Machine Learning Approach to Classify Vibrio vulnificus Necrotizing Fasciitis, Non-Vibrio Necrotizing Fasciitis and Cellulitis

被引:1
作者
Chang, Chia-Peng [1 ,2 ]
Wu, Kai-Hsiang [1 ,2 ,3 ]
机构
[1] Chang Gung Mem Hosp, Dept Emergency Med, Puzih City, Chiayi County, Taiwan
[2] Chang Gung Univ Sci & Technol, Dept Nursing, Chiayi Campus, Puzi City, Chiayi County, Taiwan
[3] Chang Gung Univ, Grad Inst Clin Med Sci, Coll Med, Taoyuan City, Taiwan
来源
INFECTION AND DRUG RESISTANCE | 2024年 / 17卷
关键词
necrotizing fasciitis; machine learning; cellulitis; Vibrio vulnificus; SOFT-TISSUE INFECTION; CLINICAL PRESENTATION; RISK; MICROBIOLOGY; MORTALITY;
D O I
10.2147/IDR.S487893
中图分类号
R51 [传染病];
学科分类号
100401 ;
摘要
Background: Recent advancements in artificial intelligence have led to increased adoption of machine learning in disease identification, particularly for challenging diagnoses like necrotizing fasciitis and Vibrio vulnificus infections. This shift is driven by the technology's efficiency, objectivity, and accuracy, offering potential solutions to longstanding diagnostic hurdles in clinical practice. Methods: This investigation incorporated 180 inpatients suffering from soft tissue infections. The participants were categorized into groups: cellulitis, non-Vibrio necrotizing fasciitis (NF), or V. Vulnificus NF. To predict the three relevant outcomes, we employed Light Gradient Boosting Machine (LightGBM) and 5-fold cross-validation methodologies for the development of a multi-class categorization model. Moreover, we applied the SHapley Additive exPlanations (SHAP) methodology to decipher the model's predictions. Results: The multi-classification model possesses substantial predictive capacity, with a weighted-average AUC of 0.86, sensitivity of 87.2%, specificity of 74.5%, NPV of 81.6%, and PPV of 85.4%. The model's calibration was assessed using the Brier score, yielding a weighted mean of 0.084. This low value demonstrates a strong correlation between predicted probabilities and actual outcomes, indicating high predictive accuracy and reliability in the model's forecasts. Conclusions: We effectively developed a multiclassification model aimed at forecasting the occurrence of cellulitis, non-Vibrio NF, or V. Vulnificus NF in patients suffering from soft tissue infection, and we further described the model's predictions using the SHAP algorithm.
引用
收藏
页码:5513 / 5521
页数:9
相关论文
共 50 条
[21]   Prognostic factor of mortality and its clinical implications in patients with necrotizing fasciitis caused by Vibrio vulnificus [J].
Yao-Chou Lee ;
Lien-I Hor ;
Haw-Yen Chiu ;
Jing-Wei Lee ;
Shyh-Jou Shieh .
European Journal of Clinical Microbiology & Infectious Diseases, 2014, 33 :1011-1018
[22]   Vibrio vulnificus necrotizing fasciitis with sepsis presenting with pain in the lower legs in winter: a case report [J].
Di, Weihua ;
Cui, Jing ;
Yu, Hui ;
Cui, Xiao ;
Sa, Huanlan ;
Fu, Zhong ;
Fu, Bingjin ;
Guan, Guofeng ;
Du, Rui ;
Shao, Cuijie ;
Gao, Yong .
BMC INFECTIOUS DISEASES, 2022, 22 (01)
[23]   Management necrotizing cellulitis and fasciitis. [J].
Derancourt, C .
MEDECINE ET MALADIES INFECTIEUSES, 2000, 30 :420S-426S
[24]   Emergency treatment of 16 patients with necrotizing fasciitis caused by Vibrio vulnificus infection complicated with septic shock [J].
Hong Guangliang ;
Wu Bin ;
Lu Caijiao ;
Li Mengfang ;
Zhao Guangju ;
Lu Zhongqiu .
CHINESE MEDICAL JOURNAL, 2014, 127 (10) :1984-1986
[25]   Vibrio vulnificus necrotizing fasciitis with sepsis presenting with pain in the lower legs in winter: a case report [J].
Weihua Di ;
Jing Cui ;
Hui Yu ;
Xiao Cui ;
Huanlan Sa ;
Zhong Fu ;
Bingjin Fu ;
Guofeng Guan ;
Rui Du ;
Cuijie Shao ;
Yong Gao .
BMC Infectious Diseases, 22
[26]   Antibiotic therapy for necrotizing fasciitis caused by Vibrio vulnificus: retrospective analysis of an 8 year period [J].
Chen, Shiuan-Chih ;
Lee, Yuan-Ti ;
Tsai, Shih-Jei ;
Chan, Khee-Siang ;
Chao, Wai-Nang ;
Wang, Po-Hui ;
Lin, Ding-Bang ;
Chen, Chun-Chieh ;
Lee, Meng-Chih .
JOURNAL OF ANTIMICROBIAL CHEMOTHERAPY, 2012, 67 (02) :488-493
[27]   Modified Laboratory Risk Indicator and Machine Learning in Classifying Necrotizing Fasciitis from Cellulitis Patients [J].
Suraphee, Sujitta ;
Busababodhin, Piyapatr ;
Chamchong, Rapeeporn ;
Suparatanachatpun, Pinyo ;
Khamthong, Khemmanant .
APPLIED SCIENCES-BASEL, 2024, 14 (20)
[28]   A clinical approach to differentiating necrotizing fasciitis from simple cellulitis [J].
Brogan, TV ;
Nizet, V .
INFECTIONS IN MEDICINE, 1997, 14 (09) :734-738
[29]   Vibrio vulnificus Necrotizing Fasciitis in Upper Limbs and Septicemia Following Pinch Injury by Mud Crab: A Case Report [J].
Phitsamai, Asadarng ;
Chueansuwan, Worawong ;
Changpradub, Dhitiwat .
CUREUS JOURNAL OF MEDICAL SCIENCE, 2022, 14 (04)
[30]   A case of necrotizing fasciitis initially misdiagnosed as cellulitis [J].
Joshi, Aditya ;
Alomar, Talal ;
Kaune, Diego F. ;
Bourgeois, Julien ;
Solomon, David .
INTERNATIONAL JOURNAL OF SURGERY CASE REPORTS, 2024, 118