sai Samayamanthula, Vinisha Bonagiri, Saumya Sharma, Nasif Zaman, Rahul Kumar, Shivam Patel

BackgroundPneumothorax is a critical condition where timely recognition on chest radiographs is essential, particularly in emergency and resource-limited settings. Emerging artificial intelligence (AI) systems capable of native image interpretation offer potential to augment clinical workflows, yet their diagnostic reliability remains underexplored.MethodsWe evaluated two state-of-the-art AI models on 2,000 publicly available frontal chest radiographs, equally divided between pneumothorax-positive and pneumothorax-negative cases. Models were prompted with standardized diagnostic instructions emphasizing pleural line visualization, asymmetry in lung translucency, and the deep sulcus sign. Predictions were assessed against reference diagnoses using accuracy, precision, recall, and F1 score.ResultsOne model achieved balanced diagnostic accuracy (64%) with a precision of 66% and a recall of 57%, while the other demonstrated higher sensitivity (88%) but lower precision (55%). These divergent profiles underscore trade-offs between minimizing false negatives and limiting false positives.ConclusionsAI systems show promise for pneumothorax detection on chest radiographs but exhibit distinct diagnostic biases that must be carefully matched to the clinical context. Balanced performance models may be suitable for general screening, whereas high-sensitivity models may better support triage workflows. Rigorous validation, integration strategies, and human supervision remain essential before deployment in real-world clinical practice.

© 2026 Intelligent Relations