Driven Clinical Decision Support for Early Detection of Sepsis in Resource
DOI:
Abstract
Sepsis remains a leading cause of morbidity and mortality worldwide, with disproportionately high burdens in low- and middle-income countries (LMICs) such as Thailand. Conventional clinical scoring tools, including qSOFA, often demonstrate limited accuracy in early sepsis detection, particularly in resource-constrained environments. This study addresses the urgent need for reliable, scalable, and interpretable predictive models by evaluating the performance of machine learning specifically Random Forest (RF) using hospital datasets from both tertiary and district hospitals in Thailand. The findings reveal that the RF model significantly outperformed logistic regression and qSOFA, achieving an AUROC of 0.89 and AUPRC of 0.76 in tertiary hospitals, and maintaining strong accuracy (AUROC 0.83, AUPRC 0.69) in district hospitals where fewer variables were available. Feature importance analysis highlighted systolic blood pressure, respiratory rate, oxygen saturation, and WBC count as the most influential predictors, aligning with established sepsis pathophysiology. Crucially, the model’s interpretability enhanced clinician trust and facilitated its potential integration into Thailand’s Universal Coverage Scheme and Health Data Center. These results demonstrate that lightweight, interpretable AI solutions can improve diagnostic accuracy and healthcare equity in LMIC settings. Thailand’s experience provides a transferable model for broader global health applications, illustrating how AI can support early sepsis detection, reduce mortality, and strengthen national health system resilience.
Downloads
Views : 260
Downloads : 163
References
L. La Via, G. Sangiorgio, S. Stefani, A. Marino, G. Nunnari, S. Cocuzza, I. La Mantia, B. Cacopardo, S. Stracquadanio, S. Spampinato, S. Lavalle, and A. Maniaci, “The global burden of sepsis and septic shock,” Epidemiologia (Basel), vol. 5, no. 3, pp. 456–478, Jul. 25, 2024.
M. Oliveira, W. Antunes, S. Mota, Á. Madureira-Carvalho, R. J. Dinis-Oliveira, and D. D. Silva, “An overview of the recent advances in antimicrobial resistance,” Microorganisms, vol. 12, no. 9, 2024.
S. Ranjit and N. Kissoon, “Challenges and solutions in translating sepsis guidelines into practice in resource-limited settings,” Transl. Pediatr., vol. 10, no. 10, pp. 2646–2665, Oct. 2021.
A. Sharma, A. Singh, M. A. Dar, R. J. Kaur, J. Charan, K. Iskandar, M. Haque, K. Murti, V. Ravichandiran, and S. Dhingra, “Menace of antimicrobial resistance in LMICs: Current surveillance practices and control measures to tackle hostility,” J. Infect. Public Health, vol. 15, no. 2, pp. 172–181, Feb. 2022.
L. Evans, A. Rhodes, W. Alhazzani, M. Antonelli, C. M. Coopersmith, C. French, F. R. Machado, et.al, “Surviving sepsis campaign: international guidelines for management of sepsis and septic shock 2021,” Intensive Care Med., vol. 47, no. 11, pp. 1181–1247, Nov. 2021.
A. R. Schertz, K. M. Lenoir, A. G. Bertoni, B. J. Levine, M. Mongraw-Chaffin, and K. W. Thomas, “Sepsis prediction model for determining sepsis vs SIRS, qSOFA, and SOFA,” JAMA Netw. Open, vol. 6, no. 8, 2023.
C. Koch, F. Edinger, T. Fischer, F. Brenck, A. Hecker, C. Katzer, M. Markmann, M. Sander, and E. Schneck, “Comparison of qSOFA score, SOFA score, and SIRS criteria for the prediction of infection and mortality among surgical intermediate and intensive care patients,” World J. Emerg. Surg., vol. 15, p. 63, 2020.
E. Dimitrov, G. Minkov, E. Enchev, K. Halacheva, and Y. Yovtchev, “The Quick Sequential Organ Failure Assessment (qSOFA) score is a poor mortality predictor in patients with complicated intra-abdominal infections,” Open Access Maced. J. Med. Sci., vol. 8, no. B, pp. 221–225, May 14, 2020.
M. Singer, C. S. Deutschman, C. W. Seymour, M. Shankar-Hari, D. Annane, M. Bauer, R. Bellomo, G. R. Bernard, J. D. Chiche, C. M. Coopersmith, R. S. Hotchkiss, M. M. Levy, J. C. Marshall, G. S. Martin, S. M. Opal, G. D. Rubenfeld, T. van der Poll, J. L. Vincent, and D. C. Angus, “The Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3),” JAMA, vol. 315, no. 8, pp. 801–810, Feb. 23, 2016.
W. L. Chua, K. D. B. Rusli, and L. M. Aitken, “Early warning scores for sepsis identification and prediction of in-hospital mortality in adults with sepsis: A systematic review and meta-analysis,” J. Clin. Nurs., vol. 33, no. 6, pp. 2005–2018, Feb. 20, 2024.
J. Bajwa, U. Munir, A. Nori, and B. Williams, “Artificial intelligence in healthcare: transforming the practice of medicine,” Future Healthc. J., vol. 8, no. 2, pp. e188–e194, Jul. 2021.
Y. Zheng, Z. Chen, S. Huang, N. Zhang, Y. Wang, S. Hong, J. S. K. Chan, K. Y. Chen, Y. Xia, Y. Zhang, G. Y. H. Lip, J. Qin, G. Tse, and T. Liu, “Machine learning in cardio-oncology: New insights from an emerging discipline,” Rev. Cardiovasc. Med., vol. 24, no. 10, p. 296, Oct. 19, 2023.
T. Kyriazos and M. Poga, “Application of machine learning models in social sciences: Managing nonlinear relationships,” Encyclopedia, vol. 4, no. 4, pp. 1790–1805, 2024.
D. O'Reilly, J. McGrath, and I. Martin-Loeches, “Optimizing artificial intelligence in sepsis management: Opportunities in the present and looking closely to the future,” J. Intensive Med., vol. 4, no. 1, pp. 34–45, Jan. 2024.
W. Cheungpasitporn, C. Thongprayoon, and K. B. Kashani, “Artificial intelligence and machine learning's role in sepsis-associated acute kidney injury,” Kidney Res. Clin. Pract., vol. 43, no. 4, pp. 417–432, Jul. 2024.
M. Gholamzadeh, H. Abtahi, and R. Safdari, “Comparison of different machine learning algorithms to classify patients suspected of having sepsis infection in the intensive care unit,” Informatics Med. Unlocked, vol. 38, 2023.
B. Baddal, F. Taner, and D. U. Ozsahin, “Harnessing of artificial intelligence for the diagnosis and prevention of hospital-acquired infections: A systematic review,” Diagnostics, vol. 14, no. 5, 2024.
M. Chatterjee et al., “Sepsis management in resource-limited settings: AI as a tool for equity,” BMJ Global Health, vol. 5, no. 6, 2020.
A. Marey, P. Arjmand, A. D. S. Alerab, M. J. Eslami, A. M. Saad, N. Sanchez, and M. Umair, “Explainability, transparency and black box challenges of AI in radiology: Impact on patient care in cardiovascular radiology,” Egypt. J. Radiol. Nucl. Med., vol. 55, Art. no. 183, 2024.
R. J. Chen, J. J. Wang, D. F. K. Williamson, T. Y. Chen, J. Lipkova, M. Y. Lu, S. Sahai, and F. Mahmood, “Algorithmic fairness in artificial intelligence for medicine and healthcare,” Nat. Biomed. Eng., vol. 7, no. 6, pp. 719–742, Jun. 2020.
F. Mușat, D. N. Păduraru, A. Bolocan, C. A. Palcău, A. M. Copăceanu, D. Ion, V. Jinga, and O. Andronic, “Machine learning models in sepsis outcome prediction for ICU patients: Integrating routine laboratory tests—a systematic review,” Biomedicines, vol. 12, no. 12, p. 2892, Dec. 19, 2024.
L. Yu, A. Halalau, B. Dalal, A. E. Abbas, F. Ivascu, M. Amin, et al., “Machine learning methods to predict mechanical ventilation and mortality in patients with COVID-19,” PLoS ONE, vol. 16, no. 4, p. e0249285, 2021.
V. Arvind, J. S. Kim, B. H. Cho, E. Geng, and S. K. Cho, “Development of a machine learning algorithm to predict intubation among hospitalized patients with COVID-19,” J. Crit. Care, vol. 62, pp. 25–30, 2021.
F. Y. Cheng, H. Joshi, P. Tandon, R. Freeman, D. L. Reich, M. Mazumdar, et al., “Using machine learning to predict ICU transfer in hospitalized COVID-19 patients,” J. Clin. Med., 2020.
C. L. Cárdenas, J. C. Yébenes, E. Vela, M. Clèries, J. M. Sirvent, C. Fuster-Bertolín, et al., “Trends in mortality in septic patients according to the different organ failure during 15 years,” Crit. Care, vol. 26, no. 1, 2022.
F. Sabry, T. Eltaras, W. Labda, K. Alzoubi, and Q. Malluhi, “Machine learning for healthcare wearable devices: The big picture,” J. Healthc. Eng., 2022.
N. Sisubalan, B. S. Sivamaruthi, P. Kesika, and C. Chaiyasut, “Addressing health inequities in Southeast Asia: Challenges and opportunities,” Lancet Reg. Health Southeast Asia, vol. 28, p. 100455, Aug. 3, 2024.
V. B. Komaragiri, “AI-driven maintenance algorithms for intelligent network systems: Leveraging neural networks to predict and optimize performance in dynamic environments,” Migration Lett., vol. 19, pp. 1949–1964, 2022.
H. K. Choi, M. Chen, L. L. Goldston, and K. Lee, “Extracellular vesicles as nanotheranostic platforms for targeted neurological disorder interventions,” Nano Convergence, vol. 11, no. 1, 2024.
S. Alsaedi, M. Ogasawara, M. Alarawi, X. Gao, and T. Gojobori, “AI-powered precision medicine: Utilizing genetic risk factor optimization to revolutionize healthcare,” NAR Genom. Bioinform., vol. 7, no. 2, p. lqaf038, May 5, 2025.
