A retrospective multi-source clinical validation of Lenek intelligent radiology assistant: an artificial intelligence-based chest radiograph screening and triage system for high-burden pulmonary and cardiac conditions in India

Vinit Singh; Ananya Jhamb; Shiladitya Sil; Sidesh Kumar; Chirag Agrawal; Anant Pareek; Aditya Gautam; Gurunath Parale; Shuchi Singh; Deepak Padmanabhan

doi:10.18203/2320-6012.ijrms20261686

Authors

Vinit Singh Jawaharlal Nehru Medical College, KLE Academy of Higher Education and Research, Belagavi, Karnataka, India
Ananya Jhamb Jawaharlal Nehru Medical College, KLE Academy of Higher Education and Research, Belagavi, Karnataka, India
Shiladitya Sil Department of Oral Medicine and Radiology, North Bengal Dental College and Hospital, Thiknikata, West Bengal, India
Sidesh Kumar Lenek Technologies Private Limited, Pune, Maharashtra, India
Chirag Agrawal Lenek Technologies Private Limited, Pune, Maharashtra, India
Anant Pareek Lenek Technologies Private Limited, Pune, Maharashtra, India
Aditya Gautam Department of Respiratory Medicine, Uttar Pradesh University of Medical Sciences, Saifai, Uttar Pradesh, India
Gurunath Parale Department of Cardiology, Ashwini Hospital, Solapur, Maharashtra, India
Shuchi Singh Department of Radiodiagnosis, Apollomedics Super Speciality Hospital, Lucknow, Uttar Pradesh, India
Deepak Padmanabhan Department of Electrophysiology, Narayana Institute of Cardiac Sciences, Bengaluru, Karnataka, India

DOI:

https://doi.org/10.18203/2320-6012.ijrms20261686

Keywords:

Chest-radiography, Tuberculosis screening, AI-driven triage, Access to healthcare, Screening tool, Artificial intelligence in radiology

Abstract

Background: A critical radiologist shortage exists in India, leading to delayed chest radiograph (CXR) interpretation. This leads to disease progression, higher morbidity, and mortality. Artificial intelligence-based CXR interpretation by Lenek Intelligent Radiology Assistant (LIRA) is a promising solution. This study aims to establish the screening and triaging capabilities of LIRA by assessing its accuracy in detecting abnormalities and pathologies in CXRs from geographically diverse institutions.

Methods: We conducted a retrospective multi-source validation of the diagnostic accuracy of LIRA for the detection of general abnormalities, tuberculosis, consolidation, pleural effusion, pneumothorax, and cardiomegaly. De-identified chest radiographs were input into LIRA models. The obtained interpretations were compared to the established ground truth reporting for the calculation of sensitivity, specificity, and AUROC with 95% CI for individual pathologies across varying probability thresholds.

Results: LIRA demonstrated high sensitivity for general abnormality detection (AUROC 0.93-0.986, 84.4-97.1% sensitivity, 88.9-92.4% specificity) and tuberculosis triaging (Shenzhen and Montgomery: 88.5-89.7% sensitivity, 89.9-90.5% specificity; Jaypee: 98.7% sensitivity, 63.6% specificity). For consolidation (AUROC 0.884-0.895, 96.4-96.9% sensitivity, 70.8-77.1% specificity), pleural effusion (AUROC 0.942-0.967, 79.7-99.1% sensitivity, 81.2-87.7% specificity), pneumothorax (AUROC 0.87, 90.6-94.8% sensitivity, 79.5-82.7% specificity) and cardiomegaly (AUROC 0.883, 95.1% sensitivity, 81.6% specificity), the model exhibited commendable accuracy as well.

Conclusions: The diagnostic performance of LIRA was consistent across various pathologies and chest radiographs from diverse geographic locations, with particular strengths in abnormality detection and tuberculosis screening. The risk-stratified triaging and high sensitivity of LIRA make it a reliable adjunct solution to address radiologist shortages, reduce turnaround times, and support India's tuberculosis elimination goals.

References

Pande T, Pai M, Khan FA, Denkinger CM. Use of chest radiography in the 22 highest tuberculosis burden countries. Eur Respir J. 2015;46(6):1816-9.

Arora R. The training and practice of radiology in India: current trends. Quant Imaging Med Surg. 2014;4(6):449-50.

Sreeramareddy CT, Qin ZZ, Satyanarayana S, Subbaraman R, Pai M. Delays in diagnosis and treatment of pulmonary tuberculosis in India: a systematic review. Int J Tuberc Lung Dis. 2014;18(3):255-66.

WHO. Global Tuberculosis Report 2025. Geneva: World Health Organization. 2025. Available at: https://www.who.int/teams/global-programme-on-tuberculosis-and-lung-health/tb-reports/globaltuberculosis-report-2025. Accessed on 14 February 2026.

Central TB Division. Ministry of Health and Family Welfare, Government of India; India TB Report 2025. 2025. Available at: https://tbcindia.mohfw.gov.in/wpcontent/uploads/2024/10/TBReport_for-Web_08_10-2024-1.pdf. Accessed on 14 February 2026.

Balasubramnian A, Francis PT, Leelamoni K, Rakesh PS, Lalu JS. Diagnostic and treatment delay among new pulmonary tuberculosis patients in Southern India: A cross-sectional study. Indian J Public Health. 2022;66(1):S60-5.

McIntosh N, Becher JC, Cunningham S, Stenson B, Laing IA, Lyon AJ, et al. Clinical diagnosis of pneumothorax is late: use of trend data and decision support might allow preclinical detection. Pediatr Res. 2000;48(3):408-15.

Annarumma M, Withey SJ, Bakewell RJ, Pesce E, Goh V, Montana G. Automated Triaging of Adult Chest Radiographs with Deep Artificial Neural Networks. Radiology. 2019;291(1):196-202.

Sheikh A, Anderson M, Albala S, Casadei B, Franklin BD, Richards M, et al. Health information technology and digital innovation for national learning health and care systems. Lancet Digit Health. 2021;3(6):383-96.

Çallı E, Sogancioglu E, Van Ginneken B, Van Leeuwen KG, Murphy K. Deep learning for chest X-ray analysis: A survey. Med Image Anal. 2021;72:102125.

Zech JR, Badgeley MA, Liu M, Costa AB, Titano JJ, Oermann EK. Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: A cross-sectional study. PLoS Med. 2018;15(11):1002683.

Wang X, Peng Y, Lu L, Lu Z, Bagheri M, Summers RM. ChestX-Ray8; hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE. 2017;3462-71.

Irvin J, Rajpurkar P, Ko M, Yu Y, Ciurea-Ilcus S, Chute C, et al. CheXpert: a large chest radiograph dataset with uncertainty labels and expert comparison. Proc AAAI Conf Artif Intell. 2019;33:590-7.

Jaeger S, Candemir S, Antani S, Wáng YX, Lu PX, Thoma G. Two public chest X-ray datasets for computeraided screening of pulmonary diseases. Quant Imaging Med Surg. 2014;4:475-7.

Zawacki A, Wu C, Shih G, Elliott J, Fomitchev M, Hussain M, et al. SIIM-ACR Pneumothorax Segmentation. Kaggle. 2019.

Chauhan A, Chauhan D, Rout C. Role of Gist and PHOG features in computer-aided diagnosis of tuberculosis without segmentation. PLoS One. 2014;9(11):112980.

Qin ZZ, Ahmed S, Sarker MS, Paul K, Adel ASS, Naheyan T, et al. Tuberculosis detection from chest x-rays for triaging in a high tuberculosis-burden setting: an evaluation of five artificial intelligence algorithms. Lancet Digit Health. 2021;3:543-54.

Chatterjee S, Das P, Stallworthy G, Bhambure G, Munje R, Vassall A. Catastrophic costs for tuberculosis patients in India: Impact of methodological choices. PLOS Glob Public. Health. 2024;4:0003078.

Raval D, Parmar D, Saha S, Sarkar R, Wadhwa M, Pandya A, et al. Cost-effectiveness analysis of AI-assisted chest X-ray interpretation tools for TB screening: a rapid HTA. Front Digit Health. 2025;7:1629127.

WHO. WHO Consolidated Guidelines on Tuberculosis. Module 2: Screening - Systematic Screening for Tuberculosis Disease. 2021. Available at: https://www.who.int/publications/i/item/9789240022676. Accessed on 14 February 2026.

Nash M, Kadavigere R, Andrade J, Sukumar CA, Chawla K, Shenoy VP, et al. Deep learning, computer-aided radiography reading for tuberculosis: a diagnostic accuracy study from a tertiary hospital in India. Sci Rep. 2020;10:210.

Shah H, Patel J, Yasobant S, Saxena D, Saha S, Sinha A, et al. Capacity Building, Knowledge Enhancement, and Consultative Processes for Development of a Digital Tool (Ni-kshay SETU) to Support the Management of Patients with Tuberculosis: Exploratory Qualitative Study. J Med Internet Res. 2023;25:e45400.

Menon S, Koura KG. Artificial intelligence for tuberculosis control: a scoping review of applications in public health. J Glob Health. 2025;15:04192.

Jan B, Dar MI, Choudhary B, Basist P, Khan R, Alhalmi A. Cardiovascular Diseases Among Indian Older Adults: A Comprehensive Review. Cardiovasc Ther. 2024;2024:6894693.

Suleman MU, Mursaleen M, Khalil U, Saboor A, Bilal M, Khan SA, et al. Assessing the generalizability of artificial intelligence in radiology: a systematic review of performance across different clinical settings. Ann Med Surg (Lond). 2025;87:8803-11.

Strohm L, Hehakaya C, Ranschaert ER, Boon WPC, Moors EHM. Implementation of artificial intelligence (AI) applications in radiology: hindering and facilitating factors. Eur Radiol. 2020;30:552532.

Blezek DJ, Olson-Williams L, Missert A, Korfiatis P. AI Integration in the Clinical Workflow. J Digit Imaging. 2021;34(6):1435-46.

Abbas Q, Jeong W, Lee SW. Explainable AI in Clinical Decision Support Systems: A Meta-Analysis of Methods, Applications, and Usability Challenges. Healthcare. 2025;13:2154.

Sridharan S, Seah XHA, Venkataraman N, Tirukonda PS, Jeyaratnam RP, John S, et al. Real-world evaluation of an AI triaging system for chest Xrays: a prospective clinical study. Eur J Radiol. 2024;181:111783.

Nagendran M, Chen Y, Lovejoy CA, Gordon AC, Komorowski M, Harvey H, et al. Artificial intelligence versus clinicians: systematic review of design, reporting standards, and claims of deep learning studies. BMJ. 2020;368:m689.