Title
Application of AI in predicting postoperative infections using routine blood parameters
Authors
Angshuman De1,*, Vasantavada Venkata Satya Sai Preeti2, Mukul Singh3, Mukesh Kumar Patwa4, Niyati Pandya5, Amrit Podder6, Parth Jani7 & Chandan Gogoi8
Affiliation
1Department of Biochemistry, Ramakrishna Mission Seva Pratishthan (Sishumangal Hospital), Kolkata, West Bengal, India; 2Department of Community Medicine, Fakir Mohan Medical College and Hospital, Balasore, Odisha, India; 3Department of General Surgery, All India Institute of Medical Sciences, Gorakhpur, Uttar Pradesh, India; 4Department of Microbiology, ASMC Gonda, Uttar Pradesh, India; 5Department of Anaesthesiology, All India Institute of Medical Sciences, Rajkot, Gujarat, India; 6Department of Physiology, Teerthanker Mahaveer Medical College & Research Centre, Teerthanker Mahaveer University, Moradabad, Uttar Pradesh, India; 7Department of General Medicine, Government Medical College, Bhavnagar, Gujarat, India; 8Department of Surgery, Dhemaji Civil Hospital, Dhemaji, Assam, India; *Corresponding author
Angshuman De - E-mail: drangshumande@gmail.com
Vasantavada Venkata Satya Sai Preeti - E-mail: preetivvss@gmail.com
Mukul Singh - E-mail: singhmukul3911@gmail.com
Mukesh Kumar Patwa - E-mail: kumar.mukesh.patwa@gmail.com
Niyati Pandya - E-mail: niyatipandya9@gmail.com
Amrit Podder- E-mail: amritpodder0@gmail.com
Parth Jani - E-mail: parthjani13@gmail.com
Chandan Gogoi - E-mail: chaolungchandangogoi09@gmail.com
Article Type
Research Article
Date
Received November 15, 2025; Revised December 15, 2025; Accepted December 15, 2025, Published December 15, 2025
Abstract
The application of artificial intelligence in predicting postoperative infections using routine blood parameters is of interest. Hence, a cohort of 120 surgical patients was analyzed and machine learning models were developed using WBC, CRP, NLR and other markers. The Random Forest model achieved the highest predictive performance with an AUC of 0.93. CRP and NLR were identified as the most influential predictors. Thus, we show the integration of AI for early infection detection in surgical care.
Keywords
Artificial intelligence, CRP, machine learning, postoperative infection, white blood cells
Citation
De et al. Bioinformation 21(12): 4271-4274 (2025)
Edited by
Ritik Kashwani
ISSN
0973-2063
Publisher
License
This is an Open Access article which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly credited. This is distributed under the terms of the Creative Commons Attribution License.
